serial/amba-pl011: Activate TX IRQ passively

The current PL011 driver transmits a dummy character when the UART
is opened, to assert the TX IRQ for the first time
(see pl011_startup()).  The UART is put in loopback mode temporarily,
so the receiver presumably shouldn't see anything.

However...

At least some platforms containing a PL011 send characters down the
wire even when loopback mode is enabled.  This means that a
spurious NUL character may be seen at the receiver when the PL011 is
opened through the TTY layer.

The current code also temporarily sets the baud rate to maximum and
the character width to the minimum, to that the dummy TX completes
as quickly as possible.  If this is seen by the receiver it will
result in a framing error and can knock the receiver out of sync --
turning subsequent output into garbage until synchronisation
is reestablished.  (Particularly problematic during boot with systemd.)

To avoid spurious transmissions, this patch removes assumptions about
whether the TX IRQ will fire until at least one TX IRQ has been seen.

Instead, the UART will unmask the TX IRQ and then slow-start via
polling and timer-based soft IRQs initially.  If the TTY layer writes
enough data to fill the FIFO to the interrupt threshold in one go,
the TX IRQ should assert, at which point the driver changes to
fully interrupt-driven TX.

In this way, the TX IRQ is activated as a side-effect instead of
being done deliberately.

This should also mean that the driver works on the SBSA Generic
UART[1] (a cut-down PL011) without invasive changes.  The Generic
UART lacks some features needed for the dummy TX approach to work
(FIFO disabling and loopback).

[1] Server Base System Architecture (ARM-DEN-0029-v2.3)
    http://infocenter.arm.com/
    (click-thru required :/)

Signed-off-by: Dave Martin <Dave.Martin@arm.com>
Tested-by: Andre Przywara <andre.przywara@arm.com>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

drivers/tty/serial/amba-pl011.c

@@ -58,6 +58,7 @@
 #include <linux/pinctrl/consumer.h>
 #include <linux/sizes.h>
 #include <linux/io.h>
+#include <linux/workqueue.h>
 
 #define UART_NR			14
 
@@ -156,7 +157,9 @@ struct uart_amba_port {
 	unsigned int		lcrh_tx;	/* vendor-specific */
 	unsigned int		lcrh_rx;	/* vendor-specific */
 	unsigned int		old_cr;		/* state during shutdown */
+	struct delayed_work	tx_softirq_work;
 	bool			autorts;
+	unsigned int		tx_irq_seen;	/* 0=none, 1=1, 2=2 or more */
 	char			type[12];
 #ifdef CONFIG_DMA_ENGINE
 	/* DMA stuff */
@@ -440,8 +443,9 @@ static void pl011_dma_remove(struct uart_amba_port *uap)
 		dma_release_channel(uap->dmarx.chan);
 }
 
-/* Forward declare this for the refill routine */
+/* Forward declare these for the refill routine */
 static int pl011_dma_tx_refill(struct uart_amba_port *uap);
+static void pl011_start_tx_pio(struct uart_amba_port *uap);
 
 /*
  * The current DMA TX buffer has been sent.
@@ -479,14 +483,13 @@ static void pl011_dma_tx_callback(void *data)
 		return;
 	}
 
-	if (pl011_dma_tx_refill(uap) <= 0) {
+	if (pl011_dma_tx_refill(uap) <= 0)
 		/*
 		 * We didn't queue a DMA buffer for some reason, but we
 		 * have data pending to be sent.  Re-enable the TX IRQ.
 		 */
-		uap->im |= UART011_TXIM;
+		pl011_start_tx_pio(uap);
-		writew(uap->im, uap->port.membase + UART011_IMSC);
+
-	}
 	spin_unlock_irqrestore(&uap->port.lock, flags);
 }
 
@@ -664,12 +667,10 @@ static inline bool pl011_dma_tx_start(struct uart_amba_port *uap)
 		if (!uap->dmatx.queued) {
 			if (pl011_dma_tx_refill(uap) > 0) {
 				uap->im &= ~UART011_TXIM;
-				ret = true;
+				writew(uap->im, uap->port.membase +
-			} else {
+				       UART011_IMSC);
-				uap->im |= UART011_TXIM;
+			} else
 				ret = false;
-			}
-			writew(uap->im, uap->port.membase + UART011_IMSC);
 		} else if (!(uap->dmacr & UART011_TXDMAE)) {
 			uap->dmacr |= UART011_TXDMAE;
 			writew(uap->dmacr,
@@ -1208,15 +1209,24 @@ static void pl011_stop_tx(struct uart_port *port)
 	pl011_dma_tx_stop(uap);
 }
 
+static bool pl011_tx_chars(struct uart_amba_port *uap);
+
+/* Start TX with programmed I/O only (no DMA) */
+static void pl011_start_tx_pio(struct uart_amba_port *uap)
+{
+	uap->im |= UART011_TXIM;
+	writew(uap->im, uap->port.membase + UART011_IMSC);
+	if (!uap->tx_irq_seen)
+		pl011_tx_chars(uap);
+}
+
 static void pl011_start_tx(struct uart_port *port)
 {
 	struct uart_amba_port *uap =
 	    container_of(port, struct uart_amba_port, port);
 
-	if (!pl011_dma_tx_start(uap)) {
+	if (!pl011_dma_tx_start(uap))
-		uap->im |= UART011_TXIM;
+		pl011_start_tx_pio(uap);
-		writew(uap->im, uap->port.membase + UART011_IMSC);
-	}
 }
 
 static void pl011_stop_rx(struct uart_port *port)
@@ -1274,40 +1284,87 @@ __acquires(&uap->port.lock)
 	spin_lock(&uap->port.lock);
 }
 
-static void pl011_tx_chars(struct uart_amba_port *uap)
+/*
+ * Transmit a character
+ * There must be at least one free entry in the TX FIFO to accept the char.
+ *
+ * Returns true if the FIFO might have space in it afterwards;
+ * returns false if the FIFO definitely became full.
+ */
+static bool pl011_tx_char(struct uart_amba_port *uap, unsigned char c)
+{
+	writew(c, uap->port.membase + UART01x_DR);
+	uap->port.icount.tx++;
+
+	if (likely(uap->tx_irq_seen > 1))
+		return true;
+
+	return !(readw(uap->port.membase + UART01x_FR) & UART01x_FR_TXFF);
+}
+
+static bool pl011_tx_chars(struct uart_amba_port *uap)
 {
 	struct circ_buf *xmit = &uap->port.state->xmit;
 	int count;
 
+	if (unlikely(uap->tx_irq_seen < 2))
+		/*
+		 * Initial FIFO fill level unknown: we must check TXFF
+		 * after each write, so just try to fill up the FIFO.
+		 */
+		count = uap->fifosize;
+	else /* tx_irq_seen >= 2 */
+		/*
+		 * FIFO initially at least half-empty, so we can simply
+		 * write half the FIFO without polling TXFF.
+
+		 * Note: the *first* TX IRQ can still race with
+		 * pl011_start_tx_pio(), which can result in the FIFO
+		 * being fuller than expected in that case.
+		 */
+		count = uap->fifosize >> 1;
+
+	/*
+	 * If the FIFO is full we're guaranteed a TX IRQ at some later point,
+	 * and can't transmit immediately in any case:
+	 */
+	if (unlikely(uap->tx_irq_seen < 2 &&
+		     readw(uap->port.membase + UART01x_FR) & UART01x_FR_TXFF))
+		return false;
+
 	if (uap->port.x_char) {
-		writew(uap->port.x_char, uap->port.membase + UART01x_DR);
+		pl011_tx_char(uap, uap->port.x_char);
-		uap->port.icount.tx++;
 		uap->port.x_char = 0;
-		return;
+		--count;
 	}
 	if (uart_circ_empty(xmit) || uart_tx_stopped(&uap->port)) {
 		pl011_stop_tx(&uap->port);
-		return;
+		goto done;
 	}
 
 	/* If we are using DMA mode, try to send some characters. */
 	if (pl011_dma_tx_irq(uap))
-		return;
+		goto done;
 
-	count = uap->fifosize >> 1;
+	while (count-- > 0 && pl011_tx_char(uap, xmit->buf[xmit->tail])) {
-	do {
-		writew(xmit->buf[xmit->tail], uap->port.membase + UART01x_DR);
 		xmit->tail = (xmit->tail + 1) & (UART_XMIT_SIZE - 1);
-		uap->port.icount.tx++;
 		if (uart_circ_empty(xmit))
 			break;
-	} while (--count > 0);
+	}
 
 	if (uart_circ_chars_pending(xmit) < WAKEUP_CHARS)
 		uart_write_wakeup(&uap->port);
 
-	if (uart_circ_empty(xmit))
+	if (uart_circ_empty(xmit)) {
 		pl011_stop_tx(&uap->port);
+		goto done;
+	}
+
+	if (unlikely(!uap->tx_irq_seen))
+		schedule_delayed_work(&uap->tx_softirq_work, uap->port.timeout);
+
+done:
+	return false;
 }
 
 static void pl011_modem_status(struct uart_amba_port *uap)
@@ -1334,6 +1391,28 @@ static void pl011_modem_status(struct uart_amba_port *uap)
 	wake_up_interruptible(&uap->port.state->port.delta_msr_wait);
 }
 
+static void pl011_tx_softirq(struct work_struct *work)
+{
+	struct delayed_work *dwork = to_delayed_work(work);
+	struct uart_amba_port *uap =
+		container_of(dwork, struct uart_amba_port, tx_softirq_work);
+
+	spin_lock(&uap->port.lock);
+	while (pl011_tx_chars(uap)) ;
+	spin_unlock(&uap->port.lock);
+}
+
+static void pl011_tx_irq_seen(struct uart_amba_port *uap)
+{
+	if (likely(uap->tx_irq_seen > 1))
+		return;
+
+	uap->tx_irq_seen++;
+	if (uap->tx_irq_seen < 2)
+		/* first TX IRQ */
+		cancel_delayed_work(&uap->tx_softirq_work);
+}
+
 static irqreturn_t pl011_int(int irq, void *dev_id)
 {
 	struct uart_amba_port *uap = dev_id;
@@ -1372,8 +1451,10 @@ static irqreturn_t pl011_int(int irq, void *dev_id)
 			if (status & (UART011_DSRMIS|UART011_DCDMIS|
 				      UART011_CTSMIS|UART011_RIMIS))
 				pl011_modem_status(uap);
-			if (status & UART011_TXIS)
+			if (status & UART011_TXIS) {
+				pl011_tx_irq_seen(uap);
 				pl011_tx_chars(uap);
+			}
 
 			if (pass_counter-- == 0)
 				break;
@@ -1577,7 +1658,7 @@ static int pl011_startup(struct uart_port *port)
 {
 	struct uart_amba_port *uap =
 	    container_of(port, struct uart_amba_port, port);
-	unsigned int cr, lcr_h, fbrd, ibrd;
+	unsigned int cr;
 	int retval;
 
 	retval = pl011_hwinit(port);
@@ -1595,30 +1676,11 @@ static int pl011_startup(struct uart_port *port)
 
 	writew(uap->vendor->ifls, uap->port.membase + UART011_IFLS);
 
-	/*
+	/* Assume that TX IRQ doesn't work until we see one: */
-	 * Provoke TX FIFO interrupt into asserting. Taking care to preserve
+	uap->tx_irq_seen = 0;
-	 * baud rate and data format specified by FBRD, IBRD and LCRH as the
+
-	 * UART may already be in use as a console.
-	 */
 	spin_lock_irq(&uap->port.lock);
 
-	fbrd = readw(uap->port.membase + UART011_FBRD);
-	ibrd = readw(uap->port.membase + UART011_IBRD);
-	lcr_h = readw(uap->port.membase + uap->lcrh_rx);
-
-	cr = UART01x_CR_UARTEN | UART011_CR_TXE | UART011_CR_LBE;
-	writew(cr, uap->port.membase + UART011_CR);
-	writew(0, uap->port.membase + UART011_FBRD);
-	writew(1, uap->port.membase + UART011_IBRD);
-	pl011_write_lcr_h(uap, 0);
-	writew(0, uap->port.membase + UART01x_DR);
-	while (readw(uap->port.membase + UART01x_FR) & UART01x_FR_BUSY)
-		barrier();
-
-	writew(fbrd, uap->port.membase + UART011_FBRD);
-	writew(ibrd, uap->port.membase + UART011_IBRD);
-	pl011_write_lcr_h(uap, lcr_h);
-
 	/* restore RTS and DTR */
 	cr = uap->old_cr & (UART011_CR_RTS | UART011_CR_DTR);
 	cr |= UART01x_CR_UARTEN | UART011_CR_RXE | UART011_CR_TXE;
@@ -1672,6 +1734,8 @@ static void pl011_shutdown(struct uart_port *port)
 	    container_of(port, struct uart_amba_port, port);
 	unsigned int cr;
 
+	cancel_delayed_work_sync(&uap->tx_softirq_work);
+
 	/*
 	 * disable all interrupts
 	 */
@@ -2218,6 +2282,7 @@ static int pl011_probe(struct amba_device *dev, const struct amba_id *id)
 	uap->port.ops = &amba_pl011_pops;
 	uap->port.flags = UPF_BOOT_AUTOCONF;
 	uap->port.line = i;
+	INIT_DELAYED_WORK(&uap->tx_softirq_work, pl011_tx_softirq);
 	pl011_dma_probe(&dev->dev, uap);
 
 	/* Ensure interrupts from this UART are masked and cleared */