diff --git a/meson.build b/meson.build
index 37c14687..ce386a4c 100644
--- a/meson.build
+++ b/meson.build
@@ -46,6 +46,7 @@ have_funcs = [
 	'memfd_create',
 	'mremap',
 	'strndup',
+	'gettid',
 ]
 foreach f: have_funcs
 	config_h.set('HAVE_' + f.underscorify().to_upper(), cc.has_function(f))
diff --git a/protocol/wayland.xml b/protocol/wayland.xml
index bee74a10..60da1ad0 100644
--- a/protocol/wayland.xml
+++ b/protocol/wayland.xml
@@ -230,8 +230,43 @@
 	The buffer is created offset bytes into the pool and has
 	width and height as specified.  The stride argument specifies
 	the number of bytes from the beginning of one row to the beginning
-	of the next.  The format is the pixel format of the buffer and
-	must be one of those advertised through the wl_shm.format event.
+	of the next; if the pixel format has multiple planes the stride
+	applies to the first plane. The format is the pixel format of the
+	buffer and must be one of those advertised through the wl_shm.format
+	event.
+
+	When the pixel format has multiple planes, the strides and starting
+	offsets of the individual planes are derived from the provided
+	stride as follows. Denote "stride", "width", "height" as the provided
+	arguments. Let "p" be the number of planes. For the sake of
+	calculating parameters, we will require that each plane, seen as a
+	width x height grid of squares, can be decomposed into an array of
+	disjoint, tightly packed, indivisible rectangular blocks (which to
+	make calculations easier, here encompass both subsampling and the
+	packing of subsampled pixel data together into short byte sequences.)
+	For each plane index "i" between 1 and p, let "blockw[i]" be the
+	width of the blocks for plane i, blockh[i] the height of the blocks,
+	and "bpb[i]" the number of bytes used to encode each block.
+	(For example: for the purely subsampled two-plane format nv12,
+	blockw[2] = blockh[2] = 2 and bpb[2] = 2, because each Cr:Cb plane
+	entry corresponds (roughly; the interpretation may be more
+	complicated) to a 2x2 region of pixels, while for the packed single
+	plane format y210, blockw[1] = 2, blockh[1] = 1, and bpb[1] = 8.
+	For p030, which has both 3x1 packing and 2x2 subsampling,
+	blockw[2] = 6, blockh[2] = 2, and bpb[2] = 8.)
+
+	Parameters are valid only if, for each plane i, width % blockw[i] = 0
+	and height % blockh[i] = 0. Furthermore, stride % bpb[1] = 0 is needed.
+	Let ext_width = stride / bpb[1]. For each plane i, ext_width must
+	satisfy ext_width % blockw[i] = 0. Then define the stride of the
+	ith plane, "stride[i]", to be ext_width * bpb[i] / blockw[i].
+	The offset of the ith plane is
+	offset + sum_{i = 1}^{i - 1} stride[i] * (height / blockh[i]); this
+	evaluates to just offset when i = 1.
+
+	Formats (like yuv420_10bit or vuy101010) whose description does not
+	match the above multiplanar, linear layout model have unspecified
+	interpretation.
 
 	A buffer will keep a reference to the pool it was created from
 	so it is valid to destroy the pool immediately after creating
diff --git a/src/connection.c b/src/connection.c
index 593f52f3..2d1e8d1d 100644
--- a/src/connection.c
+++ b/src/connection.c
@@ -26,6 +26,8 @@
 
 #define _GNU_SOURCE
 
+#include "../config.h"
+
 #include <math.h>
 #include <stdlib.h>
 #include <stdint.h>
@@ -1491,11 +1493,56 @@ wl_closure_queue(struct wl_closure *closure, struct wl_connection *connection)
 	return result;
 }
 
+bool
+wl_check_env_token(const char *env, const char *token)
+{
+	const char *ptr = env;
+	size_t token_len;
+
+	if (env == NULL)
+		return false;
+
+	token_len = strlen(token);
+
+	// Scan the string for comma-separated tokens and look for a match.
+	while (true) {
+		const char *end;
+		size_t len;
+
+		// Skip over any leading separators.
+		while (*ptr == ',')
+			ptr++;
+
+		if (*ptr == '\x00')
+			return false;
+
+		end = strchr(ptr + 1, ',');
+
+		// If there isn't another separarator, then the rest of the string
+		// is one token.
+		if (end == NULL)
+			return (strcmp(ptr, token) == 0);
+
+		len = end - ptr;
+		if (len == token_len && memcmp(ptr, token, len) == 0) {
+			return true;
+		}
+
+		// Skip to the next token.
+		ptr += len;
+	}
+
+	return false;
+}
+
 void
 wl_closure_print(struct wl_closure *closure, struct wl_object *target,
 		 int send, int discarded, uint32_t (*n_parse)(union wl_argument *arg),
 		 const char *queue_name, int color)
 {
+#if defined(HAVE_GETTID)
+	static int include_tid = -1;
+#endif // defined(HAVE_GETTID)
 	int i;
 	struct argument_details arg;
 	const char *signature = closure->message->signature;
@@ -1516,6 +1563,18 @@ wl_closure_print(struct wl_closure *closure, struct wl_object *target,
 		color ? WL_DEBUG_COLOR_GREEN : "",
 		time / 1000, time % 1000);
 
+#if defined(HAVE_GETTID)
+	if (include_tid < 0) {
+		include_tid = wl_check_env_token(getenv("WAYLAND_DEBUG"), "thread_id");
+	}
+
+	if (include_tid) {
+		fprintf(f, "%sTID#%d ",
+			color ? WL_DEBUG_COLOR_CYAN : "",
+			(int) gettid());
+	}
+#endif
+
 	if (queue_name) {
 		fprintf(f, "%s{%s} ",
 			color ? WL_DEBUG_COLOR_YELLOW : "",
diff --git a/src/wayland-client-core.h b/src/wayland-client-core.h
index 970e6254..e0523e49 100644
--- a/src/wayland-client-core.h
+++ b/src/wayland-client-core.h
@@ -268,9 +268,16 @@ int
 wl_display_dispatch_queue_pending(struct wl_display *display,
 				  struct wl_event_queue *queue);
 
+int
+wl_display_dispatch_queue_pending_single(struct wl_display *display,
+					 struct wl_event_queue *queue);
+
 int
 wl_display_dispatch_pending(struct wl_display *display);
 
+int
+wl_display_dispatch_pending_single(struct wl_display *display);
+
 int
 wl_display_get_error(struct wl_display *display);
 
diff --git a/src/wayland-client.c b/src/wayland-client.c
index c8633046..ed686b5c 100644
--- a/src/wayland-client.c
+++ b/src/wayland-client.c
@@ -1236,7 +1236,7 @@ wl_display_connect_to_fd(int fd)
 	no_color = getenv("NO_COLOR");
 	force_color = getenv("FORCE_COLOR");
 	debug = getenv("WAYLAND_DEBUG");
-	if (debug && (strstr(debug, "client") || strstr(debug, "1"))) {
+	if (debug && (wl_check_env_token(debug, "client") || wl_check_env_token(debug, "1"))) {
 		debug_client = 1;
 		if (isatty(fileno(stderr)))
 			debug_color = 1;
@@ -1882,6 +1882,34 @@ err:
 	return -1;
 }
 
+
+static int
+dispatch_queue_single(struct wl_display *display, struct wl_event_queue *queue)
+{
+	if (display->last_error)
+		goto err;
+
+	while (!wl_list_empty(&display->display_queue.event_list)) {
+		dispatch_event(display, &display->display_queue);
+		if (display->last_error)
+			goto err;
+	}
+
+	if (!wl_list_empty(&queue->event_list)) {
+		dispatch_event(display, queue);
+		if (display->last_error)
+			goto err;
+		return 1;
+	} else {
+		return 0;
+	}
+
+err:
+	errno = display->last_error;
+
+	return -1;
+}
+
 /** Prepare to read events from the display's file descriptor to a queue
  *
  * \param display The display context object
@@ -2212,6 +2240,34 @@ wl_display_dispatch_queue_pending(struct wl_display *display,
 	return ret;
 }
 
+/** Dispatch at most one pending event in an event queue
+ *
+ * \param display The display context object
+ * \param queue The event queue to dispatch
+ * \return The number of dispatched events (0 or 1) on success or -1 on failure
+ *
+ * Dispatch at most one pending event for objects assigned to the given
+ * event queue. On failure -1 is returned and errno set appropriately.
+ * If there are no events queued, this function returns immediately.
+ *
+ * \memberof wl_display
+ * \since 1.25.0
+ */
+WL_EXPORT int
+wl_display_dispatch_queue_pending_single(struct wl_display *display,
+					 struct wl_event_queue *queue)
+{
+	int ret;
+
+	pthread_mutex_lock(&display->mutex);
+
+	ret = dispatch_queue_single(display, queue);
+
+	pthread_mutex_unlock(&display->mutex);
+
+	return ret;
+}
+
 /** Process incoming events
  *
  * \param display The display context object
@@ -2272,6 +2328,25 @@ wl_display_dispatch_pending(struct wl_display *display)
 						 &display->default_queue);
 }
 
+/** Dispatch at most one pending event in the default event queue.
+ *
+ * \param display The display context object
+ * \return The number of dispatched events (0 or 1) on success or -1 on failure
+ *
+ * Dispatch at most one pending event for objects assigned to the default
+ * event queue. On failure -1 is returned and errno set appropriately.
+ * If there are no events queued, this function returns immediately.
+ *
+ * \memberof wl_display
+ * \since 1.25.0
+ */
+WL_EXPORT int
+wl_display_dispatch_pending_single(struct wl_display *display)
+{
+	return wl_display_dispatch_queue_pending_single(display,
+			                             &display->default_queue);
+}
+
 /** Retrieve the last error that occurred on a display
  *
  * \param display The display context object
diff --git a/src/wayland-private.h b/src/wayland-private.h
index d7ba9dae..d0e4cfc6 100644
--- a/src/wayland-private.h
+++ b/src/wayland-private.h
@@ -237,6 +237,9 @@ wl_closure_send(struct wl_closure *closure, struct wl_connection *connection);
 int
 wl_closure_queue(struct wl_closure *closure, struct wl_connection *connection);
 
+bool
+wl_check_env_token(const char *env, const char *token);
+
 void
 wl_closure_print(struct wl_closure *closure,
 		 struct wl_object *target, int send, int discarded,
diff --git a/src/wayland-server.c b/src/wayland-server.c
index 482743b3..c81d98f1 100644
--- a/src/wayland-server.c
+++ b/src/wayland-server.c
@@ -1198,7 +1198,7 @@ wl_display_create(void)
 	no_color = getenv("NO_COLOR");
 	force_color = getenv("FORCE_COLOR");
 	debug = getenv("WAYLAND_DEBUG");
-	if (debug && (strstr(debug, "server") || strstr(debug, "1"))) {
+	if (debug && (wl_check_env_token(debug, "server") || wl_check_env_token(debug, "1"))) {
 		debug_server = 1;
 		if (isatty(fileno(stderr)))
 			debug_color = 1;
diff --git a/tests/display-test.c b/tests/display-test.c
index 89606c73..fe78b521 100644
--- a/tests/display-test.c
+++ b/tests/display-test.c
@@ -1695,6 +1695,75 @@ TEST(global_remove)
 	display_destroy(d);
 }
 
+static void
+dispatch_single_read_events(struct wl_display *d)
+{
+	if (wl_display_prepare_read(d) < 0) {
+		return;
+	}
+
+	int ret = 0;
+	do {
+		ret = wl_display_flush(d);
+	} while (ret < 0 && (errno == EINTR || errno == EAGAIN));
+	assert(ret >= 0);
+
+	struct pollfd pfd[1];
+	pfd[0].fd = wl_display_get_fd(d);
+	pfd[0].events = POLLIN;
+
+	do {
+		ret = poll(pfd, 1, -1);
+	} while (ret < 0 && errno == EINTR);
+	assert(ret > 0);
+
+	wl_display_read_events(d);
+}
+
+static void
+dispatch_single_client(void)
+{
+	struct client *c = client_connect();
+
+	assert(wl_display_dispatch_pending_single(c->wl_display) == 0);
+
+	struct wl_registry *registry = wl_display_get_registry(c->wl_display);
+
+	dispatch_single_read_events(c->wl_display);
+
+	// [1815110.061] {Default Queue} wl_registry#3.global(1, "test", 1)
+	assert(wl_display_dispatch_pending_single(c->wl_display) == 1);
+
+	dispatch_single_read_events(c->wl_display);
+
+	// [1815110.067] {Default Queue} wl_registry#3.global(2, "wl_seat", 1)
+	assert(wl_display_dispatch_pending_single(c->wl_display) == 1);
+
+	// No more events
+	assert(wl_display_dispatch_pending_single(c->wl_display) == 0);
+
+	wl_registry_destroy(registry);
+
+	client_disconnect(c);
+}
+
+TEST(dispatch_single)
+{
+	struct display *d = display_create();
+
+	struct wl_global *global = wl_global_create(d->wl_display,
+						    &wl_seat_interface,
+						    1, d, bind_seat);
+
+	client_create_noarg(d, dispatch_single_client);
+
+	display_run(d);
+
+	wl_global_destroy(global);
+
+	display_destroy(d);
+}
+
 static void
 terminate_display(void *arg)
 {