[PATCH 6.12.y] mailbox: Fix NULL message support in mbox_send_message()

[Joonwon Kang]

From: Jassi Brar <jassisinghbrar@xxxxxxxxx>

commit c58e9456e30c ("mailbox: Fix NULL message support in mbox_send_message()") upstream.

The active_req field serves double duty as both the "is a TX in
flight" flag (NULL means idle) and the storage for the in-flight
message pointer. When a client sends NULL via mbox_send_message(),
active_req is set to NULL, which the framework misinterprets as
"no active request". This breaks the TX state machine by:

 - tx_tick() short-circuits on (!mssg), skipping the tx_done
   callback and the tx_complete completion
 - txdone_hrtimer() skips the channel entirely since active_req
   is NULL, so poll-based TX-done detection never fires.

Fix this by introducing a MBOX_NO_MSG sentinel value that means
"no active request," freeing NULL to be valid message data. The
sentinel is defined in the subsystem-internal mailbox.h so that
controller drivers within drivers/mailbox/ can reference it, but
it is not exposed to clients outside the subsystem.

Fifteen in-tree callers send NULL (doorbell-style IPCs on Qualcomm,
Tegra, TI, Xilinx, i.MX, SCMI, and PCC platforms). All were
audited for regression:

 - Most already work around the bug via knows_txdone=true with a
   manual mbox_client_txdone() call, making the framework's
   tracking irrelevant. These are unaffected.

 - Poll-based callers (Xilinx zynqmp/r5) are strictly better off:
   the poll timer now correctly detects NULL-active channels
   instead of silently skipping them.

 - irq-qcom-mpm.c was a pre-existing bug -- the only Qualcomm
   caller that omitted the knows_txdone + mbox_client_txdone()
   pattern. Fixed in a companion commit ("irqchip/qcom-mpm: Fix
   missing mailbox TX done acknowledgment").

 - No caller sets both a tx_done callback and sends NULL, nor
   combines tx_block=true with NULL sends, so the newly reachable
   callback/completion paths are never exercised.

Also update tegra-hsp's flush callback, which directly inspects
active_req to wait for the channel to drain: the old "!= NULL"
check becomes "!= MBOX_NO_MSG", otherwise flush spins until
timeout since the sentinel is non-NULL.

The only tradeoff is that 'MBOX_NO_MSG' can not be used as a message
by clients.

Reported-by: Joonwon Kang <joonwonkang@xxxxxxxxxx>
Reviewed-by: Douglas Anderson <dianders@xxxxxxxxxxxx>
Signed-off-by: Jassi Brar <jassisinghbrar@xxxxxxxxx>
Signed-off-by: Joonwon Kang <joonwonkang@xxxxxxxxxx>
---
 drivers/mailbox/mailbox.c          | 15 ++++++++-------
 drivers/mailbox/tegra-hsp.c        |  2 +-
 include/linux/mailbox_controller.h |  3 +++
 3 files changed, 12 insertions(+), 8 deletions(-)

diff --git a/drivers/mailbox/mailbox.c b/drivers/mailbox/mailbox.c
index d3d26a2c9895..aee552a2fbc7 100644
--- a/drivers/mailbox/mailbox.c
+++ b/drivers/mailbox/mailbox.c
@@ -60,7 +60,7 @@ static void msg_submit(struct mbox_chan *chan)
 
 	spin_lock_irqsave(&chan->lock, flags);
 
-	if (!chan->msg_count || chan->active_req)
+	if (!chan->msg_count || chan->active_req != MBOX_NO_MSG)
 		goto exit;
 
 	count = chan->msg_count;
@@ -98,13 +98,13 @@ static void tx_tick(struct mbox_chan *chan, int r)
 
 	spin_lock_irqsave(&chan->lock, flags);
 	mssg = chan->active_req;
-	chan->active_req = NULL;
+	chan->active_req = MBOX_NO_MSG;
 	spin_unlock_irqrestore(&chan->lock, flags);
 
 	/* Submit next message */
 	msg_submit(chan);
 
-	if (!mssg)
+	if (mssg == MBOX_NO_MSG)
 		return;
 
 	/* Notify the client */
@@ -126,7 +126,7 @@ static enum hrtimer_restart txdone_hrtimer(struct hrtimer *hrtimer)
 	for (i = 0; i < mbox->num_chans; i++) {
 		struct mbox_chan *chan = &mbox->chans[i];
 
-		if (chan->active_req && chan->cl) {
+		if (chan->active_req != MBOX_NO_MSG && chan->cl) {
 			txdone = chan->mbox->ops->last_tx_done(chan);
 			if (txdone)
 				tx_tick(chan, 0);
@@ -258,7 +258,7 @@ int mbox_send_message(struct mbox_chan *chan, void *mssg)
 {
 	int t;
 
-	if (!chan || !chan->cl)
+	if (!chan || !chan->cl || mssg == MBOX_NO_MSG)
 		return -EINVAL;
 
 	t = add_to_rbuf(chan, mssg);
@@ -332,7 +332,7 @@ static int __mbox_bind_client(struct mbox_chan *chan, struct mbox_client *cl)
 	spin_lock_irqsave(&chan->lock, flags);
 	chan->msg_free = 0;
 	chan->msg_count = 0;
-	chan->active_req = NULL;
+	chan->active_req = MBOX_NO_MSG;
 	chan->cl = cl;
 	init_completion(&chan->tx_complete);
 
@@ -485,7 +485,7 @@ void mbox_free_channel(struct mbox_chan *chan)
 	/* The queued TX requests are simply aborted, no callbacks are made */
 	spin_lock_irqsave(&chan->lock, flags);
 	chan->cl = NULL;
-	chan->active_req = NULL;
+	chan->active_req = MBOX_NO_MSG;
 	if (chan->txdone_method == TXDONE_BY_ACK)
 		chan->txdone_method = TXDONE_BY_POLL;
 
@@ -545,6 +545,7 @@ int mbox_controller_register(struct mbox_controller *mbox)
 
 		chan->cl = NULL;
 		chan->mbox = mbox;
+		chan->active_req = MBOX_NO_MSG;
 		chan->txdone_method = txdone;
 		spin_lock_init(&chan->lock);
 	}
diff --git a/drivers/mailbox/tegra-hsp.c b/drivers/mailbox/tegra-hsp.c
index 19ef56cbcfd3..7a422d563948 100644
--- a/drivers/mailbox/tegra-hsp.c
+++ b/drivers/mailbox/tegra-hsp.c
@@ -487,7 +487,7 @@ static int tegra_hsp_mailbox_flush(struct mbox_chan *chan,
 			mbox_chan_txdone(chan, 0);
 
 			/* Wait until channel is empty */
-			if (chan->active_req != NULL)
+			if (chan->active_req != MBOX_NO_MSG)
 				continue;
 
 			return 0;
diff --git a/include/linux/mailbox_controller.h b/include/linux/mailbox_controller.h
index 6fee33cb52f5..fa5020262dda 100644
--- a/include/linux/mailbox_controller.h
+++ b/include/linux/mailbox_controller.h
@@ -11,6 +11,9 @@
 
 struct mbox_chan;
 
+/* Sentinel value distinguishing "no active request" from "NULL message data" */
+#define MBOX_NO_MSG	((void *)-1)
+
 /**
  * struct mbox_chan_ops - methods to control mailbox channels
  * @send_data:	The API asks the MBOX controller driver, in atomic
-- 
2.54.0.545.g6539524ca2-goog