[PATCH AUTOSEL 6.6 01/15] wifi: nl80211: disallow setting special AP channel widths

[PATCH AUTOSEL 6.6 01/15] wifi: nl80211: disallow setting special AP channel widths

[Sasha Levin]

From: Johannes Berg <johannes.berg@intel.com>

[ Upstream commit 23daf1b4c91db9b26f8425cc7039cf96d22ccbfe ]

Setting the AP channel width is meant for use with the normal
20/40/... MHz channel width progression, and switching around
in S1G or narrow channels isn't supported. Disallow that.

Reported-by: syzbot+bc0f5b92cc7091f45fb6@syzkaller.appspotmail.com
Link: https://msgid.link/20240515141600.d4a9590bfe32.I19a32d60097e81b527eafe6b0924f6c5fbb2dc45@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 net/wireless/nl80211.c | 27 +++++++++++++++++++++++++++
 1 file changed, 27 insertions(+)

diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 8f8f077e6cd40..053258b4e28d2 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -3398,6 +3398,33 @@ static int __nl80211_set_channel(struct cfg80211_registered_device *rdev,
 			if (chandef.chan != cur_chan)
 				return -EBUSY;
 
+			/* only allow this for regular channel widths */
+			switch (wdev->links[link_id].ap.chandef.width) {
+			case NL80211_CHAN_WIDTH_20_NOHT:
+			case NL80211_CHAN_WIDTH_20:
+			case NL80211_CHAN_WIDTH_40:
+			case NL80211_CHAN_WIDTH_80:
+			case NL80211_CHAN_WIDTH_80P80:
+			case NL80211_CHAN_WIDTH_160:
+			case NL80211_CHAN_WIDTH_320:
+				break;
+			default:
+				return -EINVAL;
+			}
+
+			switch (chandef.width) {
+			case NL80211_CHAN_WIDTH_20_NOHT:
+			case NL80211_CHAN_WIDTH_20:
+			case NL80211_CHAN_WIDTH_40:
+			case NL80211_CHAN_WIDTH_80:
+			case NL80211_CHAN_WIDTH_80P80:
+			case NL80211_CHAN_WIDTH_160:
+			case NL80211_CHAN_WIDTH_320:
+				break;
+			default:
+				return -EINVAL;
+			}
+
 			result = rdev_set_ap_chanwidth(rdev, dev, link_id,
 						       &chandef);
 			if (result)
-- 
2.43.0

[PATCH AUTOSEL 6.6 02/15] r8169: remove detection of chip version 11 (early RTL8168b)

[Sasha Levin]

From: Heiner Kallweit <hkallweit1@gmail.com>

[ Upstream commit 982300c115d229565d7af8e8b38aa1ee7bb1f5bd ]

This early RTL8168b version was the first PCIe chip version, and it's
quite quirky. Last sign of life is from more than 15 yrs ago.
Let's remove detection of this chip version, we'll see whether anybody
complains. If not, support for this chip version can be removed a few
kernel versions later.

Signed-off-by: Heiner Kallweit <hkallweit1@gmail.com>
Link: https://lore.kernel.org/r/875cdcf4-843c-420a-ad5d-417447b68572@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/ethernet/realtek/r8169_main.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
index d759f3373b175..dfd114845a3ed 100644
--- a/drivers/net/ethernet/realtek/r8169_main.c
+++ b/drivers/net/ethernet/realtek/r8169_main.c
@@ -2135,7 +2135,9 @@ static enum mac_version rtl8169_get_mac_version(u16 xid, bool gmii)
 
 		/* 8168B family. */
 		{ 0x7c8, 0x380,	RTL_GIGA_MAC_VER_17 },
-		{ 0x7c8, 0x300,	RTL_GIGA_MAC_VER_11 },
+		/* This one is very old and rare, let's see if anybody complains.
+		 * { 0x7c8, 0x300,	RTL_GIGA_MAC_VER_11 },
+		 */
 
 		/* 8101 family. */
 		{ 0x7c8, 0x448,	RTL_GIGA_MAC_VER_39 },
-- 
2.43.0

[PATCH AUTOSEL 6.6 04/15] net/mlx5e: SHAMPO, Fix invalid WQ linked list unlink

[Sasha Levin]

From: Dragos Tatulea <dtatulea@nvidia.com>

[ Upstream commit fba8334721e266f92079632598e46e5f89082f30 ]

When all the strides in a WQE have been consumed, the WQE is unlinked
from the WQ linked list (mlx5_wq_ll_pop()). For SHAMPO, it is possible
to receive CQEs with 0 consumed strides for the same WQE even after the
WQE is fully consumed and unlinked. This triggers an additional unlink
for the same wqe which corrupts the linked list.

Fix this scenario by accepting 0 sized consumed strides without
unlinking the WQE again.

Signed-off-by: Dragos Tatulea <dtatulea@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://lore.kernel.org/r/20240603212219.1037656-4-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_rx.c | 3 +++
 1 file changed, 3 insertions(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index 8d9743a5e42c7..79ec6fcc9e259 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -2374,6 +2374,9 @@ static void mlx5e_handle_rx_cqe_mpwrq_shampo(struct mlx5e_rq *rq, struct mlx5_cq
 	if (likely(wi->consumed_strides < rq->mpwqe.num_strides))
 		return;
 
+	if (unlikely(!cstrides))
+		return;
+
 	wq  = &rq->mpwqe.wq;
 	wqe = mlx5_wq_ll_get_wqe(wq, wqe_id);
 	mlx5_wq_ll_pop(wq, cqe->wqe_id, &wqe->next.next_wqe_index);
-- 
2.43.0

[PATCH AUTOSEL 6.6 06/15] af_unix: Don't retry after unix_state_lock_nested() in unix_stream_connect().

[Sasha Levin]

From: Kuniyuki Iwashima <kuniyu@amazon.com>

[ Upstream commit 1ca27e0c8c13ac50a4acf9cdf77069e2d94a547d ]

When a SOCK_(STREAM|SEQPACKET) socket connect()s to another one, we need
to lock the two sockets to check their states in unix_stream_connect().

We use unix_state_lock() for the server and unix_state_lock_nested() for
client with tricky sk->sk_state check to avoid deadlock.

The possible deadlock scenario are the following:

  1) Self connect()
  2) Simultaneous connect()

The former is simple, attempt to grab the same lock, and the latter is
AB-BA deadlock.

After the server's unix_state_lock(), we check the server socket's state,
and if it's not TCP_LISTEN, connect() fails with -EINVAL.

Then, we avoid the former deadlock by checking the client's state before
unix_state_lock_nested().  If its state is not TCP_LISTEN, we can make
sure that the client and the server are not identical based on the state.

Also, the latter deadlock can be avoided in the same way.  Due to the
server sk->sk_state requirement, AB-BA deadlock could happen only with
TCP_LISTEN sockets.  So, if the client's state is TCP_LISTEN, we can
give up the second lock to avoid the deadlock.

  CPU 1                 CPU 2                  CPU 3
  connect(A -> B)       connect(B -> A)        listen(A)
  ---                   ---                    ---
  unix_state_lock(B)
  B->sk_state == TCP_LISTEN
  READ_ONCE(A->sk_state) == TCP_CLOSE
                            ^^^^^^^^^
                            ok, will lock A    unix_state_lock(A)
             .--------------'                  WRITE_ONCE(A->sk_state, TCP_LISTEN)
             |                                 unix_state_unlock(A)
             |
             |          unix_state_lock(A)
             |          A->sk_sk_state == TCP_LISTEN
             |          READ_ONCE(B->sk_state) == TCP_LISTEN
             v                                    ^^^^^^^^^^
  unix_state_lock_nested(A)                       Don't lock B !!

Currently, while checking the client's state, we also check if it's
TCP_ESTABLISHED, but this is unlikely and can be checked after we know
the state is not TCP_CLOSE.

Moreover, if it happens after the second lock, we now jump to the restart
label, but it's unlikely that the server is not found during the retry,
so the jump is mostly to revist the client state check.

Let's remove the retry logic and check the state against TCP_CLOSE first.

Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 net/unix/af_unix.c | 34 +++++++++-------------------------
 1 file changed, 9 insertions(+), 25 deletions(-)

diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index 5a26e785ce70d..bb66bcd4a50ea 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -1483,6 +1483,7 @@ static int unix_stream_connect(struct socket *sock, struct sockaddr *uaddr,
 	struct unix_sock *u = unix_sk(sk), *newu, *otheru;
 	struct net *net = sock_net(sk);
 	struct sk_buff *skb = NULL;
+	unsigned char state;
 	long timeo;
 	int err;
 
@@ -1529,7 +1530,6 @@ static int unix_stream_connect(struct socket *sock, struct sockaddr *uaddr,
 		goto out;
 	}
 
-	/* Latch state of peer */
 	unix_state_lock(other);
 
 	/* Apparently VFS overslept socket death. Retry. */
@@ -1559,37 +1559,21 @@ static int unix_stream_connect(struct socket *sock, struct sockaddr *uaddr,
 		goto restart;
 	}
 
-	/* Latch our state.
-
-	   It is tricky place. We need to grab our state lock and cannot
-	   drop lock on peer. It is dangerous because deadlock is
-	   possible. Connect to self case and simultaneous
-	   attempt to connect are eliminated by checking socket
-	   state. other is TCP_LISTEN, if sk is TCP_LISTEN we
-	   check this before attempt to grab lock.
-
-	   Well, and we have to recheck the state after socket locked.
+	/* self connect and simultaneous connect are eliminated
+	 * by rejecting TCP_LISTEN socket to avoid deadlock.
 	 */
-	switch (READ_ONCE(sk->sk_state)) {
-	case TCP_CLOSE:
-		/* This is ok... continue with connect */
-		break;
-	case TCP_ESTABLISHED:
-		/* Socket is already connected */
-		err = -EISCONN;
-		goto out_unlock;
-	default:
-		err = -EINVAL;
+	state = READ_ONCE(sk->sk_state);
+	if (unlikely(state != TCP_CLOSE)) {
+		err = state == TCP_ESTABLISHED ? -EISCONN : -EINVAL;
 		goto out_unlock;
 	}
 
 	unix_state_lock_nested(sk, U_LOCK_SECOND);
 
-	if (sk->sk_state != TCP_CLOSE) {
+	if (unlikely(sk->sk_state != TCP_CLOSE)) {
+		err = sk->sk_state == TCP_ESTABLISHED ? -EISCONN : -EINVAL;
 		unix_state_unlock(sk);
-		unix_state_unlock(other);
-		sock_put(other);
-		goto restart;
+		goto out_unlock;
 	}
 
 	err = security_unix_stream_connect(sk, other, newsk);
-- 
2.43.0

[PATCH AUTOSEL 6.6 09/15] wifi: nl80211: don't give key data to userspace

[Sasha Levin]

From: Johannes Berg <johannes.berg@intel.com>

[ Upstream commit a7e5793035792cc46a1a4b0a783655ffa897dfe9 ]

When a key is requested by userspace, there's really no need
to include the key data, the sequence counter is really what
userspace needs in this case. The fact that it's included is
just a historic quirk.

Remove the key data.

Reviewed-by: Miriam Rachel Korenblit <miriam.rachel.korenblit@intel.com>
Link: https://patch.msgid.link/20240627104411.b6a4f097e4ea.I7e6cc976cb9e8a80ef25a3351330f313373b4578@changeid
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 net/wireless/nl80211.c | 10 ++--------
 1 file changed, 2 insertions(+), 8 deletions(-)

diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
index 053258b4e28d2..be5c42d6ffbea 100644
--- a/net/wireless/nl80211.c
+++ b/net/wireless/nl80211.c
@@ -4473,10 +4473,7 @@ static void get_key_callback(void *c, struct key_params *params)
 	struct nlattr *key;
 	struct get_key_cookie *cookie = c;
 
-	if ((params->key &&
-	     nla_put(cookie->msg, NL80211_ATTR_KEY_DATA,
-		     params->key_len, params->key)) ||
-	    (params->seq &&
+	if ((params->seq &&
 	     nla_put(cookie->msg, NL80211_ATTR_KEY_SEQ,
 		     params->seq_len, params->seq)) ||
 	    (params->cipher &&
@@ -4488,10 +4485,7 @@ static void get_key_callback(void *c, struct key_params *params)
 	if (!key)
 		goto nla_put_failure;
 
-	if ((params->key &&
-	     nla_put(cookie->msg, NL80211_KEY_DATA,
-		     params->key_len, params->key)) ||
-	    (params->seq &&
+	if ((params->seq &&
 	     nla_put(cookie->msg, NL80211_KEY_SEQ,
 		     params->seq_len, params->seq)) ||
 	    (params->cipher &&
-- 
2.43.0

[PATCH AUTOSEL 6.6 10/15] can: mcp251xfd: tef: prepare to workaround broken TEF FIFO tail index erratum

[Sasha Levin]

From: Marc Kleine-Budde <mkl@pengutronix.de>

[ Upstream commit b8e0ddd36ce9536ad7478dd27df06c9ae92370ba ]

This is a preparatory patch to work around a problem similar to
erratum DS80000789E 6 of the mcp2518fd, the other variants of the chip
family (mcp2517fd and mcp251863) are probably also affected.

Erratum DS80000789E 6 says "reading of the FIFOCI bits in the FIFOSTA
register for an RX FIFO may be corrupted". However observation shows
that this problem is not limited to RX FIFOs but also effects the TEF
FIFO.

When handling the TEF interrupt, the driver reads the FIFO header
index from the TEF FIFO STA register of the chip.

In the bad case, the driver reads a too large head index. In the
original code, the driver always trusted the read value, which caused
old CAN transmit complete events that were already processed to be
re-processed.

Instead of reading and trusting the head index, read the head index
and calculate the number of CAN frames that were supposedly received -
replace mcp251xfd_tef_ring_update() with mcp251xfd_get_tef_len().

The mcp251xfd_handle_tefif() function reads the CAN transmit complete
events from the chip, iterates over them and pushes them into the
network stack. The original driver already contains code to detect old
CAN transmit complete events, that will be updated in the next patch.

Cc: Stefan Althöfer <Stefan.Althoefer@janztec.com>
Cc: Thomas Kopp <thomas.kopp@microchip.com>
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 .../net/can/spi/mcp251xfd/mcp251xfd-ring.c    |  2 +
 drivers/net/can/spi/mcp251xfd/mcp251xfd-tef.c | 54 +++++++++++++------
 drivers/net/can/spi/mcp251xfd/mcp251xfd.h     | 13 ++---
 3 files changed, 43 insertions(+), 26 deletions(-)

diff --git a/drivers/net/can/spi/mcp251xfd/mcp251xfd-ring.c b/drivers/net/can/spi/mcp251xfd/mcp251xfd-ring.c
index bfe4caa0c99d4..4cb79a4f24612 100644
--- a/drivers/net/can/spi/mcp251xfd/mcp251xfd-ring.c
+++ b/drivers/net/can/spi/mcp251xfd/mcp251xfd-ring.c
@@ -485,6 +485,8 @@ int mcp251xfd_ring_alloc(struct mcp251xfd_priv *priv)
 		clear_bit(MCP251XFD_FLAGS_FD_MODE, priv->flags);
 	}
 
+	tx_ring->obj_num_shift_to_u8 = BITS_PER_TYPE(tx_ring->obj_num) -
+		ilog2(tx_ring->obj_num);
 	tx_ring->obj_size = tx_obj_size;
 
 	rem = priv->rx_obj_num;
diff --git a/drivers/net/can/spi/mcp251xfd/mcp251xfd-tef.c b/drivers/net/can/spi/mcp251xfd/mcp251xfd-tef.c
index e5bd57b65aafe..b41fad3b37c06 100644
--- a/drivers/net/can/spi/mcp251xfd/mcp251xfd-tef.c
+++ b/drivers/net/can/spi/mcp251xfd/mcp251xfd-tef.c
@@ -2,7 +2,7 @@
 //
 // mcp251xfd - Microchip MCP251xFD Family CAN controller driver
 //
-// Copyright (c) 2019, 2020, 2021 Pengutronix,
+// Copyright (c) 2019, 2020, 2021, 2023 Pengutronix,
 //               Marc Kleine-Budde <kernel@pengutronix.de>
 //
 // Based on:
@@ -16,6 +16,11 @@
 
 #include "mcp251xfd.h"
 
+static inline bool mcp251xfd_tx_fifo_sta_full(u32 fifo_sta)
+{
+	return !(fifo_sta & MCP251XFD_REG_FIFOSTA_TFNRFNIF);
+}
+
 static inline int
 mcp251xfd_tef_tail_get_from_chip(const struct mcp251xfd_priv *priv,
 				 u8 *tef_tail)
@@ -120,28 +125,44 @@ mcp251xfd_handle_tefif_one(struct mcp251xfd_priv *priv,
 	return 0;
 }
 
-static int mcp251xfd_tef_ring_update(struct mcp251xfd_priv *priv)
+static int
+mcp251xfd_get_tef_len(struct mcp251xfd_priv *priv, u8 *len_p)
 {
 	const struct mcp251xfd_tx_ring *tx_ring = priv->tx;
-	unsigned int new_head;
-	u8 chip_tx_tail;
+	const u8 shift = tx_ring->obj_num_shift_to_u8;
+	u8 chip_tx_tail, tail, len;
+	u32 fifo_sta;
 	int err;
 
-	err = mcp251xfd_tx_tail_get_from_chip(priv, &chip_tx_tail);
+	err = regmap_read(priv->map_reg, MCP251XFD_REG_FIFOSTA(priv->tx->fifo_nr),
+			  &fifo_sta);
 	if (err)
 		return err;
 
-	/* chip_tx_tail, is the next TX-Object send by the HW.
-	 * The new TEF head must be >= the old head, ...
+	if (mcp251xfd_tx_fifo_sta_full(fifo_sta)) {
+		*len_p = tx_ring->obj_num;
+		return 0;
+	}
+
+	chip_tx_tail = FIELD_GET(MCP251XFD_REG_FIFOSTA_FIFOCI_MASK, fifo_sta);
+
+	err =  mcp251xfd_check_tef_tail(priv);
+	if (err)
+		return err;
+	tail = mcp251xfd_get_tef_tail(priv);
+
+	/* First shift to full u8. The subtraction works on signed
+	 * values, that keeps the difference steady around the u8
+	 * overflow. The right shift acts on len, which is an u8.
 	 */
-	new_head = round_down(priv->tef->head, tx_ring->obj_num) + chip_tx_tail;
-	if (new_head <= priv->tef->head)
-		new_head += tx_ring->obj_num;
+	BUILD_BUG_ON(sizeof(tx_ring->obj_num) != sizeof(chip_tx_tail));
+	BUILD_BUG_ON(sizeof(tx_ring->obj_num) != sizeof(tail));
+	BUILD_BUG_ON(sizeof(tx_ring->obj_num) != sizeof(len));
 
-	/* ... but it cannot exceed the TX head. */
-	priv->tef->head = min(new_head, tx_ring->head);
+	len = (chip_tx_tail << shift) - (tail << shift);
+	*len_p = len >> shift;
 
-	return mcp251xfd_check_tef_tail(priv);
+	return 0;
 }
 
 static inline int
@@ -182,13 +203,12 @@ int mcp251xfd_handle_tefif(struct mcp251xfd_priv *priv)
 	u8 tef_tail, len, l;
 	int err, i;
 
-	err = mcp251xfd_tef_ring_update(priv);
+	err = mcp251xfd_get_tef_len(priv, &len);
 	if (err)
 		return err;
 
 	tef_tail = mcp251xfd_get_tef_tail(priv);
-	len = mcp251xfd_get_tef_len(priv);
-	l = mcp251xfd_get_tef_linear_len(priv);
+	l = mcp251xfd_get_tef_linear_len(priv, len);
 	err = mcp251xfd_tef_obj_read(priv, hw_tef_obj, tef_tail, l);
 	if (err)
 		return err;
@@ -223,6 +243,8 @@ int mcp251xfd_handle_tefif(struct mcp251xfd_priv *priv)
 		struct mcp251xfd_tx_ring *tx_ring = priv->tx;
 		int offset;
 
+		ring->head += len;
+
 		/* Increment the TEF FIFO tail pointer 'len' times in
 		 * a single SPI message.
 		 *
diff --git a/drivers/net/can/spi/mcp251xfd/mcp251xfd.h b/drivers/net/can/spi/mcp251xfd/mcp251xfd.h
index b35bfebd23f29..4628bf847bc9b 100644
--- a/drivers/net/can/spi/mcp251xfd/mcp251xfd.h
+++ b/drivers/net/can/spi/mcp251xfd/mcp251xfd.h
@@ -524,6 +524,7 @@ struct mcp251xfd_tef_ring {
 
 	/* u8 obj_num equals tx_ring->obj_num */
 	/* u8 obj_size equals sizeof(struct mcp251xfd_hw_tef_obj) */
+	/* u8 obj_num_shift_to_u8 equals tx_ring->obj_num_shift_to_u8 */
 
 	union mcp251xfd_write_reg_buf irq_enable_buf;
 	struct spi_transfer irq_enable_xfer;
@@ -542,6 +543,7 @@ struct mcp251xfd_tx_ring {
 	u8 nr;
 	u8 fifo_nr;
 	u8 obj_num;
+	u8 obj_num_shift_to_u8;
 	u8 obj_size;
 
 	struct mcp251xfd_tx_obj obj[MCP251XFD_TX_OBJ_NUM_MAX];
@@ -861,17 +863,8 @@ static inline u8 mcp251xfd_get_tef_tail(const struct mcp251xfd_priv *priv)
 	return priv->tef->tail & (priv->tx->obj_num - 1);
 }
 
-static inline u8 mcp251xfd_get_tef_len(const struct mcp251xfd_priv *priv)
+static inline u8 mcp251xfd_get_tef_linear_len(const struct mcp251xfd_priv *priv, u8 len)
 {
-	return priv->tef->head - priv->tef->tail;
-}
-
-static inline u8 mcp251xfd_get_tef_linear_len(const struct mcp251xfd_priv *priv)
-{
-	u8 len;
-
-	len = mcp251xfd_get_tef_len(priv);
-
 	return min_t(u8, len, priv->tx->obj_num - mcp251xfd_get_tef_tail(priv));
 }
 
-- 
2.43.0

[PATCH AUTOSEL 6.6 11/15] can: mcp251xfd: tef: update workaround for erratum DS80000789E 6 of mcp2518fd

[Sasha Levin]

From: Marc Kleine-Budde <mkl@pengutronix.de>

[ Upstream commit 3a0a88fcbaf9e027ecca3fe8775be9700b4d6460 ]

This patch updates the workaround for a problem similar to erratum
DS80000789E 6 of the mcp2518fd, the other variants of the chip
family (mcp2517fd and mcp251863) are probably also affected.

Erratum DS80000789E 6 says "reading of the FIFOCI bits in the FIFOSTA
register for an RX FIFO may be corrupted". However observation shows
that this problem is not limited to RX FIFOs but also effects the TEF
FIFO.

In the bad case, the driver reads a too large head index. As the FIFO
is implemented as a ring buffer, this results in re-handling old CAN
transmit complete events.

Every transmit complete event contains with a sequence number that
equals to the sequence number of the corresponding TX request. This
way old TX complete events can be detected.

If the original driver detects a non matching sequence number, it
prints an info message and tries again later. As wrong sequence
numbers can be explained by the erratum DS80000789E 6, demote the info
message to debug level, streamline the code and update the comments.

Keep the behavior: If an old CAN TX complete event is detected, abort
the iteration and mark the number of valid CAN TX complete events as
processed in the chip by incrementing the FIFO's tail index.

Cc: Stefan Althöfer <Stefan.Althoefer@janztec.com>
Cc: Thomas Kopp <thomas.kopp@microchip.com>
Signed-off-by: Marc Kleine-Budde <mkl@pengutronix.de>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 drivers/net/can/spi/mcp251xfd/mcp251xfd-tef.c | 71 +++++++------------
 1 file changed, 27 insertions(+), 44 deletions(-)

diff --git a/drivers/net/can/spi/mcp251xfd/mcp251xfd-tef.c b/drivers/net/can/spi/mcp251xfd/mcp251xfd-tef.c
index b41fad3b37c06..5b0c7890d4b44 100644
--- a/drivers/net/can/spi/mcp251xfd/mcp251xfd-tef.c
+++ b/drivers/net/can/spi/mcp251xfd/mcp251xfd-tef.c
@@ -60,56 +60,39 @@ static int mcp251xfd_check_tef_tail(const struct mcp251xfd_priv *priv)
 	return 0;
 }
 
-static int
-mcp251xfd_handle_tefif_recover(const struct mcp251xfd_priv *priv, const u32 seq)
-{
-	const struct mcp251xfd_tx_ring *tx_ring = priv->tx;
-	u32 tef_sta;
-	int err;
-
-	err = regmap_read(priv->map_reg, MCP251XFD_REG_TEFSTA, &tef_sta);
-	if (err)
-		return err;
-
-	if (tef_sta & MCP251XFD_REG_TEFSTA_TEFOVIF) {
-		netdev_err(priv->ndev,
-			   "Transmit Event FIFO buffer overflow.\n");
-		return -ENOBUFS;
-	}
-
-	netdev_info(priv->ndev,
-		    "Transmit Event FIFO buffer %s. (seq=0x%08x, tef_tail=0x%08x, tef_head=0x%08x, tx_head=0x%08x).\n",
-		    tef_sta & MCP251XFD_REG_TEFSTA_TEFFIF ?
-		    "full" : tef_sta & MCP251XFD_REG_TEFSTA_TEFNEIF ?
-		    "not empty" : "empty",
-		    seq, priv->tef->tail, priv->tef->head, tx_ring->head);
-
-	/* The Sequence Number in the TEF doesn't match our tef_tail. */
-	return -EAGAIN;
-}
-
 static int
 mcp251xfd_handle_tefif_one(struct mcp251xfd_priv *priv,
 			   const struct mcp251xfd_hw_tef_obj *hw_tef_obj,
 			   unsigned int *frame_len_ptr)
 {
 	struct net_device_stats *stats = &priv->ndev->stats;
+	u32 seq, tef_tail_masked, tef_tail;
 	struct sk_buff *skb;
-	u32 seq, seq_masked, tef_tail_masked, tef_tail;
 
-	seq = FIELD_GET(MCP251XFD_OBJ_FLAGS_SEQ_MCP2518FD_MASK,
+	 /* Use the MCP2517FD mask on the MCP2518FD, too. We only
+	  * compare 7 bits, this is enough to detect old TEF objects.
+	  */
+	seq = FIELD_GET(MCP251XFD_OBJ_FLAGS_SEQ_MCP2517FD_MASK,
 			hw_tef_obj->flags);
-
-	/* Use the MCP2517FD mask on the MCP2518FD, too. We only
-	 * compare 7 bits, this should be enough to detect
-	 * net-yet-completed, i.e. old TEF objects.
-	 */
-	seq_masked = seq &
-		field_mask(MCP251XFD_OBJ_FLAGS_SEQ_MCP2517FD_MASK);
 	tef_tail_masked = priv->tef->tail &
 		field_mask(MCP251XFD_OBJ_FLAGS_SEQ_MCP2517FD_MASK);
-	if (seq_masked != tef_tail_masked)
-		return mcp251xfd_handle_tefif_recover(priv, seq);
+
+	/* According to mcp2518fd erratum DS80000789E 6. the FIFOCI
+	 * bits of a FIFOSTA register, here the TX FIFO tail index
+	 * might be corrupted and we might process past the TEF FIFO's
+	 * head into old CAN frames.
+	 *
+	 * Compare the sequence number of the currently processed CAN
+	 * frame with the expected sequence number. Abort with
+	 * -EBADMSG if an old CAN frame is detected.
+	 */
+	if (seq != tef_tail_masked) {
+		netdev_dbg(priv->ndev, "%s: chip=0x%02x ring=0x%02x\n", __func__,
+			   seq, tef_tail_masked);
+		stats->tx_fifo_errors++;
+
+		return -EBADMSG;
+	}
 
 	tef_tail = mcp251xfd_get_tef_tail(priv);
 	skb = priv->can.echo_skb[tef_tail];
@@ -223,12 +206,12 @@ int mcp251xfd_handle_tefif(struct mcp251xfd_priv *priv)
 		unsigned int frame_len = 0;
 
 		err = mcp251xfd_handle_tefif_one(priv, &hw_tef_obj[i], &frame_len);
-		/* -EAGAIN means the Sequence Number in the TEF
-		 * doesn't match our tef_tail. This can happen if we
-		 * read the TEF objects too early. Leave loop let the
-		 * interrupt handler call us again.
+		/* -EBADMSG means we're affected by mcp2518fd erratum
+		 * DS80000789E 6., i.e. the Sequence Number in the TEF
+		 * doesn't match our tef_tail. Don't process any
+		 * further and mark processed frames as good.
 		 */
-		if (err == -EAGAIN)
+		if (err == -EBADMSG)
 			goto out_netif_wake_queue;
 		if (err)
 			return err;
-- 
2.43.0

[PATCH AUTOSEL 6.6 12/15] net: stmmac: qcom-ethqos: enable SGMII loopback during DMA reset on sa8775p-ride-r3

[Sasha Levin]

From: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>

[ Upstream commit 3c466d6537b99f801b3f68af3d8124d4312437a0 ]

On sa8775p-ride-r3 the RX clocks from the AQR115C PHY are not available at
the time of the DMA reset. We can however extract the RX clock from the
internal SERDES block. Once the link is up, we can revert to the
previous state.

The AQR115C PHY doesn't support in-band signalling so we can count on
getting the link up notification and safely reuse existing callbacks
which are already used by another HW quirk workaround which enables the
functional clock to avoid a DMA reset due to timeout.

Only enable loopback on revision 3 of the board - check the phy_mode to
make sure.

Signed-off-by: Bartosz Golaszewski <bartosz.golaszewski@linaro.org>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://patch.msgid.link/20240703181500.28491-3-brgl@bgdev.pl
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 .../stmicro/stmmac/dwmac-qcom-ethqos.c        | 23 +++++++++++++++++++
 1 file changed, 23 insertions(+)

diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c
index d5d2a4c776c1c..ded1bbda5266f 100644
--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c
+++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c
@@ -21,6 +21,7 @@
 #define RGMII_IO_MACRO_CONFIG2		0x1C
 #define RGMII_IO_MACRO_DEBUG1		0x20
 #define EMAC_SYSTEM_LOW_POWER_DEBUG	0x28
+#define EMAC_WRAPPER_SGMII_PHY_CNTRL1	0xf4
 
 /* RGMII_IO_MACRO_CONFIG fields */
 #define RGMII_CONFIG_FUNC_CLK_EN		BIT(30)
@@ -79,6 +80,9 @@
 #define ETHQOS_MAC_CTRL_SPEED_MODE		BIT(14)
 #define ETHQOS_MAC_CTRL_PORT_SEL		BIT(15)
 
+/* EMAC_WRAPPER_SGMII_PHY_CNTRL1 bits */
+#define SGMII_PHY_CNTRL1_SGMII_TX_TO_RX_LOOPBACK_EN	BIT(3)
+
 #define SGMII_10M_RX_CLK_DVDR			0x31
 
 struct ethqos_emac_por {
@@ -95,6 +99,7 @@ struct ethqos_emac_driver_data {
 	bool has_integrated_pcs;
 	u32 dma_addr_width;
 	struct dwmac4_addrs dwmac4_addrs;
+	bool needs_sgmii_loopback;
 };
 
 struct qcom_ethqos {
@@ -113,6 +118,7 @@ struct qcom_ethqos {
 	unsigned int num_por;
 	bool rgmii_config_loopback_en;
 	bool has_emac_ge_3;
+	bool needs_sgmii_loopback;
 };
 
 static int rgmii_readl(struct qcom_ethqos *ethqos, unsigned int offset)
@@ -187,8 +193,22 @@ ethqos_update_link_clk(struct qcom_ethqos *ethqos, unsigned int speed)
 	clk_set_rate(ethqos->link_clk, ethqos->link_clk_rate);
 }
 
+static void
+qcom_ethqos_set_sgmii_loopback(struct qcom_ethqos *ethqos, bool enable)
+{
+	if (!ethqos->needs_sgmii_loopback ||
+	    ethqos->phy_mode != PHY_INTERFACE_MODE_2500BASEX)
+		return;
+
+	rgmii_updatel(ethqos,
+		      SGMII_PHY_CNTRL1_SGMII_TX_TO_RX_LOOPBACK_EN,
+		      enable ? SGMII_PHY_CNTRL1_SGMII_TX_TO_RX_LOOPBACK_EN : 0,
+		      EMAC_WRAPPER_SGMII_PHY_CNTRL1);
+}
+
 static void ethqos_set_func_clk_en(struct qcom_ethqos *ethqos)
 {
+	qcom_ethqos_set_sgmii_loopback(ethqos, true);
 	rgmii_updatel(ethqos, RGMII_CONFIG_FUNC_CLK_EN,
 		      RGMII_CONFIG_FUNC_CLK_EN, RGMII_IO_MACRO_CONFIG);
 }
@@ -273,6 +293,7 @@ static const struct ethqos_emac_driver_data emac_v4_0_0_data = {
 	.has_emac_ge_3 = true,
 	.link_clk_name = "phyaux",
 	.has_integrated_pcs = true,
+	.needs_sgmii_loopback = true,
 	.dma_addr_width = 36,
 	.dwmac4_addrs = {
 		.dma_chan = 0x00008100,
@@ -646,6 +667,7 @@ static void ethqos_fix_mac_speed(void *priv, unsigned int speed, unsigned int mo
 {
 	struct qcom_ethqos *ethqos = priv;
 
+	qcom_ethqos_set_sgmii_loopback(ethqos, false);
 	ethqos->speed = speed;
 	ethqos_update_link_clk(ethqos, speed);
 	ethqos_configure(ethqos);
@@ -781,6 +803,7 @@ static int qcom_ethqos_probe(struct platform_device *pdev)
 	ethqos->num_por = data->num_por;
 	ethqos->rgmii_config_loopback_en = data->rgmii_config_loopback_en;
 	ethqos->has_emac_ge_3 = data->has_emac_ge_3;
+	ethqos->needs_sgmii_loopback = data->needs_sgmii_loopback;
 
 	ethqos->link_clk = devm_clk_get(dev, data->link_clk_name ?: "rgmii");
 	if (IS_ERR(ethqos->link_clk))
-- 
2.43.0