[PATCH v2] serial/pmac_zilog: Remove flawed mitigation for rx irq flood

Finn Thain fthain at linux-m68k.org
Fri Apr 5 10:24:00 AEDT 2024


The mitigation was intended to stop the irq completely. That may be
better than a hard lock-up but it turns out that you get a crash anyway
if you're using pmac_zilog as a serial console:

ttyPZ0: pmz: rx irq flood !
BUG: spinlock recursion on CPU#0, swapper/0

That's because the pr_err() call in pmz_receive_chars() results in
pmz_console_write() attempting to lock a spinlock already locked in
pmz_interrupt(). With CONFIG_DEBUG_SPINLOCK=y, this produces a fatal
BUG splat. The spinlock in question is the one in struct uart_port.

Even when it's not fatal, the serial port rx function ceases to work.
Also, the iteration limit doesn't play nicely with QEMU, as can be
seen in the bug report linked below.

A web search for other reports of the error message "pmz: rx irq flood"
didn't produce anything. So I don't think this code is needed any more.
Remove it.

Link: https://github.com/vivier/qemu-m68k/issues/44
Link: https://lore.kernel.org/all/1078874617.9746.36.camel@gaston/
Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Finn Thain <fthain at linux-m68k.org>
---
Changed since v1:
 - Reworked commit log according to comments from Andy Shevchenko.
---
 drivers/tty/serial/pmac_zilog.c | 14 --------------
 1 file changed, 14 deletions(-)

diff --git a/drivers/tty/serial/pmac_zilog.c b/drivers/tty/serial/pmac_zilog.c
index c8bf08c19c64..77691fbbf779 100644
--- a/drivers/tty/serial/pmac_zilog.c
+++ b/drivers/tty/serial/pmac_zilog.c
@@ -210,7 +210,6 @@ static bool pmz_receive_chars(struct uart_pmac_port *uap)
 {
 	struct tty_port *port;
 	unsigned char ch, r1, drop, flag;
-	int loops = 0;
 
 	/* Sanity check, make sure the old bug is no longer happening */
 	if (uap->port.state == NULL) {
@@ -291,24 +290,11 @@ static bool pmz_receive_chars(struct uart_pmac_port *uap)
 		if (r1 & Rx_OVR)
 			tty_insert_flip_char(port, 0, TTY_OVERRUN);
 	next_char:
-		/* We can get stuck in an infinite loop getting char 0 when the
-		 * line is in a wrong HW state, we break that here.
-		 * When that happens, I disable the receive side of the driver.
-		 * Note that what I've been experiencing is a real irq loop where
-		 * I'm getting flooded regardless of the actual port speed.
-		 * Something strange is going on with the HW
-		 */
-		if ((++loops) > 1000)
-			goto flood;
 		ch = read_zsreg(uap, R0);
 		if (!(ch & Rx_CH_AV))
 			break;
 	}
 
-	return true;
- flood:
-	pmz_interrupt_control(uap, 0);
-	pmz_error("pmz: rx irq flood !\n");
 	return true;
 }
 
-- 
2.39.3



More information about the Linuxppc-dev mailing list