summaryrefslogtreecommitdiffstats
path: root/fs
diff options
context:
space:
mode:
authorDavid Howells <dhowells@redhat.com>2023-09-28 12:46:49 +0200
committerDavid Howells <dhowells@redhat.com>2023-12-28 10:45:26 +0100
commit62c3b7481b9a108cb99ef9438dba66bb4738768b (patch)
treedc2d51af99c688a2a2a861277170165654920bcd /fs
parentnetfs, cachefiles: Pass upper bound length to allow expansion (diff)
downloadlinux-62c3b7481b9a108cb99ef9438dba66bb4738768b.tar.xz
linux-62c3b7481b9a108cb99ef9438dba66bb4738768b.zip
netfs: Provide a writepages implementation
Provide an implementation of writepages for network filesystems to delegate to. Signed-off-by: David Howells <dhowells@redhat.com> Reviewed-by: Jeff Layton <jlayton@kernel.org> cc: linux-cachefs@redhat.com cc: linux-fsdevel@vger.kernel.org cc: linux-mm@kvack.org
Diffstat (limited to 'fs')
-rw-r--r--fs/netfs/buffered_write.c636
1 files changed, 636 insertions, 0 deletions
diff --git a/fs/netfs/buffered_write.c b/fs/netfs/buffered_write.c
index 70cb8e98d068..c078826f7fe6 100644
--- a/fs/netfs/buffered_write.c
+++ b/fs/netfs/buffered_write.c
@@ -32,6 +32,18 @@ static void netfs_set_group(struct folio *folio, struct netfs_group *netfs_group
folio_attach_private(folio, netfs_get_group(netfs_group));
}
+#if IS_ENABLED(CONFIG_FSCACHE)
+static void netfs_folio_start_fscache(bool caching, struct folio *folio)
+{
+ if (caching)
+ folio_start_fscache(folio);
+}
+#else
+static void netfs_folio_start_fscache(bool caching, struct folio *folio)
+{
+}
+#endif
+
/*
* Decide how we should modify a folio. We might be attempting to do
* write-streaming, in which case we don't want to a local RMW cycle if we can
@@ -475,3 +487,627 @@ out:
return ret;
}
EXPORT_SYMBOL(netfs_page_mkwrite);
+
+/*
+ * Kill all the pages in the given range
+ */
+static void netfs_kill_pages(struct address_space *mapping,
+ loff_t start, loff_t len)
+{
+ struct folio *folio;
+ pgoff_t index = start / PAGE_SIZE;
+ pgoff_t last = (start + len - 1) / PAGE_SIZE, next;
+
+ _enter("%llx-%llx", start, start + len - 1);
+
+ do {
+ _debug("kill %lx (to %lx)", index, last);
+
+ folio = filemap_get_folio(mapping, index);
+ if (IS_ERR(folio)) {
+ next = index + 1;
+ continue;
+ }
+
+ next = folio_next_index(folio);
+
+ trace_netfs_folio(folio, netfs_folio_trace_kill);
+ folio_clear_uptodate(folio);
+ if (folio_test_fscache(folio))
+ folio_end_fscache(folio);
+ folio_end_writeback(folio);
+ folio_lock(folio);
+ generic_error_remove_page(mapping, &folio->page);
+ folio_unlock(folio);
+ folio_put(folio);
+
+ } while (index = next, index <= last);
+
+ _leave("");
+}
+
+/*
+ * Redirty all the pages in a given range.
+ */
+static void netfs_redirty_pages(struct address_space *mapping,
+ loff_t start, loff_t len)
+{
+ struct folio *folio;
+ pgoff_t index = start / PAGE_SIZE;
+ pgoff_t last = (start + len - 1) / PAGE_SIZE, next;
+
+ _enter("%llx-%llx", start, start + len - 1);
+
+ do {
+ _debug("redirty %llx @%llx", len, start);
+
+ folio = filemap_get_folio(mapping, index);
+ if (IS_ERR(folio)) {
+ next = index + 1;
+ continue;
+ }
+
+ next = folio_next_index(folio);
+ trace_netfs_folio(folio, netfs_folio_trace_redirty);
+ filemap_dirty_folio(mapping, folio);
+ if (folio_test_fscache(folio))
+ folio_end_fscache(folio);
+ folio_end_writeback(folio);
+ folio_put(folio);
+ } while (index = next, index <= last);
+
+ balance_dirty_pages_ratelimited(mapping);
+
+ _leave("");
+}
+
+/*
+ * Completion of write to server
+ */
+static void netfs_pages_written_back(struct netfs_io_request *wreq)
+{
+ struct address_space *mapping = wreq->mapping;
+ struct netfs_folio *finfo;
+ struct netfs_group *group = NULL;
+ struct folio *folio;
+ pgoff_t last;
+ int gcount = 0;
+
+ XA_STATE(xas, &mapping->i_pages, wreq->start / PAGE_SIZE);
+
+ _enter("%llx-%llx", wreq->start, wreq->start + wreq->len);
+
+ rcu_read_lock();
+
+ last = (wreq->start + wreq->len - 1) / PAGE_SIZE;
+ xas_for_each(&xas, folio, last) {
+ WARN(!folio_test_writeback(folio),
+ "bad %zx @%llx page %lx %lx\n",
+ wreq->len, wreq->start, folio_index(folio), last);
+
+ if ((finfo = netfs_folio_info(folio))) {
+ /* Streaming writes cannot be redirtied whilst under
+ * writeback, so discard the streaming record.
+ */
+ folio_detach_private(folio);
+ group = finfo->netfs_group;
+ gcount++;
+ trace_netfs_folio(folio, netfs_folio_trace_clear_s);
+ kfree(finfo);
+ } else if ((group = netfs_folio_group(folio))) {
+ /* Need to detach the group pointer if the page didn't
+ * get redirtied. If it has been redirtied, then it
+ * must be within the same group.
+ */
+ if (folio_test_dirty(folio)) {
+ trace_netfs_folio(folio, netfs_folio_trace_redirtied);
+ goto end_wb;
+ }
+ if (folio_trylock(folio)) {
+ if (!folio_test_dirty(folio)) {
+ folio_detach_private(folio);
+ gcount++;
+ trace_netfs_folio(folio, netfs_folio_trace_clear_g);
+ } else {
+ trace_netfs_folio(folio, netfs_folio_trace_redirtied);
+ }
+ folio_unlock(folio);
+ goto end_wb;
+ }
+
+ xas_pause(&xas);
+ rcu_read_unlock();
+ folio_lock(folio);
+ if (!folio_test_dirty(folio)) {
+ folio_detach_private(folio);
+ gcount++;
+ trace_netfs_folio(folio, netfs_folio_trace_clear_g);
+ } else {
+ trace_netfs_folio(folio, netfs_folio_trace_redirtied);
+ }
+ folio_unlock(folio);
+ rcu_read_lock();
+ } else {
+ trace_netfs_folio(folio, netfs_folio_trace_clear);
+ }
+ end_wb:
+ if (folio_test_fscache(folio))
+ folio_end_fscache(folio);
+ folio_end_writeback(folio);
+ }
+
+ rcu_read_unlock();
+ netfs_put_group_many(group, gcount);
+ _leave("");
+}
+
+/*
+ * Deal with the disposition of the folios that are under writeback to close
+ * out the operation.
+ */
+static void netfs_cleanup_buffered_write(struct netfs_io_request *wreq)
+{
+ struct address_space *mapping = wreq->mapping;
+
+ _enter("");
+
+ switch (wreq->error) {
+ case 0:
+ netfs_pages_written_back(wreq);
+ break;
+
+ default:
+ pr_notice("R=%08x Unexpected error %d\n", wreq->debug_id, wreq->error);
+ fallthrough;
+ case -EACCES:
+ case -EPERM:
+ case -ENOKEY:
+ case -EKEYEXPIRED:
+ case -EKEYREJECTED:
+ case -EKEYREVOKED:
+ case -ENETRESET:
+ case -EDQUOT:
+ case -ENOSPC:
+ netfs_redirty_pages(mapping, wreq->start, wreq->len);
+ break;
+
+ case -EROFS:
+ case -EIO:
+ case -EREMOTEIO:
+ case -EFBIG:
+ case -ENOENT:
+ case -ENOMEDIUM:
+ case -ENXIO:
+ netfs_kill_pages(mapping, wreq->start, wreq->len);
+ break;
+ }
+
+ if (wreq->error)
+ mapping_set_error(mapping, wreq->error);
+ if (wreq->netfs_ops->done)
+ wreq->netfs_ops->done(wreq);
+}
+
+/*
+ * Extend the region to be written back to include subsequent contiguously
+ * dirty pages if possible, but don't sleep while doing so.
+ *
+ * If this page holds new content, then we can include filler zeros in the
+ * writeback.
+ */
+static void netfs_extend_writeback(struct address_space *mapping,
+ struct netfs_group *group,
+ struct xa_state *xas,
+ long *_count,
+ loff_t start,
+ loff_t max_len,
+ bool caching,
+ size_t *_len,
+ size_t *_top)
+{
+ struct netfs_folio *finfo;
+ struct folio_batch fbatch;
+ struct folio *folio;
+ unsigned int i;
+ pgoff_t index = (start + *_len) / PAGE_SIZE;
+ size_t len;
+ void *priv;
+ bool stop = true;
+
+ folio_batch_init(&fbatch);
+
+ do {
+ /* Firstly, we gather up a batch of contiguous dirty pages
+ * under the RCU read lock - but we can't clear the dirty flags
+ * there if any of those pages are mapped.
+ */
+ rcu_read_lock();
+
+ xas_for_each(xas, folio, ULONG_MAX) {
+ stop = true;
+ if (xas_retry(xas, folio))
+ continue;
+ if (xa_is_value(folio))
+ break;
+ if (folio_index(folio) != index) {
+ xas_reset(xas);
+ break;
+ }
+
+ if (!folio_try_get_rcu(folio)) {
+ xas_reset(xas);
+ continue;
+ }
+
+ /* Has the folio moved or been split? */
+ if (unlikely(folio != xas_reload(xas))) {
+ folio_put(folio);
+ xas_reset(xas);
+ break;
+ }
+
+ if (!folio_trylock(folio)) {
+ folio_put(folio);
+ xas_reset(xas);
+ break;
+ }
+ if (!folio_test_dirty(folio) ||
+ folio_test_writeback(folio) ||
+ folio_test_fscache(folio)) {
+ folio_unlock(folio);
+ folio_put(folio);
+ xas_reset(xas);
+ break;
+ }
+
+ stop = false;
+ len = folio_size(folio);
+ priv = folio_get_private(folio);
+ if ((const struct netfs_group *)priv != group) {
+ stop = true;
+ finfo = netfs_folio_info(folio);
+ if (finfo->netfs_group != group ||
+ finfo->dirty_offset > 0) {
+ folio_unlock(folio);
+ folio_put(folio);
+ xas_reset(xas);
+ break;
+ }
+ len = finfo->dirty_len;
+ }
+
+ *_top += folio_size(folio);
+ index += folio_nr_pages(folio);
+ *_count -= folio_nr_pages(folio);
+ *_len += len;
+ if (*_len >= max_len || *_count <= 0)
+ stop = true;
+
+ if (!folio_batch_add(&fbatch, folio))
+ break;
+ if (stop)
+ break;
+ }
+
+ xas_pause(xas);
+ rcu_read_unlock();
+
+ /* Now, if we obtained any folios, we can shift them to being
+ * writable and mark them for caching.
+ */
+ if (!folio_batch_count(&fbatch))
+ break;
+
+ for (i = 0; i < folio_batch_count(&fbatch); i++) {
+ folio = fbatch.folios[i];
+ trace_netfs_folio(folio, netfs_folio_trace_store_plus);
+
+ if (!folio_clear_dirty_for_io(folio))
+ BUG();
+ folio_start_writeback(folio);
+ netfs_folio_start_fscache(caching, folio);
+ folio_unlock(folio);
+ }
+
+ folio_batch_release(&fbatch);
+ cond_resched();
+ } while (!stop);
+}
+
+/*
+ * Synchronously write back the locked page and any subsequent non-locked dirty
+ * pages.
+ */
+static ssize_t netfs_write_back_from_locked_folio(struct address_space *mapping,
+ struct writeback_control *wbc,
+ struct netfs_group *group,
+ struct xa_state *xas,
+ struct folio *folio,
+ unsigned long long start,
+ unsigned long long end)
+{
+ struct netfs_io_request *wreq;
+ struct netfs_folio *finfo;
+ struct netfs_inode *ctx = netfs_inode(mapping->host);
+ unsigned long long i_size = i_size_read(&ctx->inode);
+ size_t len, max_len;
+ bool caching = netfs_is_cache_enabled(ctx);
+ long count = wbc->nr_to_write;
+ int ret;
+
+ _enter(",%lx,%llx-%llx,%u", folio_index(folio), start, end, caching);
+
+ wreq = netfs_alloc_request(mapping, NULL, start, folio_size(folio),
+ NETFS_WRITEBACK);
+ if (IS_ERR(wreq)) {
+ folio_unlock(folio);
+ return PTR_ERR(wreq);
+ }
+
+ if (!folio_clear_dirty_for_io(folio))
+ BUG();
+ folio_start_writeback(folio);
+ netfs_folio_start_fscache(caching, folio);
+
+ count -= folio_nr_pages(folio);
+
+ /* Find all consecutive lockable dirty pages that have contiguous
+ * written regions, stopping when we find a page that is not
+ * immediately lockable, is not dirty or is missing, or we reach the
+ * end of the range.
+ */
+ trace_netfs_folio(folio, netfs_folio_trace_store);
+
+ len = wreq->len;
+ finfo = netfs_folio_info(folio);
+ if (finfo) {
+ start += finfo->dirty_offset;
+ if (finfo->dirty_offset + finfo->dirty_len != len) {
+ len = finfo->dirty_len;
+ goto cant_expand;
+ }
+ len = finfo->dirty_len;
+ }
+
+ if (start < i_size) {
+ /* Trim the write to the EOF; the extra data is ignored. Also
+ * put an upper limit on the size of a single storedata op.
+ */
+ max_len = 65536 * 4096;
+ max_len = min_t(unsigned long long, max_len, end - start + 1);
+ max_len = min_t(unsigned long long, max_len, i_size - start);
+
+ if (len < max_len)
+ netfs_extend_writeback(mapping, group, xas, &count, start,
+ max_len, caching, &len, &wreq->upper_len);
+ }
+
+cant_expand:
+ len = min_t(unsigned long long, len, i_size - start);
+
+ /* We now have a contiguous set of dirty pages, each with writeback
+ * set; the first page is still locked at this point, but all the rest
+ * have been unlocked.
+ */
+ folio_unlock(folio);
+ wreq->start = start;
+ wreq->len = len;
+
+ if (start < i_size) {
+ _debug("write back %zx @%llx [%llx]", len, start, i_size);
+
+ /* Speculatively write to the cache. We have to fix this up
+ * later if the store fails.
+ */
+ wreq->cleanup = netfs_cleanup_buffered_write;
+
+ iov_iter_xarray(&wreq->iter, ITER_SOURCE, &mapping->i_pages, start,
+ wreq->upper_len);
+ __set_bit(NETFS_RREQ_UPLOAD_TO_SERVER, &wreq->flags);
+ ret = netfs_begin_write(wreq, true, netfs_write_trace_writeback);
+ if (ret == 0 || ret == -EIOCBQUEUED)
+ wbc->nr_to_write -= len / PAGE_SIZE;
+ } else {
+ _debug("write discard %zx @%llx [%llx]", len, start, i_size);
+
+ /* The dirty region was entirely beyond the EOF. */
+ fscache_clear_page_bits(mapping, start, len, caching);
+ netfs_pages_written_back(wreq);
+ ret = 0;
+ }
+
+ netfs_put_request(wreq, false, netfs_rreq_trace_put_return);
+ _leave(" = 1");
+ return 1;
+}
+
+/*
+ * Write a region of pages back to the server
+ */
+static ssize_t netfs_writepages_begin(struct address_space *mapping,
+ struct writeback_control *wbc,
+ struct netfs_group *group,
+ struct xa_state *xas,
+ unsigned long long *_start,
+ unsigned long long end)
+{
+ const struct netfs_folio *finfo;
+ struct folio *folio;
+ unsigned long long start = *_start;
+ ssize_t ret;
+ void *priv;
+ int skips = 0;
+
+ _enter("%llx,%llx,", start, end);
+
+search_again:
+ /* Find the first dirty page in the group. */
+ rcu_read_lock();
+
+ for (;;) {
+ folio = xas_find_marked(xas, end / PAGE_SIZE, PAGECACHE_TAG_DIRTY);
+ if (xas_retry(xas, folio) || xa_is_value(folio))
+ continue;
+ if (!folio)
+ break;
+
+ if (!folio_try_get_rcu(folio)) {
+ xas_reset(xas);
+ continue;
+ }
+
+ if (unlikely(folio != xas_reload(xas))) {
+ folio_put(folio);
+ xas_reset(xas);
+ continue;
+ }
+
+ /* Skip any dirty folio that's not in the group of interest. */
+ priv = folio_get_private(folio);
+ if ((const struct netfs_group *)priv != group) {
+ finfo = netfs_folio_info(folio);
+ if (finfo->netfs_group != group) {
+ folio_put(folio);
+ continue;
+ }
+ }
+
+ xas_pause(xas);
+ break;
+ }
+ rcu_read_unlock();
+ if (!folio)
+ return 0;
+
+ start = folio_pos(folio); /* May regress with THPs */
+
+ _debug("wback %lx", folio_index(folio));
+
+ /* At this point we hold neither the i_pages lock nor the page lock:
+ * the page may be truncated or invalidated (changing page->mapping to
+ * NULL), or even swizzled back from swapper_space to tmpfs file
+ * mapping
+ */
+lock_again:
+ if (wbc->sync_mode != WB_SYNC_NONE) {
+ ret = folio_lock_killable(folio);
+ if (ret < 0)
+ return ret;
+ } else {
+ if (!folio_trylock(folio))
+ goto search_again;
+ }
+
+ if (folio->mapping != mapping ||
+ !folio_test_dirty(folio)) {
+ start += folio_size(folio);
+ folio_unlock(folio);
+ goto search_again;
+ }
+
+ if (folio_test_writeback(folio) ||
+ folio_test_fscache(folio)) {
+ folio_unlock(folio);
+ if (wbc->sync_mode != WB_SYNC_NONE) {
+ folio_wait_writeback(folio);
+#ifdef CONFIG_NETFS_FSCACHE
+ folio_wait_fscache(folio);
+#endif
+ goto lock_again;
+ }
+
+ start += folio_size(folio);
+ if (wbc->sync_mode == WB_SYNC_NONE) {
+ if (skips >= 5 || need_resched()) {
+ ret = 0;
+ goto out;
+ }
+ skips++;
+ }
+ goto search_again;
+ }
+
+ ret = netfs_write_back_from_locked_folio(mapping, wbc, group, xas,
+ folio, start, end);
+out:
+ if (ret > 0)
+ *_start = start + ret;
+ _leave(" = %zd [%llx]", ret, *_start);
+ return ret;
+}
+
+/*
+ * Write a region of pages back to the server
+ */
+static int netfs_writepages_region(struct address_space *mapping,
+ struct writeback_control *wbc,
+ struct netfs_group *group,
+ unsigned long long *_start,
+ unsigned long long end)
+{
+ ssize_t ret;
+
+ XA_STATE(xas, &mapping->i_pages, *_start / PAGE_SIZE);
+
+ do {
+ ret = netfs_writepages_begin(mapping, wbc, group, &xas,
+ _start, end);
+ if (ret > 0 && wbc->nr_to_write > 0)
+ cond_resched();
+ } while (ret > 0 && wbc->nr_to_write > 0);
+
+ return ret > 0 ? 0 : ret;
+}
+
+/*
+ * write some of the pending data back to the server
+ */
+int netfs_writepages(struct address_space *mapping,
+ struct writeback_control *wbc)
+{
+ struct netfs_group *group = NULL;
+ loff_t start, end;
+ int ret;
+
+ _enter("");
+
+ /* We have to be careful as we can end up racing with setattr()
+ * truncating the pagecache since the caller doesn't take a lock here
+ * to prevent it.
+ */
+
+ if (wbc->range_cyclic && mapping->writeback_index) {
+ start = mapping->writeback_index * PAGE_SIZE;
+ ret = netfs_writepages_region(mapping, wbc, group,
+ &start, LLONG_MAX);
+ if (ret < 0)
+ goto out;
+
+ if (wbc->nr_to_write <= 0) {
+ mapping->writeback_index = start / PAGE_SIZE;
+ goto out;
+ }
+
+ start = 0;
+ end = mapping->writeback_index * PAGE_SIZE;
+ mapping->writeback_index = 0;
+ ret = netfs_writepages_region(mapping, wbc, group, &start, end);
+ if (ret == 0)
+ mapping->writeback_index = start / PAGE_SIZE;
+ } else if (wbc->range_start == 0 && wbc->range_end == LLONG_MAX) {
+ start = 0;
+ ret = netfs_writepages_region(mapping, wbc, group,
+ &start, LLONG_MAX);
+ if (wbc->nr_to_write > 0 && ret == 0)
+ mapping->writeback_index = start / PAGE_SIZE;
+ } else {
+ start = wbc->range_start;
+ ret = netfs_writepages_region(mapping, wbc, group,
+ &start, wbc->range_end);
+ }
+
+out:
+ _leave(" = %d", ret);
+ return ret;
+}
+EXPORT_SYMBOL(netfs_writepages);