1 files changed, 79 insertions, 282 deletions

diff --git a/fs/netfs/write_collect.c b/fs/netfs/write_collect.c
index ca3a11ed9b54..e2b102ffb768 100644
--- a/fs/netfs/write_collect.c
+++ b/fs/netfs/write_collect.c
@@ -17,10 +17,38 @@
 #define HIT_PENDING		0x01	/* A front op was still pending */
 #define NEED_REASSESS		0x02	/* Need to loop round and reassess */
 #define MADE_PROGRESS		0x04	/* Made progress cleaning up a stream or the folio set */
-#define BUFFERED		0x08	/* The pagecache needs cleaning up */
+#define NEED_UNLOCK		0x08	/* The pagecache needs unlocking */
 #define NEED_RETRY		0x10	/* A front op requests retrying */
 #define SAW_FAILURE		0x20	/* One stream or hit a permanent failure */
 
+static void netfs_dump_request(const struct netfs_io_request *rreq)
+{
+	pr_err("Request R=%08x r=%d fl=%lx or=%x e=%ld\n",
+	       rreq->debug_id, refcount_read(&rreq->ref), rreq->flags,
+	       rreq->origin, rreq->error);
+	pr_err("  st=%llx tsl=%zx/%llx/%llx\n",
+	       rreq->start, rreq->transferred, rreq->submitted, rreq->len);
+	pr_err("  cci=%llx/%llx/%llx\n",
+	       rreq->cleaned_to, rreq->collected_to, atomic64_read(&rreq->issued_to));
+	pr_err("  iw=%pSR\n", rreq->netfs_ops->issue_write);
+	for (int i = 0; i < NR_IO_STREAMS; i++) {
+		const struct netfs_io_subrequest *sreq;
+		const struct netfs_io_stream *s = &rreq->io_streams[i];
+
+		pr_err("  str[%x] s=%x e=%d acnf=%u,%u,%u,%u\n",
+		       s->stream_nr, s->source, s->error,
+		       s->avail, s->active, s->need_retry, s->failed);
+		pr_err("  str[%x] ct=%llx t=%zx\n",
+		       s->stream_nr, s->collected_to, s->transferred);
+		list_for_each_entry(sreq, &s->subrequests, rreq_link) {
+			pr_err("  sreq[%x:%x] sc=%u s=%llx t=%zx/%zx r=%d f=%lx\n",
+			       sreq->stream_nr, sreq->debug_index, sreq->source,
+			       sreq->start, sreq->transferred, sreq->len,
+			       refcount_read(&sreq->ref), sreq->flags);
+		}
+	}
+}
+
 /*
  * Successful completion of write of a folio to the server and/or cache.  Note
  * that we are not allowed to lock the folio here on pain of deadlocking with
@@ -83,9 +111,15 @@ end_wb:
 static void netfs_writeback_unlock_folios(struct netfs_io_request *wreq,
 					  unsigned int *notes)
 {
-	struct folio_queue *folioq = wreq->buffer;
+	struct folio_queue *folioq = wreq->buffer.tail;
 	unsigned long long collected_to = wreq->collected_to;
-	unsigned int slot = wreq->buffer_head_slot;
+	unsigned int slot = wreq->buffer.first_tail_slot;
+
+	if (WARN_ON_ONCE(!folioq)) {
+		pr_err("[!] Writeback unlock found empty rolling buffer!\n");
+		netfs_dump_request(wreq);
+		return;
+	}
 
 	if (wreq->origin == NETFS_PGPRIV2_COPY_TO_CACHE) {
 		if (netfs_pgpriv2_unlock_copied_folios(wreq))
@@ -94,7 +128,9 @@ static void netfs_writeback_unlock_folios(struct netfs_io_request *wreq,
 	}
 
 	if (slot >= folioq_nr_slots(folioq)) {
-		folioq = netfs_delete_buffer_head(wreq);
+		folioq = rolling_buffer_delete_spent(&wreq->buffer);
+		if (!folioq)
+			return;
 		slot = 0;
 	}
 
@@ -134,9 +170,9 @@ static void netfs_writeback_unlock_folios(struct netfs_io_request *wreq,
 		folioq_clear(folioq, slot);
 		slot++;
 		if (slot >= folioq_nr_slots(folioq)) {
-			if (READ_ONCE(wreq->buffer_tail) == folioq)
-				break;
-			folioq = netfs_delete_buffer_head(wreq);
+			folioq = rolling_buffer_delete_spent(&wreq->buffer);
+			if (!folioq)
+				goto done;
 			slot = 0;
 		}
 
@@ -144,222 +180,9 @@ static void netfs_writeback_unlock_folios(struct netfs_io_request *wreq,
 			break;
 	}
 
-	wreq->buffer = folioq;
-	wreq->buffer_head_slot = slot;
-}
-
-/*
- * Perform retries on the streams that need it.
- */
-static void netfs_retry_write_stream(struct netfs_io_request *wreq,
-				     struct netfs_io_stream *stream)
-{
-	struct list_head *next;
-
-	_enter("R=%x[%x:]", wreq->debug_id, stream->stream_nr);
-
-	if (list_empty(&stream->subrequests))
-		return;
-
-	if (stream->source == NETFS_UPLOAD_TO_SERVER &&
-	    wreq->netfs_ops->retry_request)
-		wreq->netfs_ops->retry_request(wreq, stream);
-
-	if (unlikely(stream->failed))
-		return;
-
-	/* If there's no renegotiation to do, just resend each failed subreq. */
-	if (!stream->prepare_write) {
-		struct netfs_io_subrequest *subreq;
-
-		list_for_each_entry(subreq, &stream->subrequests, rreq_link) {
-			if (test_bit(NETFS_SREQ_FAILED, &subreq->flags))
-				break;
-			if (__test_and_clear_bit(NETFS_SREQ_NEED_RETRY, &subreq->flags)) {
-				struct iov_iter source = subreq->io_iter;
-
-				iov_iter_revert(&source, subreq->len - source.count);
-				netfs_get_subrequest(subreq, netfs_sreq_trace_get_resubmit);
-				netfs_reissue_write(stream, subreq, &source);
-			}
-		}
-		return;
-	}
-
-	next = stream->subrequests.next;
-
-	do {
-		struct netfs_io_subrequest *subreq = NULL, *from, *to, *tmp;
-		struct iov_iter source;
-		unsigned long long start, len;
-		size_t part;
-		bool boundary = false;
-
-		/* Go through the stream and find the next span of contiguous
-		 * data that we then rejig (cifs, for example, needs the wsize
-		 * renegotiating) and reissue.
-		 */
-		from = list_entry(next, struct netfs_io_subrequest, rreq_link);
-		to = from;
-		start = from->start + from->transferred;
-		len   = from->len   - from->transferred;
-
-		if (test_bit(NETFS_SREQ_FAILED, &from->flags) ||
-		    !test_bit(NETFS_SREQ_NEED_RETRY, &from->flags))
-			return;
-
-		list_for_each_continue(next, &stream->subrequests) {
-			subreq = list_entry(next, struct netfs_io_subrequest, rreq_link);
-			if (subreq->start + subreq->transferred != start + len ||
-			    test_bit(NETFS_SREQ_BOUNDARY, &subreq->flags) ||
-			    !test_bit(NETFS_SREQ_NEED_RETRY, &subreq->flags))
-				break;
-			to = subreq;
-			len += to->len;
-		}
-
-		/* Determine the set of buffers we're going to use.  Each
-		 * subreq gets a subset of a single overall contiguous buffer.
-		 */
-		netfs_reset_iter(from);
-		source = from->io_iter;
-		source.count = len;
-
-		/* Work through the sublist. */
-		subreq = from;
-		list_for_each_entry_from(subreq, &stream->subrequests, rreq_link) {
-			if (!len)
-				break;
-			/* Renegotiate max_len (wsize) */
-			trace_netfs_sreq(subreq, netfs_sreq_trace_retry);
-			__clear_bit(NETFS_SREQ_NEED_RETRY, &subreq->flags);
-			subreq->retry_count++;
-			stream->prepare_write(subreq);
-
-			part = min(len, stream->sreq_max_len);
-			subreq->len = part;
-			subreq->start = start;
-			subreq->transferred = 0;
-			len -= part;
-			start += part;
-			if (len && subreq == to &&
-			    __test_and_clear_bit(NETFS_SREQ_BOUNDARY, &to->flags))
-				boundary = true;
-
-			netfs_get_subrequest(subreq, netfs_sreq_trace_get_resubmit);
-			netfs_reissue_write(stream, subreq, &source);
-			if (subreq == to)
-				break;
-		}
-
-		/* If we managed to use fewer subreqs, we can discard the
-		 * excess; if we used the same number, then we're done.
-		 */
-		if (!len) {
-			if (subreq == to)
-				continue;
-			list_for_each_entry_safe_from(subreq, tmp,
-						      &stream->subrequests, rreq_link) {
-				trace_netfs_sreq(subreq, netfs_sreq_trace_discard);
-				list_del(&subreq->rreq_link);
-				netfs_put_subrequest(subreq, false, netfs_sreq_trace_put_done);
-				if (subreq == to)
-					break;
-			}
-			continue;
-		}
-
-		/* We ran out of subrequests, so we need to allocate some more
-		 * and insert them after.
-		 */
-		do {
-			subreq = netfs_alloc_subrequest(wreq);
-			subreq->source		= to->source;
-			subreq->start		= start;
-			subreq->debug_index	= atomic_inc_return(&wreq->subreq_counter);
-			subreq->stream_nr	= to->stream_nr;
-			subreq->retry_count	= 1;
-
-			trace_netfs_sreq_ref(wreq->debug_id, subreq->debug_index,
-					     refcount_read(&subreq->ref),
-					     netfs_sreq_trace_new);
-			netfs_get_subrequest(subreq, netfs_sreq_trace_get_resubmit);
-
-			list_add(&subreq->rreq_link, &to->rreq_link);
-			to = list_next_entry(to, rreq_link);
-			trace_netfs_sreq(subreq, netfs_sreq_trace_retry);
-
-			stream->sreq_max_len	= len;
-			stream->sreq_max_segs	= INT_MAX;
-			switch (stream->source) {
-			case NETFS_UPLOAD_TO_SERVER:
-				netfs_stat(&netfs_n_wh_upload);
-				stream->sreq_max_len = umin(len, wreq->wsize);
-				break;
-			case NETFS_WRITE_TO_CACHE:
-				netfs_stat(&netfs_n_wh_write);
-				break;
-			default:
-				WARN_ON_ONCE(1);
-			}
-
-			stream->prepare_write(subreq);
-
-			part = umin(len, stream->sreq_max_len);
-			subreq->len = subreq->transferred + part;
-			len -= part;
-			start += part;
-			if (!len && boundary) {
-				__set_bit(NETFS_SREQ_BOUNDARY, &to->flags);
-				boundary = false;
-			}
-
-			netfs_reissue_write(stream, subreq, &source);
-			if (!len)
-				break;
-
-		} while (len);
-
-	} while (!list_is_head(next, &stream->subrequests));
-}
-
-/*
- * Perform retries on the streams that need it.  If we're doing content
- * encryption and the server copy changed due to a third-party write, we may
- * need to do an RMW cycle and also rewrite the data to the cache.
- */
-static void netfs_retry_writes(struct netfs_io_request *wreq)
-{
-	struct netfs_io_subrequest *subreq;
-	struct netfs_io_stream *stream;
-	int s;
-
-	/* Wait for all outstanding I/O to quiesce before performing retries as
-	 * we may need to renegotiate the I/O sizes.
-	 */
-	for (s = 0; s < NR_IO_STREAMS; s++) {
-		stream = &wreq->io_streams[s];
-		if (!stream->active)
-			continue;
-
-		list_for_each_entry(subreq, &stream->subrequests, rreq_link) {
-			wait_on_bit(&subreq->flags, NETFS_SREQ_IN_PROGRESS,
-				    TASK_UNINTERRUPTIBLE);
-		}
-	}
-
-	// TODO: Enc: Fetch changed partial pages
-	// TODO: Enc: Reencrypt content if needed.
-	// TODO: Enc: Wind back transferred point.
-	// TODO: Enc: Mark cache pages for retry.
-
-	for (s = 0; s < NR_IO_STREAMS; s++) {
-		stream = &wreq->io_streams[s];
-		if (stream->need_retry) {
-			stream->need_retry = false;
-			netfs_retry_write_stream(wreq, stream);
-		}
-	}
+	wreq->buffer.tail = folioq;
+done:
+	wreq->buffer.first_tail_slot = slot;
 }
 
 /*
@@ -390,7 +213,7 @@ reassess_streams:
 	if (wreq->origin == NETFS_WRITEBACK ||
 	    wreq->origin == NETFS_WRITETHROUGH ||
 	    wreq->origin == NETFS_PGPRIV2_COPY_TO_CACHE)
-		notes = BUFFERED;
+		notes = NEED_UNLOCK;
 	else
 		notes = 0;
 
@@ -449,15 +272,15 @@ reassess_streams:
 
 		cancel:
 			/* Remove if completely consumed. */
-			spin_lock_bh(&wreq->lock);
+			spin_lock(&wreq->lock);
 
 			remove = front;
 			list_del_init(&front->rreq_link);
 			front = list_first_entry_or_null(&stream->subrequests,
 							 struct netfs_io_subrequest, rreq_link);
 			stream->front = front;
-			spin_unlock_bh(&wreq->lock);
-			netfs_put_subrequest(remove, false,
+			spin_unlock(&wreq->lock);
+			netfs_put_subrequest(remove,
 					     notes & SAW_FAILURE ?
 					     netfs_sreq_trace_put_cancel :
 					     netfs_sreq_trace_put_done);
@@ -487,7 +310,7 @@ reassess_streams:
 	trace_netfs_collect_state(wreq, wreq->collected_to, notes);
 
 	/* Unlock any folios that we have now finished with. */
-	if (notes & BUFFERED) {
+	if (notes & NEED_UNLOCK) {
 		if (wreq->cleaned_to < wreq->collected_to)
 			netfs_writeback_unlock_folios(wreq, &notes);
 	} else {
@@ -498,16 +321,14 @@ reassess_streams:
 
 	if (notes & NEED_RETRY)
 		goto need_retry;
-	if ((notes & MADE_PROGRESS) && test_bit(NETFS_RREQ_PAUSE, &wreq->flags)) {
-		trace_netfs_rreq(wreq, netfs_rreq_trace_unpause);
-		clear_and_wake_up_bit(NETFS_RREQ_PAUSE, &wreq->flags);
-	}
 
-	if (notes & NEED_REASSESS) {
+	if (notes & MADE_PROGRESS) {
+		netfs_wake_rreq_flag(wreq, NETFS_RREQ_PAUSE, netfs_rreq_trace_unpause);
 		//cond_resched();
 		goto reassess_streams;
 	}
-	if (notes & MADE_PROGRESS) {
+
+	if (notes & NEED_REASSESS) {
 		//cond_resched();
 		goto reassess_streams;
 	}
@@ -531,30 +352,21 @@ need_retry:
 /*
  * Perform the collection of subrequests, folios and encryption buffers.
  */
-void netfs_write_collection_worker(struct work_struct *work)
+bool netfs_write_collection(struct netfs_io_request *wreq)
 {
-	struct netfs_io_request *wreq = container_of(work, struct netfs_io_request, work);
 	struct netfs_inode *ictx = netfs_inode(wreq->inode);
 	size_t transferred;
 	int s;
 
 	_enter("R=%x", wreq->debug_id);
 
-	netfs_see_request(wreq, netfs_rreq_trace_see_work);
-	if (!test_bit(NETFS_RREQ_IN_PROGRESS, &wreq->flags)) {
-		netfs_put_request(wreq, false, netfs_rreq_trace_put_work);
-		return;
-	}
-
 	netfs_collect_write_results(wreq);
 
 	/* We're done when the app thread has finished posting subreqs and all
 	 * the queues in all the streams are empty.
 	 */
-	if (!test_bit(NETFS_RREQ_ALL_QUEUED, &wreq->flags)) {
-		netfs_put_request(wreq, false, netfs_rreq_trace_put_work);
-		return;
-	}
+	if (!test_bit(NETFS_RREQ_ALL_QUEUED, &wreq->flags))
+		return false;
 	smp_rmb(); /* Read ALL_QUEUED before lists. */
 
 	transferred = LONG_MAX;
@@ -562,10 +374,8 @@ void netfs_write_collection_worker(struct work_struct *work)
 		struct netfs_io_stream *stream = &wreq->io_streams[s];
 		if (!stream->active)
 			continue;
-		if (!list_empty(&stream->subrequests)) {
-			netfs_put_request(wreq, false, netfs_rreq_trace_put_work);
-			return;
-		}
+		if (!list_empty(&stream->subrequests))
+			return false;
 		if (stream->transferred < transferred)
 			transferred = stream->transferred;
 	}
@@ -575,7 +385,8 @@ void netfs_write_collection_worker(struct work_struct *work)
 	trace_netfs_rreq(wreq, netfs_rreq_trace_write_done);
 
 	if (wreq->io_streams[1].active &&
-	    wreq->io_streams[1].failed) {
+	    wreq->io_streams[1].failed &&
+	    ictx->ops->invalidate_cache) {
 		/* Cache write failure doesn't prevent writeback completion
 		 * unless we're in disconnected mode.
 		 */
@@ -602,8 +413,8 @@ void netfs_write_collection_worker(struct work_struct *work)
 		inode_dio_end(wreq->inode);
 
 	_debug("finished");
-	trace_netfs_rreq(wreq, netfs_rreq_trace_wake_ip);
-	clear_and_wake_up_bit(NETFS_RREQ_IN_PROGRESS, &wreq->flags);
+	netfs_wake_rreq_flag(wreq, NETFS_RREQ_IN_PROGRESS, netfs_rreq_trace_wake_ip);
+	/* As we cleared NETFS_RREQ_IN_PROGRESS, we acquired its ref. */
 
 	if (wreq->iocb) {
 		size_t written = min(wreq->transferred, wreq->len);
@@ -614,19 +425,21 @@ void netfs_write_collection_worker(struct work_struct *work)
 		wreq->iocb = VFS_PTR_POISON;
 	}
 
-	netfs_clear_subrequests(wreq, false);
-	netfs_put_request(wreq, false, netfs_rreq_trace_put_work_complete);
+	netfs_clear_subrequests(wreq);
+	return true;
 }
 
-/*
- * Wake the collection work item.
- */
-void netfs_wake_write_collector(struct netfs_io_request *wreq, bool was_async)
+void netfs_write_collection_worker(struct work_struct *work)
 {
-	if (!work_pending(&wreq->work)) {
-		netfs_get_request(wreq, netfs_rreq_trace_get_work);
-		if (!queue_work(system_unbound_wq, &wreq->work))
-			netfs_put_request(wreq, was_async, netfs_rreq_trace_put_work_nq);
+	struct netfs_io_request *rreq = container_of(work, struct netfs_io_request, work);
+
+	netfs_see_request(rreq, netfs_rreq_trace_see_work);
+	if (test_bit(NETFS_RREQ_IN_PROGRESS, &rreq->flags)) {
+		if (netfs_write_collection(rreq))
+			/* Drop the ref from the IN_PROGRESS flag. */
+			netfs_put_request(rreq, netfs_rreq_trace_put_work_ip);
+		else
+			netfs_see_request(rreq, netfs_rreq_trace_see_work_complete);
 	}
 }
 
@@ -634,7 +447,6 @@ void netfs_wake_write_collector(struct netfs_io_request *wreq, bool was_async)
  * netfs_write_subrequest_terminated - Note the termination of a write operation.
  * @_op: The I/O request that has terminated.
  * @transferred_or_error: The amount of data transferred or an error code.
- * @was_async: The termination was asynchronous
  *
  * This tells the library that a contributory write I/O operation has
  * terminated, one way or another, and that it should collect the results.
@@ -644,21 +456,16 @@ void netfs_wake_write_collector(struct netfs_io_request *wreq, bool was_async)
  * negative error code.  The library will look after reissuing I/O operations
  * as appropriate and writing downloaded data to the cache.
  *
- * If @was_async is true, the caller might be running in softirq or interrupt
- * context and we can't sleep.
- *
  * When this is called, ownership of the subrequest is transferred back to the
  * library, along with a ref.
  *
  * Note that %_op is a void* so that the function can be passed to
  * kiocb::term_func without the need for a casting wrapper.
  */
-void netfs_write_subrequest_terminated(void *_op, ssize_t transferred_or_error,
-				       bool was_async)
+void netfs_write_subrequest_terminated(void *_op, ssize_t transferred_or_error)
 {
 	struct netfs_io_subrequest *subreq = _op;
 	struct netfs_io_request *wreq = subreq->rreq;
-	struct netfs_io_stream *stream = &wreq->io_streams[subreq->stream_nr];
 
 	_enter("%x[%x] %zd", wreq->debug_id, subreq->debug_index, transferred_or_error);
 
@@ -669,8 +476,6 @@ void netfs_write_subrequest_terminated(void *_op, ssize_t transferred_or_error,
 	case NETFS_WRITE_TO_CACHE:
 		netfs_stat(&netfs_n_wh_write_done);
 		break;
-	case NETFS_INVALID_WRITE:
-		break;
 	default:
 		BUG();
 	}
@@ -710,15 +515,7 @@ void netfs_write_subrequest_terminated(void *_op, ssize_t transferred_or_error,
 	}
 
 	trace_netfs_sreq(subreq, netfs_sreq_trace_terminated);
-
-	clear_and_wake_up_bit(NETFS_SREQ_IN_PROGRESS, &subreq->flags);
-
-	/* If we are at the head of the queue, wake up the collector,
-	 * transferring a ref to it if we were the ones to do so.
-	 */
-	if (list_is_first(&subreq->rreq_link, &stream->subrequests))
-		netfs_wake_write_collector(wreq, was_async);
-
-	netfs_put_subrequest(subreq, was_async, netfs_sreq_trace_put_terminated);
+	netfs_subreq_clear_in_progress(subreq);
+	netfs_put_subrequest(subreq, netfs_sreq_trace_put_terminated);
 }
 EXPORT_SYMBOL(netfs_write_subrequest_terminated);