From: Jassi Brar Date: Fri, 27 Mar 2026 22:00:40 +0000 (-0500) Subject: mailbox: Fix NULL message support in mbox_send_message() X-Git-Url: http://git.ipfire.org/cgi-bin/gitweb.cgi?a=commitdiff_plain;h=c58e9456e30c7098cbcd9f04571992be8a2e4e63;p=thirdparty%2Fkernel%2Flinux.git mailbox: Fix NULL message support in mbox_send_message() 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 Reviewed-by: Douglas Anderson Signed-off-by: Jassi Brar --- diff --git a/drivers/mailbox/mailbox.c b/drivers/mailbox/mailbox.c index 13de3d047853..138ffbcd4fde 100644 --- a/drivers/mailbox/mailbox.c +++ b/drivers/mailbox/mailbox.c @@ -50,7 +50,7 @@ static void msg_submit(struct mbox_chan *chan) int err = -EBUSY; scoped_guard(spinlock_irqsave, &chan->lock) { - if (!chan->msg_count || chan->active_req) + if (!chan->msg_count || chan->active_req != MBOX_NO_MSG) break; count = chan->msg_count; @@ -85,13 +85,13 @@ static void tx_tick(struct mbox_chan *chan, int r) scoped_guard(spinlock_irqsave, &chan->lock) { mssg = chan->active_req; - chan->active_req = NULL; + chan->active_req = MBOX_NO_MSG; } /* Submit next message */ msg_submit(chan); - if (!mssg) + if (mssg == MBOX_NO_MSG) return; /* Notify the client */ @@ -112,7 +112,7 @@ 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); @@ -267,7 +267,7 @@ 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); @@ -340,7 +340,7 @@ static int __mbox_bind_client(struct mbox_chan *chan, struct mbox_client *cl) scoped_guard(spinlock_irqsave, &chan->lock) { 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); @@ -498,7 +498,7 @@ void mbox_free_channel(struct mbox_chan *chan) /* The queued TX requests are simply aborted, no callbacks are made */ scoped_guard(spinlock_irqsave, &chan->lock) { 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; } @@ -553,6 +553,7 @@ 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 2231050bb5a9..7b1e1b83ea29 100644 --- a/drivers/mailbox/tegra-hsp.c +++ b/drivers/mailbox/tegra-hsp.c @@ -495,7 +495,7 @@ 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 16fef421c30c..e3896b08f22e 100644 --- a/include/linux/mailbox_controller.h +++ b/include/linux/mailbox_controller.h @@ -12,6 +12,9 @@ struct mbox_chan; +/* Sentinel value distinguishing "no active request" from "NULL message data" */ +#define MBOX_NO_MSG ((void *)-1) + #define TXDONE_BY_IRQ BIT(0) /* controller has remote RTR irq */ #define TXDONE_BY_POLL BIT(1) /* controller can read status of last TX */ #define TXDONE_BY_ACK BIT(2) /* S/W ACK received by Client ticks the TX */