All of lore.kernel.org
 help / color / mirror / Atom feed
From: Jiri Slaby <jslaby@suse.cz>
To: gregkh@linuxfoundation.org
Cc: linux-serial@vger.kernel.org, linux-kernel@vger.kernel.org,
	Jiri Slaby <jslaby@suse.cz>
Subject: [PATCH 14/19] mxser: don't throttle manually
Date: Thu, 18 Nov 2021 08:31:20 +0100	[thread overview]
Message-ID: <20211118073125.12283-15-jslaby@suse.cz> (raw)
In-Reply-To: <20211118073125.12283-1-jslaby@suse.cz>

First, checking tty->receive_room to signalize whether there is enough space
in the tty buffers does not make much sense. Provided the tty buffers
are in tty_port and those are not checked at all.

Second, if the rx path is throttled, with CRTSCTS, RTS is deasserted,
but is never asserted again. This leads to port "lockup", not accepting
any more input.

So:
1) stty -F /dev/ttyMI0 crtscts # the mxser port
2) stty -F /dev/ttyS6 crtscts # the connected port
3) cat /dev/ttyMI0
4) "write in a loop" to /dev/ttyS6
5) cat from 3) produces the bytes from 4)
6) killall -STOP cat (the 3)'s one)
7) wait for RTS to drop on /dev/ttyMI0
8) killall -CONT cat (again the 3)'s one)

cat erroneously produces no more output now (i.e. no data sent from
ttyS6 to ttyMI can be seen).

Note that the step 7) is performed twice: once from n_tty by
tty_throttle_safe(), once by mxser_stoprx() from the receive path. Then
after step 7), n_tty correctly unthrottles the input, but mxser calls
mxser_stoprx() again as there is still only a little space in n_tty
buffers (tty->receive_room mentioned at the beginning), but the device's
FIFO is/can be already filled.

After this patch, the output is correctly resumed, i.e. n_tty both
throttles and unthrottles without interfering with mxser's attempts.

This allows us to get rid of the non-standard ldisc_stop_rx flag from
struct mxser_port.

Signed-off-by: Jiri Slaby <jslaby@suse.cz>
---
 drivers/tty/mxser.c | 36 ++++++------------------------------
 1 file changed, 6 insertions(+), 30 deletions(-)

diff --git a/drivers/tty/mxser.c b/drivers/tty/mxser.c
index c3f262dc936d..2359b4aa68af 100644
--- a/drivers/tty/mxser.c
+++ b/drivers/tty/mxser.c
@@ -251,8 +251,6 @@ struct mxser_port {
 	u8 MCR;			/* Modem control register */
 	u8 FCR;			/* FIFO control register */
 
-	bool ldisc_stop_rx;
-
 	struct async_icount icount; /* kernel counters for 4 input interrupts */
 	unsigned int timeout;
 
@@ -1286,11 +1284,14 @@ static int mxser_get_icount(struct tty_struct *tty,
 	return 0;
 }
 
-static void mxser_stoprx(struct tty_struct *tty)
+/*
+ * This routine is called by the upper-layer tty layer to signal that
+ * incoming characters should be throttled.
+ */
+static void mxser_throttle(struct tty_struct *tty)
 {
 	struct mxser_port *info = tty->driver_data;
 
-	info->ldisc_stop_rx = true;
 	if (I_IXOFF(tty)) {
 		if (info->board->must_hwid) {
 			info->IER &= ~MOXA_MUST_RECV_ISR;
@@ -1309,21 +1310,11 @@ static void mxser_stoprx(struct tty_struct *tty)
 	}
 }
 
-/*
- * This routine is called by the upper-layer tty layer to signal that
- * incoming characters should be throttled.
- */
-static void mxser_throttle(struct tty_struct *tty)
-{
-	mxser_stoprx(tty);
-}
-
 static void mxser_unthrottle(struct tty_struct *tty)
 {
 	struct mxser_port *info = tty->driver_data;
 
 	/* startrx */
-	info->ldisc_stop_rx = false;
 	if (I_IXOFF(tty)) {
 		if (info->x_char)
 			info->x_char = 0;
@@ -1515,9 +1506,6 @@ static bool mxser_receive_chars_new(struct tty_struct *tty,
 	if (hwid == MOXA_MUST_MU150_HWID)
 		gdl &= MOXA_MUST_GDL_MASK;
 
-	if (gdl >= tty->receive_room && !port->ldisc_stop_rx)
-		mxser_stoprx(tty);
-
 	while (gdl--) {
 		u8 ch = inb(port->ioaddr + UART_RX);
 		tty_insert_flip_char(&port->port, ch, 0);
@@ -1530,10 +1518,8 @@ static u8 mxser_receive_chars_old(struct tty_struct *tty,
 		                struct mxser_port *port, u8 status)
 {
 	enum mxser_must_hwid hwid = port->board->must_hwid;
-	int recv_room = tty->receive_room;
 	int ignored = 0;
 	int max = 256;
-	int cnt = 0;
 	u8 ch;
 
 	do {
@@ -1568,14 +1554,8 @@ static u8 mxser_receive_chars_old(struct tty_struct *tty,
 					port->icount.overrun++;
 				}
 			}
-			tty_insert_flip_char(&port->port, ch, flag);
-			cnt++;
-			if (cnt >= recv_room) {
-				if (!port->ldisc_stop_rx)
-					mxser_stoprx(tty);
+			if (!tty_insert_flip_char(&port->port, ch, flag))
 				break;
-			}
-
 		}
 
 		if (hwid)
@@ -1590,9 +1570,6 @@ static u8 mxser_receive_chars_old(struct tty_struct *tty,
 static u8 mxser_receive_chars(struct tty_struct *tty,
 		struct mxser_port *port, u8 status)
 {
-	if (tty->receive_room == 0 && !port->ldisc_stop_rx)
-		mxser_stoprx(tty);
-
 	if (!mxser_receive_chars_new(tty, port, status))
 		status = mxser_receive_chars_old(tty, port, status);
 
@@ -1798,7 +1775,6 @@ static void mxser_initbrd(struct mxser_board *brd, bool high_baud)
 		tty_port_init(&info->port);
 		info->port.ops = &mxser_port_ops;
 		info->board = brd;
-		info->ldisc_stop_rx = false;
 
 		/* Enhance mode enabled here */
 		if (brd->must_hwid != MOXA_OTHER_UART)
-- 
2.33.1


  parent reply	other threads:[~2021-11-18  7:32 UTC|newest]

Thread overview: 21+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2021-11-18  7:31 [PATCH 00/19] mxser: another round of cleanups and fixes Jiri Slaby
2021-11-18  7:31 ` [PATCH 01/19] mxser: remove wait for sent from mxser_close_port Jiri Slaby
2021-11-18  7:31 ` [PATCH 02/19] mxser: rename mxser_close_port() to mxser_stop_rx() Jiri Slaby
2021-11-18  7:31 ` [PATCH 03/19] mxser: keep only !tty test in ISR Jiri Slaby
2021-11-18  7:31 ` [PATCH 04/19] mxser: move MSR read to mxser_check_modem_status() Jiri Slaby
2021-11-18  7:31 ` [PATCH 05/19] mxser: clean up tx handling in mxser_transmit_chars() Jiri Slaby
2021-11-18  7:31 ` [PATCH 06/19] mxser: remove pointless xmit_buf checks Jiri Slaby
2021-11-18  7:31 ` [PATCH 07/19] mxser: remove tty->driver_data NULL check Jiri Slaby
2021-11-18  7:31 ` [PATCH 08/19] mxser: call stop_rx from mxser_shutdown_port() Jiri Slaby
2021-11-18  7:31 ` [PATCH 09/19] mxser: don't flush buffer from mxser_close() directly Jiri Slaby
2021-11-18  7:31 ` [PATCH 10/19] mxser: use tty_port_close() in mxser_close() Jiri Slaby
2021-11-18  7:31 ` [PATCH 11/19] mxser: extract TX empty check from mxser_wait_until_sent() Jiri Slaby
2021-11-18  7:31 ` [PATCH 12/19] mxser: use msleep_interruptible() in mxser_wait_until_sent() Jiri Slaby
2021-11-18  7:31 ` [PATCH 13/19] mxser: clean up timeout handling " Jiri Slaby
2021-11-18  7:31 ` Jiri Slaby [this message]
2021-11-18  7:31 ` [PATCH 15/19] mxser: remove tty parameter from mxser_receive_chars_new() Jiri Slaby
2021-11-18  7:31 ` [PATCH 16/19] mxser: increase buf_overrun if tty_insert_flip_char() fails Jiri Slaby
2021-11-18  7:31 ` [PATCH 17/19] mxser: add MOXA prefix to some PCI device IDs Jiri Slaby
2021-11-18  7:31 ` [PATCH 18/19] mxser: move ids from pci_ids.h here Jiri Slaby
2021-11-18 20:58   ` Bjorn Helgaas
2021-11-18  7:31 ` [PATCH 19/19] mxser: use PCI_DEVICE_DATA Jiri Slaby

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20211118073125.12283-15-jslaby@suse.cz \
    --to=jslaby@suse.cz \
    --cc=gregkh@linuxfoundation.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-serial@vger.kernel.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.