From: Chris Babroski <cbabroski@nvidia.com>
To: <bryan.whitehead@microchip.com>, <UNGLinuxDriver@microchip.com>,
<andrew+netdev@lunn.ch>, <davem@davemloft.net>,
<edumazet@kernel.org>, <kuba@kernel.org>, <pabeni@redhat.com>,
<netdev@vger.kernel.org>, <linux-kernel@vger.kernel.org>,
<richardcochran@gmail.com>, <linux@armlinux.org.uk>
Cc: <maxime.chevallier@bootlin.com>, <Raju.Lakkaraju@microchip.com>,
<cbabroski@nvidia.com>, <davthompson@nvidia.com>
Subject: [PATCH net-next v1 1/5] net: lan743x: reset DMA channels that fail to stop
Date: Thu, 15 Oct 2026 11:00:40 -0400 [thread overview]
Message-ID: <bf487e5d01fe6352069d4314087f680fea717cc5.1792008404.git.cbabroski@nvidia.com> (raw)
In-Reply-To: <cover.1792008404.git.cbabroski@nvidia.com>
lan743x_tx_close() and lan743x_rx_close() ask the DMA controller to stop
the channel and wait for it, but ignore the result. If the channel is
still stop-pending when the wait gives up, the descriptor ring, the head
write-back buffer and the packet buffers are unmapped and freed while
the channel may still be fetching from or writing to them.
A TX channel has been seen to stop making progress, with its head index
no longer advancing while DMAC_CMD still reports it as started. A
channel in that state may not honour the stop request either, and
closing the interface would then free memory the engine can still
access.
If the channel is still stop-pending after the wait, or still reads as
started, issue a channel soft reset and wait for it before anything is
freed, and log when that happens.
Use the same helpers for the channel resets that lan743x_tx_open() and
lan743x_rx_open() already open-code, and log there too if the reset
times out.
Fixes: 23f0703c125b ("lan743x: Add main source files for new lan743x driver")
Assisted-by: LLM
Signed-off-by: Chris Babroski <cbabroski@nvidia.com>
---
drivers/net/ethernet/microchip/lan743x_main.c | 64 +++++++++++++++----
1 file changed, 52 insertions(+), 12 deletions(-)
diff --git a/drivers/net/ethernet/microchip/lan743x_main.c b/drivers/net/ethernet/microchip/lan743x_main.c
index 82d3ec20ba25..9e1276cf313c 100644
--- a/drivers/net/ethernet/microchip/lan743x_main.c
+++ b/drivers/net/ethernet/microchip/lan743x_main.c
@@ -1584,6 +1584,15 @@ static int lan743x_dmac_tx_wait_till_stopped(struct lan743x_adapter *adapter,
return result;
}
+static int lan743x_dmac_tx_reset(struct lan743x_adapter *adapter,
+ int tx_channel)
+{
+ lan743x_csr_write(adapter, DMAC_CMD, DMAC_CMD_TX_SWR_(tx_channel));
+ return lan743x_csr_wait_for_bit(adapter, DMAC_CMD,
+ DMAC_CMD_TX_SWR_(tx_channel),
+ 0, 1000, 20000, 100);
+}
+
static int lan743x_dmac_rx_get_state(struct lan743x_adapter *adapter,
int rx_channel)
{
@@ -1613,6 +1622,15 @@ static int lan743x_dmac_rx_wait_till_stopped(struct lan743x_adapter *adapter,
return result;
}
+static int lan743x_dmac_rx_reset(struct lan743x_adapter *adapter,
+ int rx_channel)
+{
+ lan743x_csr_write(adapter, DMAC_CMD, DMAC_CMD_RX_SWR_(rx_channel));
+ return lan743x_csr_wait_for_bit(adapter, DMAC_CMD,
+ DMAC_CMD_RX_SWR_(rx_channel),
+ 0, 1000, 20000, 100);
+}
+
static void lan743x_tx_release_desc(struct lan743x_tx *tx,
int descriptor_index, bool cleanup)
{
@@ -2221,11 +2239,22 @@ static int lan743x_tx_ring_init(struct lan743x_tx *tx)
static void lan743x_tx_close(struct lan743x_tx *tx)
{
struct lan743x_adapter *adapter = tx->adapter;
+ int ret;
lan743x_csr_write(adapter,
DMAC_CMD,
DMAC_CMD_STOP_T_(tx->channel_number));
- lan743x_dmac_tx_wait_till_stopped(adapter, tx->channel_number);
+ ret = lan743x_dmac_tx_wait_till_stopped(adapter, tx->channel_number);
+ if (ret < 0 || ret == DMAC_CHANNEL_STATE_STARTED) {
+ netdev_warn(adapter->netdev,
+ "TX channel %d failed to stop, resetting it\n",
+ tx->channel_number);
+ ret = lan743x_dmac_tx_reset(adapter, tx->channel_number);
+ if (ret)
+ netdev_err(adapter->netdev,
+ "TX channel %d reset timed out\n",
+ tx->channel_number);
+ }
lan743x_csr_write(adapter,
DMAC_INT_EN_CLR,
@@ -2271,11 +2300,11 @@ static int lan743x_tx_open(struct lan743x_tx *tx)
FCT_TX_CTL_EN_(tx->channel_number));
/* reset tx channel */
- lan743x_csr_write(adapter, DMAC_CMD,
- DMAC_CMD_TX_SWR_(tx->channel_number));
- lan743x_csr_wait_for_bit(adapter, DMAC_CMD,
- DMAC_CMD_TX_SWR_(tx->channel_number),
- 0, 1000, 20000, 100);
+ ret = lan743x_dmac_tx_reset(adapter, tx->channel_number);
+ if (ret)
+ netdev_err(adapter->netdev,
+ "TX channel %d reset timed out\n",
+ tx->channel_number);
/* Write TX_BASE_ADDR */
lan743x_csr_write(adapter,
@@ -2775,6 +2804,7 @@ static int lan743x_rx_ring_init(struct lan743x_rx *rx)
static void lan743x_rx_close(struct lan743x_rx *rx)
{
struct lan743x_adapter *adapter = rx->adapter;
+ int ret;
lan743x_csr_write(adapter, FCT_RX_CTL,
FCT_RX_CTL_DIS_(rx->channel_number));
@@ -2784,7 +2814,17 @@ static void lan743x_rx_close(struct lan743x_rx *rx)
lan743x_csr_write(adapter, DMAC_CMD,
DMAC_CMD_STOP_R_(rx->channel_number));
- lan743x_dmac_rx_wait_till_stopped(adapter, rx->channel_number);
+ ret = lan743x_dmac_rx_wait_till_stopped(adapter, rx->channel_number);
+ if (ret < 0 || ret == DMAC_CHANNEL_STATE_STARTED) {
+ netdev_warn(adapter->netdev,
+ "RX channel %d failed to stop, resetting it\n",
+ rx->channel_number);
+ ret = lan743x_dmac_rx_reset(adapter, rx->channel_number);
+ if (ret)
+ netdev_err(adapter->netdev,
+ "RX channel %d reset timed out\n",
+ rx->channel_number);
+ }
lan743x_csr_write(adapter, DMAC_INT_EN_CLR,
DMAC_INT_BIT_RXFRM_(rx->channel_number));
@@ -2810,11 +2850,11 @@ static int lan743x_rx_open(struct lan743x_rx *rx)
netif_napi_add(adapter->netdev, &rx->napi, lan743x_rx_napi_poll);
- lan743x_csr_write(adapter, DMAC_CMD,
- DMAC_CMD_RX_SWR_(rx->channel_number));
- lan743x_csr_wait_for_bit(adapter, DMAC_CMD,
- DMAC_CMD_RX_SWR_(rx->channel_number),
- 0, 1000, 20000, 100);
+ ret = lan743x_dmac_rx_reset(adapter, rx->channel_number);
+ if (ret)
+ netdev_err(adapter->netdev,
+ "RX channel %d reset timed out\n",
+ rx->channel_number);
/* set ring base address */
lan743x_csr_write(adapter,
--
2.34.1
next prev parent reply other threads:[~2026-10-15 15:02 UTC|newest]
Thread overview: 6+ messages / expand[flat|nested] mbox.gz Atom feed top
2026-10-15 15:00 [PATCH net-next v1 0/5] net: lan743x: automatically recover from TX hang Chris Babroski
2026-10-15 15:00 ` Chris Babroski [this message]
2026-10-15 15:00 ` [PATCH net-next v1 2/5] net: lan743x: start phylink last and stop it first Chris Babroski
2026-10-15 15:00 ` [PATCH net-next v1 3/5] net: lan743x: quiesce TX before freeing the rings Chris Babroski
2026-10-15 15:00 ` [PATCH net-next v1 4/5] net: lan743x: reset the device on TX timeout Chris Babroski
2026-10-15 15:00 ` [PATCH net-next v1 5/5] net: lan743x: add byte queue limits support Chris Babroski
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=bf487e5d01fe6352069d4314087f680fea717cc5.1792008404.git.cbabroski@nvidia.com \
--to=cbabroski@nvidia.com \
--cc=Raju.Lakkaraju@microchip.com \
--cc=UNGLinuxDriver@microchip.com \
--cc=andrew+netdev@lunn.ch \
--cc=bryan.whitehead@microchip.com \
--cc=davem@davemloft.net \
--cc=davthompson@nvidia.com \
--cc=edumazet@kernel.org \
--cc=kuba@kernel.org \
--cc=linux-kernel@vger.kernel.org \
--cc=linux@armlinux.org.uk \
--cc=maxime.chevallier@bootlin.com \
--cc=netdev@vger.kernel.org \
--cc=pabeni@redhat.com \
--cc=richardcochran@gmail.com \
/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 a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox
all inboxes | Powered by JetHome®