From aae6b81260fd9a7224f7eb4fc440d625852245bb Mon Sep 17 00:00:00 2001
From: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
Date: Mon, 12 Aug 2024 10:43:48 -0400
Subject: [PATCH 01/82] Bluetooth: HCI: Invert LE State quirk to be opt-out
 rather then opt-in

This inverts the LE State quirk so by default we assume the controllers
would report valid states rather than invalid which is how quirks
normally behave, also this would result in HCI command failing it the LE
States are really broken thus exposing the controllers that are really
broken in this respect.

Link: https://github.com/bluez/bluez/issues/584
Fixes: 220915857e29 ("Bluetooth: Adding driver and quirk defs for multi-role LE")
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 drivers/bluetooth/btintel.c      | 10 ----------
 drivers/bluetooth/btintel_pcie.c |  3 ---
 drivers/bluetooth/btmtksdio.c    |  3 ---
 drivers/bluetooth/btrtl.c        |  1 -
 drivers/bluetooth/btusb.c        |  4 ++--
 drivers/bluetooth/hci_qca.c      |  4 ++--
 drivers/bluetooth/hci_vhci.c     |  2 --
 include/net/bluetooth/hci.h      | 17 ++++++++++-------
 include/net/bluetooth/hci_core.h |  2 +-
 net/bluetooth/hci_event.c        |  2 +-
 10 files changed, 16 insertions(+), 32 deletions(-)

diff --git a/drivers/bluetooth/btintel.c b/drivers/bluetooth/btintel.c
index 2ebc970e6573..7d5e4de64e3c 100644
--- a/drivers/bluetooth/btintel.c
+++ b/drivers/bluetooth/btintel.c
@@ -2945,9 +2945,6 @@ static int btintel_setup_combined(struct hci_dev *hdev)
 					       INTEL_ROM_LEGACY_NO_WBS_SUPPORT))
 				set_bit(HCI_QUIRK_WIDEBAND_SPEECH_SUPPORTED,
 					&hdev->quirks);
-			if (ver.hw_variant == 0x08 && ver.fw_variant == 0x22)
-				set_bit(HCI_QUIRK_VALID_LE_STATES,
-					&hdev->quirks);
 
 			err = btintel_legacy_rom_setup(hdev, &ver);
 			break;
@@ -2956,7 +2953,6 @@ static int btintel_setup_combined(struct hci_dev *hdev)
 		case 0x12:      /* ThP */
 		case 0x13:      /* HrP */
 		case 0x14:      /* CcP */
-			set_bit(HCI_QUIRK_VALID_LE_STATES, &hdev->quirks);
 			fallthrough;
 		case 0x0c:	/* WsP */
 			/* Apply the device specific HCI quirks
@@ -3048,9 +3044,6 @@ static int btintel_setup_combined(struct hci_dev *hdev)
 		/* These variants don't seem to support LE Coded PHY */
 		set_bit(HCI_QUIRK_BROKEN_LE_CODED, &hdev->quirks);
 
-		/* Set Valid LE States quirk */
-		set_bit(HCI_QUIRK_VALID_LE_STATES, &hdev->quirks);
-
 		/* Setup MSFT Extension support */
 		btintel_set_msft_opcode(hdev, ver.hw_variant);
 
@@ -3076,9 +3069,6 @@ static int btintel_setup_combined(struct hci_dev *hdev)
 		 */
 		set_bit(HCI_QUIRK_WIDEBAND_SPEECH_SUPPORTED, &hdev->quirks);
 
-		/* Apply LE States quirk from solar onwards */
-		set_bit(HCI_QUIRK_VALID_LE_STATES, &hdev->quirks);
-
 		/* Setup MSFT Extension support */
 		btintel_set_msft_opcode(hdev,
 					INTEL_HW_VARIANT(ver_tlv.cnvi_bt));
diff --git a/drivers/bluetooth/btintel_pcie.c b/drivers/bluetooth/btintel_pcie.c
index 0d1a0415557b..1c7631f22c52 100644
--- a/drivers/bluetooth/btintel_pcie.c
+++ b/drivers/bluetooth/btintel_pcie.c
@@ -1180,9 +1180,6 @@ static int btintel_pcie_setup(struct hci_dev *hdev)
 		 */
 		set_bit(HCI_QUIRK_WIDEBAND_SPEECH_SUPPORTED, &hdev->quirks);
 
-		/* Apply LE States quirk from solar onwards */
-		set_bit(HCI_QUIRK_VALID_LE_STATES, &hdev->quirks);
-
 		/* Setup MSFT Extension support */
 		btintel_set_msft_opcode(hdev,
 					INTEL_HW_VARIANT(ver_tlv.cnvi_bt));
diff --git a/drivers/bluetooth/btmtksdio.c b/drivers/bluetooth/btmtksdio.c
index 39d6898497a4..497e4c87f5be 100644
--- a/drivers/bluetooth/btmtksdio.c
+++ b/drivers/bluetooth/btmtksdio.c
@@ -1148,9 +1148,6 @@ static int btmtksdio_setup(struct hci_dev *hdev)
 			}
 		}
 
-		/* Valid LE States quirk for MediaTek 7921 */
-		set_bit(HCI_QUIRK_VALID_LE_STATES, &hdev->quirks);
-
 		break;
 	case 0x7663:
 	case 0x7668:
diff --git a/drivers/bluetooth/btrtl.c b/drivers/bluetooth/btrtl.c
index f2f37143c454..fd7991ea7672 100644
--- a/drivers/bluetooth/btrtl.c
+++ b/drivers/bluetooth/btrtl.c
@@ -1287,7 +1287,6 @@ void btrtl_set_quirks(struct hci_dev *hdev, struct btrtl_device_info *btrtl_dev)
 	case CHIP_ID_8852C:
 	case CHIP_ID_8851B:
 	case CHIP_ID_8852BT:
-		set_bit(HCI_QUIRK_VALID_LE_STATES, &hdev->quirks);
 		set_bit(HCI_QUIRK_WIDEBAND_SPEECH_SUPPORTED, &hdev->quirks);
 
 		/* RTL8852C needs to transmit mSBC data continuously without
diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c
index acdba5d77694..51d9d4532dda 100644
--- a/drivers/bluetooth/btusb.c
+++ b/drivers/bluetooth/btusb.c
@@ -3956,8 +3956,8 @@ static int btusb_probe(struct usb_interface *intf,
 	if (id->driver_info & BTUSB_WIDEBAND_SPEECH)
 		set_bit(HCI_QUIRK_WIDEBAND_SPEECH_SUPPORTED, &hdev->quirks);
 
-	if (id->driver_info & BTUSB_VALID_LE_STATES)
-		set_bit(HCI_QUIRK_VALID_LE_STATES, &hdev->quirks);
+	if (!(id->driver_info & BTUSB_VALID_LE_STATES))
+		set_bit(HCI_QUIRK_BROKEN_LE_STATES, &hdev->quirks);
 
 	if (id->driver_info & BTUSB_DIGIANSWER) {
 		data->cmdreq_type = USB_TYPE_VENDOR;
diff --git a/drivers/bluetooth/hci_qca.c b/drivers/bluetooth/hci_qca.c
index 45adc1560d94..4b1ad7ea5b95 100644
--- a/drivers/bluetooth/hci_qca.c
+++ b/drivers/bluetooth/hci_qca.c
@@ -2474,8 +2474,8 @@ static int qca_serdev_probe(struct serdev_device *serdev)
 			set_bit(HCI_QUIRK_WIDEBAND_SPEECH_SUPPORTED,
 				&hdev->quirks);
 
-		if (data->capabilities & QCA_CAP_VALID_LE_STATES)
-			set_bit(HCI_QUIRK_VALID_LE_STATES, &hdev->quirks);
+		if (!(data->capabilities & QCA_CAP_VALID_LE_STATES))
+			set_bit(HCI_QUIRK_BROKEN_LE_STATES, &hdev->quirks);
 	}
 
 	return 0;
diff --git a/drivers/bluetooth/hci_vhci.c b/drivers/bluetooth/hci_vhci.c
index c4046f8f1985..43e9ac5a3324 100644
--- a/drivers/bluetooth/hci_vhci.c
+++ b/drivers/bluetooth/hci_vhci.c
@@ -425,8 +425,6 @@ static int __vhci_create_device(struct vhci_data *data, __u8 opcode)
 	if (opcode & 0x80)
 		set_bit(HCI_QUIRK_RAW_DEVICE, &hdev->quirks);
 
-	set_bit(HCI_QUIRK_VALID_LE_STATES, &hdev->quirks);
-
 	if (hci_register_dev(hdev) < 0) {
 		BT_ERR("Can't register HCI device");
 		hci_free_dev(hdev);
diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h
index e372a88e8c3f..d1d073089f38 100644
--- a/include/net/bluetooth/hci.h
+++ b/include/net/bluetooth/hci.h
@@ -206,14 +206,17 @@ enum {
 	 */
 	HCI_QUIRK_WIDEBAND_SPEECH_SUPPORTED,
 
-	/* When this quirk is set, the controller has validated that
-	 * LE states reported through the HCI_LE_READ_SUPPORTED_STATES are
-	 * valid.  This mechanism is necessary as many controllers have
-	 * been seen has having trouble initiating a connectable
-	 * advertisement despite the state combination being reported as
-	 * supported.
+	/* When this quirk is set, the LE states reported through the
+	 * HCI_LE_READ_SUPPORTED_STATES are invalid/broken.
+	 *
+	 * This mechanism is necessary as many controllers have been seen has
+	 * having trouble initiating a connectable advertisement despite the
+	 * state combination being reported as supported.
+	 *
+	 * This quirk can be set before hci_register_dev is called or
+	 * during the hdev->setup vendor callback.
 	 */
-	HCI_QUIRK_VALID_LE_STATES,
+	HCI_QUIRK_BROKEN_LE_STATES,
 
 	/* When this quirk is set, then erroneous data reporting
 	 * is ignored. This is mainly due to the fact that the HCI
diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
index 31020891fc68..e449dba698f3 100644
--- a/include/net/bluetooth/hci_core.h
+++ b/include/net/bluetooth/hci_core.h
@@ -825,7 +825,7 @@ extern struct mutex hci_cb_list_lock;
 	} while (0)
 
 #define hci_dev_le_state_simultaneous(hdev) \
-	(test_bit(HCI_QUIRK_VALID_LE_STATES, &hdev->quirks) && \
+	(!test_bit(HCI_QUIRK_BROKEN_LE_STATES, &hdev->quirks) && \
 	 (hdev->le_states[4] & 0x08) &&	/* Central */ \
 	 (hdev->le_states[4] & 0x40) &&	/* Peripheral */ \
 	 (hdev->le_states[3] & 0x10))	/* Simultaneous */
diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
index d0c118c47f6c..1c82dcdf6e8f 100644
--- a/net/bluetooth/hci_event.c
+++ b/net/bluetooth/hci_event.c
@@ -5920,7 +5920,7 @@ static struct hci_conn *check_pending_le_conn(struct hci_dev *hdev,
 	 * while we have an existing one in peripheral role.
 	 */
 	if (hdev->conn_hash.le_num_peripheral > 0 &&
-	    (!test_bit(HCI_QUIRK_VALID_LE_STATES, &hdev->quirks) ||
+	    (test_bit(HCI_QUIRK_BROKEN_LE_STATES, &hdev->quirks) ||
 	     !(hdev->le_states[3] & 0x10)))
 		return NULL;
 

From 932021a11805b9da4bd6abf66fe233cccd59fe0e Mon Sep 17 00:00:00 2001
From: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
Date: Mon, 12 Aug 2024 11:22:08 -0400
Subject: [PATCH 02/82] Bluetooth: hci_core: Fix LE quote calculation

Function hci_sched_le needs to update the respective counter variable
inplace other the likes of hci_quote_sent would attempt to use the
possible outdated value of conn->{le_cnt,acl_cnt}.

Link: https://github.com/bluez/bluez/issues/915
Fixes: 73d80deb7bdf ("Bluetooth: prioritizing data over HCI")
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 net/bluetooth/hci_core.c | 19 +++++++------------
 1 file changed, 7 insertions(+), 12 deletions(-)

diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
index 06da8ac13dca..f25a21f532aa 100644
--- a/net/bluetooth/hci_core.c
+++ b/net/bluetooth/hci_core.c
@@ -3664,19 +3664,19 @@ static void hci_sched_le(struct hci_dev *hdev)
 {
 	struct hci_chan *chan;
 	struct sk_buff *skb;
-	int quote, cnt, tmp;
+	int quote, *cnt, tmp;
 
 	BT_DBG("%s", hdev->name);
 
 	if (!hci_conn_num(hdev, LE_LINK))
 		return;
 
-	cnt = hdev->le_pkts ? hdev->le_cnt : hdev->acl_cnt;
+	cnt = hdev->le_pkts ? &hdev->le_cnt : &hdev->acl_cnt;
 
-	__check_timeout(hdev, cnt, LE_LINK);
+	__check_timeout(hdev, *cnt, LE_LINK);
 
-	tmp = cnt;
-	while (cnt && (chan = hci_chan_sent(hdev, LE_LINK, &quote))) {
+	tmp = *cnt;
+	while (*cnt && (chan = hci_chan_sent(hdev, LE_LINK, &quote))) {
 		u32 priority = (skb_peek(&chan->data_q))->priority;
 		while (quote-- && (skb = skb_peek(&chan->data_q))) {
 			BT_DBG("chan %p skb %p len %d priority %u", chan, skb,
@@ -3691,7 +3691,7 @@ static void hci_sched_le(struct hci_dev *hdev)
 			hci_send_frame(hdev, skb);
 			hdev->le_last_tx = jiffies;
 
-			cnt--;
+			(*cnt)--;
 			chan->sent++;
 			chan->conn->sent++;
 
@@ -3701,12 +3701,7 @@ static void hci_sched_le(struct hci_dev *hdev)
 		}
 	}
 
-	if (hdev->le_pkts)
-		hdev->le_cnt = cnt;
-	else
-		hdev->acl_cnt = cnt;
-
-	if (cnt != tmp)
+	if (*cnt != tmp)
 		hci_prio_recalculate(hdev, LE_LINK);
 }
 

From 28cd47f75185c4818b0fb1b46f2f02faaba96376 Mon Sep 17 00:00:00 2001
From: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
Date: Wed, 30 Aug 2023 15:08:06 -0700
Subject: [PATCH 03/82] Bluetooth: SMP: Fix assumption of Central always being
 Initiator

SMP initiator role shall be considered the one that initiates the
pairing procedure with SMP_CMD_PAIRING_REQ:

BLUETOOTH CORE SPECIFICATION Version 5.3 | Vol 3, Part H
page 1557:

Figure 2.1: LE pairing phases

Note that by sending SMP_CMD_SECURITY_REQ it doesn't change the role to
be Initiator.

Link: https://github.com/bluez/bluez/issues/567
Fixes: b28b4943660f ("Bluetooth: Add strict checks for allowed SMP PDUs")
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 net/bluetooth/smp.c | 146 ++++++++++++++++++++++----------------------
 1 file changed, 73 insertions(+), 73 deletions(-)

diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c
index 1e7ea3a4b7ef..4f9fdf400584 100644
--- a/net/bluetooth/smp.c
+++ b/net/bluetooth/smp.c
@@ -914,7 +914,7 @@ static int tk_request(struct l2cap_conn *conn, u8 remote_oob, u8 auth,
 	 * Confirms and the responder Enters the passkey.
 	 */
 	if (smp->method == OVERLAP) {
-		if (hcon->role == HCI_ROLE_MASTER)
+		if (test_bit(SMP_FLAG_INITIATOR, &smp->flags))
 			smp->method = CFM_PASSKEY;
 		else
 			smp->method = REQ_PASSKEY;
@@ -964,7 +964,7 @@ static u8 smp_confirm(struct smp_chan *smp)
 
 	smp_send_cmd(smp->conn, SMP_CMD_PAIRING_CONFIRM, sizeof(cp), &cp);
 
-	if (conn->hcon->out)
+	if (test_bit(SMP_FLAG_INITIATOR, &smp->flags))
 		SMP_ALLOW_CMD(smp, SMP_CMD_PAIRING_CONFIRM);
 	else
 		SMP_ALLOW_CMD(smp, SMP_CMD_PAIRING_RANDOM);
@@ -980,7 +980,8 @@ static u8 smp_random(struct smp_chan *smp)
 	int ret;
 
 	bt_dev_dbg(conn->hcon->hdev, "conn %p %s", conn,
-		   conn->hcon->out ? "initiator" : "responder");
+		   test_bit(SMP_FLAG_INITIATOR, &smp->flags) ? "initiator" :
+		   "responder");
 
 	ret = smp_c1(smp->tk, smp->rrnd, smp->preq, smp->prsp,
 		     hcon->init_addr_type, &hcon->init_addr,
@@ -994,7 +995,7 @@ static u8 smp_random(struct smp_chan *smp)
 		return SMP_CONFIRM_FAILED;
 	}
 
-	if (hcon->out) {
+	if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) {
 		u8 stk[16];
 		__le64 rand = 0;
 		__le16 ediv = 0;
@@ -1256,14 +1257,15 @@ static void smp_distribute_keys(struct smp_chan *smp)
 	rsp = (void *) &smp->prsp[1];
 
 	/* The responder sends its keys first */
-	if (hcon->out && (smp->remote_key_dist & KEY_DIST_MASK)) {
+	if (test_bit(SMP_FLAG_INITIATOR, &smp->flags) &&
+	    (smp->remote_key_dist & KEY_DIST_MASK)) {
 		smp_allow_key_dist(smp);
 		return;
 	}
 
 	req = (void *) &smp->preq[1];
 
-	if (hcon->out) {
+	if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) {
 		keydist = &rsp->init_key_dist;
 		*keydist &= req->init_key_dist;
 	} else {
@@ -1432,7 +1434,7 @@ static int sc_mackey_and_ltk(struct smp_chan *smp, u8 mackey[16], u8 ltk[16])
 	struct hci_conn *hcon = smp->conn->hcon;
 	u8 *na, *nb, a[7], b[7];
 
-	if (hcon->out) {
+	if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) {
 		na   = smp->prnd;
 		nb   = smp->rrnd;
 	} else {
@@ -1460,7 +1462,7 @@ static void sc_dhkey_check(struct smp_chan *smp)
 	a[6] = hcon->init_addr_type;
 	b[6] = hcon->resp_addr_type;
 
-	if (hcon->out) {
+	if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) {
 		local_addr = a;
 		remote_addr = b;
 		memcpy(io_cap, &smp->preq[1], 3);
@@ -1539,7 +1541,7 @@ static u8 sc_passkey_round(struct smp_chan *smp, u8 smp_op)
 		/* The round is only complete when the initiator
 		 * receives pairing random.
 		 */
-		if (!hcon->out) {
+		if (!test_bit(SMP_FLAG_INITIATOR, &smp->flags)) {
 			smp_send_cmd(conn, SMP_CMD_PAIRING_RANDOM,
 				     sizeof(smp->prnd), smp->prnd);
 			if (smp->passkey_round == 20)
@@ -1567,7 +1569,7 @@ static u8 sc_passkey_round(struct smp_chan *smp, u8 smp_op)
 
 		SMP_ALLOW_CMD(smp, SMP_CMD_PAIRING_RANDOM);
 
-		if (hcon->out) {
+		if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) {
 			smp_send_cmd(conn, SMP_CMD_PAIRING_RANDOM,
 				     sizeof(smp->prnd), smp->prnd);
 			return 0;
@@ -1578,7 +1580,7 @@ static u8 sc_passkey_round(struct smp_chan *smp, u8 smp_op)
 	case SMP_CMD_PUBLIC_KEY:
 	default:
 		/* Initiating device starts the round */
-		if (!hcon->out)
+		if (!test_bit(SMP_FLAG_INITIATOR, &smp->flags))
 			return 0;
 
 		bt_dev_dbg(hdev, "Starting passkey round %u",
@@ -1623,7 +1625,7 @@ static int sc_user_reply(struct smp_chan *smp, u16 mgmt_op, __le32 passkey)
 	}
 
 	/* Initiator sends DHKey check first */
-	if (hcon->out) {
+	if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) {
 		sc_dhkey_check(smp);
 		SMP_ALLOW_CMD(smp, SMP_CMD_DHKEY_CHECK);
 	} else if (test_and_clear_bit(SMP_FLAG_DHKEY_PENDING, &smp->flags)) {
@@ -1746,7 +1748,7 @@ static u8 smp_cmd_pairing_req(struct l2cap_conn *conn, struct sk_buff *skb)
 	struct smp_cmd_pairing rsp, *req = (void *) skb->data;
 	struct l2cap_chan *chan = conn->smp;
 	struct hci_dev *hdev = conn->hcon->hdev;
-	struct smp_chan *smp;
+	struct smp_chan *smp = chan->data;
 	u8 key_size, auth, sec_level;
 	int ret;
 
@@ -1755,16 +1757,14 @@ static u8 smp_cmd_pairing_req(struct l2cap_conn *conn, struct sk_buff *skb)
 	if (skb->len < sizeof(*req))
 		return SMP_INVALID_PARAMS;
 
-	if (conn->hcon->role != HCI_ROLE_SLAVE)
+	if (smp && test_bit(SMP_FLAG_INITIATOR, &smp->flags))
 		return SMP_CMD_NOTSUPP;
 
-	if (!chan->data)
+	if (!smp) {
 		smp = smp_chan_create(conn);
-	else
-		smp = chan->data;
-
-	if (!smp)
-		return SMP_UNSPECIFIED;
+		if (!smp)
+			return SMP_UNSPECIFIED;
+	}
 
 	/* We didn't start the pairing, so match remote */
 	auth = req->auth_req & AUTH_REQ_MASK(hdev);
@@ -1946,7 +1946,7 @@ static u8 smp_cmd_pairing_rsp(struct l2cap_conn *conn, struct sk_buff *skb)
 	if (skb->len < sizeof(*rsp))
 		return SMP_INVALID_PARAMS;
 
-	if (conn->hcon->role != HCI_ROLE_MASTER)
+	if (!test_bit(SMP_FLAG_INITIATOR, &smp->flags))
 		return SMP_CMD_NOTSUPP;
 
 	skb_pull(skb, sizeof(*rsp));
@@ -2041,7 +2041,7 @@ static u8 sc_check_confirm(struct smp_chan *smp)
 	if (smp->method == REQ_PASSKEY || smp->method == DSP_PASSKEY)
 		return sc_passkey_round(smp, SMP_CMD_PAIRING_CONFIRM);
 
-	if (conn->hcon->out) {
+	if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) {
 		smp_send_cmd(conn, SMP_CMD_PAIRING_RANDOM, sizeof(smp->prnd),
 			     smp->prnd);
 		SMP_ALLOW_CMD(smp, SMP_CMD_PAIRING_RANDOM);
@@ -2063,7 +2063,7 @@ static int fixup_sc_false_positive(struct smp_chan *smp)
 	u8 auth;
 
 	/* The issue is only observed when we're in responder role */
-	if (hcon->out)
+	if (test_bit(SMP_FLAG_INITIATOR, &smp->flags))
 		return SMP_UNSPECIFIED;
 
 	if (hci_dev_test_flag(hdev, HCI_SC_ONLY)) {
@@ -2099,7 +2099,8 @@ static u8 smp_cmd_pairing_confirm(struct l2cap_conn *conn, struct sk_buff *skb)
 	struct hci_dev *hdev = hcon->hdev;
 
 	bt_dev_dbg(hdev, "conn %p %s", conn,
-		   hcon->out ? "initiator" : "responder");
+		   test_bit(SMP_FLAG_INITIATOR, &smp->flags) ? "initiator" :
+		   "responder");
 
 	if (skb->len < sizeof(smp->pcnf))
 		return SMP_INVALID_PARAMS;
@@ -2121,7 +2122,7 @@ static u8 smp_cmd_pairing_confirm(struct l2cap_conn *conn, struct sk_buff *skb)
 			return ret;
 	}
 
-	if (conn->hcon->out) {
+	if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) {
 		smp_send_cmd(conn, SMP_CMD_PAIRING_RANDOM, sizeof(smp->prnd),
 			     smp->prnd);
 		SMP_ALLOW_CMD(smp, SMP_CMD_PAIRING_RANDOM);
@@ -2156,7 +2157,7 @@ static u8 smp_cmd_pairing_random(struct l2cap_conn *conn, struct sk_buff *skb)
 	if (!test_bit(SMP_FLAG_SC, &smp->flags))
 		return smp_random(smp);
 
-	if (hcon->out) {
+	if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) {
 		pkax = smp->local_pk;
 		pkbx = smp->remote_pk;
 		na   = smp->prnd;
@@ -2169,7 +2170,7 @@ static u8 smp_cmd_pairing_random(struct l2cap_conn *conn, struct sk_buff *skb)
 	}
 
 	if (smp->method == REQ_OOB) {
-		if (!hcon->out)
+		if (!test_bit(SMP_FLAG_INITIATOR, &smp->flags))
 			smp_send_cmd(conn, SMP_CMD_PAIRING_RANDOM,
 				     sizeof(smp->prnd), smp->prnd);
 		SMP_ALLOW_CMD(smp, SMP_CMD_DHKEY_CHECK);
@@ -2180,7 +2181,7 @@ static u8 smp_cmd_pairing_random(struct l2cap_conn *conn, struct sk_buff *skb)
 	if (smp->method == REQ_PASSKEY || smp->method == DSP_PASSKEY)
 		return sc_passkey_round(smp, SMP_CMD_PAIRING_RANDOM);
 
-	if (hcon->out) {
+	if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) {
 		u8 cfm[16];
 
 		err = smp_f4(smp->tfm_cmac, smp->remote_pk, smp->local_pk,
@@ -2221,7 +2222,7 @@ static u8 smp_cmd_pairing_random(struct l2cap_conn *conn, struct sk_buff *skb)
 		return SMP_UNSPECIFIED;
 
 	if (smp->method == REQ_OOB) {
-		if (hcon->out) {
+		if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) {
 			sc_dhkey_check(smp);
 			SMP_ALLOW_CMD(smp, SMP_CMD_DHKEY_CHECK);
 		}
@@ -2295,10 +2296,27 @@ bool smp_sufficient_security(struct hci_conn *hcon, u8 sec_level,
 	return false;
 }
 
+static void smp_send_pairing_req(struct smp_chan *smp, __u8 auth)
+{
+	struct smp_cmd_pairing cp;
+
+	if (smp->conn->hcon->type == ACL_LINK)
+		build_bredr_pairing_cmd(smp, &cp, NULL);
+	else
+		build_pairing_cmd(smp->conn, &cp, NULL, auth);
+
+	smp->preq[0] = SMP_CMD_PAIRING_REQ;
+	memcpy(&smp->preq[1], &cp, sizeof(cp));
+
+	smp_send_cmd(smp->conn, SMP_CMD_PAIRING_REQ, sizeof(cp), &cp);
+	SMP_ALLOW_CMD(smp, SMP_CMD_PAIRING_RSP);
+
+	set_bit(SMP_FLAG_INITIATOR, &smp->flags);
+}
+
 static u8 smp_cmd_security_req(struct l2cap_conn *conn, struct sk_buff *skb)
 {
 	struct smp_cmd_security_req *rp = (void *) skb->data;
-	struct smp_cmd_pairing cp;
 	struct hci_conn *hcon = conn->hcon;
 	struct hci_dev *hdev = hcon->hdev;
 	struct smp_chan *smp;
@@ -2347,18 +2365,22 @@ static u8 smp_cmd_security_req(struct l2cap_conn *conn, struct sk_buff *skb)
 
 	skb_pull(skb, sizeof(*rp));
 
-	memset(&cp, 0, sizeof(cp));
-	build_pairing_cmd(conn, &cp, NULL, auth);
-
-	smp->preq[0] = SMP_CMD_PAIRING_REQ;
-	memcpy(&smp->preq[1], &cp, sizeof(cp));
-
-	smp_send_cmd(conn, SMP_CMD_PAIRING_REQ, sizeof(cp), &cp);
-	SMP_ALLOW_CMD(smp, SMP_CMD_PAIRING_RSP);
+	smp_send_pairing_req(smp, auth);
 
 	return 0;
 }
 
+static void smp_send_security_req(struct smp_chan *smp, __u8 auth)
+{
+	struct smp_cmd_security_req cp;
+
+	cp.auth_req = auth;
+	smp_send_cmd(smp->conn, SMP_CMD_SECURITY_REQ, sizeof(cp), &cp);
+	SMP_ALLOW_CMD(smp, SMP_CMD_PAIRING_REQ);
+
+	clear_bit(SMP_FLAG_INITIATOR, &smp->flags);
+}
+
 int smp_conn_security(struct hci_conn *hcon, __u8 sec_level)
 {
 	struct l2cap_conn *conn = hcon->l2cap_data;
@@ -2427,23 +2449,11 @@ int smp_conn_security(struct hci_conn *hcon, __u8 sec_level)
 			authreq |= SMP_AUTH_MITM;
 	}
 
-	if (hcon->role == HCI_ROLE_MASTER) {
-		struct smp_cmd_pairing cp;
+	if (hcon->role == HCI_ROLE_MASTER)
+		smp_send_pairing_req(smp, authreq);
+	else
+		smp_send_security_req(smp, authreq);
 
-		build_pairing_cmd(conn, &cp, NULL, authreq);
-		smp->preq[0] = SMP_CMD_PAIRING_REQ;
-		memcpy(&smp->preq[1], &cp, sizeof(cp));
-
-		smp_send_cmd(conn, SMP_CMD_PAIRING_REQ, sizeof(cp), &cp);
-		SMP_ALLOW_CMD(smp, SMP_CMD_PAIRING_RSP);
-	} else {
-		struct smp_cmd_security_req cp;
-		cp.auth_req = authreq;
-		smp_send_cmd(conn, SMP_CMD_SECURITY_REQ, sizeof(cp), &cp);
-		SMP_ALLOW_CMD(smp, SMP_CMD_PAIRING_REQ);
-	}
-
-	set_bit(SMP_FLAG_INITIATOR, &smp->flags);
 	ret = 0;
 
 unlock:
@@ -2694,8 +2704,6 @@ static int smp_cmd_sign_info(struct l2cap_conn *conn, struct sk_buff *skb)
 
 static u8 sc_select_method(struct smp_chan *smp)
 {
-	struct l2cap_conn *conn = smp->conn;
-	struct hci_conn *hcon = conn->hcon;
 	struct smp_cmd_pairing *local, *remote;
 	u8 local_mitm, remote_mitm, local_io, remote_io, method;
 
@@ -2708,7 +2716,7 @@ static u8 sc_select_method(struct smp_chan *smp)
 	 * the "struct smp_cmd_pairing" from them we need to skip the
 	 * first byte which contains the opcode.
 	 */
-	if (hcon->out) {
+	if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) {
 		local = (void *) &smp->preq[1];
 		remote = (void *) &smp->prsp[1];
 	} else {
@@ -2777,7 +2785,7 @@ static int smp_cmd_public_key(struct l2cap_conn *conn, struct sk_buff *skb)
 	/* Non-initiating device sends its public key after receiving
 	 * the key from the initiating device.
 	 */
-	if (!hcon->out) {
+	if (!test_bit(SMP_FLAG_INITIATOR, &smp->flags)) {
 		err = sc_send_public_key(smp);
 		if (err)
 			return err;
@@ -2839,7 +2847,7 @@ static int smp_cmd_public_key(struct l2cap_conn *conn, struct sk_buff *skb)
 	}
 
 	if (smp->method == REQ_OOB) {
-		if (hcon->out)
+		if (test_bit(SMP_FLAG_INITIATOR, &smp->flags))
 			smp_send_cmd(conn, SMP_CMD_PAIRING_RANDOM,
 				     sizeof(smp->prnd), smp->prnd);
 
@@ -2848,7 +2856,7 @@ static int smp_cmd_public_key(struct l2cap_conn *conn, struct sk_buff *skb)
 		return 0;
 	}
 
-	if (hcon->out)
+	if (test_bit(SMP_FLAG_INITIATOR, &smp->flags))
 		SMP_ALLOW_CMD(smp, SMP_CMD_PAIRING_CONFIRM);
 
 	if (smp->method == REQ_PASSKEY) {
@@ -2863,7 +2871,7 @@ static int smp_cmd_public_key(struct l2cap_conn *conn, struct sk_buff *skb)
 	/* The Initiating device waits for the non-initiating device to
 	 * send the confirm value.
 	 */
-	if (conn->hcon->out)
+	if (test_bit(SMP_FLAG_INITIATOR, &smp->flags))
 		return 0;
 
 	err = smp_f4(smp->tfm_cmac, smp->local_pk, smp->remote_pk, smp->prnd,
@@ -2897,7 +2905,7 @@ static int smp_cmd_dhkey_check(struct l2cap_conn *conn, struct sk_buff *skb)
 	a[6] = hcon->init_addr_type;
 	b[6] = hcon->resp_addr_type;
 
-	if (hcon->out) {
+	if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) {
 		local_addr = a;
 		remote_addr = b;
 		memcpy(io_cap, &smp->prsp[1], 3);
@@ -2922,7 +2930,7 @@ static int smp_cmd_dhkey_check(struct l2cap_conn *conn, struct sk_buff *skb)
 	if (crypto_memneq(check->e, e, 16))
 		return SMP_DHKEY_CHECK_FAILED;
 
-	if (!hcon->out) {
+	if (!test_bit(SMP_FLAG_INITIATOR, &smp->flags)) {
 		if (test_bit(SMP_FLAG_WAIT_USER, &smp->flags)) {
 			set_bit(SMP_FLAG_DHKEY_PENDING, &smp->flags);
 			return 0;
@@ -2934,7 +2942,7 @@ static int smp_cmd_dhkey_check(struct l2cap_conn *conn, struct sk_buff *skb)
 
 	sc_add_ltk(smp);
 
-	if (hcon->out) {
+	if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) {
 		hci_le_start_enc(hcon, 0, 0, smp->tk, smp->enc_key_size);
 		hcon->enc_key_size = smp->enc_key_size;
 	}
@@ -3083,7 +3091,6 @@ static void bredr_pairing(struct l2cap_chan *chan)
 	struct l2cap_conn *conn = chan->conn;
 	struct hci_conn *hcon = conn->hcon;
 	struct hci_dev *hdev = hcon->hdev;
-	struct smp_cmd_pairing req;
 	struct smp_chan *smp;
 
 	bt_dev_dbg(hdev, "chan %p", chan);
@@ -3135,14 +3142,7 @@ static void bredr_pairing(struct l2cap_chan *chan)
 
 	bt_dev_dbg(hdev, "starting SMP over BR/EDR");
 
-	/* Prepare and send the BR/EDR SMP Pairing Request */
-	build_bredr_pairing_cmd(smp, &req, NULL);
-
-	smp->preq[0] = SMP_CMD_PAIRING_REQ;
-	memcpy(&smp->preq[1], &req, sizeof(req));
-
-	smp_send_cmd(conn, SMP_CMD_PAIRING_REQ, sizeof(req), &req);
-	SMP_ALLOW_CMD(smp, SMP_CMD_PAIRING_RSP);
+	smp_send_pairing_req(smp, 0x00);
 }
 
 static void smp_resume_cb(struct l2cap_chan *chan)

From 538fd3921afac97158d4177139a0ad39f056dbb2 Mon Sep 17 00:00:00 2001
From: Griffin Kroah-Hartman <griffin@kroah.com>
Date: Thu, 15 Aug 2024 13:51:00 +0200
Subject: [PATCH 04/82] Bluetooth: MGMT: Add error handling to pair_device()

hci_conn_params_add() never checks for a NULL value and could lead to a NULL
pointer dereference causing a crash.

Fixed by adding error handling in the function.

Cc: Stable <stable@kernel.org>
Fixes: 5157b8a503fa ("Bluetooth: Fix initializing conn_params in scan phase")
Signed-off-by: Griffin Kroah-Hartman <griffin@kroah.com>
Reported-by: Yiwei Zhang <zhan4630@purdue.edu>
Signed-off-by: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
---
 net/bluetooth/mgmt.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
index 40d4887c7f79..25979f4283a6 100644
--- a/net/bluetooth/mgmt.c
+++ b/net/bluetooth/mgmt.c
@@ -3456,6 +3456,10 @@ static int pair_device(struct sock *sk, struct hci_dev *hdev, void *data,
 		 * will be kept and this function does nothing.
 		 */
 		p = hci_conn_params_add(hdev, &cp->addr.bdaddr, addr_type);
+		if (!p) {
+			err = -EIO;
+			goto unlock;
+		}
 
 		if (p->auto_connect == HCI_AUTO_CONN_EXPLICIT)
 			p->auto_connect = HCI_AUTO_CONN_DISABLED;

From b96ed2c97c791954abc881ef384e773010945aec Mon Sep 17 00:00:00 2001
From: Jiri Pirko <jiri@nvidia.com>
Date: Wed, 14 Aug 2024 14:25:00 +0200
Subject: [PATCH 05/82] virtio_net: move netdev_tx_reset_queue() call before RX
 napi enable
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

During suspend/resume the following BUG was hit:
------------[ cut here ]------------
kernel BUG at lib/dynamic_queue_limits.c:99!
Internal error: Oops - BUG: 0 [#1] SMP ARM
Modules linked in: bluetooth ecdh_generic ecc libaes
CPU: 1 PID: 1282 Comm: rtcwake Not tainted
6.10.0-rc3-00732-gc8bd1f7f3e61 #15240
Hardware name: Generic DT based system
PC is at dql_completed+0x270/0x2cc
LR is at __free_old_xmit+0x120/0x198
pc : [<c07ffa54>]    lr : [<c0c42bf4>]    psr: 80000013
...
Flags: Nzcv  IRQs on  FIQs on  Mode SVC_32  ISA ARM  Segment none
Control: 10c5387d  Table: 43a4406a  DAC: 00000051
...
Process rtcwake (pid: 1282, stack limit = 0xfbc21278)
Stack: (0xe0805e80 to 0xe0806000)
...
Call trace:
  dql_completed from __free_old_xmit+0x120/0x198
  __free_old_xmit from free_old_xmit+0x44/0xe4
  free_old_xmit from virtnet_poll_tx+0x88/0x1b4
  virtnet_poll_tx from __napi_poll+0x2c/0x1d4
  __napi_poll from net_rx_action+0x140/0x2b4
  net_rx_action from handle_softirqs+0x11c/0x350
  handle_softirqs from call_with_stack+0x18/0x20
  call_with_stack from do_softirq+0x48/0x50
  do_softirq from __local_bh_enable_ip+0xa0/0xa4
  __local_bh_enable_ip from virtnet_open+0xd4/0x21c
  virtnet_open from virtnet_restore+0x94/0x120
  virtnet_restore from virtio_device_restore+0x110/0x1f4
  virtio_device_restore from dpm_run_callback+0x3c/0x100
  dpm_run_callback from device_resume+0x12c/0x2a8
  device_resume from dpm_resume+0x12c/0x1e0
  dpm_resume from dpm_resume_end+0xc/0x18
  dpm_resume_end from suspend_devices_and_enter+0x1f0/0x72c
  suspend_devices_and_enter from pm_suspend+0x270/0x2a0
  pm_suspend from state_store+0x68/0xc8
  state_store from kernfs_fop_write_iter+0x10c/0x1cc
  kernfs_fop_write_iter from vfs_write+0x2b0/0x3dc
  vfs_write from ksys_write+0x5c/0xd4
  ksys_write from ret_fast_syscall+0x0/0x54
Exception stack(0xe8bf1fa8 to 0xe8bf1ff0)
...
---[ end trace 0000000000000000 ]---

After virtnet_napi_enable() is called, the following path is hit:
  __napi_poll()
    -> virtnet_poll()
      -> virtnet_poll_cleantx()
        -> netif_tx_wake_queue()

That wakes the TX queue and allows skbs to be submitted and accounted by
BQL counters.

Then netdev_tx_reset_queue() is called that resets BQL counters and
eventually leads to the BUG in dql_completed().

Move virtnet_napi_tx_enable() what does BQL counters reset before RX
napi enable to avoid the issue.

Reported-by: Marek Szyprowski <m.szyprowski@samsung.com>
Closes: https://lore.kernel.org/netdev/e632e378-d019-4de7-8f13-07c572ab37a9@samsung.com/
Fixes: c8bd1f7f3e61 ("virtio_net: add support for Byte Queue Limits")
Tested-by: Marek Szyprowski <m.szyprowski@samsung.com>
Signed-off-by: Jiri Pirko <jiri@nvidia.com>
Acked-by: Michael S. Tsirkin <mst@redhat.com>
Acked-by: Jason Wang <jasowang@redhat.com>
Link: https://patch.msgid.link/20240814122500.1710279-1-jiri@resnulli.us
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/virtio_net.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
index 3f10c72743e9..c6af18948092 100644
--- a/drivers/net/virtio_net.c
+++ b/drivers/net/virtio_net.c
@@ -2867,8 +2867,8 @@ static int virtnet_enable_queue_pair(struct virtnet_info *vi, int qp_index)
 	if (err < 0)
 		goto err_xdp_reg_mem_model;
 
-	virtnet_napi_enable(vi->rq[qp_index].vq, &vi->rq[qp_index].napi);
 	netdev_tx_reset_queue(netdev_get_tx_queue(vi->dev, qp_index));
+	virtnet_napi_enable(vi->rq[qp_index].vq, &vi->rq[qp_index].napi);
 	virtnet_napi_tx_enable(vi, vi->sq[qp_index].vq, &vi->sq[qp_index].napi);
 
 	return 0;

From c948c0973df5db9314459da621342e1170bd9e8e Mon Sep 17 00:00:00 2001
From: Pavan Chebbi <pavan.chebbi@broadcom.com>
Date: Wed, 14 Aug 2024 15:54:29 -0700
Subject: [PATCH 06/82] bnxt_en: Don't clear ntuple filters and rss contexts
 during ethtool ops

The driver currently blindly deletes its cache of RSS cotexts and
ntuple filters when the ethtool channel count is changing.  It also
deletes the ntuple filters cache when the default indirection table
is changing.

The core will not allow ethtool channels to drop below any that
have been configured as ntuple destinations since this commit from 2022:

47f3ecf4763d ("ethtool: Fail number of channels change when it conflicts with rxnfc")

So there is absolutely no need to delete the ntuple filters and
RSS contexts when changing ethtool channels.

It is also unnecessary to delete ntuple filters when the default
RSS indirection table is changing.

Remove bnxt_clear_usr_fltrs() and bnxt_clear_rss_ctxis() from the
ethtool ops and change them to static functions.

This bug will cause confusion to the end user and causes failure when
running the rss_ctx.py selftest.

Fixes: 1018319f949c ("bnxt_en: Invalidate user filters when needed")
Reported-by: Jakub Kicinski <kuba@kernel.org>
Closes: https://lore.kernel.org/netdev/20240725111912.7bc17cf6@kernel.org/
Reviewed-by: Andy Gospodarek <andrew.gospodarek@broadcom.com>
Signed-off-by: Pavan Chebbi <pavan.chebbi@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Link: https://patch.msgid.link/20240814225429.199280-1-michael.chan@broadcom.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c         | 4 ++--
 drivers/net/ethernet/broadcom/bnxt/bnxt.h         | 2 --
 drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c | 4 ----
 3 files changed, 2 insertions(+), 8 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index e27e1082ee33..04a623b3eee2 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -5056,7 +5056,7 @@ void bnxt_del_one_usr_fltr(struct bnxt *bp, struct bnxt_filter_base *fltr)
 		list_del_init(&fltr->list);
 }
 
-void bnxt_clear_usr_fltrs(struct bnxt *bp, bool all)
+static void bnxt_clear_usr_fltrs(struct bnxt *bp, bool all)
 {
 	struct bnxt_filter_base *usr_fltr, *tmp;
 
@@ -10248,7 +10248,7 @@ static void bnxt_hwrm_realloc_rss_ctx_vnic(struct bnxt *bp)
 	}
 }
 
-void bnxt_clear_rss_ctxs(struct bnxt *bp)
+static void bnxt_clear_rss_ctxs(struct bnxt *bp)
 {
 	struct ethtool_rxfh_context *ctx;
 	unsigned long context;
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
index 6bbdc718c3a7..059a6f81c1a8 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h
@@ -2790,7 +2790,6 @@ void bnxt_set_ring_params(struct bnxt *);
 int bnxt_set_rx_skb_mode(struct bnxt *bp, bool page_mode);
 void bnxt_insert_usr_fltr(struct bnxt *bp, struct bnxt_filter_base *fltr);
 void bnxt_del_one_usr_fltr(struct bnxt *bp, struct bnxt_filter_base *fltr);
-void bnxt_clear_usr_fltrs(struct bnxt *bp, bool all);
 int bnxt_hwrm_func_drv_rgtr(struct bnxt *bp, unsigned long *bmap,
 			    int bmap_size, bool async_only);
 int bnxt_hwrm_func_drv_unrgtr(struct bnxt *bp);
@@ -2842,7 +2841,6 @@ int bnxt_hwrm_vnic_rss_cfg_p5(struct bnxt *bp, struct bnxt_vnic_info *vnic);
 int __bnxt_setup_vnic_p5(struct bnxt *bp, struct bnxt_vnic_info *vnic);
 void bnxt_del_one_rss_ctx(struct bnxt *bp, struct bnxt_rss_ctx *rss_ctx,
 			  bool all);
-void bnxt_clear_rss_ctxs(struct bnxt *bp);
 int bnxt_open_nic(struct bnxt *, bool, bool);
 int bnxt_half_open_nic(struct bnxt *bp);
 void bnxt_half_close_nic(struct bnxt *bp);
diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
index 9dadc89378f0..4cf9bf8b01b0 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c
@@ -968,9 +968,6 @@ static int bnxt_set_channels(struct net_device *dev,
 		return -EINVAL;
 	}
 
-	bnxt_clear_usr_fltrs(bp, true);
-	if (BNXT_SUPPORTS_MULTI_RSS_CTX(bp))
-		bnxt_clear_rss_ctxs(bp);
 	if (netif_running(dev)) {
 		if (BNXT_PF(bp)) {
 			/* TODO CHIMP_FW: Send message to all VF's
@@ -2000,7 +1997,6 @@ static int bnxt_set_rxfh(struct net_device *dev,
 
 	bnxt_modify_rss(bp, NULL, NULL, rxfh);
 
-	bnxt_clear_usr_fltrs(bp, false);
 	if (netif_running(bp->dev)) {
 		bnxt_close_nic(bp, false, false);
 		rc = bnxt_open_nic(bp, false, false);

From b153b3c747003e1ce312ba205e552db4bd9e8df7 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Wed, 14 Aug 2024 07:28:32 -0700
Subject: [PATCH 07/82] MAINTAINERS: add selftests to network drivers

tools/testing/selftests/drivers/net/ is not listed under
networking entries. Add it to NETWORKING DRIVERS.

Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20240814142832.3473685-1-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 MAINTAINERS | 1 +
 1 file changed, 1 insertion(+)

diff --git a/MAINTAINERS b/MAINTAINERS
index f328373463b0..a964a34651f5 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -15886,6 +15886,7 @@ F:	include/linux/netdevice.h
 F:	include/uapi/linux/cn_proc.h
 F:	include/uapi/linux/if_*
 F:	include/uapi/linux/netdevice.h
+F:	tools/testing/selftests/drivers/net/
 X:	drivers/net/wireless/
 
 NETWORKING DRIVERS (WIRELESS)

From 8d019b15ddd55d6dc5685b1f51902c4aa8e01939 Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Thu, 15 Aug 2024 03:06:54 +0300
Subject: [PATCH 08/82] selftests: net: local_termination: refactor macvlan
 creation/deletion

This will be used in other subtests as well; make new macvlan_create()
and macvlan_destroy() functions.

Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/forwarding/local_termination.sh       | 30 +++++++++++--------
 1 file changed, 18 insertions(+), 12 deletions(-)

diff --git a/tools/testing/selftests/net/forwarding/local_termination.sh b/tools/testing/selftests/net/forwarding/local_termination.sh
index 4b364cdf3ef0..36f3d577d0be 100755
--- a/tools/testing/selftests/net/forwarding/local_termination.sh
+++ b/tools/testing/selftests/net/forwarding/local_termination.sh
@@ -247,19 +247,29 @@ bridge_destroy()
 	ip link del br0
 }
 
+macvlan_create()
+{
+	local lower=$1
+
+	ip link add link $lower name macvlan0 type macvlan mode private
+	ip link set macvlan0 address $MACVLAN_ADDR
+	ip link set macvlan0 up
+}
+
+macvlan_destroy()
+{
+	ip link del macvlan0
+}
+
 standalone()
 {
 	h1_create
 	h2_create
-
-	ip link add link $h2 name macvlan0 type macvlan mode private
-	ip link set macvlan0 address $MACVLAN_ADDR
-	ip link set macvlan0 up
+	macvlan_create $h2
 
 	run_test $h2
 
-	ip link del macvlan0
-
+	macvlan_destroy
 	h2_destroy
 	h1_destroy
 }
@@ -268,15 +278,11 @@ bridge()
 {
 	h1_create
 	bridge_create
-
-	ip link add link br0 name macvlan0 type macvlan mode private
-	ip link set macvlan0 address $MACVLAN_ADDR
-	ip link set macvlan0 up
+	macvlan_create br0
 
 	run_test br0
 
-	ip link del macvlan0
-
+	macvlan_destroy
 	bridge_destroy
 	h1_destroy
 }

From 4261fa35185c0112acca0496d3732c8fcfe1dcf2 Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Thu, 15 Aug 2024 03:06:55 +0300
Subject: [PATCH 09/82] selftests: net: local_termination: parameterize sending
 interface

In future changes we will want to subject the DUT, $h2, to additional
VLAN-tagged traffic. For that, we need to run the tests using $h1.100 as
a sending interface, rather than the currently hardcoded $h1.

Add a parameter to run_test() and modify its 2 callers to explicitly
pass $h1, as was implicit before.

Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/forwarding/local_termination.sh       | 39 ++++++++++---------
 1 file changed, 20 insertions(+), 19 deletions(-)

diff --git a/tools/testing/selftests/net/forwarding/local_termination.sh b/tools/testing/selftests/net/forwarding/local_termination.sh
index 36f3d577d0be..92f0e242d119 100755
--- a/tools/testing/selftests/net/forwarding/local_termination.sh
+++ b/tools/testing/selftests/net/forwarding/local_termination.sh
@@ -104,44 +104,45 @@ mc_route_destroy()
 
 run_test()
 {
-	local rcv_if_name=$1
-	local smac=$(mac_get $h1)
+	local send_if_name=$1; shift
+	local rcv_if_name=$1; shift
+	local smac=$(mac_get $send_if_name)
 	local rcv_dmac=$(mac_get $rcv_if_name)
 
 	tcpdump_start $rcv_if_name
 
-	mc_route_prepare $h1
+	mc_route_prepare $send_if_name
 	mc_route_prepare $rcv_if_name
 
-	send_uc_ipv4 $h1 $rcv_dmac
-	send_uc_ipv4 $h1 $MACVLAN_ADDR
-	send_uc_ipv4 $h1 $UNKNOWN_UC_ADDR1
+	send_uc_ipv4 $send_if_name $rcv_dmac
+	send_uc_ipv4 $send_if_name $MACVLAN_ADDR
+	send_uc_ipv4 $send_if_name $UNKNOWN_UC_ADDR1
 
 	ip link set dev $rcv_if_name promisc on
-	send_uc_ipv4 $h1 $UNKNOWN_UC_ADDR2
-	mc_send $h1 $UNKNOWN_IPV4_MC_ADDR2
-	mc_send $h1 $UNKNOWN_IPV6_MC_ADDR2
+	send_uc_ipv4 $send_if_name $UNKNOWN_UC_ADDR2
+	mc_send $send_if_name $UNKNOWN_IPV4_MC_ADDR2
+	mc_send $send_if_name $UNKNOWN_IPV6_MC_ADDR2
 	ip link set dev $rcv_if_name promisc off
 
 	mc_join $rcv_if_name $JOINED_IPV4_MC_ADDR
-	mc_send $h1 $JOINED_IPV4_MC_ADDR
+	mc_send $send_if_name $JOINED_IPV4_MC_ADDR
 	mc_leave
 
 	mc_join $rcv_if_name $JOINED_IPV6_MC_ADDR
-	mc_send $h1 $JOINED_IPV6_MC_ADDR
+	mc_send $send_if_name $JOINED_IPV6_MC_ADDR
 	mc_leave
 
-	mc_send $h1 $UNKNOWN_IPV4_MC_ADDR1
-	mc_send $h1 $UNKNOWN_IPV6_MC_ADDR1
+	mc_send $send_if_name $UNKNOWN_IPV4_MC_ADDR1
+	mc_send $send_if_name $UNKNOWN_IPV6_MC_ADDR1
 
 	ip link set dev $rcv_if_name allmulticast on
-	send_uc_ipv4 $h1 $UNKNOWN_UC_ADDR3
-	mc_send $h1 $UNKNOWN_IPV4_MC_ADDR3
-	mc_send $h1 $UNKNOWN_IPV6_MC_ADDR3
+	send_uc_ipv4 $send_if_name $UNKNOWN_UC_ADDR3
+	mc_send $send_if_name $UNKNOWN_IPV4_MC_ADDR3
+	mc_send $send_if_name $UNKNOWN_IPV6_MC_ADDR3
 	ip link set dev $rcv_if_name allmulticast off
 
 	mc_route_destroy $rcv_if_name
-	mc_route_destroy $h1
+	mc_route_destroy $send_if_name
 
 	sleep 1
 
@@ -267,7 +268,7 @@ standalone()
 	h2_create
 	macvlan_create $h2
 
-	run_test $h2
+	run_test $h1 $h2
 
 	macvlan_destroy
 	h2_destroy
@@ -280,7 +281,7 @@ bridge()
 	bridge_create
 	macvlan_create br0
 
-	run_test br0
+	run_test $h1 br0
 
 	macvlan_destroy
 	bridge_destroy

From df7cf5cc551c7c0a92520e91e1184993784c6386 Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Thu, 15 Aug 2024 03:06:56 +0300
Subject: [PATCH 10/82] selftests: net: local_termination: parameterize test
 name

There are upcoming tests which verify the RX filtering of a bridge
(or bridge port), but under differing vlan_filtering conditions.
Since we currently print $h2 (the DUT) in the log_test() output, it
becomes necessary to make a further distinction between tests, to not
give the user the impression that the exact same thing is run twice.

Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/forwarding/local_termination.sh       | 38 ++++++++++---------
 1 file changed, 20 insertions(+), 18 deletions(-)

diff --git a/tools/testing/selftests/net/forwarding/local_termination.sh b/tools/testing/selftests/net/forwarding/local_termination.sh
index 92f0e242d119..af284edaf401 100755
--- a/tools/testing/selftests/net/forwarding/local_termination.sh
+++ b/tools/testing/selftests/net/forwarding/local_termination.sh
@@ -68,10 +68,11 @@ send_uc_ipv4()
 
 check_rcv()
 {
-	local if_name=$1
-	local type=$2
-	local pattern=$3
-	local should_receive=$4
+	local if_name=$1; shift
+	local type=$1; shift
+	local pattern=$1; shift
+	local should_receive=$1; shift
+	local test_name="$1"; shift
 	local should_fail=
 
 	[ $should_receive = true ] && should_fail=0 || should_fail=1
@@ -81,7 +82,7 @@ check_rcv()
 
 	check_err_fail "$should_fail" "$?" "reception"
 
-	log_test "$if_name: $type"
+	log_test "$test_name: $type"
 }
 
 mc_route_prepare()
@@ -106,6 +107,7 @@ run_test()
 {
 	local send_if_name=$1; shift
 	local rcv_if_name=$1; shift
+	local test_name="$1"; shift
 	local smac=$(mac_get $send_if_name)
 	local rcv_dmac=$(mac_get $rcv_if_name)
 
@@ -150,61 +152,61 @@ run_test()
 
 	check_rcv $rcv_if_name "Unicast IPv4 to primary MAC address" \
 		"$smac > $rcv_dmac, ethertype IPv4 (0x0800)" \
-		true
+		true "$test_name"
 
 	check_rcv $rcv_if_name "Unicast IPv4 to macvlan MAC address" \
 		"$smac > $MACVLAN_ADDR, ethertype IPv4 (0x0800)" \
-		true
+		true "$test_name"
 
 	xfail_on_veth $h1 \
 		check_rcv $rcv_if_name "Unicast IPv4 to unknown MAC address" \
 			"$smac > $UNKNOWN_UC_ADDR1, ethertype IPv4 (0x0800)" \
-			false
+			false "$test_name"
 
 	check_rcv $rcv_if_name "Unicast IPv4 to unknown MAC address, promisc" \
 		"$smac > $UNKNOWN_UC_ADDR2, ethertype IPv4 (0x0800)" \
-		true
+		true "$test_name"
 
 	xfail_on_veth $h1 \
 		check_rcv $rcv_if_name \
 			"Unicast IPv4 to unknown MAC address, allmulti" \
 			"$smac > $UNKNOWN_UC_ADDR3, ethertype IPv4 (0x0800)" \
-			false
+			false "$test_name"
 
 	check_rcv $rcv_if_name "Multicast IPv4 to joined group" \
 		"$smac > $JOINED_MACV4_MC_ADDR, ethertype IPv4 (0x0800)" \
-		true
+		true "$test_name"
 
 	xfail_on_veth $h1 \
 		check_rcv $rcv_if_name \
 			"Multicast IPv4 to unknown group" \
 			"$smac > $UNKNOWN_MACV4_MC_ADDR1, ethertype IPv4 (0x0800)" \
-			false
+			false "$test_name"
 
 	check_rcv $rcv_if_name "Multicast IPv4 to unknown group, promisc" \
 		"$smac > $UNKNOWN_MACV4_MC_ADDR2, ethertype IPv4 (0x0800)" \
-		true
+		true "$test_name"
 
 	check_rcv $rcv_if_name "Multicast IPv4 to unknown group, allmulti" \
 		"$smac > $UNKNOWN_MACV4_MC_ADDR3, ethertype IPv4 (0x0800)" \
-		true
+		true "$test_name"
 
 	check_rcv $rcv_if_name "Multicast IPv6 to joined group" \
 		"$smac > $JOINED_MACV6_MC_ADDR, ethertype IPv6 (0x86dd)" \
-		true
+		true "$test_name"
 
 	xfail_on_veth $h1 \
 		check_rcv $rcv_if_name "Multicast IPv6 to unknown group" \
 			"$smac > $UNKNOWN_MACV6_MC_ADDR1, ethertype IPv6 (0x86dd)" \
-			false
+			false "$test_name"
 
 	check_rcv $rcv_if_name "Multicast IPv6 to unknown group, promisc" \
 		"$smac > $UNKNOWN_MACV6_MC_ADDR2, ethertype IPv6 (0x86dd)" \
-		true
+		true "$test_name"
 
 	check_rcv $rcv_if_name "Multicast IPv6 to unknown group, allmulti" \
 		"$smac > $UNKNOWN_MACV6_MC_ADDR3, ethertype IPv6 (0x86dd)" \
-		true
+		true "$test_name"
 
 	tcpdump_cleanup $rcv_if_name
 }

From 5b8e74182ed3d4f1c38c626e6120275ca9d92bee Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Thu, 15 Aug 2024 03:06:57 +0300
Subject: [PATCH 11/82] selftests: net: local_termination: add one more test
 for VLAN-aware bridges

The current bridge() test is for packet reception on a VLAN-unaware
bridge. Some things are different enough with VLAN-aware bridges that
it's worth renaming this test into vlan_unaware_bridge(), and add a new
vlan_aware_bridge() test.

The two will share the same implementation: bridge() becomes a common
function, which receives $vlan_filtering as an argument. Rename it to
test_bridge() at the same time, because just bridge() pollutes the
global namespace and we cannot invoke the binary with the same name from
the iproute2 package currently.

Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/forwarding/local_termination.sh       | 22 +++++++++++++++----
 1 file changed, 18 insertions(+), 4 deletions(-)

diff --git a/tools/testing/selftests/net/forwarding/local_termination.sh b/tools/testing/selftests/net/forwarding/local_termination.sh
index af284edaf401..5aa364b40e33 100755
--- a/tools/testing/selftests/net/forwarding/local_termination.sh
+++ b/tools/testing/selftests/net/forwarding/local_termination.sh
@@ -1,7 +1,7 @@
 #!/bin/bash
 # SPDX-License-Identifier: GPL-2.0
 
-ALL_TESTS="standalone bridge"
+ALL_TESTS="standalone vlan_unaware_bridge vlan_aware_bridge"
 NUM_NETIFS=2
 PING_COUNT=1
 REQUIRE_MTOOLS=yes
@@ -233,7 +233,9 @@ h2_destroy()
 
 bridge_create()
 {
-	ip link add br0 type bridge
+	local vlan_filtering=$1
+
+	ip link add br0 type bridge vlan_filtering $vlan_filtering
 	ip link set br0 address $BRIDGE_ADDR
 	ip link set br0 up
 
@@ -277,10 +279,12 @@ standalone()
 	h1_destroy
 }
 
-bridge()
+test_bridge()
 {
+	local vlan_filtering=$1
+
 	h1_create
-	bridge_create
+	bridge_create $vlan_filtering
 	macvlan_create br0
 
 	run_test $h1 br0
@@ -290,6 +294,16 @@ bridge()
 	h1_destroy
 }
 
+vlan_unaware_bridge()
+{
+	test_bridge 0
+}
+
+vlan_aware_bridge()
+{
+	test_bridge 1
+}
+
 cleanup()
 {
 	pre_cleanup

From 5fea8bb009744bbb90b3f6ca41c558429ee4c849 Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Thu, 15 Aug 2024 03:06:58 +0300
Subject: [PATCH 12/82] selftests: net: local_termination: introduce new tests
 which capture VLAN behavior

Add more coverage to the local termination selftest as follows:
- 8021q upper of $h2
- 8021q upper of $h2, where $h2 is a port of a VLAN-unaware bridge
- 8021q upper of $h2, where $h2 is a port of a VLAN-aware bridge
- 8021q upper of VLAN-unaware br0, which is the upper of $h2
- 8021q upper of VLAN-aware br0, which is the upper of $h2

Especially the cases with traffic sent through the VLAN upper of a
VLAN-aware bridge port will be immediately relevant when we will start
transmitting PTP packets as an additional kind of traffic.

Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/forwarding/local_termination.sh       | 117 ++++++++++++++++--
 1 file changed, 110 insertions(+), 7 deletions(-)

diff --git a/tools/testing/selftests/net/forwarding/local_termination.sh b/tools/testing/selftests/net/forwarding/local_termination.sh
index 5aa364b40e33..e22c6a693bef 100755
--- a/tools/testing/selftests/net/forwarding/local_termination.sh
+++ b/tools/testing/selftests/net/forwarding/local_termination.sh
@@ -1,7 +1,9 @@
 #!/bin/bash
 # SPDX-License-Identifier: GPL-2.0
 
-ALL_TESTS="standalone vlan_unaware_bridge vlan_aware_bridge"
+ALL_TESTS="standalone vlan_unaware_bridge vlan_aware_bridge test_vlan \
+	   vlan_over_vlan_unaware_bridged_port vlan_over_vlan_aware_bridged_port \
+	   vlan_over_vlan_unaware_bridge vlan_over_vlan_aware_bridge"
 NUM_NETIFS=2
 PING_COUNT=1
 REQUIRE_MTOOLS=yes
@@ -231,6 +233,30 @@ h2_destroy()
 	simple_if_fini $h2 $H2_IPV4/24 $H2_IPV6/64
 }
 
+h1_vlan_create()
+{
+	simple_if_init $h1
+	vlan_create $h1 100 v$h1 $H1_IPV4/24 $H1_IPV6/64
+}
+
+h1_vlan_destroy()
+{
+	vlan_destroy $h1 100
+	simple_if_fini $h1
+}
+
+h2_vlan_create()
+{
+	simple_if_init $h2
+	vlan_create $h2 100 v$h2 $H2_IPV4/24 $H2_IPV6/64
+}
+
+h2_vlan_destroy()
+{
+	vlan_destroy $h2 100
+	simple_if_fini $h2
+}
+
 bridge_create()
 {
 	local vlan_filtering=$1
@@ -241,14 +267,10 @@ bridge_create()
 
 	ip link set $h2 master br0
 	ip link set $h2 up
-
-	simple_if_init br0 $H2_IPV4/24 $H2_IPV6/64
 }
 
 bridge_destroy()
 {
-	simple_if_fini br0 $H2_IPV4/24 $H2_IPV6/64
-
 	ip link del br0
 }
 
@@ -272,7 +294,7 @@ standalone()
 	h2_create
 	macvlan_create $h2
 
-	run_test $h1 $h2
+	run_test $h1 $h2 "$h2"
 
 	macvlan_destroy
 	h2_destroy
@@ -285,11 +307,13 @@ test_bridge()
 
 	h1_create
 	bridge_create $vlan_filtering
+	simple_if_init br0 $H2_IPV4/24 $H2_IPV6/64
 	macvlan_create br0
 
-	run_test $h1 br0
+	run_test $h1 br0 "vlan_filtering=$vlan_filtering bridge"
 
 	macvlan_destroy
+	simple_if_fini br0 $H2_IPV4/24 $H2_IPV6/64
 	bridge_destroy
 	h1_destroy
 }
@@ -304,6 +328,85 @@ vlan_aware_bridge()
 	test_bridge 1
 }
 
+test_vlan()
+{
+	h1_vlan_create
+	h2_vlan_create
+	macvlan_create $h2.100
+
+	run_test $h1.100 $h2.100 "VLAN upper"
+
+	macvlan_destroy
+	h2_vlan_destroy
+	h1_vlan_destroy
+}
+
+vlan_over_bridged_port()
+{
+	local vlan_filtering=$1
+
+	h1_vlan_create
+	h2_vlan_create
+	bridge_create $vlan_filtering
+	macvlan_create $h2.100
+
+	run_test $h1.100 $h2.100 "VLAN over vlan_filtering=$vlan_filtering bridged port"
+
+	macvlan_destroy
+	bridge_destroy
+	h2_vlan_destroy
+	h1_vlan_destroy
+}
+
+vlan_over_vlan_unaware_bridged_port()
+{
+	vlan_over_bridged_port 0
+}
+
+vlan_over_vlan_aware_bridged_port()
+{
+	vlan_over_bridged_port 1
+}
+
+vlan_over_bridge()
+{
+	local vlan_filtering=$1
+
+	h1_vlan_create
+	bridge_create $vlan_filtering
+	simple_if_init br0
+	vlan_create br0 100 vbr0 $H2_IPV4/24 $H2_IPV6/64
+	macvlan_create br0.100
+
+	if [ $vlan_filtering = 1 ]; then
+		bridge vlan add dev $h2 vid 100 master
+		bridge vlan add dev br0 vid 100 self
+	fi
+
+	run_test $h1.100 br0.100 "VLAN over vlan_filtering=$vlan_filtering bridge"
+
+	if [ $vlan_filtering = 1 ]; then
+		bridge vlan del dev br0 vid 100 self
+		bridge vlan del dev $h2 vid 100 master
+	fi
+
+	macvlan_destroy
+	vlan_destroy br0 100
+	simple_if_fini br0
+	bridge_destroy
+	h1_vlan_destroy
+}
+
+vlan_over_vlan_unaware_bridge()
+{
+	vlan_over_bridge 0
+}
+
+vlan_over_vlan_aware_bridge()
+{
+	vlan_over_bridge 1
+}
+
 cleanup()
 {
 	pre_cleanup

From 9aa3749ca4a880c1a59720aab3eacf344ed8d68d Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Thu, 15 Aug 2024 03:06:59 +0300
Subject: [PATCH 13/82] selftests: net: local_termination: don't use
 xfail_on_veth()

xfail_on_veth() for this test is an incorrect approximation which gives
false positives and false negatives.

When local_termination fails with "reception succeeded, but should have failed",
it is because the DUT ($h2) accepts packets even when not configured as
promiscuous. This is not something specific to veth; even the bridge
behaves that way, but this is not captured by the xfail_on_veth test.

The IFF_UNICAST_FLT flag is not explicitly exported to user space, but
it can somewhat be determined from the interface's behavior. We have to
create a macvlan upper with a different MAC address. This forces a
dev_uc_add() call in the kernel. When the unicast filtering list is
not empty, but the device doesn't support IFF_UNICAST_FLT,
__dev_set_rx_mode() force-enables promiscuity on the interface, to
ensure correct behavior (that the requested address is received).

We can monitor the change in the promiscuity flag and infer from it
whether the device supports unicast filtering.

There is no equivalent thing for allmulti, unfortunately. We never know
what's hiding behind a device which has allmulti=off. Whether it will
actually perform RX multicast filtering of unknown traffic is a strong
"maybe". The bridge driver, for example, completely ignores the flag.
We'll have to keep the xfail behavior, but instead of XFAIL on just
veth, always XFAIL.

Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/forwarding/lib.sh | 57 ++++++++++++++++++
 .../net/forwarding/local_termination.sh       | 58 ++++++++++++++-----
 2 files changed, 99 insertions(+), 16 deletions(-)

diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh
index ff96bb7535ff..718d04a4f72d 100644
--- a/tools/testing/selftests/net/forwarding/lib.sh
+++ b/tools/testing/selftests/net/forwarding/lib.sh
@@ -500,6 +500,11 @@ check_err_fail()
 	fi
 }
 
+xfail()
+{
+	FAIL_TO_XFAIL=yes "$@"
+}
+
 xfail_on_slow()
 {
 	if [[ $KSFT_MACHINE_SLOW = yes ]]; then
@@ -1113,6 +1118,39 @@ mac_get()
 	ip -j link show dev $if_name | jq -r '.[]["address"]'
 }
 
+ether_addr_to_u64()
+{
+	local addr="$1"
+	local order="$((1 << 40))"
+	local val=0
+	local byte
+
+	addr="${addr//:/ }"
+
+	for byte in $addr; do
+		byte="0x$byte"
+		val=$((val + order * byte))
+		order=$((order >> 8))
+	done
+
+	printf "0x%x" $val
+}
+
+u64_to_ether_addr()
+{
+	local val=$1
+	local byte
+	local i
+
+	for ((i = 40; i >= 0; i -= 8)); do
+		byte=$(((val & (0xff << i)) >> i))
+		printf "%02x" $byte
+		if [ $i -ne 0 ]; then
+			printf ":"
+		fi
+	done
+}
+
 ipv6_lladdr_get()
 {
 	local if_name=$1
@@ -2229,3 +2267,22 @@ absval()
 
 	echo $((v > 0 ? v : -v))
 }
+
+has_unicast_flt()
+{
+	local dev=$1; shift
+	local mac_addr=$(mac_get $dev)
+	local tmp=$(ether_addr_to_u64 $mac_addr)
+	local promisc
+
+	ip link set $dev up
+	ip link add link $dev name macvlan-tmp type macvlan mode private
+	ip link set macvlan-tmp address $(u64_to_ether_addr $((tmp + 1)))
+	ip link set macvlan-tmp up
+
+	promisc=$(ip -j -d link show dev $dev | jq -r '.[].promiscuity')
+
+	ip link del macvlan-tmp
+
+	[[ $promisc == 1 ]] && echo "no" || echo "yes"
+}
diff --git a/tools/testing/selftests/net/forwarding/local_termination.sh b/tools/testing/selftests/net/forwarding/local_termination.sh
index e22c6a693bef..80ea4c10d764 100755
--- a/tools/testing/selftests/net/forwarding/local_termination.sh
+++ b/tools/testing/selftests/net/forwarding/local_termination.sh
@@ -109,9 +109,11 @@ run_test()
 {
 	local send_if_name=$1; shift
 	local rcv_if_name=$1; shift
+	local no_unicast_flt=$1; shift
 	local test_name="$1"; shift
 	local smac=$(mac_get $send_if_name)
 	local rcv_dmac=$(mac_get $rcv_if_name)
+	local should_receive
 
 	tcpdump_start $rcv_if_name
 
@@ -160,26 +162,26 @@ run_test()
 		"$smac > $MACVLAN_ADDR, ethertype IPv4 (0x0800)" \
 		true "$test_name"
 
-	xfail_on_veth $h1 \
-		check_rcv $rcv_if_name "Unicast IPv4 to unknown MAC address" \
-			"$smac > $UNKNOWN_UC_ADDR1, ethertype IPv4 (0x0800)" \
-			false "$test_name"
+	[ $no_unicast_flt = true ] && should_receive=true || should_receive=false
+	check_rcv $rcv_if_name "Unicast IPv4 to unknown MAC address" \
+		"$smac > $UNKNOWN_UC_ADDR1, ethertype IPv4 (0x0800)" \
+		$should_receive "$test_name"
 
 	check_rcv $rcv_if_name "Unicast IPv4 to unknown MAC address, promisc" \
 		"$smac > $UNKNOWN_UC_ADDR2, ethertype IPv4 (0x0800)" \
 		true "$test_name"
 
-	xfail_on_veth $h1 \
-		check_rcv $rcv_if_name \
-			"Unicast IPv4 to unknown MAC address, allmulti" \
-			"$smac > $UNKNOWN_UC_ADDR3, ethertype IPv4 (0x0800)" \
-			false "$test_name"
+	[ $no_unicast_flt = true ] && should_receive=true || should_receive=false
+	check_rcv $rcv_if_name \
+		"Unicast IPv4 to unknown MAC address, allmulti" \
+		"$smac > $UNKNOWN_UC_ADDR3, ethertype IPv4 (0x0800)" \
+		$should_receive "$test_name"
 
 	check_rcv $rcv_if_name "Multicast IPv4 to joined group" \
 		"$smac > $JOINED_MACV4_MC_ADDR, ethertype IPv4 (0x0800)" \
 		true "$test_name"
 
-	xfail_on_veth $h1 \
+	xfail \
 		check_rcv $rcv_if_name \
 			"Multicast IPv4 to unknown group" \
 			"$smac > $UNKNOWN_MACV4_MC_ADDR1, ethertype IPv4 (0x0800)" \
@@ -197,7 +199,7 @@ run_test()
 		"$smac > $JOINED_MACV6_MC_ADDR, ethertype IPv6 (0x86dd)" \
 		true "$test_name"
 
-	xfail_on_veth $h1 \
+	xfail \
 		check_rcv $rcv_if_name "Multicast IPv6 to unknown group" \
 			"$smac > $UNKNOWN_MACV6_MC_ADDR1, ethertype IPv6 (0x86dd)" \
 			false "$test_name"
@@ -290,11 +292,17 @@ macvlan_destroy()
 
 standalone()
 {
+	local no_unicast_flt=true
+
+	if [ $(has_unicast_flt $h2) = yes ]; then
+		no_unicast_flt=false
+	fi
+
 	h1_create
 	h2_create
 	macvlan_create $h2
 
-	run_test $h1 $h2 "$h2"
+	run_test $h1 $h2 $no_unicast_flt "$h2"
 
 	macvlan_destroy
 	h2_destroy
@@ -303,6 +311,7 @@ standalone()
 
 test_bridge()
 {
+	local no_unicast_flt=true
 	local vlan_filtering=$1
 
 	h1_create
@@ -310,7 +319,7 @@ test_bridge()
 	simple_if_init br0 $H2_IPV4/24 $H2_IPV6/64
 	macvlan_create br0
 
-	run_test $h1 br0 "vlan_filtering=$vlan_filtering bridge"
+	run_test $h1 br0 $no_unicast_flt "vlan_filtering=$vlan_filtering bridge"
 
 	macvlan_destroy
 	simple_if_fini br0 $H2_IPV4/24 $H2_IPV6/64
@@ -330,11 +339,17 @@ vlan_aware_bridge()
 
 test_vlan()
 {
+	local no_unicast_flt=true
+
+	if [ $(has_unicast_flt $h2) = yes ]; then
+		no_unicast_flt=false
+	fi
+
 	h1_vlan_create
 	h2_vlan_create
 	macvlan_create $h2.100
 
-	run_test $h1.100 $h2.100 "VLAN upper"
+	run_test $h1.100 $h2.100 $no_unicast_flt "VLAN upper"
 
 	macvlan_destroy
 	h2_vlan_destroy
@@ -343,14 +358,23 @@ test_vlan()
 
 vlan_over_bridged_port()
 {
+	local no_unicast_flt=true
 	local vlan_filtering=$1
 
+	# br_manage_promisc() will not force a single vlan_filtering port to
+	# promiscuous mode, so we should still expect unicast filtering to take
+	# place if the device can do it.
+	if [ $(has_unicast_flt $h2) = yes ] && [ $vlan_filtering = 1 ]; then
+		no_unicast_flt=false
+	fi
+
 	h1_vlan_create
 	h2_vlan_create
 	bridge_create $vlan_filtering
 	macvlan_create $h2.100
 
-	run_test $h1.100 $h2.100 "VLAN over vlan_filtering=$vlan_filtering bridged port"
+	run_test $h1.100 $h2.100 $no_unicast_flt \
+		"VLAN over vlan_filtering=$vlan_filtering bridged port"
 
 	macvlan_destroy
 	bridge_destroy
@@ -370,6 +394,7 @@ vlan_over_vlan_aware_bridged_port()
 
 vlan_over_bridge()
 {
+	local no_unicast_flt=true
 	local vlan_filtering=$1
 
 	h1_vlan_create
@@ -383,7 +408,8 @@ vlan_over_bridge()
 		bridge vlan add dev br0 vid 100 self
 	fi
 
-	run_test $h1.100 br0.100 "VLAN over vlan_filtering=$vlan_filtering bridge"
+	run_test $h1.100 br0.100 $no_unicast_flt \
+		"VLAN over vlan_filtering=$vlan_filtering bridge"
 
 	if [ $vlan_filtering = 1 ]; then
 		bridge vlan del dev br0 vid 100 self

From 237979504264912a9797dabc0db35126e705fe0d Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Thu, 15 Aug 2024 03:07:00 +0300
Subject: [PATCH 14/82] selftests: net: local_termination: add PTP frames to
 the mix

A breakage in the felix DSA driver shows we do not have enough test
coverage. More generally, it is sufficiently special that it is likely
drivers will treat it differently.

This is not meant to be a full PTP test, it just makes sure that PTP
packets sent to the different addresses corresponding to their profiles
are received correctly. The local_termination selftest seemed like the
most appropriate place for this addition.

PTP RX/TX in some cases makes no sense (over a bridge) and this is why
$skip_ptp exists. And in others - PTP over a bridge port - the IP stack
needs convincing through the available bridge netfilter hooks to leave
the PTP packets alone and not stolen by the bridge rx_handler. It is
safe to assume that users have that figured out already. This is a
driver level test, and by using tcpdump, all that extra setup is out of
scope here.

send_non_ip() was an unfinished idea; written but never used.
Replace it with a more generic send_raw(), and send 3 PTP packet types
times 3 transports.

Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/forwarding/local_termination.sh       | 161 ++++++++++++++++--
 1 file changed, 148 insertions(+), 13 deletions(-)

diff --git a/tools/testing/selftests/net/forwarding/local_termination.sh b/tools/testing/selftests/net/forwarding/local_termination.sh
index 80ea4c10d764..648868f74604 100755
--- a/tools/testing/selftests/net/forwarding/local_termination.sh
+++ b/tools/testing/selftests/net/forwarding/local_termination.sh
@@ -39,9 +39,68 @@ UNKNOWN_MACV6_MC_ADDR1="33:33:01:02:03:05"
 UNKNOWN_MACV6_MC_ADDR2="33:33:01:02:03:06"
 UNKNOWN_MACV6_MC_ADDR3="33:33:01:02:03:07"
 
-NON_IP_MC="01:02:03:04:05:06"
-NON_IP_PKT="00:04 48:45:4c:4f"
-BC="ff:ff:ff:ff:ff:ff"
+PTP_1588_L2_SYNC=" \
+01:1b:19:00:00:00 00:00:de:ad:be:ef 88:f7 00 02 \
+00 2c 00 00 02 00 00 00 00 00 00 00 00 00 00 00 \
+00 00 3e 37 63 ff fe cf 17 0e 00 01 00 00 00 00 \
+00 00 00 00 00 00 00 00 00 00"
+PTP_1588_L2_FOLLOW_UP=" \
+01:1b:19:00:00:00 00:00:de:ad:be:ef 88:f7 08 02 \
+00 2c 00 00 00 00 00 00 00 00 00 00 00 00 00 00 \
+00 00 3e 37 63 ff fe cf 17 0e 00 01 00 00 02 00 \
+00 00 66 83 c5 f1 17 97 ed f0"
+PTP_1588_L2_PDELAY_REQ=" \
+01:80:c2:00:00:0e 00:00:de:ad:be:ef 88:f7 02 02 \
+00 36 00 00 00 00 00 00 00 00 00 00 00 00 00 00 \
+00 00 3e 37 63 ff fe cf 17 0e 00 01 00 06 05 7f \
+00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 \
+00 00 00 00"
+PTP_1588_IPV4_SYNC=" \
+01:00:5e:00:01:81 00:00:de:ad:be:ef 08:00 45 00 \
+00 48 0a 9a 40 00 01 11 cb 88 c0 00 02 01 e0 00 \
+01 81 01 3f 01 3f 00 34 a3 c8 00 02 00 2c 00 00 \
+02 00 00 00 00 00 00 00 00 00 00 00 00 00 3e 37 \
+63 ff fe cf 17 0e 00 01 00 00 00 00 00 00 00 00 \
+00 00 00 00 00 00"
+PTP_1588_IPV4_FOLLOW_UP="
+01:00:5e:00:01:81 00:00:de:ad:be:ef 08:00 45 00 \
+00 48 0a 9b 40 00 01 11 cb 87 c0 00 02 01 e0 00 \
+01 81 01 40 01 40 00 34 a3 c8 08 02 00 2c 00 00 \
+00 00 00 00 00 00 00 00 00 00 00 00 00 00 3e 37 \
+63 ff fe cf 17 0e 00 01 00 00 02 00 00 00 66 83 \
+c6 0f 1d 9a 61 87"
+PTP_1588_IPV4_PDELAY_REQ=" \
+01:00:5e:00:00:6b 00:00:de:ad:be:ef 08:00 45 00 \
+00 52 35 a9 40 00 01 11 a1 85 c0 00 02 01 e0 00 \
+00 6b 01 3f 01 3f 00 3e a2 bc 02 02 00 36 00 00 \
+00 00 00 00 00 00 00 00 00 00 00 00 00 00 3e 37 \
+63 ff fe cf 17 0e 00 01 00 01 05 7f 00 00 00 00 \
+00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00"
+PTP_1588_IPV6_SYNC=" \
+33:33:00:00:01:81 00:00:de:ad:be:ef 86:dd 60 06 \
+7c 2f 00 36 11 01 20 01 0d b8 00 01 00 00 00 00 \
+00 00 00 00 00 01 ff 0e 00 00 00 00 00 00 00 00 \
+00 00 00 00 01 81 01 3f 01 3f 00 36 2e 92 00 02 \
+00 2c 00 00 02 00 00 00 00 00 00 00 00 00 00 00 \
+00 00 3e 37 63 ff fe cf 17 0e 00 01 00 00 00 00 \
+00 00 00 00 00 00 00 00 00 00 00 00"
+PTP_1588_IPV6_FOLLOW_UP=" \
+33:33:00:00:01:81 00:00:de:ad:be:ef 86:dd 60 0a \
+00 bc 00 36 11 01 20 01 0d b8 00 01 00 00 00 00 \
+00 00 00 00 00 01 ff 0e 00 00 00 00 00 00 00 00 \
+00 00 00 00 01 81 01 40 01 40 00 36 2e 92 08 02 \
+00 2c 00 00 00 00 00 00 00 00 00 00 00 00 00 00 \
+00 00 3e 37 63 ff fe cf 17 0e 00 01 00 00 02 00 \
+00 00 66 83 c6 2a 32 09 bd 74 00 00"
+PTP_1588_IPV6_PDELAY_REQ=" \
+33:33:00:00:00:6b 00:00:de:ad:be:ef 86:dd 60 0c \
+5c fd 00 40 11 01 fe 80 00 00 00 00 00 00 3c 37 \
+63 ff fe cf 17 0e ff 02 00 00 00 00 00 00 00 00 \
+00 00 00 00 00 6b 01 3f 01 3f 00 40 b4 54 02 02 \
+00 36 00 00 00 00 00 00 00 00 00 00 00 00 00 00 \
+00 00 3e 37 63 ff fe cf 17 0e 00 01 00 01 05 7f \
+00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 00 \
+00 00 00 00 00 00"
 
 # Disable promisc to ensure we don't receive unknown MAC DA packets
 export TCPDUMP_EXTRA_FLAGS="-pl"
@@ -49,13 +108,15 @@ export TCPDUMP_EXTRA_FLAGS="-pl"
 h1=${NETIFS[p1]}
 h2=${NETIFS[p2]}
 
-send_non_ip()
+send_raw()
 {
-	local if_name=$1
-	local smac=$2
-	local dmac=$3
+	local if_name=$1; shift
+	local pkt="$1"; shift
+	local smac=$(mac_get $if_name)
 
-	$MZ -q $if_name "$dmac $smac $NON_IP_PKT"
+	pkt="${pkt/00:00:de:ad:be:ef/$smac}"
+
+	$MZ -q $if_name "$pkt"
 }
 
 send_uc_ipv4()
@@ -109,6 +170,7 @@ run_test()
 {
 	local send_if_name=$1; shift
 	local rcv_if_name=$1; shift
+	local skip_ptp=$1; shift
 	local no_unicast_flt=$1; shift
 	local test_name="$1"; shift
 	local smac=$(mac_get $send_if_name)
@@ -150,6 +212,35 @@ run_test()
 	mc_route_destroy $rcv_if_name
 	mc_route_destroy $send_if_name
 
+	if [ $skip_ptp = false ]; then
+		ip maddress add 01:1b:19:00:00:00 dev $rcv_if_name
+		send_raw $send_if_name "$PTP_1588_L2_SYNC"
+		send_raw $send_if_name "$PTP_1588_L2_FOLLOW_UP"
+		ip maddress del 01:1b:19:00:00:00 dev $rcv_if_name
+
+		ip maddress add 01:80:c2:00:00:0e dev $rcv_if_name
+		send_raw $send_if_name "$PTP_1588_L2_PDELAY_REQ"
+		ip maddress del 01:80:c2:00:00:0e dev $rcv_if_name
+
+		mc_join $rcv_if_name 224.0.1.129
+		send_raw $send_if_name "$PTP_1588_IPV4_SYNC"
+		send_raw $send_if_name "$PTP_1588_IPV4_FOLLOW_UP"
+		mc_leave
+
+		mc_join $rcv_if_name 224.0.0.107
+		send_raw $send_if_name "$PTP_1588_IPV4_PDELAY_REQ"
+		mc_leave
+
+		mc_join $rcv_if_name ff0e::181
+		send_raw $send_if_name "$PTP_1588_IPV6_SYNC"
+		send_raw $send_if_name "$PTP_1588_IPV6_FOLLOW_UP"
+		mc_leave
+
+		mc_join $rcv_if_name ff02::6b
+		send_raw $send_if_name "$PTP_1588_IPV6_PDELAY_REQ"
+		mc_leave
+	fi
+
 	sleep 1
 
 	tcpdump_stop $rcv_if_name
@@ -212,6 +303,44 @@ run_test()
 		"$smac > $UNKNOWN_MACV6_MC_ADDR3, ethertype IPv6 (0x86dd)" \
 		true "$test_name"
 
+	if [ $skip_ptp = false ]; then
+		check_rcv $rcv_if_name "1588v2 over L2 transport, Sync" \
+			"ethertype PTP (0x88f7).* PTPv2.* msg type : sync msg" \
+			true "$test_name"
+
+		check_rcv $rcv_if_name "1588v2 over L2 transport, Follow-Up" \
+			"ethertype PTP (0x88f7).* PTPv2.* msg type : follow up msg" \
+			true "$test_name"
+
+		check_rcv $rcv_if_name "1588v2 over L2 transport, Peer Delay Request" \
+			"ethertype PTP (0x88f7).* PTPv2.* msg type : peer delay req msg" \
+			true "$test_name"
+
+		check_rcv $rcv_if_name "1588v2 over IPv4, Sync" \
+			"ethertype IPv4 (0x0800).* PTPv2.* msg type : sync msg" \
+			true "$test_name"
+
+		check_rcv $rcv_if_name "1588v2 over IPv4, Follow-Up" \
+			"ethertype IPv4 (0x0800).* PTPv2.* msg type : follow up msg" \
+			true "$test_name"
+
+		check_rcv $rcv_if_name "1588v2 over IPv4, Peer Delay Request" \
+			"ethertype IPv4 (0x0800).* PTPv2.* msg type : peer delay req msg" \
+			true "$test_name"
+
+		check_rcv $rcv_if_name "1588v2 over IPv6, Sync" \
+			"ethertype IPv6 (0x86dd).* PTPv2.* msg type : sync msg" \
+			true "$test_name"
+
+		check_rcv $rcv_if_name "1588v2 over IPv6, Follow-Up" \
+			"ethertype IPv6 (0x86dd).* PTPv2.* msg type : follow up msg" \
+			true "$test_name"
+
+		check_rcv $rcv_if_name "1588v2 over IPv6, Peer Delay Request" \
+			"ethertype IPv6 (0x86dd).* PTPv2.* msg type : peer delay req msg" \
+			true "$test_name"
+	fi
+
 	tcpdump_cleanup $rcv_if_name
 }
 
@@ -293,6 +422,7 @@ macvlan_destroy()
 standalone()
 {
 	local no_unicast_flt=true
+	local skip_ptp=false
 
 	if [ $(has_unicast_flt $h2) = yes ]; then
 		no_unicast_flt=false
@@ -302,7 +432,7 @@ standalone()
 	h2_create
 	macvlan_create $h2
 
-	run_test $h1 $h2 $no_unicast_flt "$h2"
+	run_test $h1 $h2 $skip_ptp $no_unicast_flt "$h2"
 
 	macvlan_destroy
 	h2_destroy
@@ -313,13 +443,15 @@ test_bridge()
 {
 	local no_unicast_flt=true
 	local vlan_filtering=$1
+	local skip_ptp=true
 
 	h1_create
 	bridge_create $vlan_filtering
 	simple_if_init br0 $H2_IPV4/24 $H2_IPV6/64
 	macvlan_create br0
 
-	run_test $h1 br0 $no_unicast_flt "vlan_filtering=$vlan_filtering bridge"
+	run_test $h1 br0 $skip_ptp $no_unicast_flt \
+		"vlan_filtering=$vlan_filtering bridge"
 
 	macvlan_destroy
 	simple_if_fini br0 $H2_IPV4/24 $H2_IPV6/64
@@ -340,6 +472,7 @@ vlan_aware_bridge()
 test_vlan()
 {
 	local no_unicast_flt=true
+	local skip_ptp=false
 
 	if [ $(has_unicast_flt $h2) = yes ]; then
 		no_unicast_flt=false
@@ -349,7 +482,7 @@ test_vlan()
 	h2_vlan_create
 	macvlan_create $h2.100
 
-	run_test $h1.100 $h2.100 $no_unicast_flt "VLAN upper"
+	run_test $h1.100 $h2.100 $skip_ptp $no_unicast_flt "VLAN upper"
 
 	macvlan_destroy
 	h2_vlan_destroy
@@ -360,6 +493,7 @@ vlan_over_bridged_port()
 {
 	local no_unicast_flt=true
 	local vlan_filtering=$1
+	local skip_ptp=false
 
 	# br_manage_promisc() will not force a single vlan_filtering port to
 	# promiscuous mode, so we should still expect unicast filtering to take
@@ -373,7 +507,7 @@ vlan_over_bridged_port()
 	bridge_create $vlan_filtering
 	macvlan_create $h2.100
 
-	run_test $h1.100 $h2.100 $no_unicast_flt \
+	run_test $h1.100 $h2.100 $skip_ptp $no_unicast_flt \
 		"VLAN over vlan_filtering=$vlan_filtering bridged port"
 
 	macvlan_destroy
@@ -396,6 +530,7 @@ vlan_over_bridge()
 {
 	local no_unicast_flt=true
 	local vlan_filtering=$1
+	local skip_ptp=true
 
 	h1_vlan_create
 	bridge_create $vlan_filtering
@@ -408,7 +543,7 @@ vlan_over_bridge()
 		bridge vlan add dev br0 vid 100 self
 	fi
 
-	run_test $h1.100 br0.100 $no_unicast_flt \
+	run_test $h1.100 br0.100 $skip_ptp $no_unicast_flt \
 		"VLAN over vlan_filtering=$vlan_filtering bridge"
 
 	if [ $vlan_filtering = 1 ]; then

From e29b82ef27616777e21c07dc263a8769cbdaa358 Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Thu, 15 Aug 2024 03:07:01 +0300
Subject: [PATCH 15/82] selftests: net: bridge_vlan_aware: test that other
 TPIDs are seen as untagged

The bridge VLAN implementation w.r.t. VLAN protocol is described in
merge commit 1a0b20b25732 ("Merge branch 'bridge-next'"). We are only
sensitive to those VLAN tags whose TPID is equal to the bridge's
vlan_protocol. Thus, an 802.1ad VLAN should be treated as 802.1Q-untagged.

Add 3 tests which validate that:
- 802.1ad-tagged traffic is learned into the PVID of an 802.1Q-aware
  bridge
- Double-tagged traffic is forwarded when just the PVID of the port is
  present in the VLAN group of the ports
- Double-tagged traffic is not forwarded when the PVID of the port is
  absent from the VLAN group of the ports

The test passes with both veth and ocelot.

Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Reviewed-by: Ido Schimmel <idosch@nvidia.com>
Tested-by: Ido Schimmel <idosch@nvidia.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 .../net/forwarding/bridge_vlan_aware.sh       | 54 ++++++++++++++++++-
 1 file changed, 53 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/net/forwarding/bridge_vlan_aware.sh b/tools/testing/selftests/net/forwarding/bridge_vlan_aware.sh
index 64bd00fe9a4f..90f8a244ea90 100755
--- a/tools/testing/selftests/net/forwarding/bridge_vlan_aware.sh
+++ b/tools/testing/selftests/net/forwarding/bridge_vlan_aware.sh
@@ -1,7 +1,7 @@
 #!/bin/bash
 # SPDX-License-Identifier: GPL-2.0
 
-ALL_TESTS="ping_ipv4 ping_ipv6 learning flooding vlan_deletion extern_learn"
+ALL_TESTS="ping_ipv4 ping_ipv6 learning flooding vlan_deletion extern_learn other_tpid"
 NUM_NETIFS=4
 CHECK_TC="yes"
 source lib.sh
@@ -142,6 +142,58 @@ extern_learn()
 	bridge fdb del de:ad:be:ef:13:37 dev $swp1 master vlan 1 &> /dev/null
 }
 
+other_tpid()
+{
+	local mac=de:ad:be:ef:13:37
+
+	# Test that packets with TPID 802.1ad VID 3 + TPID 802.1Q VID 5 are
+	# classified as untagged by a bridge with vlan_protocol 802.1Q, and
+	# are processed in the PVID of the ingress port (here 1). Not VID 3,
+	# and not VID 5.
+	RET=0
+
+	tc qdisc add dev $h2 clsact
+	tc filter add dev $h2 ingress protocol all pref 1 handle 101 \
+		flower dst_mac $mac action drop
+	ip link set $h2 promisc on
+	ethtool -K $h2 rx-vlan-filter off rx-vlan-stag-filter off
+
+	$MZ -q $h1 -c 1 -b $mac -a own "88:a8 00:03 81:00 00:05 08:00 aa-aa-aa-aa-aa-aa-aa-aa-aa"
+	sleep 1
+
+	# Match on 'self' addresses as well, for those drivers which
+	# do not push their learned addresses to the bridge software
+	# database
+	bridge -j fdb show $swp1 | \
+		jq -e ".[] | select(.mac == \"$(mac_get $h1)\") | select(.vlan == 1)" &> /dev/null
+	check_err $? "FDB entry was not learned when it should"
+
+	log_test "FDB entry in PVID for VLAN-tagged with other TPID"
+
+	RET=0
+	tc -j -s filter show dev $h2 ingress \
+		| jq -e ".[] | select(.options.handle == 101) \
+		| select(.options.actions[0].stats.packets == 1)" &> /dev/null
+	check_err $? "Packet was not forwarded when it should"
+	log_test "Reception of VLAN with other TPID as untagged"
+
+	bridge vlan del dev $swp1 vid 1
+
+	$MZ -q $h1 -c 1 -b $mac -a own "88:a8 00:03 81:00 00:05 08:00 aa-aa-aa-aa-aa-aa-aa-aa-aa"
+	sleep 1
+
+	RET=0
+	tc -j -s filter show dev $h2 ingress \
+		| jq -e ".[] | select(.options.handle == 101) \
+		| select(.options.actions[0].stats.packets == 1)" &> /dev/null
+	check_err $? "Packet was forwarded when should not"
+	log_test "Reception of VLAN with other TPID as untagged (no PVID)"
+
+	bridge vlan add dev $swp1 vid 1 pvid untagged
+	ip link set $h2 promisc off
+	tc qdisc del dev $h2 clsact
+}
+
 trap cleanup EXIT
 
 setup_prepare

From 67c3ca2c5cfe6a50772514e3349b5e7b3b0fac03 Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Thu, 15 Aug 2024 03:07:02 +0300
Subject: [PATCH 16/82] net: mscc: ocelot: use ocelot_xmit_get_vlan_info() also
 for FDMA and register injection

Problem description
-------------------

On an NXP LS1028A (felix DSA driver) with the following configuration:

- ocelot-8021q tagging protocol
- VLAN-aware bridge (with STP) spanning at least swp0 and swp1
- 8021q VLAN upper interfaces on swp0 and swp1: swp0.700, swp1.700
- ptp4l on swp0.700 and swp1.700

we see that the ptp4l instances do not see each other's traffic,
and they all go to the grand master state due to the
ANNOUNCE_RECEIPT_TIMEOUT_EXPIRES condition.

Jumping to the conclusion for the impatient
-------------------------------------------

There is a zero-day bug in the ocelot switchdev driver in the way it
handles VLAN-tagged packet injection. The correct logic already exists in
the source code, in function ocelot_xmit_get_vlan_info() added by commit
5ca721c54d86 ("net: dsa: tag_ocelot: set the classified VLAN during xmit").
But it is used only for normal NPI-based injection with the DSA "ocelot"
tagging protocol. The other injection code paths (register-based and
FDMA-based) roll their own wrong logic. This affects and was noticed on
the DSA "ocelot-8021q" protocol because it uses register-based injection.

By moving ocelot_xmit_get_vlan_info() to a place that's common for both
the DSA tagger and the ocelot switch library, it can also be called from
ocelot_port_inject_frame() in ocelot.c.

We need to touch the lines with ocelot_ifh_port_set()'s prototype
anyway, so let's rename it to something clearer regarding what it does,
and add a kernel-doc. ocelot_ifh_set_basic() should do.

Investigation notes
-------------------

Debugging reveals that PTP event (aka those carrying timestamps, like
Sync) frames injected into swp0.700 (but also swp1.700) hit the wire
with two VLAN tags:

00000000: 01 1b 19 00 00 00 00 01 02 03 04 05 81 00 02 bc
                                              ~~~~~~~~~~~
00000010: 81 00 02 bc 88 f7 00 12 00 2c 00 00 02 00 00 00
          ~~~~~~~~~~~
00000020: 00 00 00 00 00 00 00 00 00 00 00 01 02 ff fe 03
00000030: 04 05 00 01 00 04 00 00 00 00 00 00 00 00 00 00
00000040: 00 00

The second (unexpected) VLAN tag makes felix_check_xtr_pkt() ->
ptp_classify_raw() fail to see these as PTP packets at the link
partner's receiving end, and return PTP_CLASS_NONE (because the BPF
classifier is not written to expect 2 VLAN tags).

The reason why packets have 2 VLAN tags is because the transmission
code treats VLAN incorrectly.

Neither ocelot switchdev, nor felix DSA, declare the NETIF_F_HW_VLAN_CTAG_TX
feature. Therefore, at xmit time, all VLANs should be in the skb head,
and none should be in the hwaccel area. This is done by:

static struct sk_buff *validate_xmit_vlan(struct sk_buff *skb,
					  netdev_features_t features)
{
	if (skb_vlan_tag_present(skb) &&
	    !vlan_hw_offload_capable(features, skb->vlan_proto))
		skb = __vlan_hwaccel_push_inside(skb);
	return skb;
}

But ocelot_port_inject_frame() handles things incorrectly:

	ocelot_ifh_port_set(ifh, port, rew_op, skb_vlan_tag_get(skb));

void ocelot_ifh_port_set(struct sk_buff *skb, void *ifh, int port, u32 rew_op)
{
	(...)
	if (vlan_tag)
		ocelot_ifh_set_vlan_tci(ifh, vlan_tag);
	(...)
}

The way __vlan_hwaccel_push_inside() pushes the tag inside the skb head
is by calling:

static inline void __vlan_hwaccel_clear_tag(struct sk_buff *skb)
{
	skb->vlan_present = 0;
}

which does _not_ zero out skb->vlan_tci as seen by skb_vlan_tag_get().
This means that ocelot, when it calls skb_vlan_tag_get(), sees
(and uses) a residual skb->vlan_tci, while the same VLAN tag is
_already_ in the skb head.

The trivial fix for double VLAN headers is to replace the content of
ocelot_ifh_port_set() with:

	if (skb_vlan_tag_present(skb))
		ocelot_ifh_set_vlan_tci(ifh, skb_vlan_tag_get(skb));

but this would not be correct either, because, as mentioned,
vlan_hw_offload_capable() is false for us, so we'd be inserting dead
code and we'd always transmit packets with VID=0 in the injection frame
header.

I can't actually test the ocelot switchdev driver and rely exclusively
on code inspection, but I don't think traffic from 8021q uppers has ever
been injected properly, and not double-tagged. Thus I'm blaming the
introduction of VLAN fields in the injection header - early driver code.

As hinted at in the early conclusion, what we _want_ to happen for
VLAN transmission was already described once in commit 5ca721c54d86
("net: dsa: tag_ocelot: set the classified VLAN during xmit").

ocelot_xmit_get_vlan_info() intends to ensure that if the port through
which we're transmitting is under a VLAN-aware bridge, the outer VLAN
tag from the skb head is stripped from there and inserted into the
injection frame header (so that the packet is processed in hardware
through that actual VLAN). And in all other cases, the packet is sent
with VID=0 in the injection frame header, since the port is VLAN-unaware
and has logic to strip this VID on egress (making it invisible to the
wire).

Fixes: 08d02364b12f ("net: mscc: fix the injection header")
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mscc/ocelot.c      | 29 +++++++++++----
 drivers/net/ethernet/mscc/ocelot_fdma.c |  2 +-
 include/linux/dsa/ocelot.h              | 47 +++++++++++++++++++++++++
 include/soc/mscc/ocelot.h               |  3 +-
 net/dsa/tag_ocelot.c                    | 37 ++-----------------
 5 files changed, 75 insertions(+), 43 deletions(-)

diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c
index ed2fb44500b0..69a4e5a90475 100644
--- a/drivers/net/ethernet/mscc/ocelot.c
+++ b/drivers/net/ethernet/mscc/ocelot.c
@@ -1193,17 +1193,34 @@ bool ocelot_can_inject(struct ocelot *ocelot, int grp)
 }
 EXPORT_SYMBOL(ocelot_can_inject);
 
-void ocelot_ifh_port_set(void *ifh, int port, u32 rew_op, u32 vlan_tag)
+/**
+ * ocelot_ifh_set_basic - Set basic information in Injection Frame Header
+ * @ifh: Pointer to Injection Frame Header memory
+ * @ocelot: Switch private data structure
+ * @port: Egress port number
+ * @rew_op: Egress rewriter operation for PTP
+ * @skb: Pointer to socket buffer (packet)
+ *
+ * Populate the Injection Frame Header with basic information for this skb: the
+ * analyzer bypass bit, destination port, VLAN info, egress rewriter info.
+ */
+void ocelot_ifh_set_basic(void *ifh, struct ocelot *ocelot, int port,
+			  u32 rew_op, struct sk_buff *skb)
 {
+	struct ocelot_port *ocelot_port = ocelot->ports[port];
+	u64 vlan_tci, tag_type;
+
+	ocelot_xmit_get_vlan_info(skb, ocelot_port->bridge, &vlan_tci,
+				  &tag_type);
+
 	ocelot_ifh_set_bypass(ifh, 1);
 	ocelot_ifh_set_dest(ifh, BIT_ULL(port));
-	ocelot_ifh_set_tag_type(ifh, IFH_TAG_TYPE_C);
-	if (vlan_tag)
-		ocelot_ifh_set_vlan_tci(ifh, vlan_tag);
+	ocelot_ifh_set_tag_type(ifh, tag_type);
+	ocelot_ifh_set_vlan_tci(ifh, vlan_tci);
 	if (rew_op)
 		ocelot_ifh_set_rew_op(ifh, rew_op);
 }
-EXPORT_SYMBOL(ocelot_ifh_port_set);
+EXPORT_SYMBOL(ocelot_ifh_set_basic);
 
 void ocelot_port_inject_frame(struct ocelot *ocelot, int port, int grp,
 			      u32 rew_op, struct sk_buff *skb)
@@ -1214,7 +1231,7 @@ void ocelot_port_inject_frame(struct ocelot *ocelot, int port, int grp,
 	ocelot_write_rix(ocelot, QS_INJ_CTRL_GAP_SIZE(1) |
 			 QS_INJ_CTRL_SOF, QS_INJ_CTRL, grp);
 
-	ocelot_ifh_port_set(ifh, port, rew_op, skb_vlan_tag_get(skb));
+	ocelot_ifh_set_basic(ifh, ocelot, port, rew_op, skb);
 
 	for (i = 0; i < OCELOT_TAG_LEN / 4; i++)
 		ocelot_write_rix(ocelot, ifh[i], QS_INJ_WR, grp);
diff --git a/drivers/net/ethernet/mscc/ocelot_fdma.c b/drivers/net/ethernet/mscc/ocelot_fdma.c
index 312a46832154..87b59cc5e441 100644
--- a/drivers/net/ethernet/mscc/ocelot_fdma.c
+++ b/drivers/net/ethernet/mscc/ocelot_fdma.c
@@ -666,7 +666,7 @@ static int ocelot_fdma_prepare_skb(struct ocelot *ocelot, int port, u32 rew_op,
 	ifh = skb_push(skb, OCELOT_TAG_LEN);
 	skb_put(skb, ETH_FCS_LEN);
 	memset(ifh, 0, OCELOT_TAG_LEN);
-	ocelot_ifh_port_set(ifh, port, rew_op, skb_vlan_tag_get(skb));
+	ocelot_ifh_set_basic(ifh, ocelot, port, rew_op, skb);
 
 	return 0;
 }
diff --git a/include/linux/dsa/ocelot.h b/include/linux/dsa/ocelot.h
index dca2969015d8..6fbfbde68a37 100644
--- a/include/linux/dsa/ocelot.h
+++ b/include/linux/dsa/ocelot.h
@@ -5,6 +5,8 @@
 #ifndef _NET_DSA_TAG_OCELOT_H
 #define _NET_DSA_TAG_OCELOT_H
 
+#include <linux/if_bridge.h>
+#include <linux/if_vlan.h>
 #include <linux/kthread.h>
 #include <linux/packing.h>
 #include <linux/skbuff.h>
@@ -273,4 +275,49 @@ static inline u32 ocelot_ptp_rew_op(struct sk_buff *skb)
 	return rew_op;
 }
 
+/**
+ * ocelot_xmit_get_vlan_info: Determine VLAN_TCI and TAG_TYPE for injected frame
+ * @skb: Pointer to socket buffer
+ * @br: Pointer to bridge device that the port is under, if any
+ * @vlan_tci:
+ * @tag_type:
+ *
+ * If the port is under a VLAN-aware bridge, remove the VLAN header from the
+ * payload and move it into the DSA tag, which will make the switch classify
+ * the packet to the bridge VLAN. Otherwise, leave the classified VLAN at zero,
+ * which is the pvid of standalone ports (OCELOT_STANDALONE_PVID), although not
+ * of VLAN-unaware bridge ports (that would be ocelot_vlan_unaware_pvid()).
+ * Anyway, VID 0 is fine because it is stripped on egress for these port modes,
+ * and source address learning is not performed for packets injected from the
+ * CPU anyway, so it doesn't matter that the VID is "wrong".
+ */
+static inline void ocelot_xmit_get_vlan_info(struct sk_buff *skb,
+					     struct net_device *br,
+					     u64 *vlan_tci, u64 *tag_type)
+{
+	struct vlan_ethhdr *hdr;
+	u16 proto, tci;
+
+	if (!br || !br_vlan_enabled(br)) {
+		*vlan_tci = 0;
+		*tag_type = IFH_TAG_TYPE_C;
+		return;
+	}
+
+	hdr = (struct vlan_ethhdr *)skb_mac_header(skb);
+	br_vlan_get_proto(br, &proto);
+
+	if (ntohs(hdr->h_vlan_proto) == proto) {
+		vlan_remove_tag(skb, &tci);
+		*vlan_tci = tci;
+	} else {
+		rcu_read_lock();
+		br_vlan_get_pvid_rcu(br, &tci);
+		rcu_read_unlock();
+		*vlan_tci = tci;
+	}
+
+	*tag_type = (proto != ETH_P_8021Q) ? IFH_TAG_TYPE_S : IFH_TAG_TYPE_C;
+}
+
 #endif
diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h
index 6a37b29f4b4c..ed18e6bafc8d 100644
--- a/include/soc/mscc/ocelot.h
+++ b/include/soc/mscc/ocelot.h
@@ -969,7 +969,8 @@ void __ocelot_target_write_ix(struct ocelot *ocelot, enum ocelot_target target,
 bool ocelot_can_inject(struct ocelot *ocelot, int grp);
 void ocelot_port_inject_frame(struct ocelot *ocelot, int port, int grp,
 			      u32 rew_op, struct sk_buff *skb);
-void ocelot_ifh_port_set(void *ifh, int port, u32 rew_op, u32 vlan_tag);
+void ocelot_ifh_set_basic(void *ifh, struct ocelot *ocelot, int port,
+			  u32 rew_op, struct sk_buff *skb);
 int ocelot_xtr_poll_frame(struct ocelot *ocelot, int grp, struct sk_buff **skb);
 void ocelot_drain_cpu_queue(struct ocelot *ocelot, int grp);
 void ocelot_ptp_rx_timestamp(struct ocelot *ocelot, struct sk_buff *skb,
diff --git a/net/dsa/tag_ocelot.c b/net/dsa/tag_ocelot.c
index e0e4300bfbd3..bf6608fc6be7 100644
--- a/net/dsa/tag_ocelot.c
+++ b/net/dsa/tag_ocelot.c
@@ -8,40 +8,6 @@
 #define OCELOT_NAME	"ocelot"
 #define SEVILLE_NAME	"seville"
 
-/* If the port is under a VLAN-aware bridge, remove the VLAN header from the
- * payload and move it into the DSA tag, which will make the switch classify
- * the packet to the bridge VLAN. Otherwise, leave the classified VLAN at zero,
- * which is the pvid of standalone and VLAN-unaware bridge ports.
- */
-static void ocelot_xmit_get_vlan_info(struct sk_buff *skb, struct dsa_port *dp,
-				      u64 *vlan_tci, u64 *tag_type)
-{
-	struct net_device *br = dsa_port_bridge_dev_get(dp);
-	struct vlan_ethhdr *hdr;
-	u16 proto, tci;
-
-	if (!br || !br_vlan_enabled(br)) {
-		*vlan_tci = 0;
-		*tag_type = IFH_TAG_TYPE_C;
-		return;
-	}
-
-	hdr = skb_vlan_eth_hdr(skb);
-	br_vlan_get_proto(br, &proto);
-
-	if (ntohs(hdr->h_vlan_proto) == proto) {
-		vlan_remove_tag(skb, &tci);
-		*vlan_tci = tci;
-	} else {
-		rcu_read_lock();
-		br_vlan_get_pvid_rcu(br, &tci);
-		rcu_read_unlock();
-		*vlan_tci = tci;
-	}
-
-	*tag_type = (proto != ETH_P_8021Q) ? IFH_TAG_TYPE_S : IFH_TAG_TYPE_C;
-}
-
 static void ocelot_xmit_common(struct sk_buff *skb, struct net_device *netdev,
 			       __be32 ifh_prefix, void **ifh)
 {
@@ -53,7 +19,8 @@ static void ocelot_xmit_common(struct sk_buff *skb, struct net_device *netdev,
 	u32 rew_op = 0;
 	u64 qos_class;
 
-	ocelot_xmit_get_vlan_info(skb, dp, &vlan_tci, &tag_type);
+	ocelot_xmit_get_vlan_info(skb, dsa_port_bridge_dev_get(dp), &vlan_tci,
+				  &tag_type);
 
 	qos_class = netdev_get_num_tc(netdev) ?
 		    netdev_get_prio_tc_map(netdev, skb->priority) : skb->priority;

From e1b9e80236c540fa85d76e2d510d1b38e1968c5d Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Thu, 15 Aug 2024 03:07:03 +0300
Subject: [PATCH 17/82] net: mscc: ocelot: fix QoS class for injected packets
 with "ocelot-8021q"

There are 2 distinct code paths (listed below) in the source code which
set up an injection header for Ocelot(-like) switches. Code path (2)
lacks the QoS class and source port being set correctly. Especially the
improper QoS classification is a problem for the "ocelot-8021q"
alternative DSA tagging protocol, because we support tc-taprio and each
packet needs to be scheduled precisely through its time slot. This
includes PTP, which is normally assigned to a traffic class other than
0, but would be sent through TC 0 nonetheless.

The code paths are:

(1) ocelot_xmit_common() from net/dsa/tag_ocelot.c - called only by the
    standard "ocelot" DSA tagging protocol which uses NPI-based
    injection - sets up bit fields in the tag manually to account for
    a small difference (destination port offset) between Ocelot and
    Seville. Namely, ocelot_ifh_set_dest() is omitted out of
    ocelot_xmit_common(), because there's also seville_ifh_set_dest().

(2) ocelot_ifh_set_basic(), called by:
    - ocelot_fdma_prepare_skb() for FDMA transmission of the ocelot
      switchdev driver
    - ocelot_port_xmit() -> ocelot_port_inject_frame() for
      register-based transmission of the ocelot switchdev driver
    - felix_port_deferred_xmit() -> ocelot_port_inject_frame() for the
      DSA tagger ocelot-8021q when it must transmit PTP frames (also
      through register-based injection).
    sets the bit fields according to its own logic.

The problem is that (2) doesn't call ocelot_ifh_set_qos_class().
Copying that logic from ocelot_xmit_common() fixes that.

Unfortunately, although desirable, it is not easily possible to
de-duplicate code paths (1) and (2), and make net/dsa/tag_ocelot.c
directly call ocelot_ifh_set_basic()), because of the ocelot/seville
difference. This is the "minimal" fix with some logic duplicated (but
at least more consolidated).

Fixes: 0a6f17c6ae21 ("net: dsa: tag_ocelot_8021q: add support for PTP timestamping")
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mscc/ocelot.c      | 10 +++++++++-
 drivers/net/ethernet/mscc/ocelot_fdma.c |  1 -
 2 files changed, 9 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c
index 69a4e5a90475..9301716e21d5 100644
--- a/drivers/net/ethernet/mscc/ocelot.c
+++ b/drivers/net/ethernet/mscc/ocelot.c
@@ -1208,13 +1208,21 @@ void ocelot_ifh_set_basic(void *ifh, struct ocelot *ocelot, int port,
 			  u32 rew_op, struct sk_buff *skb)
 {
 	struct ocelot_port *ocelot_port = ocelot->ports[port];
+	struct net_device *dev = skb->dev;
 	u64 vlan_tci, tag_type;
+	int qos_class;
 
 	ocelot_xmit_get_vlan_info(skb, ocelot_port->bridge, &vlan_tci,
 				  &tag_type);
 
+	qos_class = netdev_get_num_tc(dev) ?
+		    netdev_get_prio_tc_map(dev, skb->priority) : skb->priority;
+
+	memset(ifh, 0, OCELOT_TAG_LEN);
 	ocelot_ifh_set_bypass(ifh, 1);
+	ocelot_ifh_set_src(ifh, BIT_ULL(ocelot->num_phys_ports));
 	ocelot_ifh_set_dest(ifh, BIT_ULL(port));
+	ocelot_ifh_set_qos_class(ifh, qos_class);
 	ocelot_ifh_set_tag_type(ifh, tag_type);
 	ocelot_ifh_set_vlan_tci(ifh, vlan_tci);
 	if (rew_op)
@@ -1225,7 +1233,7 @@ EXPORT_SYMBOL(ocelot_ifh_set_basic);
 void ocelot_port_inject_frame(struct ocelot *ocelot, int port, int grp,
 			      u32 rew_op, struct sk_buff *skb)
 {
-	u32 ifh[OCELOT_TAG_LEN / 4] = {0};
+	u32 ifh[OCELOT_TAG_LEN / 4];
 	unsigned int i, count, last;
 
 	ocelot_write_rix(ocelot, QS_INJ_CTRL_GAP_SIZE(1) |
diff --git a/drivers/net/ethernet/mscc/ocelot_fdma.c b/drivers/net/ethernet/mscc/ocelot_fdma.c
index 87b59cc5e441..00326ae8c708 100644
--- a/drivers/net/ethernet/mscc/ocelot_fdma.c
+++ b/drivers/net/ethernet/mscc/ocelot_fdma.c
@@ -665,7 +665,6 @@ static int ocelot_fdma_prepare_skb(struct ocelot *ocelot, int port, u32 rew_op,
 
 	ifh = skb_push(skb, OCELOT_TAG_LEN);
 	skb_put(skb, ETH_FCS_LEN);
-	memset(ifh, 0, OCELOT_TAG_LEN);
 	ocelot_ifh_set_basic(ifh, ocelot, port, rew_op, skb);
 
 	return 0;

From c5e12ac3beb0dd3a718296b2d8af5528e9ab728e Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Thu, 15 Aug 2024 03:07:04 +0300
Subject: [PATCH 18/82] net: mscc: ocelot: serialize access to the
 injection/extraction groups

As explained by Horatiu Vultur in commit 603ead96582d ("net: sparx5: Add
spinlock for frame transmission from CPU") which is for a similar
hardware design, multiple CPUs can simultaneously perform injection
or extraction. There are only 2 register groups for injection and 2
for extraction, and the driver only uses one of each. So we'd better
serialize access using spin locks, otherwise frame corruption is
possible.

Note that unlike in sparx5, FDMA in ocelot does not have this issue
because struct ocelot_fdma_tx_ring already contains an xmit_lock.

I guess this is mostly a problem for NXP LS1028A, as that is dual core.
I don't think VSC7514 is. So I'm blaming the commit where LS1028A (aka
the felix DSA driver) started using register-based packet injection and
extraction.

Fixes: 0a6f17c6ae21 ("net: dsa: tag_ocelot_8021q: add support for PTP timestamping")
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/ocelot/felix.c             | 11 +++++
 drivers/net/ethernet/mscc/ocelot.c         | 52 ++++++++++++++++++++++
 drivers/net/ethernet/mscc/ocelot_vsc7514.c |  4 ++
 include/soc/mscc/ocelot.h                  |  9 ++++
 4 files changed, 76 insertions(+)

diff --git a/drivers/net/dsa/ocelot/felix.c b/drivers/net/dsa/ocelot/felix.c
index e554699f06d4..8d31ff18c5c7 100644
--- a/drivers/net/dsa/ocelot/felix.c
+++ b/drivers/net/dsa/ocelot/felix.c
@@ -528,7 +528,9 @@ static int felix_tag_8021q_setup(struct dsa_switch *ds)
 	 * so we need to be careful that there are no extra frames to be
 	 * dequeued over MMIO, since we would never know to discard them.
 	 */
+	ocelot_lock_xtr_grp_bh(ocelot, 0);
 	ocelot_drain_cpu_queue(ocelot, 0);
+	ocelot_unlock_xtr_grp_bh(ocelot, 0);
 
 	return 0;
 }
@@ -1518,6 +1520,8 @@ static void felix_port_deferred_xmit(struct kthread_work *work)
 	int port = xmit_work->dp->index;
 	int retries = 10;
 
+	ocelot_lock_inj_grp(ocelot, 0);
+
 	do {
 		if (ocelot_can_inject(ocelot, 0))
 			break;
@@ -1526,6 +1530,7 @@ static void felix_port_deferred_xmit(struct kthread_work *work)
 	} while (--retries);
 
 	if (!retries) {
+		ocelot_unlock_inj_grp(ocelot, 0);
 		dev_err(ocelot->dev, "port %d failed to inject skb\n",
 			port);
 		ocelot_port_purge_txtstamp_skb(ocelot, port, skb);
@@ -1535,6 +1540,8 @@ static void felix_port_deferred_xmit(struct kthread_work *work)
 
 	ocelot_port_inject_frame(ocelot, port, 0, rew_op, skb);
 
+	ocelot_unlock_inj_grp(ocelot, 0);
+
 	consume_skb(skb);
 	kfree(xmit_work);
 }
@@ -1694,6 +1701,8 @@ static bool felix_check_xtr_pkt(struct ocelot *ocelot)
 	if (!felix->info->quirk_no_xtr_irq)
 		return false;
 
+	ocelot_lock_xtr_grp(ocelot, grp);
+
 	while (ocelot_read(ocelot, QS_XTR_DATA_PRESENT) & BIT(grp)) {
 		struct sk_buff *skb;
 		unsigned int type;
@@ -1730,6 +1739,8 @@ static bool felix_check_xtr_pkt(struct ocelot *ocelot)
 		ocelot_drain_cpu_queue(ocelot, 0);
 	}
 
+	ocelot_unlock_xtr_grp(ocelot, grp);
+
 	return true;
 }
 
diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c
index 9301716e21d5..f4e027a6fe95 100644
--- a/drivers/net/ethernet/mscc/ocelot.c
+++ b/drivers/net/ethernet/mscc/ocelot.c
@@ -1099,6 +1099,48 @@ void ocelot_ptp_rx_timestamp(struct ocelot *ocelot, struct sk_buff *skb,
 }
 EXPORT_SYMBOL(ocelot_ptp_rx_timestamp);
 
+void ocelot_lock_inj_grp(struct ocelot *ocelot, int grp)
+			 __acquires(&ocelot->inj_lock)
+{
+	spin_lock(&ocelot->inj_lock);
+}
+EXPORT_SYMBOL_GPL(ocelot_lock_inj_grp);
+
+void ocelot_unlock_inj_grp(struct ocelot *ocelot, int grp)
+			   __releases(&ocelot->inj_lock)
+{
+	spin_unlock(&ocelot->inj_lock);
+}
+EXPORT_SYMBOL_GPL(ocelot_unlock_inj_grp);
+
+void ocelot_lock_xtr_grp(struct ocelot *ocelot, int grp)
+			 __acquires(&ocelot->inj_lock)
+{
+	spin_lock(&ocelot->inj_lock);
+}
+EXPORT_SYMBOL_GPL(ocelot_lock_xtr_grp);
+
+void ocelot_unlock_xtr_grp(struct ocelot *ocelot, int grp)
+			   __releases(&ocelot->inj_lock)
+{
+	spin_unlock(&ocelot->inj_lock);
+}
+EXPORT_SYMBOL_GPL(ocelot_unlock_xtr_grp);
+
+void ocelot_lock_xtr_grp_bh(struct ocelot *ocelot, int grp)
+			    __acquires(&ocelot->xtr_lock)
+{
+	spin_lock_bh(&ocelot->xtr_lock);
+}
+EXPORT_SYMBOL_GPL(ocelot_lock_xtr_grp_bh);
+
+void ocelot_unlock_xtr_grp_bh(struct ocelot *ocelot, int grp)
+			      __releases(&ocelot->xtr_lock)
+{
+	spin_unlock_bh(&ocelot->xtr_lock);
+}
+EXPORT_SYMBOL_GPL(ocelot_unlock_xtr_grp_bh);
+
 int ocelot_xtr_poll_frame(struct ocelot *ocelot, int grp, struct sk_buff **nskb)
 {
 	u64 timestamp, src_port, len;
@@ -1109,6 +1151,8 @@ int ocelot_xtr_poll_frame(struct ocelot *ocelot, int grp, struct sk_buff **nskb)
 	u32 val, *buf;
 	int err;
 
+	lockdep_assert_held(&ocelot->xtr_lock);
+
 	err = ocelot_xtr_poll_xfh(ocelot, grp, xfh);
 	if (err)
 		return err;
@@ -1184,6 +1228,8 @@ bool ocelot_can_inject(struct ocelot *ocelot, int grp)
 {
 	u32 val = ocelot_read(ocelot, QS_INJ_STATUS);
 
+	lockdep_assert_held(&ocelot->inj_lock);
+
 	if (!(val & QS_INJ_STATUS_FIFO_RDY(BIT(grp))))
 		return false;
 	if (val & QS_INJ_STATUS_WMARK_REACHED(BIT(grp)))
@@ -1236,6 +1282,8 @@ void ocelot_port_inject_frame(struct ocelot *ocelot, int port, int grp,
 	u32 ifh[OCELOT_TAG_LEN / 4];
 	unsigned int i, count, last;
 
+	lockdep_assert_held(&ocelot->inj_lock);
+
 	ocelot_write_rix(ocelot, QS_INJ_CTRL_GAP_SIZE(1) |
 			 QS_INJ_CTRL_SOF, QS_INJ_CTRL, grp);
 
@@ -1272,6 +1320,8 @@ EXPORT_SYMBOL(ocelot_port_inject_frame);
 
 void ocelot_drain_cpu_queue(struct ocelot *ocelot, int grp)
 {
+	lockdep_assert_held(&ocelot->xtr_lock);
+
 	while (ocelot_read(ocelot, QS_XTR_DATA_PRESENT) & BIT(grp))
 		ocelot_read_rix(ocelot, QS_XTR_RD, grp);
 }
@@ -2954,6 +3004,8 @@ int ocelot_init(struct ocelot *ocelot)
 	mutex_init(&ocelot->fwd_domain_lock);
 	spin_lock_init(&ocelot->ptp_clock_lock);
 	spin_lock_init(&ocelot->ts_id_lock);
+	spin_lock_init(&ocelot->inj_lock);
+	spin_lock_init(&ocelot->xtr_lock);
 
 	ocelot->owq = alloc_ordered_workqueue("ocelot-owq", 0);
 	if (!ocelot->owq)
diff --git a/drivers/net/ethernet/mscc/ocelot_vsc7514.c b/drivers/net/ethernet/mscc/ocelot_vsc7514.c
index 993212c3a7da..c09dd2e3343c 100644
--- a/drivers/net/ethernet/mscc/ocelot_vsc7514.c
+++ b/drivers/net/ethernet/mscc/ocelot_vsc7514.c
@@ -51,6 +51,8 @@ static irqreturn_t ocelot_xtr_irq_handler(int irq, void *arg)
 	struct ocelot *ocelot = arg;
 	int grp = 0, err;
 
+	ocelot_lock_xtr_grp(ocelot, grp);
+
 	while (ocelot_read(ocelot, QS_XTR_DATA_PRESENT) & BIT(grp)) {
 		struct sk_buff *skb;
 
@@ -69,6 +71,8 @@ static irqreturn_t ocelot_xtr_irq_handler(int irq, void *arg)
 	if (err < 0)
 		ocelot_drain_cpu_queue(ocelot, 0);
 
+	ocelot_unlock_xtr_grp(ocelot, grp);
+
 	return IRQ_HANDLED;
 }
 
diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h
index ed18e6bafc8d..462c653e1017 100644
--- a/include/soc/mscc/ocelot.h
+++ b/include/soc/mscc/ocelot.h
@@ -813,6 +813,9 @@ struct ocelot {
 	const u32 *const		*map;
 	struct list_head		stats_regions;
 
+	spinlock_t			inj_lock;
+	spinlock_t			xtr_lock;
+
 	u32				pool_size[OCELOT_SB_NUM][OCELOT_SB_POOL_NUM];
 	int				packet_buffer_size;
 	int				num_frame_refs;
@@ -966,6 +969,12 @@ void __ocelot_target_write_ix(struct ocelot *ocelot, enum ocelot_target target,
 			      u32 val, u32 reg, u32 offset);
 
 /* Packet I/O */
+void ocelot_lock_inj_grp(struct ocelot *ocelot, int grp);
+void ocelot_unlock_inj_grp(struct ocelot *ocelot, int grp);
+void ocelot_lock_xtr_grp(struct ocelot *ocelot, int grp);
+void ocelot_unlock_xtr_grp(struct ocelot *ocelot, int grp);
+void ocelot_lock_xtr_grp_bh(struct ocelot *ocelot, int grp);
+void ocelot_unlock_xtr_grp_bh(struct ocelot *ocelot, int grp);
 bool ocelot_can_inject(struct ocelot *ocelot, int grp);
 void ocelot_port_inject_frame(struct ocelot *ocelot, int port, int grp,
 			      u32 rew_op, struct sk_buff *skb);

From 93e4649efa964201c73b0a03c35c04a0d6fc809f Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Thu, 15 Aug 2024 03:07:05 +0300
Subject: [PATCH 19/82] net: dsa: provide a software untagging function on RX
 for VLAN-aware bridges

Through code analysis, I realized that the ds->untag_bridge_pvid logic
is contradictory - see the newly added FIXME above the kernel-doc for
dsa_software_untag_vlan_unaware_bridge().

Moreover, for the Felix driver, I need something very similar, but which
is actually _not_ contradictory: untag the bridge PVID on RX, but for
VLAN-aware bridges. The existing logic does it for VLAN-unaware bridges.

Since I don't want to change the functionality of drivers which were
supposedly properly tested with the ds->untag_bridge_pvid flag, I have
introduced a new one: ds->untag_vlan_aware_bridge_pvid, and I have
refactored the DSA reception code into a common path for both flags.

TODO: both flags should be unified under a single ds->software_vlan_untag,
which users of both current flags should set. This is not something that
can be carried out right away. It needs very careful examination of all
drivers which make use of this functionality, since some of them
actually get this wrong in the first place.

For example, commit 9130c2d30c17 ("net: dsa: microchip: ksz8795: Use
software untagging on CPU port") uses this in a driver which has
ds->configure_vlan_while_not_filtering = true. The latter mechanism has
been known for many years to be broken by design:
https://lore.kernel.org/netdev/CABumfLzJmXDN_W-8Z=p9KyKUVi_HhS7o_poBkeKHS2BkAiyYpw@mail.gmail.com/
and we have the situation of 2 bugs canceling each other. There is no
private VLAN, and the port follows the PVID of the VLAN-unaware bridge.
So, it's kinda ok for that driver to use the ds->untag_bridge_pvid
mechanism, in a broken way.

Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 include/net/dsa.h |  16 ++++--
 net/dsa/tag.c     |   5 +-
 net/dsa/tag.h     | 141 +++++++++++++++++++++++++++++++++++-----------
 3 files changed, 121 insertions(+), 41 deletions(-)

diff --git a/include/net/dsa.h b/include/net/dsa.h
index b06f97ae3da1..d7a6c2930277 100644
--- a/include/net/dsa.h
+++ b/include/net/dsa.h
@@ -403,14 +403,18 @@ struct dsa_switch {
 	 */
 	u32			configure_vlan_while_not_filtering:1;
 
-	/* If the switch driver always programs the CPU port as egress tagged
-	 * despite the VLAN configuration indicating otherwise, then setting
-	 * @untag_bridge_pvid will force the DSA receive path to pop the
-	 * bridge's default_pvid VLAN tagged frames to offer a consistent
-	 * behavior between a vlan_filtering=0 and vlan_filtering=1 bridge
-	 * device.
+	/* Pop the default_pvid of VLAN-unaware bridge ports from tagged frames.
+	 * DEPRECATED: Do NOT set this field in new drivers. Instead look at
+	 * the dsa_software_vlan_untag() comments.
 	 */
 	u32			untag_bridge_pvid:1;
+	/* Pop the default_pvid of VLAN-aware bridge ports from tagged frames.
+	 * Useful if the switch cannot preserve the VLAN tag as seen on the
+	 * wire for user port ingress, and chooses to send all frames as
+	 * VLAN-tagged to the CPU, including those which were originally
+	 * untagged.
+	 */
+	u32			untag_vlan_aware_bridge_pvid:1;
 
 	/* Let DSA manage the FDB entries towards the
 	 * CPU, based on the software bridge database.
diff --git a/net/dsa/tag.c b/net/dsa/tag.c
index 6e402d49afd3..79ad105902d9 100644
--- a/net/dsa/tag.c
+++ b/net/dsa/tag.c
@@ -105,8 +105,9 @@ static int dsa_switch_rcv(struct sk_buff *skb, struct net_device *dev,
 
 	p = netdev_priv(skb->dev);
 
-	if (unlikely(cpu_dp->ds->untag_bridge_pvid)) {
-		nskb = dsa_untag_bridge_pvid(skb);
+	if (unlikely(cpu_dp->ds->untag_bridge_pvid ||
+		     cpu_dp->ds->untag_vlan_aware_bridge_pvid)) {
+		nskb = dsa_software_vlan_untag(skb);
 		if (!nskb) {
 			kfree_skb(skb);
 			return 0;
diff --git a/net/dsa/tag.h b/net/dsa/tag.h
index f6b9c73718df..d5707870906b 100644
--- a/net/dsa/tag.h
+++ b/net/dsa/tag.h
@@ -44,46 +44,81 @@ static inline struct net_device *dsa_conduit_find_user(struct net_device *dev,
 	return NULL;
 }
 
-/* If under a bridge with vlan_filtering=0, make sure to send pvid-tagged
- * frames as untagged, since the bridge will not untag them.
+/**
+ * dsa_software_untag_vlan_aware_bridge: Software untagging for VLAN-aware bridge
+ * @skb: Pointer to received socket buffer (packet)
+ * @br: Pointer to bridge upper interface of ingress port
+ * @vid: Parsed VID from packet
+ *
+ * The bridge can process tagged packets. Software like STP/PTP may not. The
+ * bridge can also process untagged packets, to the same effect as if they were
+ * tagged with the PVID of the ingress port. So packets tagged with the PVID of
+ * the bridge port must be software-untagged, to support both use cases.
  */
-static inline struct sk_buff *dsa_untag_bridge_pvid(struct sk_buff *skb)
+static inline void dsa_software_untag_vlan_aware_bridge(struct sk_buff *skb,
+							struct net_device *br,
+							u16 vid)
 {
-	struct dsa_port *dp = dsa_user_to_port(skb->dev);
-	struct net_device *br = dsa_port_bridge_dev_get(dp);
-	struct net_device *dev = skb->dev;
-	struct net_device *upper_dev;
-	u16 vid, pvid, proto;
+	u16 pvid, proto;
 	int err;
 
-	if (!br || br_vlan_enabled(br))
-		return skb;
-
 	err = br_vlan_get_proto(br, &proto);
 	if (err)
-		return skb;
+		return;
 
-	/* Move VLAN tag from data to hwaccel */
-	if (!skb_vlan_tag_present(skb) && skb->protocol == htons(proto)) {
-		skb = skb_vlan_untag(skb);
-		if (!skb)
-			return NULL;
-	}
-
-	if (!skb_vlan_tag_present(skb))
-		return skb;
-
-	vid = skb_vlan_tag_get_id(skb);
-
-	/* We already run under an RCU read-side critical section since
-	 * we are called from netif_receive_skb_list_internal().
-	 */
-	err = br_vlan_get_pvid_rcu(dev, &pvid);
+	err = br_vlan_get_pvid_rcu(skb->dev, &pvid);
 	if (err)
-		return skb;
+		return;
 
-	if (vid != pvid)
-		return skb;
+	if (vid == pvid && skb->vlan_proto == htons(proto))
+		__vlan_hwaccel_clear_tag(skb);
+}
+
+/**
+ * dsa_software_untag_vlan_unaware_bridge: Software untagging for VLAN-unaware bridge
+ * @skb: Pointer to received socket buffer (packet)
+ * @br: Pointer to bridge upper interface of ingress port
+ * @vid: Parsed VID from packet
+ *
+ * The bridge ignores all VLAN tags. Software like STP/PTP may not (it may run
+ * on the plain port, or on a VLAN upper interface). Maybe packets are coming
+ * to software as tagged with a driver-defined VID which is NOT equal to the
+ * PVID of the bridge port (since the bridge is VLAN-unaware, its configuration
+ * should NOT be committed to hardware). DSA needs a method for this private
+ * VID to be communicated by software to it, and if packets are tagged with it,
+ * software-untag them. Note: the private VID may be different per bridge, to
+ * support the FDB isolation use case.
+ *
+ * FIXME: this is currently implemented based on the broken assumption that
+ * the "private VID" used by the driver in VLAN-unaware mode is equal to the
+ * bridge PVID. It should not be, except for a coincidence; the bridge PVID is
+ * irrelevant to the data path in the VLAN-unaware mode. Thus, the VID that
+ * this function removes is wrong.
+ *
+ * All users of ds->untag_bridge_pvid should fix their drivers, if necessary,
+ * to make the two independent. Only then, if there still remains a need to
+ * strip the private VID from packets, then a new ds->ops->get_private_vid()
+ * API shall be introduced to communicate to DSA what this VID is, which needs
+ * to be stripped here.
+ */
+static inline void dsa_software_untag_vlan_unaware_bridge(struct sk_buff *skb,
+							  struct net_device *br,
+							  u16 vid)
+{
+	struct net_device *upper_dev;
+	u16 pvid, proto;
+	int err;
+
+	err = br_vlan_get_proto(br, &proto);
+	if (err)
+		return;
+
+	err = br_vlan_get_pvid_rcu(skb->dev, &pvid);
+	if (err)
+		return;
+
+	if (vid != pvid || skb->vlan_proto != htons(proto))
+		return;
 
 	/* The sad part about attempting to untag from DSA is that we
 	 * don't know, unless we check, if the skb will end up in
@@ -95,10 +130,50 @@ static inline struct sk_buff *dsa_untag_bridge_pvid(struct sk_buff *skb)
 	 * definitely keep the tag, to make sure it keeps working.
 	 */
 	upper_dev = __vlan_find_dev_deep_rcu(br, htons(proto), vid);
-	if (upper_dev)
+	if (!upper_dev)
+		__vlan_hwaccel_clear_tag(skb);
+}
+
+/**
+ * dsa_software_vlan_untag: Software VLAN untagging in DSA receive path
+ * @skb: Pointer to socket buffer (packet)
+ *
+ * Receive path method for switches which cannot avoid tagging all packets
+ * towards the CPU port. Called when ds->untag_bridge_pvid (legacy) or
+ * ds->untag_vlan_aware_bridge_pvid is set to true.
+ *
+ * As a side effect of this method, any VLAN tag from the skb head is moved
+ * to hwaccel.
+ */
+static inline struct sk_buff *dsa_software_vlan_untag(struct sk_buff *skb)
+{
+	struct dsa_port *dp = dsa_user_to_port(skb->dev);
+	struct net_device *br = dsa_port_bridge_dev_get(dp);
+	u16 vid;
+
+	/* software untagging for standalone ports not yet necessary */
+	if (!br)
 		return skb;
 
-	__vlan_hwaccel_clear_tag(skb);
+	/* Move VLAN tag from data to hwaccel */
+	if (!skb_vlan_tag_present(skb)) {
+		skb = skb_vlan_untag(skb);
+		if (!skb)
+			return NULL;
+	}
+
+	if (!skb_vlan_tag_present(skb))
+		return skb;
+
+	vid = skb_vlan_tag_get_id(skb);
+
+	if (br_vlan_enabled(br)) {
+		if (dp->ds->untag_vlan_aware_bridge_pvid)
+			dsa_software_untag_vlan_aware_bridge(skb, br, vid);
+	} else {
+		if (dp->ds->untag_bridge_pvid)
+			dsa_software_untag_vlan_unaware_bridge(skb, br, vid);
+	}
 
 	return skb;
 }

From f1288fd7293b91442ad7420394c252a252ecaa30 Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Thu, 15 Aug 2024 03:07:06 +0300
Subject: [PATCH 20/82] net: dsa: felix: fix VLAN tag loss on CPU reception
 with ocelot-8021q

There is a major design bug with ocelot-8021q, which is that it expects
more of the hardware than the hardware can actually do. The short
summary of the issue is that when a port is under a VLAN-aware bridge
and we use this tagging protocol, VLAN upper interfaces of this port do
not see RX traffic.

We use VCAP ES0 (egress rewriter) rules towards the tag_8021q CPU port
to encapsulate packets with an outer tag, later stripped by software,
that depends on the source user port. We do this so that packets can be
identified in ocelot_rcv(). To be precise, we create rules with
push_outer_tag = OCELOT_ES0_TAG and push_inner_tag = 0.

With this configuration, we expect the switch to keep the inner tag
configuration as found in the packet (if it was untagged on user port
ingress, keep it untagged, otherwise preserve the VLAN tag unmodified
as the inner tag towards the tag_8021q CPU port). But this is not what
happens.

Instead, table "Tagging Combinations" from the user manual suggests
that when the ES0 action is "PUSH_OUTER_TAG=1 and PUSH_INNER_TAG=0",
there will be "no inner tag". Experimentation further clarifies what
this means.

It appears that this "inner tag" which is not pushed into the packet on
its egress towards the CPU is none other than the classified VLAN.

When the ingress user port is standalone or under a VLAN-unaware bridge,
the classified VLAN is a discardable quantity: it is a fixed value - the
result of ocelot_vlan_unaware_pvid()'s configuration, and actually
independent of the VID from any 802.1Q header that may be in the frame.
It is actually preferable to discard the "inner tag" in this case.

The problem is when the ingress port is under a VLAN-aware bridge.
Then, the classified VLAN is taken from the frame's 802.1Q header, with
a fallback on the bridge port's PVID. It would be very good to not
discard the "inner tag" here, because if we do, we break communication
with any 8021q VLAN uppers that the port might have. These have a
processing path outside the bridge.

There seems to be nothing else we can do except to change the
configuration for VCAP ES0 rules, to actually push the inner VLAN into
the frame. There are 2 options for that, first is to push a fixed value
specified in the rule, and second is to push a fixed value, plus
(aka arithmetic +) the classified VLAN. We choose the second option,
and we select that fixed value as 0. Thus, what is pushed in the inner
tag is just the classified VLAN.

From there, we need to perform software untagging, in the receive path,
of stuff that was untagged on the wire.

Fixes: 7c83a7c539ab ("net: dsa: add a second tagger for Ocelot switches based on tag_8021q")
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/dsa/ocelot/felix.c | 115 +++++++++++++++++++++++++++++++--
 1 file changed, 109 insertions(+), 6 deletions(-)

diff --git a/drivers/net/dsa/ocelot/felix.c b/drivers/net/dsa/ocelot/felix.c
index 8d31ff18c5c7..4a705f7333f4 100644
--- a/drivers/net/dsa/ocelot/felix.c
+++ b/drivers/net/dsa/ocelot/felix.c
@@ -61,11 +61,46 @@ static int felix_cpu_port_for_conduit(struct dsa_switch *ds,
 	return cpu_dp->index;
 }
 
+/**
+ * felix_update_tag_8021q_rx_rule - Update VCAP ES0 tag_8021q rule after
+ *				    vlan_filtering change
+ * @outer_tagging_rule: Pointer to VCAP filter on which the update is performed
+ * @vlan_filtering: Current bridge VLAN filtering setting
+ *
+ * Source port identification for tag_8021q is done using VCAP ES0 rules on the
+ * CPU port(s). The ES0 tag B (inner tag from the packet) can be configured as
+ * either:
+ * - push_inner_tag=0: the inner tag is never pushed into the frame
+ *		       (and we lose info about the classified VLAN). This is
+ *		       good when the classified VLAN is a discardable quantity
+ *		       for the software RX path: it is either set to
+ *		       OCELOT_STANDALONE_PVID, or to
+ *		       ocelot_vlan_unaware_pvid(bridge).
+ * - push_inner_tag=1: the inner tag is always pushed. This is good when the
+ *		       classified VLAN is not a discardable quantity (the port
+ *		       is under a VLAN-aware bridge, and software needs to
+ *		       continue processing the packet in the same VLAN as the
+ *		       hardware).
+ * The point is that what is good for a VLAN-unaware port is not good for a
+ * VLAN-aware port, and vice versa. Thus, the RX tagging rules must be kept in
+ * sync with the VLAN filtering state of the port.
+ */
+static void
+felix_update_tag_8021q_rx_rule(struct ocelot_vcap_filter *outer_tagging_rule,
+			       bool vlan_filtering)
+{
+	if (vlan_filtering)
+		outer_tagging_rule->action.push_inner_tag = OCELOT_ES0_TAG;
+	else
+		outer_tagging_rule->action.push_inner_tag = OCELOT_NO_ES0_TAG;
+}
+
 /* Set up VCAP ES0 rules for pushing a tag_8021q VLAN towards the CPU such that
  * the tagger can perform RX source port identification.
  */
 static int felix_tag_8021q_vlan_add_rx(struct dsa_switch *ds, int port,
-				       int upstream, u16 vid)
+				       int upstream, u16 vid,
+				       bool vlan_filtering)
 {
 	struct ocelot_vcap_filter *outer_tagging_rule;
 	struct ocelot *ocelot = ds->priv;
@@ -96,6 +131,14 @@ static int felix_tag_8021q_vlan_add_rx(struct dsa_switch *ds, int port,
 	outer_tagging_rule->action.tag_a_tpid_sel = OCELOT_TAG_TPID_SEL_8021AD;
 	outer_tagging_rule->action.tag_a_vid_sel = 1;
 	outer_tagging_rule->action.vid_a_val = vid;
+	felix_update_tag_8021q_rx_rule(outer_tagging_rule, vlan_filtering);
+	outer_tagging_rule->action.tag_b_tpid_sel = OCELOT_TAG_TPID_SEL_8021Q;
+	/* Leave TAG_B_VID_SEL at 0 (Classified VID + VID_B_VAL). Since we also
+	 * leave VID_B_VAL at 0, this makes ES0 tag B (the inner tag) equal to
+	 * the classified VID, which we need to see in the DSA tagger's receive
+	 * path. Note: the inner tag is only visible in the packet when pushed
+	 * (push_inner_tag == OCELOT_ES0_TAG).
+	 */
 
 	err = ocelot_vcap_filter_add(ocelot, outer_tagging_rule, NULL);
 	if (err)
@@ -227,6 +270,7 @@ static int felix_tag_8021q_vlan_del_tx(struct dsa_switch *ds, int port, u16 vid)
 static int felix_tag_8021q_vlan_add(struct dsa_switch *ds, int port, u16 vid,
 				    u16 flags)
 {
+	struct dsa_port *dp = dsa_to_port(ds, port);
 	struct dsa_port *cpu_dp;
 	int err;
 
@@ -234,11 +278,12 @@ static int felix_tag_8021q_vlan_add(struct dsa_switch *ds, int port, u16 vid,
 	 * membership, which we aren't. So we don't need to add any VCAP filter
 	 * for the CPU port.
 	 */
-	if (!dsa_is_user_port(ds, port))
+	if (!dsa_port_is_user(dp))
 		return 0;
 
 	dsa_switch_for_each_cpu_port(cpu_dp, ds) {
-		err = felix_tag_8021q_vlan_add_rx(ds, port, cpu_dp->index, vid);
+		err = felix_tag_8021q_vlan_add_rx(ds, port, cpu_dp->index, vid,
+						  dsa_port_is_vlan_filtering(dp));
 		if (err)
 			return err;
 	}
@@ -258,10 +303,11 @@ static int felix_tag_8021q_vlan_add(struct dsa_switch *ds, int port, u16 vid,
 
 static int felix_tag_8021q_vlan_del(struct dsa_switch *ds, int port, u16 vid)
 {
+	struct dsa_port *dp = dsa_to_port(ds, port);
 	struct dsa_port *cpu_dp;
 	int err;
 
-	if (!dsa_is_user_port(ds, port))
+	if (!dsa_port_is_user(dp))
 		return 0;
 
 	dsa_switch_for_each_cpu_port(cpu_dp, ds) {
@@ -278,11 +324,41 @@ static int felix_tag_8021q_vlan_del(struct dsa_switch *ds, int port, u16 vid)
 
 del_tx_failed:
 	dsa_switch_for_each_cpu_port(cpu_dp, ds)
-		felix_tag_8021q_vlan_add_rx(ds, port, cpu_dp->index, vid);
+		felix_tag_8021q_vlan_add_rx(ds, port, cpu_dp->index, vid,
+					    dsa_port_is_vlan_filtering(dp));
 
 	return err;
 }
 
+static int felix_update_tag_8021q_rx_rules(struct dsa_switch *ds, int port,
+					   bool vlan_filtering)
+{
+	struct ocelot_vcap_filter *outer_tagging_rule;
+	struct ocelot_vcap_block *block_vcap_es0;
+	struct ocelot *ocelot = ds->priv;
+	struct dsa_port *cpu_dp;
+	unsigned long cookie;
+	int err;
+
+	block_vcap_es0 = &ocelot->block[VCAP_ES0];
+
+	dsa_switch_for_each_cpu_port(cpu_dp, ds) {
+		cookie = OCELOT_VCAP_ES0_TAG_8021Q_RXVLAN(ocelot, port,
+							  cpu_dp->index);
+
+		outer_tagging_rule = ocelot_vcap_block_find_filter_by_id(block_vcap_es0,
+									 cookie, false);
+
+		felix_update_tag_8021q_rx_rule(outer_tagging_rule, vlan_filtering);
+
+		err = ocelot_vcap_filter_replace(ocelot, outer_tagging_rule);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
 static int felix_trap_get_cpu_port(struct dsa_switch *ds,
 				   const struct ocelot_vcap_filter *trap)
 {
@@ -532,6 +608,16 @@ static int felix_tag_8021q_setup(struct dsa_switch *ds)
 	ocelot_drain_cpu_queue(ocelot, 0);
 	ocelot_unlock_xtr_grp_bh(ocelot, 0);
 
+	/* Problem: when using push_inner_tag=1 for ES0 tag B, we lose info
+	 * about whether the received packets were VLAN-tagged on the wire,
+	 * since they are always tagged on egress towards the CPU port.
+	 *
+	 * Since using push_inner_tag=1 is unavoidable for VLAN-aware bridges,
+	 * we must work around the fallout by untagging in software to make
+	 * untagged reception work more or less as expected.
+	 */
+	ds->untag_vlan_aware_bridge_pvid = true;
+
 	return 0;
 }
 
@@ -556,6 +642,8 @@ static void felix_tag_8021q_teardown(struct dsa_switch *ds)
 		ocelot_port_teardown_dsa_8021q_cpu(ocelot, dp->index);
 
 	dsa_tag_8021q_unregister(ds);
+
+	ds->untag_vlan_aware_bridge_pvid = false;
 }
 
 static unsigned long felix_tag_8021q_get_host_fwd_mask(struct dsa_switch *ds)
@@ -1010,8 +1098,23 @@ static int felix_vlan_filtering(struct dsa_switch *ds, int port, bool enabled,
 				struct netlink_ext_ack *extack)
 {
 	struct ocelot *ocelot = ds->priv;
+	bool using_tag_8021q;
+	struct felix *felix;
+	int err;
 
-	return ocelot_port_vlan_filtering(ocelot, port, enabled, extack);
+	err = ocelot_port_vlan_filtering(ocelot, port, enabled, extack);
+	if (err)
+		return err;
+
+	felix = ocelot_to_felix(ocelot);
+	using_tag_8021q = felix->tag_proto == DSA_TAG_PROTO_OCELOT_8021Q;
+	if (using_tag_8021q) {
+		err = felix_update_tag_8021q_rx_rules(ds, port, enabled);
+		if (err)
+			return err;
+	}
+
+	return 0;
 }
 
 static int felix_vlan_add(struct dsa_switch *ds, int port,

From 36dd1141be70b5966906919714dc504a24c65ddf Mon Sep 17 00:00:00 2001
From: Vladimir Oltean <vladimir.oltean@nxp.com>
Date: Thu, 15 Aug 2024 03:07:07 +0300
Subject: [PATCH 21/82] net: mscc: ocelot: treat 802.1ad tagged traffic as
 802.1Q-untagged

I was revisiting the topic of 802.1ad treatment in the Ocelot switch [0]
and realized that not only is its basic VLAN classification pipeline
improper for offloading vlan_protocol 802.1ad bridges, but also improper
for offloading regular 802.1Q bridges already.

Namely, 802.1ad-tagged traffic should be treated as VLAN-untagged by
bridged ports, but this switch treats it as if it was 802.1Q-tagged with
the same VID as in the 802.1ad header. This is markedly different to
what the Linux bridge expects; see the "other_tpid()" function in
tools/testing/selftests/net/forwarding/bridge_vlan_aware.sh.

An idea came to me that the VCAP IS1 TCAM is more powerful than I'm
giving it credit for, and that it actually overwrites the classified VID
before the VLAN Table lookup takes place. In other words, it can be
used even to save a packet from being dropped on ingress due to VLAN
membership.

Add a sophisticated TCAM rule hardcoded into the driver to force the
switch to behave like a Linux bridge with vlan_filtering 1 vlan_protocol
802.1Q.

Regarding the lifetime of the filter: eventually the bridge will
disappear, and vlan_filtering on the port will be restored to 0 for
standalone mode. Then the filter will be deleted.

[0]: https://lore.kernel.org/netdev/20201009122947.nvhye4hvcha3tljh@skbuf/

Fixes: 7142529f1688 ("net: mscc: ocelot: add VLAN filtering")
Signed-off-by: Vladimir Oltean <vladimir.oltean@nxp.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/mscc/ocelot.c      | 188 ++++++++++++++++++++++--
 drivers/net/ethernet/mscc/ocelot_vcap.c |   1 +
 include/soc/mscc/ocelot_vcap.h          |   2 +
 3 files changed, 180 insertions(+), 11 deletions(-)

diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c
index f4e027a6fe95..3d72aa7b1305 100644
--- a/drivers/net/ethernet/mscc/ocelot.c
+++ b/drivers/net/ethernet/mscc/ocelot.c
@@ -453,9 +453,158 @@ static u16 ocelot_vlan_unaware_pvid(struct ocelot *ocelot,
 	return VLAN_N_VID - bridge_num - 1;
 }
 
+/**
+ * ocelot_update_vlan_reclassify_rule() - Make switch aware only to bridge VLAN TPID
+ *
+ * @ocelot: Switch private data structure
+ * @port: Index of ingress port
+ *
+ * IEEE 802.1Q-2018 clauses "5.5 C-VLAN component conformance" and "5.6 S-VLAN
+ * component conformance" suggest that a C-VLAN component should only recognize
+ * and filter on C-Tags, and an S-VLAN component should only recognize and
+ * process based on C-Tags.
+ *
+ * In Linux, as per commit 1a0b20b25732 ("Merge branch 'bridge-next'"), C-VLAN
+ * components are largely represented by a bridge with vlan_protocol 802.1Q,
+ * and S-VLAN components by a bridge with vlan_protocol 802.1ad.
+ *
+ * Currently the driver only offloads vlan_protocol 802.1Q, but the hardware
+ * design is non-conformant, because the switch assigns each frame to a VLAN
+ * based on an entirely different question, as detailed in figure "Basic VLAN
+ * Classification Flow" from its manual and reproduced below.
+ *
+ * Set TAG_TYPE, PCP, DEI, VID to port-default values in VLAN_CFG register
+ * if VLAN_AWARE_ENA[port] and frame has outer tag then:
+ *   if VLAN_INNER_TAG_ENA[port] and frame has inner tag then:
+ *     TAG_TYPE = (Frame.InnerTPID <> 0x8100)
+ *     Set PCP, DEI, VID to values from inner VLAN header
+ *   else:
+ *     TAG_TYPE = (Frame.OuterTPID <> 0x8100)
+ *     Set PCP, DEI, VID to values from outer VLAN header
+ *   if VID == 0 then:
+ *     VID = VLAN_CFG.VLAN_VID
+ *
+ * Summarized, the switch will recognize both 802.1Q and 802.1ad TPIDs as VLAN
+ * "with equal rights", and just set the TAG_TYPE bit to 0 (if 802.1Q) or to 1
+ * (if 802.1ad). It will classify based on whichever of the tags is "outer", no
+ * matter what TPID that may have (or "inner", if VLAN_INNER_TAG_ENA[port]).
+ *
+ * In the VLAN Table, the TAG_TYPE information is not accessible - just the
+ * classified VID is - so it is as if each VLAN Table entry is for 2 VLANs:
+ * C-VLAN X, and S-VLAN X.
+ *
+ * Whereas the Linux bridge behavior is to only filter on frames with a TPID
+ * equal to the vlan_protocol, and treat everything else as VLAN-untagged.
+ *
+ * Consider an ingress packet tagged with 802.1ad VID=3 and 802.1Q VID=5,
+ * received on a bridge vlan_filtering=1 vlan_protocol=802.1Q port. This frame
+ * should be treated as 802.1Q-untagged, and classified to the PVID of that
+ * bridge port. Not to VID=3, and not to VID=5.
+ *
+ * The VCAP IS1 TCAM has everything we need to overwrite the choices made in
+ * the basic VLAN classification pipeline: it can match on TAG_TYPE in the key,
+ * and it can modify the classified VID in the action. Thus, for each port
+ * under a vlan_filtering bridge, we can insert a rule in VCAP IS1 lookup 0 to
+ * match on 802.1ad tagged frames and modify their classified VID to the 802.1Q
+ * PVID of the port. This effectively makes it appear to the outside world as
+ * if those packets were processed as VLAN-untagged.
+ *
+ * The rule needs to be updated each time the bridge PVID changes, and needs
+ * to be deleted if the bridge PVID is deleted, or if the port becomes
+ * VLAN-unaware.
+ */
+static int ocelot_update_vlan_reclassify_rule(struct ocelot *ocelot, int port)
+{
+	unsigned long cookie = OCELOT_VCAP_IS1_VLAN_RECLASSIFY(ocelot, port);
+	struct ocelot_vcap_block *block_vcap_is1 = &ocelot->block[VCAP_IS1];
+	struct ocelot_port *ocelot_port = ocelot->ports[port];
+	const struct ocelot_bridge_vlan *pvid_vlan;
+	struct ocelot_vcap_filter *filter;
+	int err, val, pcp, dei;
+	bool vid_replace_ena;
+	u16 vid;
+
+	pvid_vlan = ocelot_port->pvid_vlan;
+	vid_replace_ena = ocelot_port->vlan_aware && pvid_vlan;
+
+	filter = ocelot_vcap_block_find_filter_by_id(block_vcap_is1, cookie,
+						     false);
+	if (!vid_replace_ena) {
+		/* If the reclassification filter doesn't need to exist, delete
+		 * it if it was previously installed, and exit doing nothing
+		 * otherwise.
+		 */
+		if (filter)
+			return ocelot_vcap_filter_del(ocelot, filter);
+
+		return 0;
+	}
+
+	/* The reclassification rule must apply. See if it already exists
+	 * or if it must be created.
+	 */
+
+	/* Treating as VLAN-untagged means using as classified VID equal to
+	 * the bridge PVID, and PCP/DEI set to the port default QoS values.
+	 */
+	vid = pvid_vlan->vid;
+	val = ocelot_read_gix(ocelot, ANA_PORT_QOS_CFG, port);
+	pcp = ANA_PORT_QOS_CFG_QOS_DEFAULT_VAL_X(val);
+	dei = !!(val & ANA_PORT_QOS_CFG_DP_DEFAULT_VAL);
+
+	if (filter) {
+		bool changed = false;
+
+		/* Filter exists, just update it */
+		if (filter->action.vid != vid) {
+			filter->action.vid = vid;
+			changed = true;
+		}
+		if (filter->action.pcp != pcp) {
+			filter->action.pcp = pcp;
+			changed = true;
+		}
+		if (filter->action.dei != dei) {
+			filter->action.dei = dei;
+			changed = true;
+		}
+
+		if (!changed)
+			return 0;
+
+		return ocelot_vcap_filter_replace(ocelot, filter);
+	}
+
+	/* Filter doesn't exist, create it */
+	filter = kzalloc(sizeof(*filter), GFP_KERNEL);
+	if (!filter)
+		return -ENOMEM;
+
+	filter->key_type = OCELOT_VCAP_KEY_ANY;
+	filter->ingress_port_mask = BIT(port);
+	filter->vlan.tpid = OCELOT_VCAP_BIT_1;
+	filter->prio = 1;
+	filter->id.cookie = cookie;
+	filter->id.tc_offload = false;
+	filter->block_id = VCAP_IS1;
+	filter->type = OCELOT_VCAP_FILTER_OFFLOAD;
+	filter->lookup = 0;
+	filter->action.vid_replace_ena = true;
+	filter->action.pcp_dei_ena = true;
+	filter->action.vid = vid;
+	filter->action.pcp = pcp;
+	filter->action.dei = dei;
+
+	err = ocelot_vcap_filter_add(ocelot, filter, NULL);
+	if (err)
+		kfree(filter);
+
+	return err;
+}
+
 /* Default vlan to clasify for untagged frames (may be zero) */
-static void ocelot_port_set_pvid(struct ocelot *ocelot, int port,
-				 const struct ocelot_bridge_vlan *pvid_vlan)
+static int ocelot_port_set_pvid(struct ocelot *ocelot, int port,
+				const struct ocelot_bridge_vlan *pvid_vlan)
 {
 	struct ocelot_port *ocelot_port = ocelot->ports[port];
 	u16 pvid = ocelot_vlan_unaware_pvid(ocelot, ocelot_port->bridge);
@@ -475,15 +624,23 @@ static void ocelot_port_set_pvid(struct ocelot *ocelot, int port,
 	 * happens automatically), but also 802.1p traffic which gets
 	 * classified to VLAN 0, but that is always in our RX filter, so it
 	 * would get accepted were it not for this setting.
+	 *
+	 * Also, we only support the bridge 802.1Q VLAN protocol, so
+	 * 802.1ad-tagged frames (carrying S-Tags) should be considered
+	 * 802.1Q-untagged, and also dropped.
 	 */
 	if (!pvid_vlan && ocelot_port->vlan_aware)
 		val = ANA_PORT_DROP_CFG_DROP_PRIO_S_TAGGED_ENA |
-		      ANA_PORT_DROP_CFG_DROP_PRIO_C_TAGGED_ENA;
+		      ANA_PORT_DROP_CFG_DROP_PRIO_C_TAGGED_ENA |
+		      ANA_PORT_DROP_CFG_DROP_S_TAGGED_ENA;
 
 	ocelot_rmw_gix(ocelot, val,
 		       ANA_PORT_DROP_CFG_DROP_PRIO_S_TAGGED_ENA |
-		       ANA_PORT_DROP_CFG_DROP_PRIO_C_TAGGED_ENA,
+		       ANA_PORT_DROP_CFG_DROP_PRIO_C_TAGGED_ENA |
+		       ANA_PORT_DROP_CFG_DROP_S_TAGGED_ENA,
 		       ANA_PORT_DROP_CFG, port);
+
+	return ocelot_update_vlan_reclassify_rule(ocelot, port);
 }
 
 static struct ocelot_bridge_vlan *ocelot_bridge_vlan_find(struct ocelot *ocelot,
@@ -631,7 +788,10 @@ int ocelot_port_vlan_filtering(struct ocelot *ocelot, int port,
 		       ANA_PORT_VLAN_CFG_VLAN_POP_CNT_M,
 		       ANA_PORT_VLAN_CFG, port);
 
-	ocelot_port_set_pvid(ocelot, port, ocelot_port->pvid_vlan);
+	err = ocelot_port_set_pvid(ocelot, port, ocelot_port->pvid_vlan);
+	if (err)
+		return err;
+
 	ocelot_port_manage_port_tag(ocelot, port);
 
 	return 0;
@@ -684,9 +844,12 @@ int ocelot_vlan_add(struct ocelot *ocelot, int port, u16 vid, bool pvid,
 		return err;
 
 	/* Default ingress vlan classification */
-	if (pvid)
-		ocelot_port_set_pvid(ocelot, port,
-				     ocelot_bridge_vlan_find(ocelot, vid));
+	if (pvid) {
+		err = ocelot_port_set_pvid(ocelot, port,
+					   ocelot_bridge_vlan_find(ocelot, vid));
+		if (err)
+			return err;
+	}
 
 	/* Untagged egress vlan clasification */
 	ocelot_port_manage_port_tag(ocelot, port);
@@ -712,8 +875,11 @@ int ocelot_vlan_del(struct ocelot *ocelot, int port, u16 vid)
 		return err;
 
 	/* Ingress */
-	if (del_pvid)
-		ocelot_port_set_pvid(ocelot, port, NULL);
+	if (del_pvid) {
+		err = ocelot_port_set_pvid(ocelot, port, NULL);
+		if (err)
+			return err;
+	}
 
 	/* Egress */
 	ocelot_port_manage_port_tag(ocelot, port);
@@ -2607,7 +2773,7 @@ int ocelot_port_set_default_prio(struct ocelot *ocelot, int port, u8 prio)
 		       ANA_PORT_QOS_CFG,
 		       port);
 
-	return 0;
+	return ocelot_update_vlan_reclassify_rule(ocelot, port);
 }
 EXPORT_SYMBOL_GPL(ocelot_port_set_default_prio);
 
diff --git a/drivers/net/ethernet/mscc/ocelot_vcap.c b/drivers/net/ethernet/mscc/ocelot_vcap.c
index 73cdec5ca6a3..5734b86aed5b 100644
--- a/drivers/net/ethernet/mscc/ocelot_vcap.c
+++ b/drivers/net/ethernet/mscc/ocelot_vcap.c
@@ -695,6 +695,7 @@ static void is1_entry_set(struct ocelot *ocelot, int ix,
 	vcap_key_bit_set(vcap, &data, VCAP_IS1_HK_L2_MC, filter->dmac_mc);
 	vcap_key_bit_set(vcap, &data, VCAP_IS1_HK_L2_BC, filter->dmac_bc);
 	vcap_key_bit_set(vcap, &data, VCAP_IS1_HK_VLAN_TAGGED, tag->tagged);
+	vcap_key_bit_set(vcap, &data, VCAP_IS1_HK_TPID, tag->tpid);
 	vcap_key_set(vcap, &data, VCAP_IS1_HK_VID,
 		     tag->vid.value, tag->vid.mask);
 	vcap_key_set(vcap, &data, VCAP_IS1_HK_PCP,
diff --git a/include/soc/mscc/ocelot_vcap.h b/include/soc/mscc/ocelot_vcap.h
index c601a4598b0d..eb19668a06db 100644
--- a/include/soc/mscc/ocelot_vcap.h
+++ b/include/soc/mscc/ocelot_vcap.h
@@ -13,6 +13,7 @@
  */
 #define OCELOT_VCAP_ES0_TAG_8021Q_RXVLAN(ocelot, port, upstream) ((upstream) << 16 | (port))
 #define OCELOT_VCAP_IS1_TAG_8021Q_TXVLAN(ocelot, port)		(port)
+#define OCELOT_VCAP_IS1_VLAN_RECLASSIFY(ocelot, port)		((ocelot)->num_phys_ports + (port))
 #define OCELOT_VCAP_IS2_TAG_8021Q_TXVLAN(ocelot, port)		(port)
 #define OCELOT_VCAP_IS2_MRP_REDIRECT(ocelot, port)		((ocelot)->num_phys_ports + (port))
 #define OCELOT_VCAP_IS2_MRP_TRAP(ocelot)			((ocelot)->num_phys_ports * 2)
@@ -499,6 +500,7 @@ struct ocelot_vcap_key_vlan {
 	struct ocelot_vcap_u8  pcp;    /* PCP (3 bit) */
 	enum ocelot_vcap_bit dei;    /* DEI */
 	enum ocelot_vcap_bit tagged; /* Tagged/untagged frame */
+	enum ocelot_vcap_bit tpid;
 };
 
 struct ocelot_vcap_key_etype {

From f232de7cdb4b99adb2c7f2bc5e0b7e4e1292873b Mon Sep 17 00:00:00 2001
From: Dragos Tatulea <dtatulea@nvidia.com>
Date: Thu, 15 Aug 2024 10:16:08 +0300
Subject: [PATCH 22/82] net/mlx5e: SHAMPO, Fix page leak

When SHAMPO is used, a receive queue currently almost always leaks one
page on shutdown.

A page has MLX5E_SHAMPO_WQ_HEADER_PER_PAGE (8) headers. These headers
are tracked in the SHAMPO bitmap. Each page is released when the last
header index in the group is processed. During header allocation, there
can be leftovers from a page that will be used in a subsequent
allocation. This is normally fine, except for the following  scenario
(simplified a bit):

1) Allocate N new page fragments, showing only the relevant last 4
   fragments:

    0: new page
    1: new page
    2: new page
    3: new page
    4: page from previous allocation
    5: page from previous allocation
    6: page from previous allocation
    7: page from previous allocation

2) NAPI processes header indices 4-7 because they are the oldest
   allocated. Bit 7 will be set to 0.

3) Receive queue shutdown occurs. All the remaining bits are being
   iterated on to release the pages. But the page assigned to header
   indices 0-3 will not be freed due to what happened in step 2.

This patch fixes the issue by making sure that on allocation, header
fragments are always allocated in groups of
MLX5E_SHAMPO_WQ_HEADER_PER_PAGE so that there is never a partial page
left over between allocations.

A more appropriate fix would be a refactoring of
mlx5e_alloc_rx_hd_mpwqe() and mlx5e_build_shampo_hd_umr(). But this
refactoring is too big for net. It will be targeted for net-next.

Fixes: e839ac9a89cb ("net/mlx5e: SHAMPO, Simplify header page release in teardown")
Signed-off-by: Dragos Tatulea <dtatulea@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://patch.msgid.link/20240815071611.2211873-2-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_rx.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index 225da8d691fc..23aa555ca0ae 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -735,6 +735,7 @@ static int mlx5e_alloc_rx_hd_mpwqe(struct mlx5e_rq *rq)
 	ksm_entries = bitmap_find_window(shampo->bitmap,
 					 shampo->hd_per_wqe,
 					 shampo->hd_per_wq, shampo->pi);
+	ksm_entries = ALIGN_DOWN(ksm_entries, MLX5E_SHAMPO_WQ_HEADER_PER_PAGE);
 	if (!ksm_entries)
 		return 0;
 

From 94e521937839475b83bac46e4d3ccba332e12064 Mon Sep 17 00:00:00 2001
From: Dragos Tatulea <dtatulea@nvidia.com>
Date: Thu, 15 Aug 2024 10:16:09 +0300
Subject: [PATCH 23/82] net/mlx5e: SHAMPO, Release in progress headers

The change in the fixes tag cleaned up too much: it removed the part
that was releasing header pages that were posted via UMR but haven't
been acknowledged yet on the ICOSQ.

This patch corrects this omission by setting the bits between pi and ci
to on when shutting down a queue with SHAMPO. To be consistent with the
Striding RQ code, this action is done in mlx5e_free_rx_missing_descs().

Fixes: e839ac9a89cb ("net/mlx5e: SHAMPO, Simplify header page release in teardown")
Signed-off-by: Dragos Tatulea <dtatulea@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://patch.msgid.link/20240815071611.2211873-3-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/en.h  |  1 +
 .../net/ethernet/mellanox/mlx5/core/en_main.c |  8 ++++++
 .../net/ethernet/mellanox/mlx5/core/en_rx.c   | 25 +++++++++++--------
 3 files changed, 24 insertions(+), 10 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
index bb5da42edc23..d9e241423bc5 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
@@ -998,6 +998,7 @@ void mlx5e_build_ptys2ethtool_map(void);
 bool mlx5e_check_fragmented_striding_rq_cap(struct mlx5_core_dev *mdev, u8 page_shift,
 					    enum mlx5e_mpwrq_umr_mode umr_mode);
 
+void mlx5e_shampo_fill_umr(struct mlx5e_rq *rq, int len);
 void mlx5e_shampo_dealloc_hd(struct mlx5e_rq *rq);
 void mlx5e_get_stats(struct net_device *dev, struct rtnl_link_stats64 *stats);
 void mlx5e_fold_sw_stats64(struct mlx5e_priv *priv, struct rtnl_link_stats64 *s);
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 5df904639b0c..583fa24a7ae9 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -1236,6 +1236,14 @@ void mlx5e_free_rx_missing_descs(struct mlx5e_rq *rq)
 	rq->mpwqe.actual_wq_head = wq->head;
 	rq->mpwqe.umr_in_progress = 0;
 	rq->mpwqe.umr_completed = 0;
+
+	if (test_bit(MLX5E_RQ_STATE_SHAMPO, &rq->state)) {
+		struct mlx5e_shampo_hd *shampo = rq->mpwqe.shampo;
+		u16 len;
+
+		len = (shampo->pi - shampo->ci) & shampo->hd_per_wq;
+		mlx5e_shampo_fill_umr(rq, len);
+	}
 }
 
 void mlx5e_free_rx_descs(struct mlx5e_rq *rq)
diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
index 23aa555ca0ae..de9d01036c28 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
@@ -963,26 +963,31 @@ void mlx5e_free_icosq_descs(struct mlx5e_icosq *sq)
 	sq->cc = sqcc;
 }
 
-static void mlx5e_handle_shampo_hd_umr(struct mlx5e_shampo_umr umr,
-				       struct mlx5e_icosq *sq)
+void mlx5e_shampo_fill_umr(struct mlx5e_rq *rq, int len)
 {
-	struct mlx5e_channel *c = container_of(sq, struct mlx5e_channel, icosq);
-	struct mlx5e_shampo_hd *shampo;
-	/* assume 1:1 relationship between RQ and icosq */
-	struct mlx5e_rq *rq = &c->rq;
-	int end, from, len = umr.len;
+	struct mlx5e_shampo_hd *shampo = rq->mpwqe.shampo;
+	int end, from, full_len = len;
 
-	shampo = rq->mpwqe.shampo;
 	end = shampo->hd_per_wq;
 	from = shampo->ci;
-	if (from + len > shampo->hd_per_wq) {
+	if (from + len > end) {
 		len -= end - from;
 		bitmap_set(shampo->bitmap, from, end - from);
 		from = 0;
 	}
 
 	bitmap_set(shampo->bitmap, from, len);
-	shampo->ci = (shampo->ci + umr.len) & (shampo->hd_per_wq - 1);
+	shampo->ci = (shampo->ci + full_len) & (shampo->hd_per_wq - 1);
+}
+
+static void mlx5e_handle_shampo_hd_umr(struct mlx5e_shampo_umr umr,
+				       struct mlx5e_icosq *sq)
+{
+	struct mlx5e_channel *c = container_of(sq, struct mlx5e_channel, icosq);
+	/* assume 1:1 relationship between RQ and icosq */
+	struct mlx5e_rq *rq = &c->rq;
+
+	mlx5e_shampo_fill_umr(rq, umr.len);
 }
 
 int mlx5e_poll_ico_cq(struct mlx5e_cq *cq)

From a07e953dafe5ebd88942dc861dfb06eaf055fb07 Mon Sep 17 00:00:00 2001
From: Carolina Jubran <cjubran@nvidia.com>
Date: Thu, 15 Aug 2024 10:16:10 +0300
Subject: [PATCH 24/82] net/mlx5e: XPS, Fix oversight of Multi-PF Netdev
 changes

The offending commit overlooked the Multi-PF Netdev changes.

Revert mlx5e_set_default_xps_cpumasks to incorporate Multi-PF Netdev
changes.

Fixes: bcee093751f8 ("net/mlx5e: Modifying channels number and updating TX queues")
Signed-off-by: Carolina Jubran <cjubran@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://patch.msgid.link/20240815071611.2211873-4-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 15 +++++++++------
 1 file changed, 9 insertions(+), 6 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
index 583fa24a7ae9..16b67c457b60 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
@@ -3028,15 +3028,18 @@ int mlx5e_update_tx_netdev_queues(struct mlx5e_priv *priv)
 static void mlx5e_set_default_xps_cpumasks(struct mlx5e_priv *priv,
 					   struct mlx5e_params *params)
 {
-	struct mlx5_core_dev *mdev = priv->mdev;
-	int num_comp_vectors, ix, irq;
-
-	num_comp_vectors = mlx5_comp_vectors_max(mdev);
+	int ix;
 
 	for (ix = 0; ix < params->num_channels; ix++) {
-		cpumask_clear(priv->scratchpad.cpumask);
+		int num_comp_vectors, irq, vec_ix;
+		struct mlx5_core_dev *mdev;
 
-		for (irq = ix; irq < num_comp_vectors; irq += params->num_channels) {
+		mdev = mlx5_sd_ch_ix_get_dev(priv->mdev, ix);
+		num_comp_vectors = mlx5_comp_vectors_max(mdev);
+		cpumask_clear(priv->scratchpad.cpumask);
+		vec_ix = mlx5_sd_ch_ix_get_vec_ix(mdev, ix);
+
+		for (irq = vec_ix; irq < num_comp_vectors; irq += params->num_channels) {
 			int cpu = mlx5_comp_vector_get_cpu(mdev, irq);
 
 			cpumask_set_cpu(cpu, priv->scratchpad.cpumask);

From 607e1df7bd47fe91cab85a97f57870a26d066137 Mon Sep 17 00:00:00 2001
From: Patrisious Haddad <phaddad@nvidia.com>
Date: Thu, 15 Aug 2024 10:16:11 +0300
Subject: [PATCH 25/82] net/mlx5: Fix IPsec RoCE MPV trace call

Prevent the call trace below from happening, by not allowing IPsec
creation over a slave, if master device doesn't support IPsec.

WARNING: CPU: 44 PID: 16136 at kernel/locking/rwsem.c:240 down_read+0x75/0x94
Modules linked in: esp4_offload esp4 act_mirred act_vlan cls_flower sch_ingress mlx5_vdpa vringh vhost_iotlb vdpa mst_pciconf(OE) nfsv3 nfs_acl nfs lockd grace fscache netfs xt_CHECKSUM xt_MASQUERADE xt_conntrack ipt_REJECT nf_reject_ipv4 nft_compat nft_counter nft_chain_nat nf_nat nf_conntrack nf_defrag_ipv6 nf_defrag_ipv4 rfkill cuse fuse rpcrdma sunrpc rdma_ucm ib_srpt ib_isert iscsi_target_mod target_core_mod ib_umad ib_iser libiscsi scsi_transport_iscsi rdma_cm ib_ipoib iw_cm ib_cm ipmi_ssif intel_rapl_msr intel_rapl_common amd64_edac edac_mce_amd kvm_amd kvm irqbypass crct10dif_pclmul crc32_pclmul mlx5_ib ghash_clmulni_intel sha1_ssse3 dell_smbios ib_uverbs aesni_intel crypto_simd dcdbas wmi_bmof dell_wmi_descriptor cryptd pcspkr ib_core acpi_ipmi sp5100_tco ccp i2c_piix4 ipmi_si ptdma k10temp ipmi_devintf ipmi_msghandler acpi_power_meter acpi_cpufreq ext4 mbcache jbd2 sd_mod t10_pi sg mgag200 drm_kms_helper syscopyarea sysfillrect mlx5_core sysimgblt fb_sys_fops cec
 ahci libahci mlxfw drm pci_hyperv_intf libata tg3 sha256_ssse3 tls megaraid_sas i2c_algo_bit psample wmi dm_mirror dm_region_hash dm_log dm_mod [last unloaded: mst_pci]
CPU: 44 PID: 16136 Comm: kworker/44:3 Kdump: loaded Tainted: GOE 5.15.0-20240509.el8uek.uek7_u3_update_v6.6_ipsec_bf.x86_64 #2
Hardware name: Dell Inc. PowerEdge R7525/074H08, BIOS 2.0.3 01/15/2021
Workqueue: events xfrm_state_gc_task
RIP: 0010:down_read+0x75/0x94
Code: 00 48 8b 45 08 65 48 8b 14 25 80 fc 01 00 83 e0 02 48 09 d0 48 83 c8 01 48 89 45 08 5d 31 c0 89 c2 89 c6 89 c7 e9 cb 88 3b 00 <0f> 0b 48 8b 45 08 a8 01 74 b2 a8 02 75 ae 48 89 c2 48 83 ca 02 f0
RSP: 0018:ffffb26387773da8 EFLAGS: 00010282
RAX: 0000000000000000 RBX: ffffa08b658af900 RCX: 0000000000000001
RDX: 0000000000000000 RSI: ff886bc5e1366f2f RDI: 0000000000000000
RBP: ffffa08b658af940 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000000 R12: ffffa0a9bfb31540
R13: ffffa0a9bfb37900 R14: 0000000000000000 R15: ffffa0a9bfb37905
FS:  0000000000000000(0000) GS:ffffa0a9bfb00000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 000055a45ed814e8 CR3: 000000109038a000 CR4: 0000000000350ee0
Call Trace:
 <TASK>
 ? show_trace_log_lvl+0x1d6/0x2f9
 ? show_trace_log_lvl+0x1d6/0x2f9
 ? mlx5_devcom_for_each_peer_begin+0x29/0x60 [mlx5_core]
 ? down_read+0x75/0x94
 ? __warn+0x80/0x113
 ? down_read+0x75/0x94
 ? report_bug+0xa4/0x11d
 ? handle_bug+0x35/0x8b
 ? exc_invalid_op+0x14/0x75
 ? asm_exc_invalid_op+0x16/0x1b
 ? down_read+0x75/0x94
 ? down_read+0xe/0x94
 mlx5_devcom_for_each_peer_begin+0x29/0x60 [mlx5_core]
 mlx5_ipsec_fs_roce_tx_destroy+0xb1/0x130 [mlx5_core]
 tx_destroy+0x1b/0xc0 [mlx5_core]
 tx_ft_put+0x53/0xc0 [mlx5_core]
 mlx5e_xfrm_free_state+0x45/0x90 [mlx5_core]
 ___xfrm_state_destroy+0x10f/0x1a2
 xfrm_state_gc_task+0x81/0xa9
 process_one_work+0x1f1/0x3c6
 worker_thread+0x53/0x3e4
 ? process_one_work.cold+0x46/0x3c
 kthread+0x127/0x144
 ? set_kthread_struct+0x60/0x52
 ret_from_fork+0x22/0x2d
 </TASK>
---[ end trace 5ef7896144d398e1 ]---

Fixes: dfbd229abeee ("net/mlx5: Configure IPsec steering for egress RoCEv2 MPV traffic")
Reviewed-by: Leon Romanovsky <leonro@nvidia.com>
Signed-off-by: Patrisious Haddad <phaddad@nvidia.com>
Signed-off-by: Tariq Toukan <tariqt@nvidia.com>
Link: https://patch.msgid.link/20240815071611.2211873-5-tariqt@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/mellanox/mlx5/core/lib/ipsec_fs_roce.c | 6 ++++--
 1 file changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/ipsec_fs_roce.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/ipsec_fs_roce.c
index 234cd00f71a1..b7d4b1a2baf2 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/ipsec_fs_roce.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/ipsec_fs_roce.c
@@ -386,7 +386,8 @@ static int ipsec_fs_roce_tx_mpv_create(struct mlx5_core_dev *mdev,
 		return -EOPNOTSUPP;
 
 	peer_priv = mlx5_devcom_get_next_peer_data(*ipsec_roce->devcom, &tmp);
-	if (!peer_priv) {
+	if (!peer_priv || !peer_priv->ipsec) {
+		mlx5_core_err(mdev, "IPsec not supported on master device\n");
 		err = -EOPNOTSUPP;
 		goto release_peer;
 	}
@@ -455,7 +456,8 @@ static int ipsec_fs_roce_rx_mpv_create(struct mlx5_core_dev *mdev,
 		return -EOPNOTSUPP;
 
 	peer_priv = mlx5_devcom_get_next_peer_data(*ipsec_roce->devcom, &tmp);
-	if (!peer_priv) {
+	if (!peer_priv || !peer_priv->ipsec) {
+		mlx5_core_err(mdev, "IPsec not supported on master device\n");
 		err = -EOPNOTSUPP;
 		goto release_peer;
 	}

From a0c9fe5eecc97680323ee83780ea3eaf440ba1b7 Mon Sep 17 00:00:00 2001
From: Simon Horman <horms@kernel.org>
Date: Thu, 15 Aug 2024 16:37:13 +0100
Subject: [PATCH 26/82] tc-testing: don't access non-existent variable on
 exception

Since commit 255c1c7279ab ("tc-testing: Allow test cases to be skipped")
the variable test_ordinal doesn't exist in call_pre_case().
So it should not be accessed when an exception occurs.

This resolves the following splat:

  ...
  During handling of the above exception, another exception occurred:

  Traceback (most recent call last):
    File ".../tdc.py", line 1028, in <module>
      main()
    File ".../tdc.py", line 1022, in main
      set_operation_mode(pm, parser, args, remaining)
    File ".../tdc.py", line 966, in set_operation_mode
      catresults = test_runner_serial(pm, args, alltests)
    File ".../tdc.py", line 642, in test_runner_serial
      (index, tsr) = test_runner(pm, args, alltests)
    File ".../tdc.py", line 536, in test_runner
      res = run_one_test(pm, args, index, tidx)
    File ".../tdc.py", line 419, in run_one_test
      pm.call_pre_case(tidx)
    File ".../tdc.py", line 146, in call_pre_case
      print('test_ordinal is {}'.format(test_ordinal))
  NameError: name 'test_ordinal' is not defined

Fixes: 255c1c7279ab ("tc-testing: Allow test cases to be skipped")
Signed-off-by: Simon Horman <horms@kernel.org>
Acked-by: Jamal Hadi Salim <jhs@mojatatu.com>
Link: https://patch.msgid.link/20240815-tdc-test-ordinal-v1-1-0255c122a427@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/tc-testing/tdc.py | 1 -
 1 file changed, 1 deletion(-)

diff --git a/tools/testing/selftests/tc-testing/tdc.py b/tools/testing/selftests/tc-testing/tdc.py
index ee349187636f..4f255cec0c22 100755
--- a/tools/testing/selftests/tc-testing/tdc.py
+++ b/tools/testing/selftests/tc-testing/tdc.py
@@ -143,7 +143,6 @@ class PluginMgr:
             except Exception as ee:
                 print('exception {} in call to pre_case for {} plugin'.
                       format(ee, pgn_inst.__class__))
-                print('test_ordinal is {}'.format(test_ordinal))
                 print('testid is {}'.format(caseinfo['id']))
                 raise
 

From 7167395a4be7930ecac6a33b4e54d7e3dd9ee209 Mon Sep 17 00:00:00 2001
From: Hangbin Liu <liuhangbin@gmail.com>
Date: Thu, 15 Aug 2024 15:59:50 +0800
Subject: [PATCH 27/82] selftests: udpgro: report error when receive failed

Currently, we only check the latest senders's exit code. If the receiver
report failed, it is not recoreded. Fix it by checking the exit code
of all the involved processes.

Before:
  bad GRO lookup       ok
  multiple GRO socks   ./udpgso_bench_rx: recv: bad packet len, got 1452, expected 14520

 ./udpgso_bench_rx: recv: bad packet len, got 1452, expected 14520

 failed
 $ echo $?
 0

After:
  bad GRO lookup       ok
  multiple GRO socks   ./udpgso_bench_rx: recv: bad packet len, got 1452, expected 14520

 ./udpgso_bench_rx: recv: bad packet len, got 1452, expected 14520

 failed
 $ echo $?
 1

Fixes: 3327a9c46352 ("selftests: add functionals test for UDP GRO")
Suggested-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/udpgro.sh | 44 ++++++++++++++++-----------
 1 file changed, 27 insertions(+), 17 deletions(-)

diff --git a/tools/testing/selftests/net/udpgro.sh b/tools/testing/selftests/net/udpgro.sh
index 11a1ebda564f..4659cf01e438 100755
--- a/tools/testing/selftests/net/udpgro.sh
+++ b/tools/testing/selftests/net/udpgro.sh
@@ -46,17 +46,19 @@ run_one() {
 	local -r all="$@"
 	local -r tx_args=${all%rx*}
 	local -r rx_args=${all#*rx}
+	local ret=0
 
 	cfg_veth
 
-	ip netns exec "${PEER_NS}" ./udpgso_bench_rx -C 1000 -R 10 ${rx_args} && \
-		echo "ok" || \
-		echo "failed" &
+	ip netns exec "${PEER_NS}" ./udpgso_bench_rx -C 1000 -R 10 ${rx_args} &
+	local PID1=$!
 
 	wait_local_port_listen ${PEER_NS} 8000 udp
 	./udpgso_bench_tx ${tx_args}
-	ret=$?
-	wait $(jobs -p)
+	check_err $?
+	wait ${PID1}
+	check_err $?
+	[ "$ret" -eq 0 ] && echo "ok" || echo "failed"
 	return $ret
 }
 
@@ -73,6 +75,7 @@ run_one_nat() {
 	local -r all="$@"
 	local -r tx_args=${all%rx*}
 	local -r rx_args=${all#*rx}
+	local ret=0
 
 	if [[ ${tx_args} = *-4* ]]; then
 		ipt_cmd=iptables
@@ -93,16 +96,17 @@ run_one_nat() {
 	# ... so that GRO will match the UDP_GRO enabled socket, but packets
 	# will land on the 'plain' one
 	ip netns exec "${PEER_NS}" ./udpgso_bench_rx -G ${family} -b ${addr1} -n 0 &
-	pid=$!
-	ip netns exec "${PEER_NS}" ./udpgso_bench_rx -C 1000 -R 10 ${family} -b ${addr2%/*} ${rx_args} && \
-		echo "ok" || \
-		echo "failed"&
+	local PID1=$!
+	ip netns exec "${PEER_NS}" ./udpgso_bench_rx -C 1000 -R 10 ${family} -b ${addr2%/*} ${rx_args} &
+	local PID2=$!
 
 	wait_local_port_listen "${PEER_NS}" 8000 udp
 	./udpgso_bench_tx ${tx_args}
-	ret=$?
-	kill -INT $pid
-	wait $(jobs -p)
+	check_err $?
+	kill -INT ${PID1}
+	wait ${PID2}
+	check_err $?
+	[ "$ret" -eq 0 ] && echo "ok" || echo "failed"
 	return $ret
 }
 
@@ -111,20 +115,26 @@ run_one_2sock() {
 	local -r all="$@"
 	local -r tx_args=${all%rx*}
 	local -r rx_args=${all#*rx}
+	local ret=0
 
 	cfg_veth
 
 	ip netns exec "${PEER_NS}" ./udpgso_bench_rx -C 1000 -R 10 ${rx_args} -p 12345 &
-	ip netns exec "${PEER_NS}" ./udpgso_bench_rx -C 2000 -R 10 ${rx_args} && \
-		echo "ok" || \
-		echo "failed" &
+	local PID1=$!
+	ip netns exec "${PEER_NS}" ./udpgso_bench_rx -C 2000 -R 10 ${rx_args} &
+	local PID2=$!
 
 	wait_local_port_listen "${PEER_NS}" 12345 udp
 	./udpgso_bench_tx ${tx_args} -p 12345
+	check_err $?
 	wait_local_port_listen "${PEER_NS}" 8000 udp
 	./udpgso_bench_tx ${tx_args}
-	ret=$?
-	wait $(jobs -p)
+	check_err $?
+	wait ${PID1}
+	check_err $?
+	wait ${PID2}
+	check_err $?
+	[ "$ret" -eq 0 ] && echo "ok" || echo "failed"
 	return $ret
 }
 

From d7818402b1d80347c764001583f6d63fa68c2e1a Mon Sep 17 00:00:00 2001
From: Hangbin Liu <liuhangbin@gmail.com>
Date: Thu, 15 Aug 2024 15:59:51 +0800
Subject: [PATCH 28/82] selftests: udpgro: no need to load xdp for gro
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

After commit d7db7775ea2e ("net: veth: do not manipulate GRO when using
XDP"), there is no need to load XDP program to enable GRO. On the other
hand, the current test is failed due to loading the XDP program. e.g.

 # selftests: net: udpgro.sh
 # ipv4
 #  no GRO              ok
 #  no GRO chk cmsg     ok
 #  GRO                 ./udpgso_bench_rx: recv: bad packet len, got 1472, expected 14720
 #
 # failed

 [...]

 #  bad GRO lookup      ok
 #  multiple GRO socks  ./udpgso_bench_rx: recv: bad packet len, got 1452, expected 14520
 #
 # ./udpgso_bench_rx: recv: bad packet len, got 1452, expected 14520
 #
 # failed
 ok 1 selftests: net: udpgro.sh

After fix, all the test passed.

 # ./udpgro.sh
 ipv4
  no GRO                                  ok
  [...]
  multiple GRO socks                      ok

Fixes: d7db7775ea2e ("net: veth: do not manipulate GRO when using XDP")
Reported-by: Yi Chen <yiche@redhat.com>
Closes: https://issues.redhat.com/browse/RHEL-53858
Reviewed-by: Toke Høiland-Jørgensen <toke@redhat.com>
Acked-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 tools/testing/selftests/net/udpgro.sh | 9 +--------
 1 file changed, 1 insertion(+), 8 deletions(-)

diff --git a/tools/testing/selftests/net/udpgro.sh b/tools/testing/selftests/net/udpgro.sh
index 4659cf01e438..d5ffd8c9172e 100755
--- a/tools/testing/selftests/net/udpgro.sh
+++ b/tools/testing/selftests/net/udpgro.sh
@@ -7,8 +7,6 @@ source net_helper.sh
 
 readonly PEER_NS="ns-peer-$(mktemp -u XXXXXX)"
 
-BPF_FILE="xdp_dummy.bpf.o"
-
 # set global exit status, but never reset nonzero one.
 check_err()
 {
@@ -38,7 +36,7 @@ cfg_veth() {
 	ip -netns "${PEER_NS}" addr add dev veth1 192.168.1.1/24
 	ip -netns "${PEER_NS}" addr add dev veth1 2001:db8::1/64 nodad
 	ip -netns "${PEER_NS}" link set dev veth1 up
-	ip -n "${PEER_NS}" link set veth1 xdp object ${BPF_FILE} section xdp
+	ip netns exec "${PEER_NS}" ethtool -K veth1 gro on
 }
 
 run_one() {
@@ -206,11 +204,6 @@ run_all() {
 	return $ret
 }
 
-if [ ! -f ${BPF_FILE} ]; then
-	echo "Missing ${BPF_FILE}. Run 'make' first"
-	exit -1
-fi
-
 if [[ $# -eq 0 ]]; then
 	run_all
 elif [[ $1 == "__subprocess" ]]; then

From 565d121b69980637f040eb4d84289869cdaabedf Mon Sep 17 00:00:00 2001
From: Florian Westphal <fw@strlen.de>
Date: Tue, 13 Aug 2024 00:28:25 +0200
Subject: [PATCH 29/82] tcp: prevent concurrent execution of tcp_sk_exit_batch

Its possible that two threads call tcp_sk_exit_batch() concurrently,
once from the cleanup_net workqueue, once from a task that failed to clone
a new netns.  In the latter case, error unwinding calls the exit handlers
in reverse order for the 'failed' netns.

tcp_sk_exit_batch() calls tcp_twsk_purge().
Problem is that since commit b099ce2602d8 ("net: Batch inet_twsk_purge"),
this function picks up twsk in any dying netns, not just the one passed
in via exit_batch list.

This means that the error unwind of setup_net() can "steal" and destroy
timewait sockets belonging to the exiting netns.

This allows the netns exit worker to proceed to call

WARN_ON_ONCE(!refcount_dec_and_test(&net->ipv4.tcp_death_row.tw_refcount));

without the expected 1 -> 0 transition, which then splats.

At same time, error unwind path that is also running inet_twsk_purge()
will splat as well:

WARNING: .. at lib/refcount.c:31 refcount_warn_saturate+0x1ed/0x210
...
 refcount_dec include/linux/refcount.h:351 [inline]
 inet_twsk_kill+0x758/0x9c0 net/ipv4/inet_timewait_sock.c:70
 inet_twsk_deschedule_put net/ipv4/inet_timewait_sock.c:221
 inet_twsk_purge+0x725/0x890 net/ipv4/inet_timewait_sock.c:304
 tcp_sk_exit_batch+0x1c/0x170 net/ipv4/tcp_ipv4.c:3522
 ops_exit_list+0x128/0x180 net/core/net_namespace.c:178
 setup_net+0x714/0xb40 net/core/net_namespace.c:375
 copy_net_ns+0x2f0/0x670 net/core/net_namespace.c:508
 create_new_namespaces+0x3ea/0xb10 kernel/nsproxy.c:110

... because refcount_dec() of tw_refcount unexpectedly dropped to 0.

This doesn't seem like an actual bug (no tw sockets got lost and I don't
see a use-after-free) but as erroneous trigger of debug check.

Add a mutex to force strict ordering: the task that calls tcp_twsk_purge()
blocks other task from doing final _dec_and_test before mutex-owner has
removed all tw sockets of dying netns.

Fixes: e9bd0cca09d1 ("tcp: Don't allocate tcp_death_row outside of struct netns_ipv4.")
Reported-by: syzbot+8ea26396ff85d23a8929@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/netdev/0000000000003a5292061f5e4e19@google.com/
Link: https://lore.kernel.org/netdev/20240812140104.GA21559@breakpoint.cc/
Signed-off-by: Florian Westphal <fw@strlen.de>
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Reviewed-by: Jason Xing <kerneljasonxing@gmail.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20240812222857.29837-1-fw@strlen.de
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv4/tcp_ipv4.c | 14 ++++++++++++++
 1 file changed, 14 insertions(+)

diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
index fd17f25ff288..a4e510846905 100644
--- a/net/ipv4/tcp_ipv4.c
+++ b/net/ipv4/tcp_ipv4.c
@@ -97,6 +97,8 @@ static DEFINE_PER_CPU(struct sock_bh_locked, ipv4_tcp_sk) = {
 	.bh_lock = INIT_LOCAL_LOCK(bh_lock),
 };
 
+static DEFINE_MUTEX(tcp_exit_batch_mutex);
+
 static u32 tcp_v4_init_seq(const struct sk_buff *skb)
 {
 	return secure_tcp_seq(ip_hdr(skb)->daddr,
@@ -3514,6 +3516,16 @@ static void __net_exit tcp_sk_exit_batch(struct list_head *net_exit_list)
 {
 	struct net *net;
 
+	/* make sure concurrent calls to tcp_sk_exit_batch from net_cleanup_work
+	 * and failed setup_net error unwinding path are serialized.
+	 *
+	 * tcp_twsk_purge() handles twsk in any dead netns, not just those in
+	 * net_exit_list, the thread that dismantles a particular twsk must
+	 * do so without other thread progressing to refcount_dec_and_test() of
+	 * tcp_death_row.tw_refcount.
+	 */
+	mutex_lock(&tcp_exit_batch_mutex);
+
 	tcp_twsk_purge(net_exit_list);
 
 	list_for_each_entry(net, net_exit_list, exit_list) {
@@ -3521,6 +3533,8 @@ static void __net_exit tcp_sk_exit_batch(struct list_head *net_exit_list)
 		WARN_ON_ONCE(!refcount_dec_and_test(&net->ipv4.tcp_death_row.tw_refcount));
 		tcp_fastopen_ctx_destroy(net);
 	}
+
+	mutex_unlock(&tcp_exit_batch_mutex);
 }
 
 static struct pernet_operations __net_initdata tcp_sk_ops = {

From ce335db0621648472f9bb4b7191eb2e13a5793cf Mon Sep 17 00:00:00 2001
From: Jeremy Kerr <jk@codeconstruct.com.au>
Date: Fri, 16 Aug 2024 18:29:17 +0800
Subject: [PATCH 30/82] net: mctp: test: Use correct skb for route input check

In the MCTP route input test, we're routing one skb, then (when delivery
is expected) checking the resulting routed skb.

However, we're currently checking the original skb length, rather than
the routed skb. Check the routed skb instead; the original will have
been freed at this point.

Fixes: 8892c0490779 ("mctp: Add route input to socket tests")
Reported-by: Dan Carpenter <dan.carpenter@linaro.org>
Closes: https://lore.kernel.org/kernel-janitors/4ad204f0-94cf-46c5-bdab-49592addf315@kili.mountain/
Signed-off-by: Jeremy Kerr <jk@codeconstruct.com.au>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20240816-mctp-kunit-skb-fix-v1-1-3c367ac89c27@codeconstruct.com.au
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/mctp/test/route-test.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/mctp/test/route-test.c b/net/mctp/test/route-test.c
index 77e5dd422258..8551dab1d1e6 100644
--- a/net/mctp/test/route-test.c
+++ b/net/mctp/test/route-test.c
@@ -366,7 +366,7 @@ static void mctp_test_route_input_sk(struct kunit *test)
 
 		skb2 = skb_recv_datagram(sock->sk, MSG_DONTWAIT, &rc);
 		KUNIT_EXPECT_NOT_ERR_OR_NULL(test, skb2);
-		KUNIT_EXPECT_EQ(test, skb->len, 1);
+		KUNIT_EXPECT_EQ(test, skb2->len, 1);
 
 		skb_free_datagram(sock->sk, skb2);
 

From 807067bf014d4a3ae2cc55bd3de16f22a01eb580 Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@amazon.com>
Date: Thu, 15 Aug 2024 15:04:37 -0700
Subject: [PATCH 31/82] kcm: Serialise kcm_sendmsg() for the same socket.

syzkaller reported UAF in kcm_release(). [0]

The scenario is

  1. Thread A builds a skb with MSG_MORE and sets kcm->seq_skb.

  2. Thread A resumes building skb from kcm->seq_skb but is blocked
     by sk_stream_wait_memory()

  3. Thread B calls sendmsg() concurrently, finishes building kcm->seq_skb
     and puts the skb to the write queue

  4. Thread A faces an error and finally frees skb that is already in the
     write queue

  5. kcm_release() does double-free the skb in the write queue

When a thread is building a MSG_MORE skb, another thread must not touch it.

Let's add a per-sk mutex and serialise kcm_sendmsg().

[0]:
BUG: KASAN: slab-use-after-free in __skb_unlink include/linux/skbuff.h:2366 [inline]
BUG: KASAN: slab-use-after-free in __skb_dequeue include/linux/skbuff.h:2385 [inline]
BUG: KASAN: slab-use-after-free in __skb_queue_purge_reason include/linux/skbuff.h:3175 [inline]
BUG: KASAN: slab-use-after-free in __skb_queue_purge include/linux/skbuff.h:3181 [inline]
BUG: KASAN: slab-use-after-free in kcm_release+0x170/0x4c8 net/kcm/kcmsock.c:1691
Read of size 8 at addr ffff0000ced0fc80 by task syz-executor329/6167

CPU: 1 PID: 6167 Comm: syz-executor329 Tainted: G    B              6.8.0-rc5-syzkaller-g9abbc24128bc #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/25/2024
Call trace:
 dump_backtrace+0x1b8/0x1e4 arch/arm64/kernel/stacktrace.c:291
 show_stack+0x2c/0x3c arch/arm64/kernel/stacktrace.c:298
 __dump_stack lib/dump_stack.c:88 [inline]
 dump_stack_lvl+0xd0/0x124 lib/dump_stack.c:106
 print_address_description mm/kasan/report.c:377 [inline]
 print_report+0x178/0x518 mm/kasan/report.c:488
 kasan_report+0xd8/0x138 mm/kasan/report.c:601
 __asan_report_load8_noabort+0x20/0x2c mm/kasan/report_generic.c:381
 __skb_unlink include/linux/skbuff.h:2366 [inline]
 __skb_dequeue include/linux/skbuff.h:2385 [inline]
 __skb_queue_purge_reason include/linux/skbuff.h:3175 [inline]
 __skb_queue_purge include/linux/skbuff.h:3181 [inline]
 kcm_release+0x170/0x4c8 net/kcm/kcmsock.c:1691
 __sock_release net/socket.c:659 [inline]
 sock_close+0xa4/0x1e8 net/socket.c:1421
 __fput+0x30c/0x738 fs/file_table.c:376
 ____fput+0x20/0x30 fs/file_table.c:404
 task_work_run+0x230/0x2e0 kernel/task_work.c:180
 exit_task_work include/linux/task_work.h:38 [inline]
 do_exit+0x618/0x1f64 kernel/exit.c:871
 do_group_exit+0x194/0x22c kernel/exit.c:1020
 get_signal+0x1500/0x15ec kernel/signal.c:2893
 do_signal+0x23c/0x3b44 arch/arm64/kernel/signal.c:1249
 do_notify_resume+0x74/0x1f4 arch/arm64/kernel/entry-common.c:148
 exit_to_user_mode_prepare arch/arm64/kernel/entry-common.c:169 [inline]
 exit_to_user_mode arch/arm64/kernel/entry-common.c:178 [inline]
 el0_svc+0xac/0x168 arch/arm64/kernel/entry-common.c:713
 el0t_64_sync_handler+0x84/0xfc arch/arm64/kernel/entry-common.c:730
 el0t_64_sync+0x190/0x194 arch/arm64/kernel/entry.S:598

Allocated by task 6166:
 kasan_save_stack mm/kasan/common.c:47 [inline]
 kasan_save_track+0x40/0x78 mm/kasan/common.c:68
 kasan_save_alloc_info+0x70/0x84 mm/kasan/generic.c:626
 unpoison_slab_object mm/kasan/common.c:314 [inline]
 __kasan_slab_alloc+0x74/0x8c mm/kasan/common.c:340
 kasan_slab_alloc include/linux/kasan.h:201 [inline]
 slab_post_alloc_hook mm/slub.c:3813 [inline]
 slab_alloc_node mm/slub.c:3860 [inline]
 kmem_cache_alloc_node+0x204/0x4c0 mm/slub.c:3903
 __alloc_skb+0x19c/0x3d8 net/core/skbuff.c:641
 alloc_skb include/linux/skbuff.h:1296 [inline]
 kcm_sendmsg+0x1d3c/0x2124 net/kcm/kcmsock.c:783
 sock_sendmsg_nosec net/socket.c:730 [inline]
 __sock_sendmsg net/socket.c:745 [inline]
 sock_sendmsg+0x220/0x2c0 net/socket.c:768
 splice_to_socket+0x7cc/0xd58 fs/splice.c:889
 do_splice_from fs/splice.c:941 [inline]
 direct_splice_actor+0xec/0x1d8 fs/splice.c:1164
 splice_direct_to_actor+0x438/0xa0c fs/splice.c:1108
 do_splice_direct_actor fs/splice.c:1207 [inline]
 do_splice_direct+0x1e4/0x304 fs/splice.c:1233
 do_sendfile+0x460/0xb3c fs/read_write.c:1295
 __do_sys_sendfile64 fs/read_write.c:1362 [inline]
 __se_sys_sendfile64 fs/read_write.c:1348 [inline]
 __arm64_sys_sendfile64+0x160/0x3b4 fs/read_write.c:1348
 __invoke_syscall arch/arm64/kernel/syscall.c:37 [inline]
 invoke_syscall+0x98/0x2b8 arch/arm64/kernel/syscall.c:51
 el0_svc_common+0x130/0x23c arch/arm64/kernel/syscall.c:136
 do_el0_svc+0x48/0x58 arch/arm64/kernel/syscall.c:155
 el0_svc+0x54/0x168 arch/arm64/kernel/entry-common.c:712
 el0t_64_sync_handler+0x84/0xfc arch/arm64/kernel/entry-common.c:730
 el0t_64_sync+0x190/0x194 arch/arm64/kernel/entry.S:598

Freed by task 6167:
 kasan_save_stack mm/kasan/common.c:47 [inline]
 kasan_save_track+0x40/0x78 mm/kasan/common.c:68
 kasan_save_free_info+0x5c/0x74 mm/kasan/generic.c:640
 poison_slab_object+0x124/0x18c mm/kasan/common.c:241
 __kasan_slab_free+0x3c/0x78 mm/kasan/common.c:257
 kasan_slab_free include/linux/kasan.h:184 [inline]
 slab_free_hook mm/slub.c:2121 [inline]
 slab_free mm/slub.c:4299 [inline]
 kmem_cache_free+0x15c/0x3d4 mm/slub.c:4363
 kfree_skbmem+0x10c/0x19c
 __kfree_skb net/core/skbuff.c:1109 [inline]
 kfree_skb_reason+0x240/0x6f4 net/core/skbuff.c:1144
 kfree_skb include/linux/skbuff.h:1244 [inline]
 kcm_release+0x104/0x4c8 net/kcm/kcmsock.c:1685
 __sock_release net/socket.c:659 [inline]
 sock_close+0xa4/0x1e8 net/socket.c:1421
 __fput+0x30c/0x738 fs/file_table.c:376
 ____fput+0x20/0x30 fs/file_table.c:404
 task_work_run+0x230/0x2e0 kernel/task_work.c:180
 exit_task_work include/linux/task_work.h:38 [inline]
 do_exit+0x618/0x1f64 kernel/exit.c:871
 do_group_exit+0x194/0x22c kernel/exit.c:1020
 get_signal+0x1500/0x15ec kernel/signal.c:2893
 do_signal+0x23c/0x3b44 arch/arm64/kernel/signal.c:1249
 do_notify_resume+0x74/0x1f4 arch/arm64/kernel/entry-common.c:148
 exit_to_user_mode_prepare arch/arm64/kernel/entry-common.c:169 [inline]
 exit_to_user_mode arch/arm64/kernel/entry-common.c:178 [inline]
 el0_svc+0xac/0x168 arch/arm64/kernel/entry-common.c:713
 el0t_64_sync_handler+0x84/0xfc arch/arm64/kernel/entry-common.c:730
 el0t_64_sync+0x190/0x194 arch/arm64/kernel/entry.S:598

The buggy address belongs to the object at ffff0000ced0fc80
 which belongs to the cache skbuff_head_cache of size 240
The buggy address is located 0 bytes inside of
 freed 240-byte region [ffff0000ced0fc80, ffff0000ced0fd70)

The buggy address belongs to the physical page:
page:00000000d35f4ae4 refcount:1 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x10ed0f
flags: 0x5ffc00000000800(slab|node=0|zone=2|lastcpupid=0x7ff)
page_type: 0xffffffff()
raw: 05ffc00000000800 ffff0000c1cbf640 fffffdffc3423100 dead000000000004
raw: 0000000000000000 00000000000c000c 00000001ffffffff 0000000000000000
page dumped because: kasan: bad access detected

Memory state around the buggy address:
 ffff0000ced0fb80: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
 ffff0000ced0fc00: fb fb fb fb fb fb fc fc fc fc fc fc fc fc fc fc
>ffff0000ced0fc80: fa fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
                   ^
 ffff0000ced0fd00: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fc fc
 ffff0000ced0fd80: fc fc fc fc fc fc fc fc fa fb fb fb fb fb fb fb

Fixes: ab7ac4eb9832 ("kcm: Kernel Connection Multiplexor module")
Reported-by: syzbot+b72d86aa5df17ce74c60@syzkaller.appspotmail.com
Closes: https://syzkaller.appspot.com/bug?extid=b72d86aa5df17ce74c60
Tested-by: syzbot+b72d86aa5df17ce74c60@syzkaller.appspotmail.com
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20240815220437.69511-1-kuniyu@amazon.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/kcm.h | 1 +
 net/kcm/kcmsock.c | 4 ++++
 2 files changed, 5 insertions(+)

diff --git a/include/net/kcm.h b/include/net/kcm.h
index 90279e5e09a5..441e993be634 100644
--- a/include/net/kcm.h
+++ b/include/net/kcm.h
@@ -70,6 +70,7 @@ struct kcm_sock {
 	struct work_struct tx_work;
 	struct list_head wait_psock_list;
 	struct sk_buff *seq_skb;
+	struct mutex tx_mutex;
 	u32 tx_stopped : 1;
 
 	/* Don't use bit fields here, these are set under different locks */
diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c
index 2f191e50d4fc..d4118c796290 100644
--- a/net/kcm/kcmsock.c
+++ b/net/kcm/kcmsock.c
@@ -755,6 +755,7 @@ static int kcm_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
 		  !(msg->msg_flags & MSG_MORE) : !!(msg->msg_flags & MSG_EOR);
 	int err = -EPIPE;
 
+	mutex_lock(&kcm->tx_mutex);
 	lock_sock(sk);
 
 	/* Per tcp_sendmsg this should be in poll */
@@ -926,6 +927,7 @@ static int kcm_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
 	KCM_STATS_ADD(kcm->stats.tx_bytes, copied);
 
 	release_sock(sk);
+	mutex_unlock(&kcm->tx_mutex);
 	return copied;
 
 out_error:
@@ -951,6 +953,7 @@ static int kcm_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
 		sk->sk_write_space(sk);
 
 	release_sock(sk);
+	mutex_unlock(&kcm->tx_mutex);
 	return err;
 }
 
@@ -1204,6 +1207,7 @@ static void init_kcm_sock(struct kcm_sock *kcm, struct kcm_mux *mux)
 	spin_unlock_bh(&mux->lock);
 
 	INIT_WORK(&kcm->tx_work, kcm_tx_work);
+	mutex_init(&kcm->tx_mutex);
 
 	spin_lock_bh(&mux->rx_lock);
 	kcm_rcv_ready(kcm);

From 1eacdd71b3436b54d5fc8218c4bb0187d92a6892 Mon Sep 17 00:00:00 2001
From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Tue, 20 Aug 2024 09:54:30 +0200
Subject: [PATCH 32/82] netfilter: nft_counter: Disable BH in
 nft_counter_offload_stats().

The sequence counter nft_counter_seq is a per-CPU counter. There is no
lock associated with it. nft_counter_do_eval() is using the same counter
and disables BH which suggest that it can be invoked from a softirq.
This in turn means that nft_counter_offload_stats(), which disables only
preemption, can be interrupted by nft_counter_do_eval() leading to two
writer for one seqcount_t.
This can lead to loosing stats or reading statistics while they are
updated.

Disable BH during stats update in nft_counter_offload_stats() to ensure
one writer at a time.

Fixes: b72920f6e4a9d ("netfilter: nftables: counter hardware offload support")
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Reviewed-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nft_counter.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/netfilter/nft_counter.c b/net/netfilter/nft_counter.c
index 291ed2026367..16f40b503d37 100644
--- a/net/netfilter/nft_counter.c
+++ b/net/netfilter/nft_counter.c
@@ -265,7 +265,7 @@ static void nft_counter_offload_stats(struct nft_expr *expr,
 	struct nft_counter *this_cpu;
 	seqcount_t *myseq;
 
-	preempt_disable();
+	local_bh_disable();
 	this_cpu = this_cpu_ptr(priv->counter);
 	myseq = this_cpu_ptr(&nft_counter_seq);
 
@@ -273,7 +273,7 @@ static void nft_counter_offload_stats(struct nft_expr *expr,
 	this_cpu->packets += stats->pkts;
 	this_cpu->bytes += stats->bytes;
 	write_seqcount_end(myseq);
-	preempt_enable();
+	local_bh_enable();
 }
 
 void nft_counter_init_seqcount(void)

From a0b39e2dc7017ac667b70bdeee5293e410fab2fb Mon Sep 17 00:00:00 2001
From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Date: Tue, 20 Aug 2024 09:54:31 +0200
Subject: [PATCH 33/82] netfilter: nft_counter: Synchronize nft_counter_reset()
 against reader.

nft_counter_reset() resets the counter by subtracting the previously
retrieved value from the counter. This is a write operation on the
counter and as such it requires to be performed with a write sequence of
nft_counter_seq to serialize against its possible reader.

Update the packets/ bytes within write-sequence of nft_counter_seq.

Fixes: d84701ecbcd6a ("netfilter: nft_counter: rework atomic dump and reset")
Signed-off-by: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
Reviewed-by: Florian Westphal <fw@strlen.de>
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nft_counter.c | 5 +++++
 1 file changed, 5 insertions(+)

diff --git a/net/netfilter/nft_counter.c b/net/netfilter/nft_counter.c
index 16f40b503d37..eab0dc66bee6 100644
--- a/net/netfilter/nft_counter.c
+++ b/net/netfilter/nft_counter.c
@@ -107,11 +107,16 @@ static void nft_counter_reset(struct nft_counter_percpu_priv *priv,
 			      struct nft_counter *total)
 {
 	struct nft_counter *this_cpu;
+	seqcount_t *myseq;
 
 	local_bh_disable();
 	this_cpu = this_cpu_ptr(priv->counter);
+	myseq = this_cpu_ptr(&nft_counter_seq);
+
+	write_seqcount_begin(myseq);
 	this_cpu->packets -= total->packets;
 	this_cpu->bytes -= total->bytes;
+	write_seqcount_end(myseq);
 	local_bh_enable();
 }
 

From 4b3e33fcc38f7750604b065c55a43e94c5bc3145 Mon Sep 17 00:00:00 2001
From: Thomas Bogendoerfer <tbogendoerfer@suse.de>
Date: Thu, 15 Aug 2024 17:14:16 +0200
Subject: [PATCH 34/82] ip6_tunnel: Fix broken GRO

GRO code checks for matching layer 2 headers to see, if packet belongs
to the same flow and because ip6 tunnel set dev->hard_header_len
this check fails in cases, where it shouldn't. To fix this don't
set hard_header_len, but use needed_headroom like ipv4/ip_tunnel.c
does.

Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Thomas Bogendoerfer <tbogendoerfer@suse.de>
Link: https://patch.msgid.link/20240815151419.109864-1-tbogendoerfer@suse.de
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/ipv6/ip6_tunnel.c | 12 +++++++-----
 1 file changed, 7 insertions(+), 5 deletions(-)

diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
index 9dee0c127955..87dfb565a9f8 100644
--- a/net/ipv6/ip6_tunnel.c
+++ b/net/ipv6/ip6_tunnel.c
@@ -1507,7 +1507,8 @@ static void ip6_tnl_link_config(struct ip6_tnl *t)
 			tdev = __dev_get_by_index(t->net, p->link);
 
 		if (tdev) {
-			dev->hard_header_len = tdev->hard_header_len + t_hlen;
+			dev->needed_headroom = tdev->hard_header_len +
+				tdev->needed_headroom + t_hlen;
 			mtu = min_t(unsigned int, tdev->mtu, IP6_MAX_MTU);
 
 			mtu = mtu - t_hlen;
@@ -1731,7 +1732,9 @@ ip6_tnl_siocdevprivate(struct net_device *dev, struct ifreq *ifr,
 int ip6_tnl_change_mtu(struct net_device *dev, int new_mtu)
 {
 	struct ip6_tnl *tnl = netdev_priv(dev);
+	int t_hlen;
 
+	t_hlen = tnl->hlen + sizeof(struct ipv6hdr);
 	if (tnl->parms.proto == IPPROTO_IPV6) {
 		if (new_mtu < IPV6_MIN_MTU)
 			return -EINVAL;
@@ -1740,10 +1743,10 @@ int ip6_tnl_change_mtu(struct net_device *dev, int new_mtu)
 			return -EINVAL;
 	}
 	if (tnl->parms.proto == IPPROTO_IPV6 || tnl->parms.proto == 0) {
-		if (new_mtu > IP6_MAX_MTU - dev->hard_header_len)
+		if (new_mtu > IP6_MAX_MTU - dev->hard_header_len - t_hlen)
 			return -EINVAL;
 	} else {
-		if (new_mtu > IP_MAX_MTU - dev->hard_header_len)
+		if (new_mtu > IP_MAX_MTU - dev->hard_header_len - t_hlen)
 			return -EINVAL;
 	}
 	WRITE_ONCE(dev->mtu, new_mtu);
@@ -1887,12 +1890,11 @@ ip6_tnl_dev_init_gen(struct net_device *dev)
 	t_hlen = t->hlen + sizeof(struct ipv6hdr);
 
 	dev->type = ARPHRD_TUNNEL6;
-	dev->hard_header_len = LL_MAX_HEADER + t_hlen;
 	dev->mtu = ETH_DATA_LEN - t_hlen;
 	if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT))
 		dev->mtu -= 8;
 	dev->min_mtu = ETH_MIN_MTU;
-	dev->max_mtu = IP6_MAX_MTU - dev->hard_header_len;
+	dev->max_mtu = IP6_MAX_MTU - dev->hard_header_len - t_hlen;
 
 	netdev_hold(dev, &t->dev_tracker, GFP_KERNEL);
 	netdev_lockdep_set_classes(dev);

From fc59b9a5f7201b9f7272944596113a82cc7773d5 Mon Sep 17 00:00:00 2001
From: Nikolay Aleksandrov <razor@blackwall.org>
Date: Fri, 16 Aug 2024 14:48:10 +0300
Subject: [PATCH 35/82] bonding: fix bond_ipsec_offload_ok return type

Fix the return type which should be bool.

Fixes: 955b785ec6b3 ("bonding: fix suspicious RCU usage in bond_ipsec_offload_ok()")
Signed-off-by: Nikolay Aleksandrov <razor@blackwall.org>
Reviewed-by: Hangbin Liu <liuhangbin@gmail.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/bonding/bond_main.c | 18 ++++++------------
 1 file changed, 6 insertions(+), 12 deletions(-)

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 1cd92c12e782..85b5868deeea 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -599,34 +599,28 @@ static bool bond_ipsec_offload_ok(struct sk_buff *skb, struct xfrm_state *xs)
 	struct net_device *real_dev;
 	struct slave *curr_active;
 	struct bonding *bond;
-	int err;
+	bool ok = false;
 
 	bond = netdev_priv(bond_dev);
 	rcu_read_lock();
 	curr_active = rcu_dereference(bond->curr_active_slave);
 	real_dev = curr_active->dev;
 
-	if (BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP) {
-		err = false;
+	if (BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP)
 		goto out;
-	}
 
-	if (!xs->xso.real_dev) {
-		err = false;
+	if (!xs->xso.real_dev)
 		goto out;
-	}
 
 	if (!real_dev->xfrmdev_ops ||
 	    !real_dev->xfrmdev_ops->xdo_dev_offload_ok ||
-	    netif_is_bond_master(real_dev)) {
-		err = false;
+	    netif_is_bond_master(real_dev))
 		goto out;
-	}
 
-	err = real_dev->xfrmdev_ops->xdo_dev_offload_ok(skb, xs);
+	ok = real_dev->xfrmdev_ops->xdo_dev_offload_ok(skb, xs);
 out:
 	rcu_read_unlock();
-	return err;
+	return ok;
 }
 
 static const struct xfrmdev_ops bond_xfrmdev_ops = {

From 95c90e4ad89d493a7a14fa200082e466e2548f9d Mon Sep 17 00:00:00 2001
From: Nikolay Aleksandrov <razor@blackwall.org>
Date: Fri, 16 Aug 2024 14:48:11 +0300
Subject: [PATCH 36/82] bonding: fix null pointer deref in
 bond_ipsec_offload_ok

We must check if there is an active slave before dereferencing the pointer.

Fixes: 18cb261afd7b ("bonding: support hardware encryption offload to slaves")
Signed-off-by: Nikolay Aleksandrov <razor@blackwall.org>
Reviewed-by: Hangbin Liu <liuhangbin@gmail.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/bonding/bond_main.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 85b5868deeea..65ddb71eebcd 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -604,6 +604,8 @@ static bool bond_ipsec_offload_ok(struct sk_buff *skb, struct xfrm_state *xs)
 	bond = netdev_priv(bond_dev);
 	rcu_read_lock();
 	curr_active = rcu_dereference(bond->curr_active_slave);
+	if (!curr_active)
+		goto out;
 	real_dev = curr_active->dev;
 
 	if (BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP)

From f8cde9805981c50d0c029063dc7d82821806fc44 Mon Sep 17 00:00:00 2001
From: Nikolay Aleksandrov <razor@blackwall.org>
Date: Fri, 16 Aug 2024 14:48:12 +0300
Subject: [PATCH 37/82] bonding: fix xfrm real_dev null pointer dereference

We shouldn't set real_dev to NULL because packets can be in transit and
xfrm might call xdo_dev_offload_ok() in parallel. All callbacks assume
real_dev is set.

 Example trace:
 kernel: BUG: unable to handle page fault for address: 0000000000001030
 kernel: bond0: (slave eni0np1): making interface the new active one
 kernel: #PF: supervisor write access in kernel mode
 kernel: #PF: error_code(0x0002) - not-present page
 kernel: PGD 0 P4D 0
 kernel: Oops: 0002 [#1] PREEMPT SMP
 kernel: CPU: 4 PID: 2237 Comm: ping Not tainted 6.7.7+ #12
 kernel: Hardware name: QEMU Standard PC (Q35 + ICH9, 2009), BIOS 1.16.3-2.fc40 04/01/2014
 kernel: RIP: 0010:nsim_ipsec_offload_ok+0xc/0x20 [netdevsim]
 kernel: bond0: (slave eni0np1): bond_ipsec_add_sa_all: failed to add SA
 kernel: Code: e0 0f 0b 48 83 7f 38 00 74 de 0f 0b 48 8b 47 08 48 8b 37 48 8b 78 40 e9 b2 e5 9a d7 66 90 0f 1f 44 00 00 48 8b 86 80 02 00 00 <83> 80 30 10 00 00 01 b8 01 00 00 00 c3 0f 1f 80 00 00 00 00 0f 1f
 kernel: bond0: (slave eni0np1): making interface the new active one
 kernel: RSP: 0018:ffffabde81553b98 EFLAGS: 00010246
 kernel: bond0: (slave eni0np1): bond_ipsec_add_sa_all: failed to add SA
 kernel:
 kernel: RAX: 0000000000000000 RBX: ffff9eb404e74900 RCX: ffff9eb403d97c60
 kernel: RDX: ffffffffc090de10 RSI: ffff9eb404e74900 RDI: ffff9eb3c5de9e00
 kernel: RBP: ffff9eb3c0a42000 R08: 0000000000000010 R09: 0000000000000014
 kernel: R10: 7974203030303030 R11: 3030303030303030 R12: 0000000000000000
 kernel: R13: ffff9eb3c5de9e00 R14: ffffabde81553cc8 R15: ffff9eb404c53000
 kernel: FS:  00007f2a77a3ad00(0000) GS:ffff9eb43bd00000(0000) knlGS:0000000000000000
 kernel: CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
 kernel: CR2: 0000000000001030 CR3: 00000001122ab000 CR4: 0000000000350ef0
 kernel: bond0: (slave eni0np1): making interface the new active one
 kernel: Call Trace:
 kernel:  <TASK>
 kernel:  ? __die+0x1f/0x60
 kernel: bond0: (slave eni0np1): bond_ipsec_add_sa_all: failed to add SA
 kernel:  ? page_fault_oops+0x142/0x4c0
 kernel:  ? do_user_addr_fault+0x65/0x670
 kernel:  ? kvm_read_and_reset_apf_flags+0x3b/0x50
 kernel: bond0: (slave eni0np1): making interface the new active one
 kernel:  ? exc_page_fault+0x7b/0x180
 kernel:  ? asm_exc_page_fault+0x22/0x30
 kernel:  ? nsim_bpf_uninit+0x50/0x50 [netdevsim]
 kernel: bond0: (slave eni0np1): bond_ipsec_add_sa_all: failed to add SA
 kernel:  ? nsim_ipsec_offload_ok+0xc/0x20 [netdevsim]
 kernel: bond0: (slave eni0np1): making interface the new active one
 kernel:  bond_ipsec_offload_ok+0x7b/0x90 [bonding]
 kernel:  xfrm_output+0x61/0x3b0
 kernel: bond0: (slave eni0np1): bond_ipsec_add_sa_all: failed to add SA
 kernel:  ip_push_pending_frames+0x56/0x80

Fixes: 18cb261afd7b ("bonding: support hardware encryption offload to slaves")
Signed-off-by: Nikolay Aleksandrov <razor@blackwall.org>
Reviewed-by: Hangbin Liu <liuhangbin@gmail.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/bonding/bond_main.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
index 65ddb71eebcd..f74bacf071fc 100644
--- a/drivers/net/bonding/bond_main.c
+++ b/drivers/net/bonding/bond_main.c
@@ -582,7 +582,6 @@ static void bond_ipsec_del_sa_all(struct bonding *bond)
 		} else {
 			slave->dev->xfrmdev_ops->xdo_dev_state_delete(ipsec->xs);
 		}
-		ipsec->xs->xso.real_dev = NULL;
 	}
 	spin_unlock_bh(&bond->ipsec_lock);
 	rcu_read_unlock();

From c4c5c5d2ef40a9f67a9241dc5422eac9ffe19547 Mon Sep 17 00:00:00 2001
From: Nikolay Aleksandrov <razor@blackwall.org>
Date: Fri, 16 Aug 2024 14:48:13 +0300
Subject: [PATCH 38/82] bonding: fix xfrm state handling when clearing active
 slave

If the active slave is cleared manually the xfrm state is not flushed.
This leads to xfrm add/del imbalance and adding the same state multiple
times. For example when the device cannot handle anymore states we get:
 [ 1169.884811] bond0: (slave eni0np1): bond_ipsec_add_sa_all: failed to add SA
because it's filled with the same state after multiple active slave
clearings. This change also has a few nice side effects: user-space
gets a notification for the change, the old device gets its mac address
and promisc/mcast adjusted properly.

Fixes: 18cb261afd7b ("bonding: support hardware encryption offload to slaves")
Signed-off-by: Nikolay Aleksandrov <razor@blackwall.org>
Reviewed-by: Hangbin Liu <liuhangbin@gmail.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/bonding/bond_options.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c
index bc80fb6397dc..95d59a18c022 100644
--- a/drivers/net/bonding/bond_options.c
+++ b/drivers/net/bonding/bond_options.c
@@ -936,7 +936,7 @@ static int bond_option_active_slave_set(struct bonding *bond,
 	/* check to see if we are clearing active */
 	if (!slave_dev) {
 		netdev_dbg(bond->dev, "Clearing current active slave\n");
-		RCU_INIT_POINTER(bond->curr_active_slave, NULL);
+		bond_change_active_slave(bond, NULL);
 		bond_select_active_slave(bond);
 	} else {
 		struct slave *old_active = rtnl_dereference(bond->curr_active_slave);

From 50b2143356e888777fc5bca023c39f34f404613a Mon Sep 17 00:00:00 2001
From: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Date: Wed, 7 Aug 2024 12:53:24 +0200
Subject: [PATCH 39/82] ice: fix page reuse when PAGE_SIZE is over 8k

Architectures that have PAGE_SIZE >= 8192 such as arm64 should act the
same as x86 currently, meaning reuse of a page should only take place
when no one else is busy with it.

Do two things independently of underlying PAGE_SIZE:
- store the page count under ice_rx_buf::pgcnt
- then act upon its value vs ice_rx_buf::pagecnt_bias when making the
  decision regarding page reuse

Fixes: 2b245cb29421 ("ice: Implement transmit and NAPI support")
Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Tested-by: Chandan Kumar Rout <chandanx.rout@intel.com> (A Contingent Worker at Intel)
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_txrx.c | 12 +++---------
 1 file changed, 3 insertions(+), 9 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c
index 8d25b6981269..50211188c1a7 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx.c
+++ b/drivers/net/ethernet/intel/ice/ice_txrx.c
@@ -837,16 +837,15 @@ ice_can_reuse_rx_page(struct ice_rx_buf *rx_buf)
 	if (!dev_page_is_reusable(page))
 		return false;
 
-#if (PAGE_SIZE < 8192)
 	/* if we are only owner of page we can reuse it */
 	if (unlikely(rx_buf->pgcnt - pagecnt_bias > 1))
 		return false;
-#else
+#if (PAGE_SIZE >= 8192)
 #define ICE_LAST_OFFSET \
 	(SKB_WITH_OVERHEAD(PAGE_SIZE) - ICE_RXBUF_2048)
 	if (rx_buf->page_offset > ICE_LAST_OFFSET)
 		return false;
-#endif /* PAGE_SIZE < 8192) */
+#endif /* PAGE_SIZE >= 8192) */
 
 	/* If we have drained the page fragment pool we need to update
 	 * the pagecnt_bias and page count so that we fully restock the
@@ -949,12 +948,7 @@ ice_get_rx_buf(struct ice_rx_ring *rx_ring, const unsigned int size,
 	struct ice_rx_buf *rx_buf;
 
 	rx_buf = &rx_ring->rx_buf[ntc];
-	rx_buf->pgcnt =
-#if (PAGE_SIZE < 8192)
-		page_count(rx_buf->page);
-#else
-		0;
-#endif
+	rx_buf->pgcnt = page_count(rx_buf->page);
 	prefetchw(rx_buf->page);
 
 	if (!size)

From b966ad832942b5a11e002f9b5ef102b08425b84a Mon Sep 17 00:00:00 2001
From: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Date: Wed, 7 Aug 2024 12:53:25 +0200
Subject: [PATCH 40/82] ice: fix ICE_LAST_OFFSET formula

For bigger PAGE_SIZE archs, ice driver works on 3k Rx buffers.
Therefore, ICE_LAST_OFFSET should take into account ICE_RXBUF_3072, not
ICE_RXBUF_2048.

Fixes: 7237f5b0dba4 ("ice: introduce legacy Rx flag")
Suggested-by: Luiz Capitulino <luizcap@redhat.com>
Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Tested-by: Chandan Kumar Rout <chandanx.rout@intel.com> (A Contingent Worker at Intel)
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_txrx.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c
index 50211188c1a7..4b690952bb40 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx.c
+++ b/drivers/net/ethernet/intel/ice/ice_txrx.c
@@ -842,7 +842,7 @@ ice_can_reuse_rx_page(struct ice_rx_buf *rx_buf)
 		return false;
 #if (PAGE_SIZE >= 8192)
 #define ICE_LAST_OFFSET \
-	(SKB_WITH_OVERHEAD(PAGE_SIZE) - ICE_RXBUF_2048)
+	(SKB_WITH_OVERHEAD(PAGE_SIZE) - ICE_RXBUF_3072)
 	if (rx_buf->page_offset > ICE_LAST_OFFSET)
 		return false;
 #endif /* PAGE_SIZE >= 8192) */

From d53d4dcce69be5773e2d0878c9899ebfbf58c393 Mon Sep 17 00:00:00 2001
From: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Date: Wed, 7 Aug 2024 12:53:26 +0200
Subject: [PATCH 41/82] ice: fix truesize operations for PAGE_SIZE >= 8192

When working on multi-buffer packet on arch that has PAGE_SIZE >= 8192,
truesize is calculated and stored in xdp_buff::frame_sz per each
processed Rx buffer. This means that frame_sz will contain the truesize
based on last received buffer, but commit 1dc1a7e7f410 ("ice:
Centrallize Rx buffer recycling") assumed this value will be constant
for each buffer, which breaks the page recycling scheme and mess up the
way we update the page::page_offset.

To fix this, let us work on constant truesize when PAGE_SIZE >= 8192
instead of basing this on size of a packet read from Rx descriptor. This
way we can simplify the code and avoid calculating truesize per each
received frame and on top of that when using
xdp_update_skb_shared_info(), current formula for truesize update will
be valid.

This means ice_rx_frame_truesize() can be removed altogether.
Furthermore, first call to it within ice_clean_rx_irq() for 4k PAGE_SIZE
was redundant as xdp_buff::frame_sz is initialized via xdp_init_buff()
in ice_vsi_cfg_rxq(). This should have been removed at the point where
xdp_buff struct started to be a member of ice_rx_ring and it was no
longer a stack based variable.

There are two fixes tags as my understanding is that the first one
exposed us to broken truesize and page_offset handling and then second
introduced broken skb_shared_info update in ice_{construct,build}_skb().

Reported-and-tested-by: Luiz Capitulino <luizcap@redhat.com>
Closes: https://lore.kernel.org/netdev/8f9e2a5c-fd30-4206-9311-946a06d031bb@redhat.com/
Fixes: 1dc1a7e7f410 ("ice: Centrallize Rx buffer recycling")
Fixes: 2fba7dc5157b ("ice: Add support for XDP multi-buffer on Rx side")
Signed-off-by: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
Tested-by: Chandan Kumar Rout <chandanx.rout@intel.com> (A Contingent Worker at Intel)
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/ice_base.c | 21 ++++++++++++++-
 drivers/net/ethernet/intel/ice/ice_txrx.c | 33 -----------------------
 2 files changed, 20 insertions(+), 34 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/ice_base.c b/drivers/net/ethernet/intel/ice/ice_base.c
index 1facf179a96f..f448d3a84564 100644
--- a/drivers/net/ethernet/intel/ice/ice_base.c
+++ b/drivers/net/ethernet/intel/ice/ice_base.c
@@ -512,6 +512,25 @@ static void ice_xsk_pool_fill_cb(struct ice_rx_ring *ring)
 	xsk_pool_fill_cb(ring->xsk_pool, &desc);
 }
 
+/**
+ * ice_get_frame_sz - calculate xdp_buff::frame_sz
+ * @rx_ring: the ring being configured
+ *
+ * Return frame size based on underlying PAGE_SIZE
+ */
+static unsigned int ice_get_frame_sz(struct ice_rx_ring *rx_ring)
+{
+	unsigned int frame_sz;
+
+#if (PAGE_SIZE >= 8192)
+	frame_sz = rx_ring->rx_buf_len;
+#else
+	frame_sz = ice_rx_pg_size(rx_ring) / 2;
+#endif
+
+	return frame_sz;
+}
+
 /**
  * ice_vsi_cfg_rxq - Configure an Rx queue
  * @ring: the ring being configured
@@ -576,7 +595,7 @@ static int ice_vsi_cfg_rxq(struct ice_rx_ring *ring)
 		}
 	}
 
-	xdp_init_buff(&ring->xdp, ice_rx_pg_size(ring) / 2, &ring->xdp_rxq);
+	xdp_init_buff(&ring->xdp, ice_get_frame_sz(ring), &ring->xdp_rxq);
 	ring->xdp.data = NULL;
 	ring->xdp_ext.pkt_ctx = &ring->pkt_ctx;
 	err = ice_setup_rx_ctx(ring);
diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c
index 4b690952bb40..c9bc3f1add5d 100644
--- a/drivers/net/ethernet/intel/ice/ice_txrx.c
+++ b/drivers/net/ethernet/intel/ice/ice_txrx.c
@@ -521,30 +521,6 @@ int ice_setup_rx_ring(struct ice_rx_ring *rx_ring)
 	return -ENOMEM;
 }
 
-/**
- * ice_rx_frame_truesize
- * @rx_ring: ptr to Rx ring
- * @size: size
- *
- * calculate the truesize with taking into the account PAGE_SIZE of
- * underlying arch
- */
-static unsigned int
-ice_rx_frame_truesize(struct ice_rx_ring *rx_ring, const unsigned int size)
-{
-	unsigned int truesize;
-
-#if (PAGE_SIZE < 8192)
-	truesize = ice_rx_pg_size(rx_ring) / 2; /* Must be power-of-2 */
-#else
-	truesize = rx_ring->rx_offset ?
-		SKB_DATA_ALIGN(rx_ring->rx_offset + size) +
-		SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) :
-		SKB_DATA_ALIGN(size);
-#endif
-	return truesize;
-}
-
 /**
  * ice_run_xdp - Executes an XDP program on initialized xdp_buff
  * @rx_ring: Rx ring
@@ -1154,11 +1130,6 @@ int ice_clean_rx_irq(struct ice_rx_ring *rx_ring, int budget)
 	bool failure;
 	u32 first;
 
-	/* Frame size depend on rx_ring setup when PAGE_SIZE=4K */
-#if (PAGE_SIZE < 8192)
-	xdp->frame_sz = ice_rx_frame_truesize(rx_ring, 0);
-#endif
-
 	xdp_prog = READ_ONCE(rx_ring->xdp_prog);
 	if (xdp_prog) {
 		xdp_ring = rx_ring->xdp_ring;
@@ -1217,10 +1188,6 @@ int ice_clean_rx_irq(struct ice_rx_ring *rx_ring, int budget)
 			hard_start = page_address(rx_buf->page) + rx_buf->page_offset -
 				     offset;
 			xdp_prepare_buff(xdp, hard_start, offset, size, !!offset);
-#if (PAGE_SIZE > 4096)
-			/* At larger PAGE_SIZE, frame_sz depend on len size */
-			xdp->frame_sz = ice_rx_frame_truesize(rx_ring, size);
-#endif
 			xdp_buff_clear_frags_flag(xdp);
 		} else if (ice_add_xdp_frag(rx_ring, xdp, rx_buf, size)) {
 			break;

From 503ab6ee40fc103ea55cc9e50bb879e571d65aac Mon Sep 17 00:00:00 2001
From: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Date: Mon, 19 Aug 2024 09:17:42 +0200
Subject: [PATCH 42/82] ice: use internal pf id instead of function number

Use always the same pf id in devlink port number. When doing
pass-through the PF to VM bus info func number can be any value.

Fixes: 2ae0aa4758b0 ("ice: Move devlink port to PF/VF struct")
Reviewed-by: Wojciech Drewek <wojciech.drewek@intel.com>
Suggested-by: Jiri Pirko <jiri@resnulli.us>
Signed-off-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
---
 drivers/net/ethernet/intel/ice/devlink/devlink_port.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/intel/ice/devlink/devlink_port.c b/drivers/net/ethernet/intel/ice/devlink/devlink_port.c
index 00fed5a61d62..62ef8e2fb5f1 100644
--- a/drivers/net/ethernet/intel/ice/devlink/devlink_port.c
+++ b/drivers/net/ethernet/intel/ice/devlink/devlink_port.c
@@ -337,7 +337,7 @@ int ice_devlink_create_pf_port(struct ice_pf *pf)
 		return -EIO;
 
 	attrs.flavour = DEVLINK_PORT_FLAVOUR_PHYSICAL;
-	attrs.phys.port_number = pf->hw.bus.func;
+	attrs.phys.port_number = pf->hw.pf_id;
 
 	/* As FW supports only port split options for whole device,
 	 * set port split options only for first PF.
@@ -455,7 +455,7 @@ int ice_devlink_create_vf_port(struct ice_vf *vf)
 		return -EINVAL;
 
 	attrs.flavour = DEVLINK_PORT_FLAVOUR_PCI_VF;
-	attrs.pci_vf.pf = pf->hw.bus.func;
+	attrs.pci_vf.pf = pf->hw.pf_id;
 	attrs.pci_vf.vf = vf->vf_id;
 
 	ice_devlink_set_switch_id(pf, &attrs.switch_id);

From c50e7475961c36ec4d21d60af055b32f9436b431 Mon Sep 17 00:00:00 2001
From: Dan Carpenter <dan.carpenter@linaro.org>
Date: Sat, 17 Aug 2024 09:52:46 +0300
Subject: [PATCH 43/82] dpaa2-switch: Fix error checking in
 dpaa2_switch_seed_bp()

The dpaa2_switch_add_bufs() function returns the number of bufs that it
was able to add.  It returns BUFS_PER_CMD (7) for complete success or a
smaller number if there are not enough pages available.  However, the
error checking is looking at the total number of bufs instead of the
number which were added on this iteration.  Thus the error checking
only works correctly for the first iteration through the loop and
subsequent iterations are always counted as a success.

Fix this by checking only the bufs added in the current iteration.

Fixes: 0b1b71370458 ("staging: dpaa2-switch: handle Rx path on control interface")
Signed-off-by: Dan Carpenter <dan.carpenter@linaro.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Reviewed-by: Ioana Ciornei <ioana.ciornei@nxp.com>
Tested-by: Ioana Ciornei <ioana.ciornei@nxp.com>
Link: https://patch.msgid.link/eec27f30-b43f-42b6-b8ee-04a6f83423b6@stanley.mountain
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c | 7 ++++---
 1 file changed, 4 insertions(+), 3 deletions(-)

diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c
index a71f848adc05..a293b08f36d4 100644
--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c
+++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c
@@ -2638,13 +2638,14 @@ static int dpaa2_switch_refill_bp(struct ethsw_core *ethsw)
 
 static int dpaa2_switch_seed_bp(struct ethsw_core *ethsw)
 {
-	int *count, i;
+	int *count, ret, i;
 
 	for (i = 0; i < DPAA2_ETHSW_NUM_BUFS; i += BUFS_PER_CMD) {
+		ret = dpaa2_switch_add_bufs(ethsw, ethsw->bpid);
 		count = &ethsw->buf_count;
-		*count += dpaa2_switch_add_bufs(ethsw, ethsw->bpid);
+		*count += ret;
 
-		if (unlikely(*count < BUFS_PER_CMD))
+		if (unlikely(ret < BUFS_PER_CMD))
 			return -ENOMEM;
 	}
 

From 80a1e7b83bb1834b5568a3872e64c05795d88f31 Mon Sep 17 00:00:00 2001
From: Nikolay Kuratov <kniv@yandex-team.ru>
Date: Mon, 19 Aug 2024 10:54:08 +0300
Subject: [PATCH 44/82] cxgb4: add forgotten u64 ivlan cast before shift

It is done everywhere in cxgb4 code, e.g. in is_filter_exact_match()
There is no reason it should not be done here

Found by Linux Verification Center (linuxtesting.org) with SVACE

Signed-off-by: Nikolay Kuratov <kniv@yandex-team.ru>
Cc: stable@vger.kernel.org
Fixes: 12b276fbf6e0 ("cxgb4: add support to create hash filters")
Reviewed-by: Simon Horman <horms@kernel.org>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Link: https://patch.msgid.link/20240819075408.92378-1-kniv@yandex-team.ru
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c
index 786ceae34488..dd9e68465e69 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c
@@ -1244,7 +1244,8 @@ static u64 hash_filter_ntuple(struct ch_filter_specification *fs,
 	 * in the Compressed Filter Tuple.
 	 */
 	if (tp->vlan_shift >= 0 && fs->mask.ivlan)
-		ntuple |= (FT_VLAN_VLD_F | fs->val.ivlan) << tp->vlan_shift;
+		ntuple |= (u64)(FT_VLAN_VLD_F |
+				fs->val.ivlan) << tp->vlan_shift;
 
 	if (tp->port_shift >= 0 && fs->mask.iport)
 		ntuple |= (u64)fs->val.iport << tp->port_shift;

From 8aba27c4a5020abdf60149239198297f88338a8d Mon Sep 17 00:00:00 2001
From: Paolo Abeni <pabeni@redhat.com>
Date: Fri, 16 Aug 2024 17:20:34 +0200
Subject: [PATCH 45/82] igb: cope with large MAX_SKB_FRAGS

Sabrina reports that the igb driver does not cope well with large
MAX_SKB_FRAG values: setting MAX_SKB_FRAG to 45 causes payload
corruption on TX.

An easy reproducer is to run ssh to connect to the machine.  With
MAX_SKB_FRAGS=17 it works, with MAX_SKB_FRAGS=45 it fails.  This has
been reported originally in
https://bugzilla.redhat.com/show_bug.cgi?id=2265320

The root cause of the issue is that the driver does not take into
account properly the (possibly large) shared info size when selecting
the ring layout, and will try to fit two packets inside the same 4K
page even when the 1st fraglist will trump over the 2nd head.

Address the issue by checking if 2K buffers are insufficient.

Fixes: 3948b05950fd ("net: introduce a config option to tweak MAX_SKB_FRAGS")
Reported-by: Jan Tluka <jtluka@redhat.com>
Reported-by: Jirka Hladky <jhladky@redhat.com>
Reported-by: Sabrina Dubroca <sd@queasysnail.net>
Tested-by: Sabrina Dubroca <sd@queasysnail.net>
Tested-by: Corinna Vinschen <vinschen@redhat.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
Signed-off-by: Corinna Vinschen <vinschen@redhat.com>
Link: https://patch.msgid.link/20240816152034.1453285-1-vinschen@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/intel/igb/igb_main.c | 1 +
 1 file changed, 1 insertion(+)

diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
index 11be39f435f3..33a42b4c21e0 100644
--- a/drivers/net/ethernet/intel/igb/igb_main.c
+++ b/drivers/net/ethernet/intel/igb/igb_main.c
@@ -4808,6 +4808,7 @@ static void igb_set_rx_buffer_len(struct igb_adapter *adapter,
 
 #if (PAGE_SIZE < 8192)
 	if (adapter->max_frame_size > IGB_MAX_FRAME_BUILD_SKB ||
+	    IGB_2K_TOO_SMALL_WITH_PADDING ||
 	    rd32(E1000_RCTL) & E1000_RCTL_SBP)
 		set_ring_uses_large_buffer(rx_ring);
 #endif

From 6efea5135417ae8194485d1d05ea79a21cf1a11c Mon Sep 17 00:00:00 2001
From: Martin Whitaker <foss@martin-whitaker.me.uk>
Date: Sat, 17 Aug 2024 10:41:41 +0100
Subject: [PATCH 46/82] net: dsa: microchip: fix PTP config failure when using
 multiple ports

When performing the port_hwtstamp_set operation, ptp_schedule_worker()
will be called if hardware timestamoing is enabled on any of the ports.
When using multiple ports for PTP, port_hwtstamp_set is executed for
each port. When called for the first time ptp_schedule_worker() returns
0. On subsequent calls it returns 1, indicating the worker is already
scheduled. Currently the ksz driver treats 1 as an error and fails to
complete the port_hwtstamp_set operation, thus leaving the timestamping
configuration for those ports unchanged.

This patch fixes this by ignoring the ptp_schedule_worker() return
value.

Cc: stable@vger.kernel.org
Link: https://lore.kernel.org/7aae307a-35ca-4209-a850-7b2749d40f90@martin-whitaker.me.uk
Fixes: bb01ad30570b0 ("net: dsa: microchip: ptp: manipulating absolute time using ptp hw clock")
Signed-off-by: Martin Whitaker <foss@martin-whitaker.me.uk>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Acked-by: Arun Ramadoss <arun.ramadoss@microchip.com>
Link: https://patch.msgid.link/20240817094141.3332-1-foss@martin-whitaker.me.uk
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/dsa/microchip/ksz_ptp.c | 5 +----
 1 file changed, 1 insertion(+), 4 deletions(-)

diff --git a/drivers/net/dsa/microchip/ksz_ptp.c b/drivers/net/dsa/microchip/ksz_ptp.c
index f0bd46e5d4ec..050f17c43ef6 100644
--- a/drivers/net/dsa/microchip/ksz_ptp.c
+++ b/drivers/net/dsa/microchip/ksz_ptp.c
@@ -266,7 +266,6 @@ static int ksz_ptp_enable_mode(struct ksz_device *dev)
 	struct ksz_port *prt;
 	struct dsa_port *dp;
 	bool tag_en = false;
-	int ret;
 
 	dsa_switch_for_each_user_port(dp, dev->ds) {
 		prt = &dev->ports[dp->index];
@@ -277,9 +276,7 @@ static int ksz_ptp_enable_mode(struct ksz_device *dev)
 	}
 
 	if (tag_en) {
-		ret = ptp_schedule_worker(ptp_data->clock, 0);
-		if (ret)
-			return ret;
+		ptp_schedule_worker(ptp_data->clock, 0);
 	} else {
 		ptp_cancel_worker_sync(ptp_data->clock);
 	}

From 528876d867a23b5198022baf2e388052ca67c952 Mon Sep 17 00:00:00 2001
From: Joseph Huang <Joseph.Huang@garmin.com>
Date: Mon, 19 Aug 2024 19:52:50 -0400
Subject: [PATCH 47/82] net: dsa: mv88e6xxx: Fix out-of-bound access

If an ATU violation was caused by a CPU Load operation, the SPID could
be larger than DSA_MAX_PORTS (the size of mv88e6xxx_chip.ports[] array).

Fixes: 75c05a74e745 ("net: dsa: mv88e6xxx: Fix counting of ATU violations")
Signed-off-by: Joseph Huang <Joseph.Huang@garmin.com>
Reviewed-by: Andrew Lunn <andrew@lunn.ch>
Link: https://patch.msgid.link/20240819235251.1331763-1-Joseph.Huang@garmin.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/dsa/mv88e6xxx/global1_atu.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/dsa/mv88e6xxx/global1_atu.c b/drivers/net/dsa/mv88e6xxx/global1_atu.c
index ce3b3690c3c0..c47f068f56b3 100644
--- a/drivers/net/dsa/mv88e6xxx/global1_atu.c
+++ b/drivers/net/dsa/mv88e6xxx/global1_atu.c
@@ -457,7 +457,8 @@ static irqreturn_t mv88e6xxx_g1_atu_prob_irq_thread_fn(int irq, void *dev_id)
 		trace_mv88e6xxx_atu_full_violation(chip->dev, spid,
 						   entry.portvec, entry.mac,
 						   fid);
-		chip->ports[spid].atu_full_violation++;
+		if (spid < ARRAY_SIZE(chip->ports))
+			chip->ports[spid].atu_full_violation++;
 	}
 
 	return IRQ_HANDLED;

From c07ff8592d57ed258afee5a5e04991a48dbaf382 Mon Sep 17 00:00:00 2001
From: Stephen Hemminger <stephen@networkplumber.org>
Date: Mon, 19 Aug 2024 10:56:45 -0700
Subject: [PATCH 48/82] netem: fix return value if duplicate enqueue fails

There is a bug in netem_enqueue() introduced by
commit 5845f706388a ("net: netem: fix skb length BUG_ON in __skb_to_sgvec")
that can lead to a use-after-free.

This commit made netem_enqueue() always return NET_XMIT_SUCCESS
when a packet is duplicated, which can cause the parent qdisc's q.qlen
to be mistakenly incremented. When this happens qlen_notify() may be
skipped on the parent during destruction, leaving a dangling pointer
for some classful qdiscs like DRR.

There are two ways for the bug happen:

- If the duplicated packet is dropped by rootq->enqueue() and then
  the original packet is also dropped.
- If rootq->enqueue() sends the duplicated packet to a different qdisc
  and the original packet is dropped.

In both cases NET_XMIT_SUCCESS is returned even though no packets
are enqueued at the netem qdisc.

The fix is to defer the enqueue of the duplicate packet until after
the original packet has been guaranteed to return NET_XMIT_SUCCESS.

Fixes: 5845f706388a ("net: netem: fix skb length BUG_ON in __skb_to_sgvec")
Reported-by: Budimir Markovic <markovicbudimir@gmail.com>
Signed-off-by: Stephen Hemminger <stephen@networkplumber.org>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20240819175753.5151-1-stephen@networkplumber.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/sched/sch_netem.c | 47 ++++++++++++++++++++++++++-----------------
 1 file changed, 29 insertions(+), 18 deletions(-)

diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c
index edc72962ae63..0f8d581438c3 100644
--- a/net/sched/sch_netem.c
+++ b/net/sched/sch_netem.c
@@ -446,12 +446,10 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 	struct netem_sched_data *q = qdisc_priv(sch);
 	/* We don't fill cb now as skb_unshare() may invalidate it */
 	struct netem_skb_cb *cb;
-	struct sk_buff *skb2;
+	struct sk_buff *skb2 = NULL;
 	struct sk_buff *segs = NULL;
 	unsigned int prev_len = qdisc_pkt_len(skb);
 	int count = 1;
-	int rc = NET_XMIT_SUCCESS;
-	int rc_drop = NET_XMIT_DROP;
 
 	/* Do not fool qdisc_drop_all() */
 	skb->prev = NULL;
@@ -480,19 +478,11 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 		skb_orphan_partial(skb);
 
 	/*
-	 * If we need to duplicate packet, then re-insert at top of the
-	 * qdisc tree, since parent queuer expects that only one
-	 * skb will be queued.
+	 * If we need to duplicate packet, then clone it before
+	 * original is modified.
 	 */
-	if (count > 1 && (skb2 = skb_clone(skb, GFP_ATOMIC)) != NULL) {
-		struct Qdisc *rootq = qdisc_root_bh(sch);
-		u32 dupsave = q->duplicate; /* prevent duplicating a dup... */
-
-		q->duplicate = 0;
-		rootq->enqueue(skb2, rootq, to_free);
-		q->duplicate = dupsave;
-		rc_drop = NET_XMIT_SUCCESS;
-	}
+	if (count > 1)
+		skb2 = skb_clone(skb, GFP_ATOMIC);
 
 	/*
 	 * Randomized packet corruption.
@@ -504,7 +494,8 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 		if (skb_is_gso(skb)) {
 			skb = netem_segment(skb, sch, to_free);
 			if (!skb)
-				return rc_drop;
+				goto finish_segs;
+
 			segs = skb->next;
 			skb_mark_not_on_list(skb);
 			qdisc_skb_cb(skb)->pkt_len = skb->len;
@@ -530,7 +521,24 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 		/* re-link segs, so that qdisc_drop_all() frees them all */
 		skb->next = segs;
 		qdisc_drop_all(skb, sch, to_free);
-		return rc_drop;
+		if (skb2)
+			__qdisc_drop(skb2, to_free);
+		return NET_XMIT_DROP;
+	}
+
+	/*
+	 * If doing duplication then re-insert at top of the
+	 * qdisc tree, since parent queuer expects that only one
+	 * skb will be queued.
+	 */
+	if (skb2) {
+		struct Qdisc *rootq = qdisc_root_bh(sch);
+		u32 dupsave = q->duplicate; /* prevent duplicating a dup... */
+
+		q->duplicate = 0;
+		rootq->enqueue(skb2, rootq, to_free);
+		q->duplicate = dupsave;
+		skb2 = NULL;
 	}
 
 	qdisc_qstats_backlog_inc(sch, skb);
@@ -601,9 +609,12 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 	}
 
 finish_segs:
+	if (skb2)
+		__qdisc_drop(skb2, to_free);
+
 	if (segs) {
 		unsigned int len, last_len;
-		int nb;
+		int rc, nb;
 
 		len = skb ? skb->len : 0;
 		nb = skb ? 1 : 0;

From e255683c06df572ead96db5efb5d21be30c0efaa Mon Sep 17 00:00:00 2001
From: "Matthieu Baerts (NGI0)" <matttbe@kernel.org>
Date: Mon, 19 Aug 2024 21:45:19 +0200
Subject: [PATCH 49/82] mptcp: pm: re-using ID of unused removed ADD_ADDR

If no subflow is attached to the 'signal' endpoint that is being
removed, the addr ID will not be marked as available again.

Mark the linked ID as available when removing the address entry from the
list to cover this case.

Fixes: b6c08380860b ("mptcp: remove addr and subflow in PM netlink")
Cc: stable@vger.kernel.org
Reviewed-by: Mat Martineau <martineau@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20240819-net-mptcp-pm-reusing-id-v1-1-38035d40de5b@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/mptcp/pm_netlink.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c
index 4cae2aa7be5c..26f0329e16bb 100644
--- a/net/mptcp/pm_netlink.c
+++ b/net/mptcp/pm_netlink.c
@@ -1431,7 +1431,10 @@ static bool mptcp_pm_remove_anno_addr(struct mptcp_sock *msk,
 	ret = remove_anno_list_by_saddr(msk, addr);
 	if (ret || force) {
 		spin_lock_bh(&msk->pm.lock);
-		msk->pm.add_addr_signaled -= ret;
+		if (ret) {
+			__set_bit(addr->id, msk->pm.id_avail_bitmap);
+			msk->pm.add_addr_signaled--;
+		}
 		mptcp_pm_remove_addr(msk, &list);
 		spin_unlock_bh(&msk->pm.lock);
 	}

From a13d5aad4dd9a309eecdc33cfd75045bd5f376a3 Mon Sep 17 00:00:00 2001
From: "Matthieu Baerts (NGI0)" <matttbe@kernel.org>
Date: Mon, 19 Aug 2024 21:45:20 +0200
Subject: [PATCH 50/82] selftests: mptcp: join: check re-using ID of unused
 ADD_ADDR

This test extends "delete re-add signal" to validate the previous
commit. An extra address is announced by the server, but this address
cannot be used by the client. The result is that no subflow will be
established to this address.

Later, the server will delete this extra endpoint, and set a new one,
with a valid address, but re-using the same ID. Before the previous
commit, the server would not have been able to announce this new
address.

While at it, extra checks have been added to validate the expected
numbers of MPJ, ADD_ADDR and RM_ADDR.

The 'Fixes' tag here below is the same as the one from the previous
commit: this patch here is not fixing anything wrong in the selftests,
but it validates the previous fix for an issue introduced by this commit
ID.

Fixes: b6c08380860b ("mptcp: remove addr and subflow in PM netlink")
Cc: stable@vger.kernel.org
Reviewed-by: Mat Martineau <martineau@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20240819-net-mptcp-pm-reusing-id-v1-2-38035d40de5b@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../testing/selftests/net/mptcp/mptcp_join.sh  | 18 +++++++++++++-----
 1 file changed, 13 insertions(+), 5 deletions(-)

diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh
index 9ea6d698e9d3..25077ccf31d2 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_join.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh
@@ -3601,9 +3601,11 @@ endpoint_tests()
 	# remove and re-add
 	if reset "delete re-add signal" &&
 	   mptcp_lib_kallsyms_has "subflow_rebuild_header$"; then
-		pm_nl_set_limits $ns1 1 1
-		pm_nl_set_limits $ns2 1 1
+		pm_nl_set_limits $ns1 0 2
+		pm_nl_set_limits $ns2 2 2
 		pm_nl_add_endpoint $ns1 10.0.2.1 id 1 flags signal
+		# broadcast IP: no packet for this address will be received on ns1
+		pm_nl_add_endpoint $ns1 224.0.0.1 id 2 flags signal
 		test_linkfail=4 speed=20 \
 			run_tests $ns1 $ns2 10.0.1.1 &
 		local tests_pid=$!
@@ -3615,15 +3617,21 @@ endpoint_tests()
 		chk_mptcp_info subflows 1 subflows 1
 
 		pm_nl_del_endpoint $ns1 1 10.0.2.1
+		pm_nl_del_endpoint $ns1 2 224.0.0.1
 		sleep 0.5
 		chk_subflow_nr "after delete" 1
 		chk_mptcp_info subflows 0 subflows 0
 
-		pm_nl_add_endpoint $ns1 10.0.2.1 flags signal
+		pm_nl_add_endpoint $ns1 10.0.2.1 id 1 flags signal
+		pm_nl_add_endpoint $ns1 10.0.3.1 id 2 flags signal
 		wait_mpj $ns2
-		chk_subflow_nr "after re-add" 2
-		chk_mptcp_info subflows 1 subflows 1
+		chk_subflow_nr "after re-add" 3
+		chk_mptcp_info subflows 2 subflows 2
 		mptcp_lib_kill_wait $tests_pid
+
+		chk_join_nr 3 3 3
+		chk_add_nr 4 4
+		chk_rm_nr 2 1 invert
 	fi
 
 }

From edd8b5d868a4d459f3065493001e293901af758d Mon Sep 17 00:00:00 2001
From: "Matthieu Baerts (NGI0)" <matttbe@kernel.org>
Date: Mon, 19 Aug 2024 21:45:21 +0200
Subject: [PATCH 51/82] mptcp: pm: re-using ID of unused removed subflows

If no subflow is attached to the 'subflow' endpoint that is being
removed, the addr ID will not be marked as available again.

Mark the linked ID as available when removing the 'subflow' endpoint if
no subflow is attached to it.

While at it, the local_addr_used counter is decremented if the ID was
marked as being used to reflect the reality, but also to allow adding
new endpoints after that.

Fixes: b6c08380860b ("mptcp: remove addr and subflow in PM netlink")
Cc: stable@vger.kernel.org
Reviewed-by: Mat Martineau <martineau@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20240819-net-mptcp-pm-reusing-id-v1-3-38035d40de5b@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/mptcp/pm_netlink.c | 11 ++++++++++-
 1 file changed, 10 insertions(+), 1 deletion(-)

diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c
index 26f0329e16bb..8b232a210a06 100644
--- a/net/mptcp/pm_netlink.c
+++ b/net/mptcp/pm_netlink.c
@@ -1469,8 +1469,17 @@ static int mptcp_nl_remove_subflow_and_signal_addr(struct net *net,
 		remove_subflow = lookup_subflow_by_saddr(&msk->conn_list, addr);
 		mptcp_pm_remove_anno_addr(msk, addr, remove_subflow &&
 					  !(entry->flags & MPTCP_PM_ADDR_FLAG_IMPLICIT));
-		if (remove_subflow)
+
+		if (remove_subflow) {
 			mptcp_pm_remove_subflow(msk, &list);
+		} else if (entry->flags & MPTCP_PM_ADDR_FLAG_SUBFLOW) {
+			/* If the subflow has been used, but now closed */
+			spin_lock_bh(&msk->pm.lock);
+			if (!__test_and_set_bit(entry->addr.id, msk->pm.id_avail_bitmap))
+				msk->pm.local_addr_used--;
+			spin_unlock_bh(&msk->pm.lock);
+		}
+
 		release_sock(sk);
 
 next:

From 65fb58afa341ad68e71e5c4d816b407e6a683a66 Mon Sep 17 00:00:00 2001
From: "Matthieu Baerts (NGI0)" <matttbe@kernel.org>
Date: Mon, 19 Aug 2024 21:45:22 +0200
Subject: [PATCH 52/82] selftests: mptcp: join: check re-using ID of closed
 subflow

This test extends "delete and re-add" to validate the previous commit. A
new 'subflow' endpoint is added, but the subflow request will be
rejected. The result is that no subflow will be established from this
address.

Later, the endpoint is removed and re-added after having cleared the
firewall rule. Before the previous commit, the client would not have
been able to create this new subflow.

While at it, extra checks have been added to validate the expected
numbers of MPJ and RM_ADDR.

The 'Fixes' tag here below is the same as the one from the previous
commit: this patch here is not fixing anything wrong in the selftests,
but it validates the previous fix for an issue introduced by this commit
ID.

Fixes: b6c08380860b ("mptcp: remove addr and subflow in PM netlink")
Cc: stable@vger.kernel.org
Reviewed-by: Mat Martineau <martineau@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20240819-net-mptcp-pm-reusing-id-v1-4-38035d40de5b@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../testing/selftests/net/mptcp/mptcp_join.sh | 27 +++++++++++++++----
 1 file changed, 22 insertions(+), 5 deletions(-)

diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh
index 25077ccf31d2..fbb0174145ad 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_join.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh
@@ -436,9 +436,10 @@ reset_with_tcp_filter()
 	local ns="${!1}"
 	local src="${2}"
 	local target="${3}"
+	local chain="${4:-INPUT}"
 
 	if ! ip netns exec "${ns}" ${iptables} \
-			-A INPUT \
+			-A "${chain}" \
 			-s "${src}" \
 			-p tcp \
 			-j "${target}"; then
@@ -3571,10 +3572,10 @@ endpoint_tests()
 		mptcp_lib_kill_wait $tests_pid
 	fi
 
-	if reset "delete and re-add" &&
+	if reset_with_tcp_filter "delete and re-add" ns2 10.0.3.2 REJECT OUTPUT &&
 	   mptcp_lib_kallsyms_has "subflow_rebuild_header$"; then
-		pm_nl_set_limits $ns1 1 1
-		pm_nl_set_limits $ns2 1 1
+		pm_nl_set_limits $ns1 0 2
+		pm_nl_set_limits $ns2 0 2
 		pm_nl_add_endpoint $ns2 10.0.2.2 id 2 dev ns2eth2 flags subflow
 		test_linkfail=4 speed=20 \
 			run_tests $ns1 $ns2 10.0.1.1 &
@@ -3591,11 +3592,27 @@ endpoint_tests()
 		chk_subflow_nr "after delete" 1
 		chk_mptcp_info subflows 0 subflows 0
 
-		pm_nl_add_endpoint $ns2 10.0.2.2 dev ns2eth2 flags subflow
+		pm_nl_add_endpoint $ns2 10.0.2.2 id 2 dev ns2eth2 flags subflow
 		wait_mpj $ns2
 		chk_subflow_nr "after re-add" 2
 		chk_mptcp_info subflows 1 subflows 1
+
+		pm_nl_add_endpoint $ns2 10.0.3.2 id 3 flags subflow
+		wait_attempt_fail $ns2
+		chk_subflow_nr "after new reject" 2
+		chk_mptcp_info subflows 1 subflows 1
+
+		ip netns exec "${ns2}" ${iptables} -D OUTPUT -s "10.0.3.2" -p tcp -j REJECT
+		pm_nl_del_endpoint $ns2 3 10.0.3.2
+		pm_nl_add_endpoint $ns2 10.0.3.2 id 3 flags subflow
+		wait_mpj $ns2
+		chk_subflow_nr "after no reject" 3
+		chk_mptcp_info subflows 2 subflows 2
+
 		mptcp_lib_kill_wait $tests_pid
+
+		chk_join_nr 3 3 3
+		chk_rm_nr 1 1
 	fi
 
 	# remove and re-add

From ef34a6ea0cab1800f4b3c9c3c2cefd5091e03379 Mon Sep 17 00:00:00 2001
From: "Matthieu Baerts (NGI0)" <matttbe@kernel.org>
Date: Mon, 19 Aug 2024 21:45:23 +0200
Subject: [PATCH 53/82] mptcp: pm: re-using ID of unused flushed subflows

If no subflows are attached to the 'subflow' endpoints that are being
flushed, the corresponding addr IDs will not be marked as available
again.

Mark all ID as being available when flushing all the 'subflow'
endpoints, and reset local_addr_used counter to cover these cases.

Note that mptcp_pm_remove_addrs_and_subflows() helper is only called for
flushing operations, not to remove a specific set of addresses and
subflows.

Fixes: 06faa2271034 ("mptcp: remove multi addresses and subflows in PM")
Cc: stable@vger.kernel.org
Reviewed-by: Mat Martineau <martineau@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20240819-net-mptcp-pm-reusing-id-v1-5-38035d40de5b@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/mptcp/pm_netlink.c | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c
index 8b232a210a06..2c26696b820e 100644
--- a/net/mptcp/pm_netlink.c
+++ b/net/mptcp/pm_netlink.c
@@ -1623,8 +1623,15 @@ static void mptcp_pm_remove_addrs_and_subflows(struct mptcp_sock *msk,
 		mptcp_pm_remove_addr(msk, &alist);
 		spin_unlock_bh(&msk->pm.lock);
 	}
+
 	if (slist.nr)
 		mptcp_pm_remove_subflow(msk, &slist);
+
+	/* Reset counters: maybe some subflows have been removed before */
+	spin_lock_bh(&msk->pm.lock);
+	bitmap_fill(msk->pm.id_avail_bitmap, MPTCP_PM_MAX_ADDR_ID + 1);
+	msk->pm.local_addr_used = 0;
+	spin_unlock_bh(&msk->pm.lock);
 }
 
 static void mptcp_nl_remove_addrs_list(struct net *net,

From e06959e9eebdfea4654390f53b65cff57691872e Mon Sep 17 00:00:00 2001
From: "Matthieu Baerts (NGI0)" <matttbe@kernel.org>
Date: Mon, 19 Aug 2024 21:45:24 +0200
Subject: [PATCH 54/82] selftests: mptcp: join: test for flush/re-add endpoints

After having flushed endpoints that didn't cause the creation of new
subflows, it is important to check endpoints can be re-created, re-using
previously used IDs.

Before the previous commit, the client would not have been able to
re-create the subflow that was previously rejected.

The 'Fixes' tag here below is the same as the one from the previous
commit: this patch here is not fixing anything wrong in the selftests,
but it validates the previous fix for an issue introduced by this commit
ID.

Fixes: 06faa2271034 ("mptcp: remove multi addresses and subflows in PM")
Cc: stable@vger.kernel.org
Reviewed-by: Mat Martineau <martineau@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20240819-net-mptcp-pm-reusing-id-v1-6-38035d40de5b@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 .../testing/selftests/net/mptcp/mptcp_join.sh | 30 +++++++++++++++++++
 1 file changed, 30 insertions(+)

diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh
index fbb0174145ad..f609c02c6123 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_join.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh
@@ -3651,6 +3651,36 @@ endpoint_tests()
 		chk_rm_nr 2 1 invert
 	fi
 
+	# flush and re-add
+	if reset_with_tcp_filter "flush re-add" ns2 10.0.3.2 REJECT OUTPUT &&
+	   mptcp_lib_kallsyms_has "subflow_rebuild_header$"; then
+		pm_nl_set_limits $ns1 0 2
+		pm_nl_set_limits $ns2 1 2
+		# broadcast IP: no packet for this address will be received on ns1
+		pm_nl_add_endpoint $ns1 224.0.0.1 id 2 flags signal
+		pm_nl_add_endpoint $ns2 10.0.3.2 id 3 flags subflow
+		test_linkfail=4 speed=20 \
+			run_tests $ns1 $ns2 10.0.1.1 &
+		local tests_pid=$!
+
+		wait_attempt_fail $ns2
+		chk_subflow_nr "before flush" 1
+		chk_mptcp_info subflows 0 subflows 0
+
+		pm_nl_flush_endpoint $ns2
+		pm_nl_flush_endpoint $ns1
+		wait_rm_addr $ns2 0
+		ip netns exec "${ns2}" ${iptables} -D OUTPUT -s "10.0.3.2" -p tcp -j REJECT
+		pm_nl_add_endpoint $ns2 10.0.3.2 id 3 flags subflow
+		wait_mpj $ns2
+		pm_nl_add_endpoint $ns1 10.0.3.1 id 2 flags signal
+		wait_mpj $ns2
+		mptcp_lib_kill_wait $tests_pid
+
+		chk_join_nr 2 2 2
+		chk_add_nr 2 2
+		chk_rm_nr 1 0 invert
+	fi
 }
 
 # [$1: error message]

From f448451aa62d54be16acb0034223c17e0d12bc69 Mon Sep 17 00:00:00 2001
From: "Matthieu Baerts (NGI0)" <matttbe@kernel.org>
Date: Mon, 19 Aug 2024 21:45:25 +0200
Subject: [PATCH 55/82] mptcp: pm: remove mptcp_pm_remove_subflow()

This helper is confusing. It is in pm.c, but it is specific to the
in-kernel PM and it cannot be used by the userspace one. Also, it simply
calls one in-kernel specific function with the PM lock, while the
similar mptcp_pm_remove_addr() helper requires the PM lock.

What's left is the pr_debug(), which is not that useful, because a
similar one is present in the only function called by this helper:

  mptcp_pm_nl_rm_subflow_received()

After these modifications, this helper can be marked as 'static', and
the lock can be taken only once in mptcp_pm_flush_addrs_and_subflows().

Note that it is not a bug fix, but it will help backporting the
following commits.

Fixes: 0ee4261a3681 ("mptcp: implement mptcp_pm_remove_subflow")
Cc: stable@vger.kernel.org
Reviewed-by: Mat Martineau <martineau@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20240819-net-mptcp-pm-reusing-id-v1-7-38035d40de5b@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/mptcp/pm.c         | 10 ----------
 net/mptcp/pm_netlink.c | 16 +++++++---------
 net/mptcp/protocol.h   |  3 ---
 3 files changed, 7 insertions(+), 22 deletions(-)

diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c
index 23bb89c94e90..925123e99889 100644
--- a/net/mptcp/pm.c
+++ b/net/mptcp/pm.c
@@ -60,16 +60,6 @@ int mptcp_pm_remove_addr(struct mptcp_sock *msk, const struct mptcp_rm_list *rm_
 	return 0;
 }
 
-int mptcp_pm_remove_subflow(struct mptcp_sock *msk, const struct mptcp_rm_list *rm_list)
-{
-	pr_debug("msk=%p, rm_list_nr=%d", msk, rm_list->nr);
-
-	spin_lock_bh(&msk->pm.lock);
-	mptcp_pm_nl_rm_subflow_received(msk, rm_list);
-	spin_unlock_bh(&msk->pm.lock);
-	return 0;
-}
-
 /* path manager event handlers */
 
 void mptcp_pm_new_connection(struct mptcp_sock *msk, const struct sock *ssk, int server_side)
diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c
index 2c26696b820e..44fc1c5959ac 100644
--- a/net/mptcp/pm_netlink.c
+++ b/net/mptcp/pm_netlink.c
@@ -857,8 +857,8 @@ static void mptcp_pm_nl_rm_addr_received(struct mptcp_sock *msk)
 	mptcp_pm_nl_rm_addr_or_subflow(msk, &msk->pm.rm_list_rx, MPTCP_MIB_RMADDR);
 }
 
-void mptcp_pm_nl_rm_subflow_received(struct mptcp_sock *msk,
-				     const struct mptcp_rm_list *rm_list)
+static void mptcp_pm_nl_rm_subflow_received(struct mptcp_sock *msk,
+					    const struct mptcp_rm_list *rm_list)
 {
 	mptcp_pm_nl_rm_addr_or_subflow(msk, rm_list, MPTCP_MIB_RMSUBFLOW);
 }
@@ -1471,7 +1471,9 @@ static int mptcp_nl_remove_subflow_and_signal_addr(struct net *net,
 					  !(entry->flags & MPTCP_PM_ADDR_FLAG_IMPLICIT));
 
 		if (remove_subflow) {
-			mptcp_pm_remove_subflow(msk, &list);
+			spin_lock_bh(&msk->pm.lock);
+			mptcp_pm_nl_rm_subflow_received(msk, &list);
+			spin_unlock_bh(&msk->pm.lock);
 		} else if (entry->flags & MPTCP_PM_ADDR_FLAG_SUBFLOW) {
 			/* If the subflow has been used, but now closed */
 			spin_lock_bh(&msk->pm.lock);
@@ -1617,18 +1619,14 @@ static void mptcp_pm_remove_addrs_and_subflows(struct mptcp_sock *msk,
 			alist.ids[alist.nr++] = entry->addr.id;
 	}
 
+	spin_lock_bh(&msk->pm.lock);
 	if (alist.nr) {
-		spin_lock_bh(&msk->pm.lock);
 		msk->pm.add_addr_signaled -= alist.nr;
 		mptcp_pm_remove_addr(msk, &alist);
-		spin_unlock_bh(&msk->pm.lock);
 	}
-
 	if (slist.nr)
-		mptcp_pm_remove_subflow(msk, &slist);
-
+		mptcp_pm_nl_rm_subflow_received(msk, &slist);
 	/* Reset counters: maybe some subflows have been removed before */
-	spin_lock_bh(&msk->pm.lock);
 	bitmap_fill(msk->pm.id_avail_bitmap, MPTCP_PM_MAX_ADDR_ID + 1);
 	msk->pm.local_addr_used = 0;
 	spin_unlock_bh(&msk->pm.lock);
diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
index 60c6b073d65f..a1c1b0ff1ce1 100644
--- a/net/mptcp/protocol.h
+++ b/net/mptcp/protocol.h
@@ -1026,7 +1026,6 @@ int mptcp_pm_announce_addr(struct mptcp_sock *msk,
 			   const struct mptcp_addr_info *addr,
 			   bool echo);
 int mptcp_pm_remove_addr(struct mptcp_sock *msk, const struct mptcp_rm_list *rm_list);
-int mptcp_pm_remove_subflow(struct mptcp_sock *msk, const struct mptcp_rm_list *rm_list);
 void mptcp_pm_remove_addrs(struct mptcp_sock *msk, struct list_head *rm_list);
 
 void mptcp_free_local_addr_list(struct mptcp_sock *msk);
@@ -1133,8 +1132,6 @@ static inline u8 subflow_get_local_id(const struct mptcp_subflow_context *subflo
 
 void __init mptcp_pm_nl_init(void);
 void mptcp_pm_nl_work(struct mptcp_sock *msk);
-void mptcp_pm_nl_rm_subflow_received(struct mptcp_sock *msk,
-				     const struct mptcp_rm_list *rm_list);
 unsigned int mptcp_pm_get_add_addr_signal_max(const struct mptcp_sock *msk);
 unsigned int mptcp_pm_get_add_addr_accept_max(const struct mptcp_sock *msk);
 unsigned int mptcp_pm_get_subflows_max(const struct mptcp_sock *msk);

From 322ea3778965da72862cca2a0c50253aacf65fe6 Mon Sep 17 00:00:00 2001
From: "Matthieu Baerts (NGI0)" <matttbe@kernel.org>
Date: Mon, 19 Aug 2024 21:45:26 +0200
Subject: [PATCH 56/82] mptcp: pm: only mark 'subflow' endp as available

Adding the following warning ...

  WARN_ON_ONCE(msk->pm.local_addr_used == 0)

... before decrementing the local_addr_used counter helped to find a bug
when running the "remove single address" subtest from the mptcp_join.sh
selftests.

Removing a 'signal' endpoint will trigger the removal of all subflows
linked to this endpoint via mptcp_pm_nl_rm_addr_or_subflow() with
rm_type == MPTCP_MIB_RMSUBFLOW. This will decrement the local_addr_used
counter, which is wrong in this case because this counter is linked to
'subflow' endpoints, and here it is a 'signal' endpoint that is being
removed.

Now, the counter is decremented, only if the ID is being used outside
of mptcp_pm_nl_rm_addr_or_subflow(), only for 'subflow' endpoints, and
if the ID is not 0 -- local_addr_used is not taking into account these
ones. This marking of the ID as being available, and the decrement is
done no matter if a subflow using this ID is currently available,
because the subflow could have been closed before.

Fixes: 06faa2271034 ("mptcp: remove multi addresses and subflows in PM")
Cc: stable@vger.kernel.org
Reviewed-by: Mat Martineau <martineau@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20240819-net-mptcp-pm-reusing-id-v1-8-38035d40de5b@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/mptcp/pm_netlink.c | 26 +++++++++++++++++---------
 1 file changed, 17 insertions(+), 9 deletions(-)

diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c
index 44fc1c5959ac..4cf7cc851f80 100644
--- a/net/mptcp/pm_netlink.c
+++ b/net/mptcp/pm_netlink.c
@@ -833,10 +833,10 @@ static void mptcp_pm_nl_rm_addr_or_subflow(struct mptcp_sock *msk,
 			if (rm_type == MPTCP_MIB_RMSUBFLOW)
 				__MPTCP_INC_STATS(sock_net(sk), rm_type);
 		}
-		if (rm_type == MPTCP_MIB_RMSUBFLOW)
-			__set_bit(rm_id ? rm_id : msk->mpc_endpoint_id, msk->pm.id_avail_bitmap);
-		else if (rm_type == MPTCP_MIB_RMADDR)
+
+		if (rm_type == MPTCP_MIB_RMADDR)
 			__MPTCP_INC_STATS(sock_net(sk), rm_type);
+
 		if (!removed)
 			continue;
 
@@ -846,8 +846,6 @@ static void mptcp_pm_nl_rm_addr_or_subflow(struct mptcp_sock *msk,
 		if (rm_type == MPTCP_MIB_RMADDR) {
 			msk->pm.add_addr_accepted--;
 			WRITE_ONCE(msk->pm.accept_addr, true);
-		} else if (rm_type == MPTCP_MIB_RMSUBFLOW) {
-			msk->pm.local_addr_used--;
 		}
 	}
 }
@@ -1441,6 +1439,14 @@ static bool mptcp_pm_remove_anno_addr(struct mptcp_sock *msk,
 	return ret;
 }
 
+static void __mark_subflow_endp_available(struct mptcp_sock *msk, u8 id)
+{
+	/* If it was marked as used, and not ID 0, decrement local_addr_used */
+	if (!__test_and_set_bit(id ? : msk->mpc_endpoint_id, msk->pm.id_avail_bitmap) &&
+	    id && !WARN_ON_ONCE(msk->pm.local_addr_used == 0))
+		msk->pm.local_addr_used--;
+}
+
 static int mptcp_nl_remove_subflow_and_signal_addr(struct net *net,
 						   const struct mptcp_pm_addr_entry *entry)
 {
@@ -1474,11 +1480,11 @@ static int mptcp_nl_remove_subflow_and_signal_addr(struct net *net,
 			spin_lock_bh(&msk->pm.lock);
 			mptcp_pm_nl_rm_subflow_received(msk, &list);
 			spin_unlock_bh(&msk->pm.lock);
-		} else if (entry->flags & MPTCP_PM_ADDR_FLAG_SUBFLOW) {
-			/* If the subflow has been used, but now closed */
+		}
+
+		if (entry->flags & MPTCP_PM_ADDR_FLAG_SUBFLOW) {
 			spin_lock_bh(&msk->pm.lock);
-			if (!__test_and_set_bit(entry->addr.id, msk->pm.id_avail_bitmap))
-				msk->pm.local_addr_used--;
+			__mark_subflow_endp_available(msk, list.ids[0]);
 			spin_unlock_bh(&msk->pm.lock);
 		}
 
@@ -1516,6 +1522,7 @@ static int mptcp_nl_remove_id_zero_address(struct net *net,
 		spin_lock_bh(&msk->pm.lock);
 		mptcp_pm_remove_addr(msk, &list);
 		mptcp_pm_nl_rm_subflow_received(msk, &list);
+		__mark_subflow_endp_available(msk, 0);
 		spin_unlock_bh(&msk->pm.lock);
 		release_sock(sk);
 
@@ -1917,6 +1924,7 @@ static void mptcp_pm_nl_fullmesh(struct mptcp_sock *msk,
 
 	spin_lock_bh(&msk->pm.lock);
 	mptcp_pm_nl_rm_subflow_received(msk, &list);
+	__mark_subflow_endp_available(msk, list.ids[0]);
 	mptcp_pm_create_subflow_or_signal_addr(msk);
 	spin_unlock_bh(&msk->pm.lock);
 }

From 1c1f721375989579e46741f59523e39ec9b2a9bd Mon Sep 17 00:00:00 2001
From: "Matthieu Baerts (NGI0)" <matttbe@kernel.org>
Date: Mon, 19 Aug 2024 21:45:27 +0200
Subject: [PATCH 57/82] mptcp: pm: only decrement add_addr_accepted for MPJ req

Adding the following warning ...

  WARN_ON_ONCE(msk->pm.add_addr_accepted == 0)

... before decrementing the add_addr_accepted counter helped to find a
bug when running the "remove single subflow" subtest from the
mptcp_join.sh selftest.

Removing a 'subflow' endpoint will first trigger a RM_ADDR, then the
subflow closure. Before this patch, and upon the reception of the
RM_ADDR, the other peer will then try to decrement this
add_addr_accepted. That's not correct because the attached subflows have
not been created upon the reception of an ADD_ADDR.

A way to solve that is to decrement the counter only if the attached
subflow was an MP_JOIN to a remote id that was not 0, and initiated by
the host receiving the RM_ADDR.

Fixes: d0876b2284cf ("mptcp: add the incoming RM_ADDR support")
Cc: stable@vger.kernel.org
Reviewed-by: Mat Martineau <martineau@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20240819-net-mptcp-pm-reusing-id-v1-9-38035d40de5b@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/mptcp/pm_netlink.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c
index 4cf7cc851f80..882781571c7b 100644
--- a/net/mptcp/pm_netlink.c
+++ b/net/mptcp/pm_netlink.c
@@ -829,7 +829,7 @@ static void mptcp_pm_nl_rm_addr_or_subflow(struct mptcp_sock *msk,
 			mptcp_close_ssk(sk, ssk, subflow);
 			spin_lock_bh(&msk->pm.lock);
 
-			removed = true;
+			removed |= subflow->request_join;
 			if (rm_type == MPTCP_MIB_RMSUBFLOW)
 				__MPTCP_INC_STATS(sock_net(sk), rm_type);
 		}
@@ -843,7 +843,11 @@ static void mptcp_pm_nl_rm_addr_or_subflow(struct mptcp_sock *msk,
 		if (!mptcp_pm_is_kernel(msk))
 			continue;
 
-		if (rm_type == MPTCP_MIB_RMADDR) {
+		if (rm_type == MPTCP_MIB_RMADDR && rm_id &&
+		    !WARN_ON_ONCE(msk->pm.add_addr_accepted == 0)) {
+			/* Note: if the subflow has been closed before, this
+			 * add_addr_accepted counter will not be decremented.
+			 */
 			msk->pm.add_addr_accepted--;
 			WRITE_ONCE(msk->pm.accept_addr, true);
 		}

From 0137a3c7c2ea3f9df8ebfc65d78b4ba712a187bb Mon Sep 17 00:00:00 2001
From: "Matthieu Baerts (NGI0)" <matttbe@kernel.org>
Date: Mon, 19 Aug 2024 21:45:28 +0200
Subject: [PATCH 58/82] mptcp: pm: check add_addr_accept_max before accepting
 new ADD_ADDR

The limits might have changed in between, it is best to check them
before accepting new ADD_ADDR.

Fixes: d0876b2284cf ("mptcp: add the incoming RM_ADDR support")
Cc: stable@vger.kernel.org
Reviewed-by: Mat Martineau <martineau@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20240819-net-mptcp-pm-reusing-id-v1-10-38035d40de5b@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/mptcp/pm_netlink.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c
index 882781571c7b..28a9a3726146 100644
--- a/net/mptcp/pm_netlink.c
+++ b/net/mptcp/pm_netlink.c
@@ -848,8 +848,8 @@ static void mptcp_pm_nl_rm_addr_or_subflow(struct mptcp_sock *msk,
 			/* Note: if the subflow has been closed before, this
 			 * add_addr_accepted counter will not be decremented.
 			 */
-			msk->pm.add_addr_accepted--;
-			WRITE_ONCE(msk->pm.accept_addr, true);
+			if (--msk->pm.add_addr_accepted < mptcp_pm_get_add_addr_accept_max(msk))
+				WRITE_ONCE(msk->pm.accept_addr, true);
 		}
 	}
 }

From ca6e55a703ca2894611bb5c5bca8bfd2290fd91e Mon Sep 17 00:00:00 2001
From: "Matthieu Baerts (NGI0)" <matttbe@kernel.org>
Date: Mon, 19 Aug 2024 21:45:29 +0200
Subject: [PATCH 59/82] mptcp: pm: only in-kernel cannot have entries with ID 0

The ID 0 is specific per MPTCP connections. The per netns entries cannot
have this special ID 0 then.

But that's different for the userspace PM where the entries are per
connection, they can then use this special ID 0.

Fixes: f40be0db0b76 ("mptcp: unify pm get_flags_and_ifindex_by_id")
Cc: stable@vger.kernel.org
Acked-by: Geliang Tang <geliang@kernel.org>
Reviewed-by: Mat Martineau <martineau@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20240819-net-mptcp-pm-reusing-id-v1-11-38035d40de5b@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/mptcp/pm.c         | 3 ---
 net/mptcp/pm_netlink.c | 4 ++++
 2 files changed, 4 insertions(+), 3 deletions(-)

diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c
index 925123e99889..3e6e0f5510bb 100644
--- a/net/mptcp/pm.c
+++ b/net/mptcp/pm.c
@@ -434,9 +434,6 @@ int mptcp_pm_get_flags_and_ifindex_by_id(struct mptcp_sock *msk, unsigned int id
 	*flags = 0;
 	*ifindex = 0;
 
-	if (!id)
-		return 0;
-
 	if (mptcp_pm_is_userspace(msk))
 		return mptcp_userspace_pm_get_flags_and_ifindex_by_id(msk, id, flags, ifindex);
 	return mptcp_pm_nl_get_flags_and_ifindex_by_id(msk, id, flags, ifindex);
diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c
index 28a9a3726146..d0a80f537fc3 100644
--- a/net/mptcp/pm_netlink.c
+++ b/net/mptcp/pm_netlink.c
@@ -1395,6 +1395,10 @@ int mptcp_pm_nl_get_flags_and_ifindex_by_id(struct mptcp_sock *msk, unsigned int
 	struct sock *sk = (struct sock *)msk;
 	struct net *net = sock_net(sk);
 
+	/* No entries with ID 0 */
+	if (id == 0)
+		return 0;
+
 	rcu_read_lock();
 	entry = __lookup_addr_by_id(pm_nl_get_pernet(net), id);
 	if (entry) {

From 09355f7abb9fbfc1a240be029837921ea417bf4f Mon Sep 17 00:00:00 2001
From: "Matthieu Baerts (NGI0)" <matttbe@kernel.org>
Date: Mon, 19 Aug 2024 21:45:30 +0200
Subject: [PATCH 60/82] mptcp: pm: fullmesh: select the right ID later

When reacting upon the reception of an ADD_ADDR, the in-kernel PM first
looks for fullmesh endpoints. If there are some, it will pick them,
using their entry ID.

It should set the ID 0 when using the endpoint corresponding to the
initial subflow, it is a special case imposed by the MPTCP specs.

Note that msk->mpc_endpoint_id might not be set when receiving the first
ADD_ADDR from the server. So better to compare the addresses.

Fixes: 1a0d6136c5f0 ("mptcp: local addresses fullmesh")
Cc: stable@vger.kernel.org
Reviewed-by: Mat Martineau <martineau@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20240819-net-mptcp-pm-reusing-id-v1-12-38035d40de5b@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/mptcp/pm_netlink.c | 11 ++++++++++-
 1 file changed, 10 insertions(+), 1 deletion(-)

diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c
index d0a80f537fc3..a2e37ab1c40f 100644
--- a/net/mptcp/pm_netlink.c
+++ b/net/mptcp/pm_netlink.c
@@ -636,6 +636,7 @@ static unsigned int fill_local_addresses_vec(struct mptcp_sock *msk,
 {
 	struct sock *sk = (struct sock *)msk;
 	struct mptcp_pm_addr_entry *entry;
+	struct mptcp_addr_info mpc_addr;
 	struct pm_nl_pernet *pernet;
 	unsigned int subflows_max;
 	int i = 0;
@@ -643,6 +644,8 @@ static unsigned int fill_local_addresses_vec(struct mptcp_sock *msk,
 	pernet = pm_nl_get_pernet_from_msk(msk);
 	subflows_max = mptcp_pm_get_subflows_max(msk);
 
+	mptcp_local_address((struct sock_common *)msk, &mpc_addr);
+
 	rcu_read_lock();
 	list_for_each_entry_rcu(entry, &pernet->local_addr_list, list) {
 		if (!(entry->flags & MPTCP_PM_ADDR_FLAG_FULLMESH))
@@ -653,7 +656,13 @@ static unsigned int fill_local_addresses_vec(struct mptcp_sock *msk,
 
 		if (msk->pm.subflows < subflows_max) {
 			msk->pm.subflows++;
-			addrs[i++] = entry->addr;
+			addrs[i] = entry->addr;
+
+			/* Special case for ID0: set the correct ID */
+			if (mptcp_addresses_equal(&entry->addr, &mpc_addr, entry->addr.port))
+				addrs[i].id = 0;
+
+			i++;
 		}
 	}
 	rcu_read_unlock();

From 4878f9f8421f4587bee7b232c1c8a9d3a7d4d782 Mon Sep 17 00:00:00 2001
From: "Matthieu Baerts (NGI0)" <matttbe@kernel.org>
Date: Mon, 19 Aug 2024 21:45:31 +0200
Subject: [PATCH 61/82] selftests: mptcp: join: validate fullmesh endp on 1st
 sf

This case was not covered, and the wrong ID was set before the previous
commit.

The rest is not modified, it is just that it will increase the code
coverage.

The right address ID can be verified by looking at the packet traces. We
could automate that using Netfilter with some cBPF code for example, but
that's always a bit cryptic. Packetdrill seems better fitted for that.

Fixes: 4f49d63352da ("selftests: mptcp: add fullmesh testcases")
Cc: stable@vger.kernel.org
Reviewed-by: Mat Martineau <martineau@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20240819-net-mptcp-pm-reusing-id-v1-13-38035d40de5b@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/net/mptcp/mptcp_join.sh | 1 +
 1 file changed, 1 insertion(+)

diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh
index f609c02c6123..89e553e0e0c2 100755
--- a/tools/testing/selftests/net/mptcp/mptcp_join.sh
+++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh
@@ -3059,6 +3059,7 @@ fullmesh_tests()
 		pm_nl_set_limits $ns1 1 3
 		pm_nl_set_limits $ns2 1 3
 		pm_nl_add_endpoint $ns1 10.0.2.1 flags signal
+		pm_nl_add_endpoint $ns2 10.0.1.2 flags subflow,fullmesh
 		fullmesh=1 speed=slow \
 			run_tests $ns1 $ns2 10.0.1.1
 		chk_join_nr 3 3 3

From 48e50dcbcbaaf713d82bf2da5c16aeced94ad07d Mon Sep 17 00:00:00 2001
From: "Matthieu Baerts (NGI0)" <matttbe@kernel.org>
Date: Mon, 19 Aug 2024 21:45:32 +0200
Subject: [PATCH 62/82] mptcp: pm: avoid possible UaF when selecting endp

select_local_address() and select_signal_address() both select an
endpoint entry from the list inside an RCU protected section, but return
a reference to it, to be read later on. If the entry is dereferenced
after the RCU unlock, reading info could cause a Use-after-Free.

A simple solution is to copy the required info while inside the RCU
protected section to avoid any risk of UaF later. The address ID might
need to be modified later to handle the ID0 case later, so a copy seems
OK to deal with.

Reported-by: Paolo Abeni <pabeni@redhat.com>
Closes: https://lore.kernel.org/45cd30d3-7710-491c-ae4d-a1368c00beb1@redhat.com
Fixes: 01cacb00b35c ("mptcp: add netlink-based PM")
Cc: stable@vger.kernel.org
Reviewed-by: Mat Martineau <martineau@kernel.org>
Signed-off-by: Matthieu Baerts (NGI0) <matttbe@kernel.org>
Link: https://patch.msgid.link/20240819-net-mptcp-pm-reusing-id-v1-14-38035d40de5b@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/mptcp/pm_netlink.c | 64 ++++++++++++++++++++++--------------------
 1 file changed, 34 insertions(+), 30 deletions(-)

diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c
index a2e37ab1c40f..3e4ad801786f 100644
--- a/net/mptcp/pm_netlink.c
+++ b/net/mptcp/pm_netlink.c
@@ -143,11 +143,13 @@ static bool lookup_subflow_by_daddr(const struct list_head *list,
 	return false;
 }
 
-static struct mptcp_pm_addr_entry *
+static bool
 select_local_address(const struct pm_nl_pernet *pernet,
-		     const struct mptcp_sock *msk)
+		     const struct mptcp_sock *msk,
+		     struct mptcp_pm_addr_entry *new_entry)
 {
-	struct mptcp_pm_addr_entry *entry, *ret = NULL;
+	struct mptcp_pm_addr_entry *entry;
+	bool found = false;
 
 	msk_owned_by_me(msk);
 
@@ -159,17 +161,21 @@ select_local_address(const struct pm_nl_pernet *pernet,
 		if (!test_bit(entry->addr.id, msk->pm.id_avail_bitmap))
 			continue;
 
-		ret = entry;
+		*new_entry = *entry;
+		found = true;
 		break;
 	}
 	rcu_read_unlock();
-	return ret;
+
+	return found;
 }
 
-static struct mptcp_pm_addr_entry *
-select_signal_address(struct pm_nl_pernet *pernet, const struct mptcp_sock *msk)
+static bool
+select_signal_address(struct pm_nl_pernet *pernet, const struct mptcp_sock *msk,
+		      struct mptcp_pm_addr_entry *new_entry)
 {
-	struct mptcp_pm_addr_entry *entry, *ret = NULL;
+	struct mptcp_pm_addr_entry *entry;
+	bool found = false;
 
 	rcu_read_lock();
 	/* do not keep any additional per socket state, just signal
@@ -184,11 +190,13 @@ select_signal_address(struct pm_nl_pernet *pernet, const struct mptcp_sock *msk)
 		if (!(entry->flags & MPTCP_PM_ADDR_FLAG_SIGNAL))
 			continue;
 
-		ret = entry;
+		*new_entry = *entry;
+		found = true;
 		break;
 	}
 	rcu_read_unlock();
-	return ret;
+
+	return found;
 }
 
 unsigned int mptcp_pm_get_add_addr_signal_max(const struct mptcp_sock *msk)
@@ -512,9 +520,10 @@ __lookup_addr(struct pm_nl_pernet *pernet, const struct mptcp_addr_info *info)
 
 static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk)
 {
-	struct mptcp_pm_addr_entry *local, *signal_and_subflow = NULL;
 	struct sock *sk = (struct sock *)msk;
+	struct mptcp_pm_addr_entry local;
 	unsigned int add_addr_signal_max;
+	bool signal_and_subflow = false;
 	unsigned int local_addr_max;
 	struct pm_nl_pernet *pernet;
 	unsigned int subflows_max;
@@ -565,23 +574,22 @@ static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk)
 		if (msk->pm.addr_signal & BIT(MPTCP_ADD_ADDR_SIGNAL))
 			return;
 
-		local = select_signal_address(pernet, msk);
-		if (!local)
+		if (!select_signal_address(pernet, msk, &local))
 			goto subflow;
 
 		/* If the alloc fails, we are on memory pressure, not worth
 		 * continuing, and trying to create subflows.
 		 */
-		if (!mptcp_pm_alloc_anno_list(msk, &local->addr))
+		if (!mptcp_pm_alloc_anno_list(msk, &local.addr))
 			return;
 
-		__clear_bit(local->addr.id, msk->pm.id_avail_bitmap);
+		__clear_bit(local.addr.id, msk->pm.id_avail_bitmap);
 		msk->pm.add_addr_signaled++;
-		mptcp_pm_announce_addr(msk, &local->addr, false);
+		mptcp_pm_announce_addr(msk, &local.addr, false);
 		mptcp_pm_nl_addr_send_ack(msk);
 
-		if (local->flags & MPTCP_PM_ADDR_FLAG_SUBFLOW)
-			signal_and_subflow = local;
+		if (local.flags & MPTCP_PM_ADDR_FLAG_SUBFLOW)
+			signal_and_subflow = true;
 	}
 
 subflow:
@@ -592,26 +600,22 @@ static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk)
 		bool fullmesh;
 		int i, nr;
 
-		if (signal_and_subflow) {
-			local = signal_and_subflow;
-			signal_and_subflow = NULL;
-		} else {
-			local = select_local_address(pernet, msk);
-			if (!local)
-				break;
-		}
+		if (signal_and_subflow)
+			signal_and_subflow = false;
+		else if (!select_local_address(pernet, msk, &local))
+			break;
 
-		fullmesh = !!(local->flags & MPTCP_PM_ADDR_FLAG_FULLMESH);
+		fullmesh = !!(local.flags & MPTCP_PM_ADDR_FLAG_FULLMESH);
 
 		msk->pm.local_addr_used++;
-		__clear_bit(local->addr.id, msk->pm.id_avail_bitmap);
-		nr = fill_remote_addresses_vec(msk, &local->addr, fullmesh, addrs);
+		__clear_bit(local.addr.id, msk->pm.id_avail_bitmap);
+		nr = fill_remote_addresses_vec(msk, &local.addr, fullmesh, addrs);
 		if (nr == 0)
 			continue;
 
 		spin_unlock_bh(&msk->pm.lock);
 		for (i = 0; i < nr; i++)
-			__mptcp_subflow_connect(sk, &local->addr, &addrs[i]);
+			__mptcp_subflow_connect(sk, &local.addr, &addrs[i]);
 		spin_lock_bh(&msk->pm.lock);
 	}
 	mptcp_pm_nl_check_work_pending(msk);

From b128ed5ab27330deeeaf51ea8bb69f1442a96f7f Mon Sep 17 00:00:00 2001
From: Felix Fietkau <nbd@nbd.name>
Date: Mon, 19 Aug 2024 17:06:21 +0200
Subject: [PATCH 63/82] udp: fix receiving fraglist GSO packets

When assembling fraglist GSO packets, udp4_gro_complete does not set
skb->csum_start, which makes the extra validation in __udp_gso_segment fail.

Fixes: 89add40066f9 ("net: drop bad gso csum_start and offset in virtio_net_hdr")
Signed-off-by: Felix Fietkau <nbd@nbd.name>
Reviewed-by: Willem de Bruijn <willemb@google.com>
Link: https://patch.msgid.link/20240819150621.59833-1-nbd@nbd.name
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv4/udp_offload.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
index b254a5dadfcf..d842303587af 100644
--- a/net/ipv4/udp_offload.c
+++ b/net/ipv4/udp_offload.c
@@ -279,7 +279,8 @@ struct sk_buff *__udp_gso_segment(struct sk_buff *gso_skb,
 		return ERR_PTR(-EINVAL);
 
 	if (unlikely(skb_checksum_start(gso_skb) !=
-		     skb_transport_header(gso_skb)))
+		     skb_transport_header(gso_skb) &&
+		     !(skb_shinfo(gso_skb)->gso_type & SKB_GSO_FRAGLIST)))
 		return ERR_PTR(-EINVAL);
 
 	/* We don't know if egress device can segment and checksum the packet

From f8669d7b5f5d2d88959456ae9123d8bb6fdc1ebe Mon Sep 17 00:00:00 2001
From: Ido Schimmel <idosch@nvidia.com>
Date: Tue, 20 Aug 2024 12:53:47 +0200
Subject: [PATCH 64/82] selftests: mlxsw: ethtool_lanes: Source ethtool lib
 from correct path

Source the ethtool library from the correct path and avoid the following
error:

./ethtool_lanes.sh: line 14: ./../../../net/forwarding/ethtool_lib.sh: No such file or directory

Fixes: 40d269c000bd ("selftests: forwarding: Move several selftests")
Signed-off-by: Ido Schimmel <idosch@nvidia.com>
Signed-off-by: Petr Machata <petrm@nvidia.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/2112faff02e536e1ac14beb4c2be09c9574b90ae.1724150067.git.petrm@nvidia.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/drivers/net/mlxsw/ethtool_lanes.sh | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/tools/testing/selftests/drivers/net/mlxsw/ethtool_lanes.sh b/tools/testing/selftests/drivers/net/mlxsw/ethtool_lanes.sh
index 877cd6df94a1..fe905a7f34b3 100755
--- a/tools/testing/selftests/drivers/net/mlxsw/ethtool_lanes.sh
+++ b/tools/testing/selftests/drivers/net/mlxsw/ethtool_lanes.sh
@@ -2,6 +2,7 @@
 # SPDX-License-Identifier: GPL-2.0
 
 lib_dir=$(dirname $0)/../../../net/forwarding
+ethtool_lib_dir=$(dirname $0)/../hw
 
 ALL_TESTS="
 	autoneg
@@ -11,7 +12,7 @@ ALL_TESTS="
 NUM_NETIFS=2
 : ${TIMEOUT:=30000} # ms
 source $lib_dir/lib.sh
-source $lib_dir/ethtool_lib.sh
+source $ethtool_lib_dir/ethtool_lib.sh
 
 setup_prepare()
 {

From 007d4271a5f10638cba6f0b99698557ef30014b9 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 20 Aug 2024 16:20:53 +0000
Subject: [PATCH 65/82] netpoll: do not export netpoll_poll_[disable|enable]()

netpoll_poll_disable() and netpoll_poll_enable() are only used
from core networking code, there is no need to export them.

Signed-off-by: Eric Dumazet <edumazet@google.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20240820162053.3870927-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/core/netpoll.c | 2 --
 1 file changed, 2 deletions(-)

diff --git a/net/core/netpoll.c b/net/core/netpoll.c
index 55bcacf67df3..d657b042d5a0 100644
--- a/net/core/netpoll.c
+++ b/net/core/netpoll.c
@@ -228,7 +228,6 @@ void netpoll_poll_disable(struct net_device *dev)
 		down(&ni->dev_lock);
 	srcu_read_unlock(&netpoll_srcu, idx);
 }
-EXPORT_SYMBOL(netpoll_poll_disable);
 
 void netpoll_poll_enable(struct net_device *dev)
 {
@@ -239,7 +238,6 @@ void netpoll_poll_enable(struct net_device *dev)
 		up(&ni->dev_lock);
 	rcu_read_unlock();
 }
-EXPORT_SYMBOL(netpoll_poll_enable);
 
 static void refill_skbs(void)
 {

From faa389b2fbaaec7fd27a390b4896139f9da662e3 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 20 Aug 2024 16:08:57 +0000
Subject: [PATCH 66/82] ipv6: prevent UAF in ip6_send_skb()

syzbot reported an UAF in ip6_send_skb() [1]

After ip6_local_out() has returned, we no longer can safely
dereference rt, unless we hold rcu_read_lock().

A similar issue has been fixed in commit
a688caa34beb ("ipv6: take rcu lock in rawv6_send_hdrinc()")

Another potential issue in ip6_finish_output2() is handled in a
separate patch.

[1]
 BUG: KASAN: slab-use-after-free in ip6_send_skb+0x18d/0x230 net/ipv6/ip6_output.c:1964
Read of size 8 at addr ffff88806dde4858 by task syz.1.380/6530

CPU: 1 UID: 0 PID: 6530 Comm: syz.1.380 Not tainted 6.11.0-rc3-syzkaller-00306-gdf6cbc62cc9b #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 08/06/2024
Call Trace:
 <TASK>
  __dump_stack lib/dump_stack.c:93 [inline]
  dump_stack_lvl+0x241/0x360 lib/dump_stack.c:119
  print_address_description mm/kasan/report.c:377 [inline]
  print_report+0x169/0x550 mm/kasan/report.c:488
  kasan_report+0x143/0x180 mm/kasan/report.c:601
  ip6_send_skb+0x18d/0x230 net/ipv6/ip6_output.c:1964
  rawv6_push_pending_frames+0x75c/0x9e0 net/ipv6/raw.c:588
  rawv6_sendmsg+0x19c7/0x23c0 net/ipv6/raw.c:926
  sock_sendmsg_nosec net/socket.c:730 [inline]
  __sock_sendmsg+0x1a6/0x270 net/socket.c:745
  sock_write_iter+0x2dd/0x400 net/socket.c:1160
 do_iter_readv_writev+0x60a/0x890
  vfs_writev+0x37c/0xbb0 fs/read_write.c:971
  do_writev+0x1b1/0x350 fs/read_write.c:1018
  do_syscall_x64 arch/x86/entry/common.c:52 [inline]
  do_syscall_64+0xf3/0x230 arch/x86/entry/common.c:83
 entry_SYSCALL_64_after_hwframe+0x77/0x7f
RIP: 0033:0x7f936bf79e79
Code: ff ff c3 66 2e 0f 1f 84 00 00 00 00 00 0f 1f 40 00 48 89 f8 48 89 f7 48 89 d6 48 89 ca 4d 89 c2 4d 89 c8 4c 8b 4c 24 08 0f 05 <48> 3d 01 f0 ff ff 73 01 c3 48 c7 c1 a8 ff ff ff f7 d8 64 89 01 48
RSP: 002b:00007f936cd7f038 EFLAGS: 00000246 ORIG_RAX: 0000000000000014
RAX: ffffffffffffffda RBX: 00007f936c115f80 RCX: 00007f936bf79e79
RDX: 0000000000000001 RSI: 0000000020000040 RDI: 0000000000000004
RBP: 00007f936bfe7916 R08: 0000000000000000 R09: 0000000000000000
R10: 0000000000000000 R11: 0000000000000246 R12: 0000000000000000
R13: 0000000000000000 R14: 00007f936c115f80 R15: 00007fff2860a7a8
 </TASK>

Allocated by task 6530:
  kasan_save_stack mm/kasan/common.c:47 [inline]
  kasan_save_track+0x3f/0x80 mm/kasan/common.c:68
  unpoison_slab_object mm/kasan/common.c:312 [inline]
  __kasan_slab_alloc+0x66/0x80 mm/kasan/common.c:338
  kasan_slab_alloc include/linux/kasan.h:201 [inline]
  slab_post_alloc_hook mm/slub.c:3988 [inline]
  slab_alloc_node mm/slub.c:4037 [inline]
  kmem_cache_alloc_noprof+0x135/0x2a0 mm/slub.c:4044
  dst_alloc+0x12b/0x190 net/core/dst.c:89
  ip6_blackhole_route+0x59/0x340 net/ipv6/route.c:2670
  make_blackhole net/xfrm/xfrm_policy.c:3120 [inline]
  xfrm_lookup_route+0xd1/0x1c0 net/xfrm/xfrm_policy.c:3313
  ip6_dst_lookup_flow+0x13e/0x180 net/ipv6/ip6_output.c:1257
  rawv6_sendmsg+0x1283/0x23c0 net/ipv6/raw.c:898
  sock_sendmsg_nosec net/socket.c:730 [inline]
  __sock_sendmsg+0x1a6/0x270 net/socket.c:745
  ____sys_sendmsg+0x525/0x7d0 net/socket.c:2597
  ___sys_sendmsg net/socket.c:2651 [inline]
  __sys_sendmsg+0x2b0/0x3a0 net/socket.c:2680
  do_syscall_x64 arch/x86/entry/common.c:52 [inline]
  do_syscall_64+0xf3/0x230 arch/x86/entry/common.c:83
 entry_SYSCALL_64_after_hwframe+0x77/0x7f

Freed by task 45:
  kasan_save_stack mm/kasan/common.c:47 [inline]
  kasan_save_track+0x3f/0x80 mm/kasan/common.c:68
  kasan_save_free_info+0x40/0x50 mm/kasan/generic.c:579
  poison_slab_object+0xe0/0x150 mm/kasan/common.c:240
  __kasan_slab_free+0x37/0x60 mm/kasan/common.c:256
  kasan_slab_free include/linux/kasan.h:184 [inline]
  slab_free_hook mm/slub.c:2252 [inline]
  slab_free mm/slub.c:4473 [inline]
  kmem_cache_free+0x145/0x350 mm/slub.c:4548
  dst_destroy+0x2ac/0x460 net/core/dst.c:124
  rcu_do_batch kernel/rcu/tree.c:2569 [inline]
  rcu_core+0xafd/0x1830 kernel/rcu/tree.c:2843
  handle_softirqs+0x2c4/0x970 kernel/softirq.c:554
  __do_softirq kernel/softirq.c:588 [inline]
  invoke_softirq kernel/softirq.c:428 [inline]
  __irq_exit_rcu+0xf4/0x1c0 kernel/softirq.c:637
  irq_exit_rcu+0x9/0x30 kernel/softirq.c:649
  instr_sysvec_apic_timer_interrupt arch/x86/kernel/apic/apic.c:1043 [inline]
  sysvec_apic_timer_interrupt+0xa6/0xc0 arch/x86/kernel/apic/apic.c:1043
  asm_sysvec_apic_timer_interrupt+0x1a/0x20 arch/x86/include/asm/idtentry.h:702

Last potentially related work creation:
  kasan_save_stack+0x3f/0x60 mm/kasan/common.c:47
  __kasan_record_aux_stack+0xac/0xc0 mm/kasan/generic.c:541
  __call_rcu_common kernel/rcu/tree.c:3106 [inline]
  call_rcu+0x167/0xa70 kernel/rcu/tree.c:3210
  refdst_drop include/net/dst.h:263 [inline]
  skb_dst_drop include/net/dst.h:275 [inline]
  nf_ct_frag6_queue net/ipv6/netfilter/nf_conntrack_reasm.c:306 [inline]
  nf_ct_frag6_gather+0xb9a/0x2080 net/ipv6/netfilter/nf_conntrack_reasm.c:485
  ipv6_defrag+0x2c8/0x3c0 net/ipv6/netfilter/nf_defrag_ipv6_hooks.c:67
  nf_hook_entry_hookfn include/linux/netfilter.h:154 [inline]
  nf_hook_slow+0xc3/0x220 net/netfilter/core.c:626
  nf_hook include/linux/netfilter.h:269 [inline]
  __ip6_local_out+0x6fa/0x800 net/ipv6/output_core.c:143
  ip6_local_out+0x26/0x70 net/ipv6/output_core.c:153
  ip6_send_skb+0x112/0x230 net/ipv6/ip6_output.c:1959
  rawv6_push_pending_frames+0x75c/0x9e0 net/ipv6/raw.c:588
  rawv6_sendmsg+0x19c7/0x23c0 net/ipv6/raw.c:926
  sock_sendmsg_nosec net/socket.c:730 [inline]
  __sock_sendmsg+0x1a6/0x270 net/socket.c:745
  sock_write_iter+0x2dd/0x400 net/socket.c:1160
 do_iter_readv_writev+0x60a/0x890

Fixes: 0625491493d9 ("ipv6: ip6_push_pending_frames() should increment IPSTATS_MIB_OUTDISCARDS")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Reported-by: syzbot <syzkaller@googlegroups.com>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://patch.msgid.link/20240820160859.3786976-2-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv6/ip6_output.c | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index ab504d31f0cd..f7b53effc80f 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -1956,6 +1956,7 @@ int ip6_send_skb(struct sk_buff *skb)
 	struct rt6_info *rt = dst_rt6_info(skb_dst(skb));
 	int err;
 
+	rcu_read_lock();
 	err = ip6_local_out(net, skb->sk, skb);
 	if (err) {
 		if (err > 0)
@@ -1965,6 +1966,7 @@ int ip6_send_skb(struct sk_buff *skb)
 				      IPSTATS_MIB_OUTDISCARDS);
 	}
 
+	rcu_read_unlock();
 	return err;
 }
 

From da273b377ae0d9bd255281ed3c2adb228321687b Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 20 Aug 2024 16:08:58 +0000
Subject: [PATCH 67/82] ipv6: fix possible UAF in ip6_finish_output2()

If skb_expand_head() returns NULL, skb has been freed
and associated dst/idev could also have been freed.

We need to hold rcu_read_lock() to make sure the dst and
associated idev are alive.

Fixes: 5796015fa968 ("ipv6: allocate enough headroom in ip6_finish_output2()")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Vasily Averin <vasily.averin@linux.dev>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://patch.msgid.link/20240820160859.3786976-3-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv6/ip6_output.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index f7b53effc80f..1b9ebee7308f 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -70,11 +70,15 @@ static int ip6_finish_output2(struct net *net, struct sock *sk, struct sk_buff *
 
 	/* Be paranoid, rather than too clever. */
 	if (unlikely(hh_len > skb_headroom(skb)) && dev->header_ops) {
+		/* Make sure idev stays alive */
+		rcu_read_lock();
 		skb = skb_expand_head(skb, hh_len);
 		if (!skb) {
 			IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTDISCARDS);
+			rcu_read_unlock();
 			return -ENOMEM;
 		}
+		rcu_read_unlock();
 	}
 
 	hdr = ipv6_hdr(skb);

From 2d5ff7e339d04622d8282661df36151906d0e1c7 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Tue, 20 Aug 2024 16:08:59 +0000
Subject: [PATCH 68/82] ipv6: prevent possible UAF in ip6_xmit()

If skb_expand_head() returns NULL, skb has been freed
and the associated dst/idev could also have been freed.

We must use rcu_read_lock() to prevent a possible UAF.

Fixes: 0c9f227bee11 ("ipv6: use skb_expand_head in ip6_xmit")
Signed-off-by: Eric Dumazet <edumazet@google.com>
Cc: Vasily Averin <vasily.averin@linux.dev>
Reviewed-by: David Ahern <dsahern@kernel.org>
Link: https://patch.msgid.link/20240820160859.3786976-4-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/ipv6/ip6_output.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
index 1b9ebee7308f..f26841f1490f 100644
--- a/net/ipv6/ip6_output.c
+++ b/net/ipv6/ip6_output.c
@@ -287,11 +287,15 @@ int ip6_xmit(const struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6,
 		head_room += opt->opt_nflen + opt->opt_flen;
 
 	if (unlikely(head_room > skb_headroom(skb))) {
+		/* Make sure idev stays alive */
+		rcu_read_lock();
 		skb = skb_expand_head(skb, head_room);
 		if (!skb) {
 			IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTDISCARDS);
+			rcu_read_unlock();
 			return -ENOBUFS;
 		}
+		rcu_read_unlock();
 	}
 
 	if (opt) {

From 8baeef7616d5194045c5a6b97fd1246b87c55b13 Mon Sep 17 00:00:00 2001
From: Somnath Kotur <somnath.kotur@broadcom.com>
Date: Tue, 20 Aug 2024 13:34:15 -0700
Subject: [PATCH 69/82] bnxt_en: Fix double DMA unmapping for XDP_REDIRECT

Remove the dma_unmap_page_attrs() call in the driver's XDP_REDIRECT
code path.  This should have been removed when we let the page pool
handle the DMA mapping.  This bug causes the warning:

WARNING: CPU: 7 PID: 59 at drivers/iommu/dma-iommu.c:1198 iommu_dma_unmap_page+0xd5/0x100
CPU: 7 PID: 59 Comm: ksoftirqd/7 Tainted: G        W          6.8.0-1010-gcp #11-Ubuntu
Hardware name: Dell Inc. PowerEdge R7525/0PYVT1, BIOS 2.15.2 04/02/2024
RIP: 0010:iommu_dma_unmap_page+0xd5/0x100
Code: 89 ee 48 89 df e8 cb f2 69 ff 48 83 c4 08 5b 41 5c 41 5d 41 5e 41 5f 5d 31 c0 31 d2 31 c9 31 f6 31 ff 45 31 c0 e9 ab 17 71 00 <0f> 0b 48 83 c4 08 5b 41 5c 41 5d 41 5e 41 5f 5d 31 c0 31 d2 31 c9
RSP: 0018:ffffab1fc0597a48 EFLAGS: 00010246
RAX: 0000000000000000 RBX: ffff99ff838280c8 RCX: 0000000000000000
RDX: 0000000000000000 RSI: 0000000000000000 RDI: 0000000000000000
RBP: ffffab1fc0597a78 R08: 0000000000000002 R09: ffffab1fc0597c1c
R10: ffffab1fc0597cd3 R11: ffff99ffe375acd8 R12: 00000000e65b9000
R13: 0000000000000050 R14: 0000000000001000 R15: 0000000000000002
FS:  0000000000000000(0000) GS:ffff9a06efb80000(0000) knlGS:0000000000000000
CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
CR2: 0000565c34c37210 CR3: 00000005c7e3e000 CR4: 0000000000350ef0
? show_regs+0x6d/0x80
? __warn+0x89/0x150
? iommu_dma_unmap_page+0xd5/0x100
? report_bug+0x16a/0x190
? handle_bug+0x51/0xa0
? exc_invalid_op+0x18/0x80
? iommu_dma_unmap_page+0xd5/0x100
? iommu_dma_unmap_page+0x35/0x100
dma_unmap_page_attrs+0x55/0x220
? bpf_prog_4d7e87c0d30db711_xdp_dispatcher+0x64/0x9f
bnxt_rx_xdp+0x237/0x520 [bnxt_en]
bnxt_rx_pkt+0x640/0xdd0 [bnxt_en]
__bnxt_poll_work+0x1a1/0x3d0 [bnxt_en]
bnxt_poll+0xaa/0x1e0 [bnxt_en]
__napi_poll+0x33/0x1e0
net_rx_action+0x18a/0x2f0

Fixes: 578fcfd26e2a ("bnxt_en: Let the page pool manage the DMA mapping")
Reviewed-by: Andy Gospodarek <andrew.gospodarek@broadcom.com>
Reviewed-by: Kalesh AP <kalesh-anakkur.purayil@broadcom.com>
Signed-off-by: Somnath Kotur <somnath.kotur@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Link: https://patch.msgid.link/20240820203415.168178-1-michael.chan@broadcom.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c | 5 -----
 1 file changed, 5 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
index 345681d5007e..f88b641533fc 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
@@ -297,11 +297,6 @@ bool bnxt_rx_xdp(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, u16 cons,
 		 * redirect is coming from a frame received by the
 		 * bnxt_en driver.
 		 */
-		rx_buf = &rxr->rx_buf_ring[cons];
-		mapping = rx_buf->mapping - bp->rx_dma_offset;
-		dma_unmap_page_attrs(&pdev->dev, mapping,
-				     BNXT_RX_PAGE_SIZE, bp->rx_dir,
-				     DMA_ATTR_WEAK_ORDERING);
 
 		/* if we are unable to allocate a new buffer, abort and reuse */
 		if (bnxt_alloc_rx_data(bp, rxr, rxr->rx_prod, GFP_ATOMIC)) {

From 6ea14ccb60c8ab829349979b22b58a941ec4a3ee Mon Sep 17 00:00:00 2001
From: Pablo Neira Ayuso <pablo@netfilter.org>
Date: Tue, 13 Aug 2024 12:39:46 +0200
Subject: [PATCH 70/82] netfilter: flowtable: validate vlan header

Ensure there is sufficient room to access the protocol field of the
VLAN header, validate it once before the flowtable lookup.

=====================================================
BUG: KMSAN: uninit-value in nf_flow_offload_inet_hook+0x45a/0x5f0 net/netfilter/nf_flow_table_inet.c:32
 nf_flow_offload_inet_hook+0x45a/0x5f0 net/netfilter/nf_flow_table_inet.c:32
 nf_hook_entry_hookfn include/linux/netfilter.h:154 [inline]
 nf_hook_slow+0xf4/0x400 net/netfilter/core.c:626
 nf_hook_ingress include/linux/netfilter_netdev.h:34 [inline]
 nf_ingress net/core/dev.c:5440 [inline]

Fixes: 4cd91f7c290f ("netfilter: flowtable: add vlan support")
Reported-by: syzbot+8407d9bb88cd4c6bf61a@syzkaller.appspotmail.com
Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org>
---
 net/netfilter/nf_flow_table_inet.c | 3 +++
 net/netfilter/nf_flow_table_ip.c   | 3 +++
 2 files changed, 6 insertions(+)

diff --git a/net/netfilter/nf_flow_table_inet.c b/net/netfilter/nf_flow_table_inet.c
index 88787b45e30d..8b541a080342 100644
--- a/net/netfilter/nf_flow_table_inet.c
+++ b/net/netfilter/nf_flow_table_inet.c
@@ -17,6 +17,9 @@ nf_flow_offload_inet_hook(void *priv, struct sk_buff *skb,
 
 	switch (skb->protocol) {
 	case htons(ETH_P_8021Q):
+		if (!pskb_may_pull(skb, skb_mac_offset(skb) + sizeof(*veth)))
+			return NF_ACCEPT;
+
 		veth = (struct vlan_ethhdr *)skb_mac_header(skb);
 		proto = veth->h_vlan_encapsulated_proto;
 		break;
diff --git a/net/netfilter/nf_flow_table_ip.c b/net/netfilter/nf_flow_table_ip.c
index c2c005234dcd..98edcaa37b38 100644
--- a/net/netfilter/nf_flow_table_ip.c
+++ b/net/netfilter/nf_flow_table_ip.c
@@ -281,6 +281,9 @@ static bool nf_flow_skb_encap_protocol(struct sk_buff *skb, __be16 proto,
 
 	switch (skb->protocol) {
 	case htons(ETH_P_8021Q):
+		if (!pskb_may_pull(skb, skb_mac_offset(skb) + sizeof(*veth)))
+			return false;
+
 		veth = (struct vlan_ethhdr *)skb_mac_header(skb);
 		if (veth->h_vlan_encapsulated_proto == proto) {
 			*offset += VLAN_HLEN;

From f2916c83d746eb99f50f42c15cf4c47c2ea5f3b3 Mon Sep 17 00:00:00 2001
From: Mengyuan Lou <mengyuanlou@net-swift.com>
Date: Tue, 20 Aug 2024 11:04:25 +0800
Subject: [PATCH 71/82] net: ngbe: Fix phy mode set to external phy

The MAC only has add the TX delay and it can not be modified.
MAC and PHY are both set the TX delay cause transmission problems.
So just disable TX delay in PHY, when use rgmii to attach to
external phy, set PHY_INTERFACE_MODE_RGMII_RXID to phy drivers.
And it is does not matter to internal phy.

Fixes: bc2426d74aa3 ("net: ngbe: convert phylib to phylink")
Signed-off-by: Mengyuan Lou <mengyuanlou@net-swift.com>
Cc: stable@vger.kernel.org # 6.3+
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Link: https://patch.msgid.link/E6759CF1387CF84C+20240820030425.93003-1-mengyuanlou@net-swift.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/ethernet/wangxun/ngbe/ngbe_mdio.c | 8 ++++++--
 1 file changed, 6 insertions(+), 2 deletions(-)

diff --git a/drivers/net/ethernet/wangxun/ngbe/ngbe_mdio.c b/drivers/net/ethernet/wangxun/ngbe/ngbe_mdio.c
index ec54b18c5fe7..a5e9b779c44d 100644
--- a/drivers/net/ethernet/wangxun/ngbe/ngbe_mdio.c
+++ b/drivers/net/ethernet/wangxun/ngbe/ngbe_mdio.c
@@ -124,8 +124,12 @@ static int ngbe_phylink_init(struct wx *wx)
 				   MAC_SYM_PAUSE | MAC_ASYM_PAUSE;
 	config->mac_managed_pm = true;
 
-	phy_mode = PHY_INTERFACE_MODE_RGMII_ID;
-	__set_bit(PHY_INTERFACE_MODE_RGMII_ID, config->supported_interfaces);
+	/* The MAC only has add the Tx delay and it can not be modified.
+	 * So just disable TX delay in PHY, and it is does not matter to
+	 * internal phy.
+	 */
+	phy_mode = PHY_INTERFACE_MODE_RGMII_RXID;
+	__set_bit(PHY_INTERFACE_MODE_RGMII_RXID, config->supported_interfaces);
 
 	phylink = phylink_create(config, NULL, phy_mode, &ngbe_mac_ops);
 	if (IS_ERR(phylink))

From a2f5c505b4378cd6fc7c4a44ff3665ccef2037db Mon Sep 17 00:00:00 2001
From: Sava Jakovljev <savaj@meyersound.com>
Date: Wed, 21 Aug 2024 04:16:57 +0200
Subject: [PATCH 72/82] net: phy: realtek: Fix setting of PHY LEDs Mode B bit
 on RTL8211F

The current implementation incorrectly sets the mode bit of the PHY chip.
Bit 15 (RTL8211F_LEDCR_MODE) should not be shifted together with the
configuration nibble of a LED- it should be set independently of the
index of the LED being configured.
As a consequence, the RTL8211F LED control is actually operating in Mode A.
Fix the error by or-ing final register value to write with a const-value of
RTL8211F_LEDCR_MODE, thus setting Mode bit explicitly.

Fixes: 17784801d888 ("net: phy: realtek: Add support for PHY LEDs on RTL8211F")
Signed-off-by: Sava Jakovljev <savaj@meyersound.com>
Reviewed-by: Marek Vasut <marex@denx.de>
Link: https://patch.msgid.link/PAWP192MB21287372F30C4E55B6DF6158C38E2@PAWP192MB2128.EURP192.PROD.OUTLOOK.COM
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 drivers/net/phy/realtek.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/phy/realtek.c b/drivers/net/phy/realtek.c
index 87865918dab6..25e5bfbb6f89 100644
--- a/drivers/net/phy/realtek.c
+++ b/drivers/net/phy/realtek.c
@@ -555,7 +555,7 @@ static int rtl8211f_led_hw_control_set(struct phy_device *phydev, u8 index,
 				       unsigned long rules)
 {
 	const u16 mask = RTL8211F_LEDCR_MASK << (RTL8211F_LEDCR_SHIFT * index);
-	u16 reg = RTL8211F_LEDCR_MODE;	/* Mode B */
+	u16 reg = 0;
 
 	if (index >= RTL8211F_LED_COUNT)
 		return -EINVAL;
@@ -575,6 +575,7 @@ static int rtl8211f_led_hw_control_set(struct phy_device *phydev, u8 index,
 	}
 
 	reg <<= RTL8211F_LEDCR_SHIFT * index;
+	reg |= RTL8211F_LEDCR_MODE;	 /* Mode B */
 
 	return phy_modify_paged(phydev, 0xd04, RTL8211F_LEDCR, mask, reg);
 }

From af688a99eb1fc7ef69774665d61e6be51cea627a Mon Sep 17 00:00:00 2001
From: Bharat Bhushan <bbhushan2@marvell.com>
Date: Wed, 21 Aug 2024 12:35:58 +0530
Subject: [PATCH 73/82] octeontx2-af: Fix CPT AF register offset calculation

Some CPT AF registers are per LF and others are global. Translation
of PF/VF local LF slot number to actual LF slot number is required
only for accessing perf LF registers. CPT AF global registers access
do not require any LF slot number. Also, there is no reason CPT
PF/VF to know actual lf's register offset.

Without this fix microcode loading will fail, VFs cannot be created
and hardware is not usable.

Fixes: bc35e28af789 ("octeontx2-af: replace cpt slot with lf id on reg write")
Signed-off-by: Bharat Bhushan <bbhushan2@marvell.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20240821070558.1020101-1-bbhushan2@marvell.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 .../ethernet/marvell/octeontx2/af/rvu_cpt.c   | 23 +++++++++----------
 1 file changed, 11 insertions(+), 12 deletions(-)

diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cpt.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cpt.c
index 3e09d2285814..daf4b951e905 100644
--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cpt.c
+++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cpt.c
@@ -632,7 +632,9 @@ int rvu_mbox_handler_cpt_inline_ipsec_cfg(struct rvu *rvu,
 	return ret;
 }
 
-static bool is_valid_offset(struct rvu *rvu, struct cpt_rd_wr_reg_msg *req)
+static bool validate_and_update_reg_offset(struct rvu *rvu,
+					   struct cpt_rd_wr_reg_msg *req,
+					   u64 *reg_offset)
 {
 	u64 offset = req->reg_offset;
 	int blkaddr, num_lfs, lf;
@@ -663,6 +665,11 @@ static bool is_valid_offset(struct rvu *rvu, struct cpt_rd_wr_reg_msg *req)
 		if (lf < 0)
 			return false;
 
+		/* Translate local LF's offset to global CPT LF's offset to
+		 * access LFX register.
+		 */
+		*reg_offset = (req->reg_offset & 0xFF000) + (lf << 3);
+
 		return true;
 	} else if (!(req->hdr.pcifunc & RVU_PFVF_FUNC_MASK)) {
 		/* Registers that can be accessed from PF */
@@ -697,7 +704,7 @@ int rvu_mbox_handler_cpt_rd_wr_register(struct rvu *rvu,
 					struct cpt_rd_wr_reg_msg *rsp)
 {
 	u64 offset = req->reg_offset;
-	int blkaddr, lf;
+	int blkaddr;
 
 	blkaddr = validate_and_get_cpt_blkaddr(req->blkaddr);
 	if (blkaddr < 0)
@@ -708,18 +715,10 @@ int rvu_mbox_handler_cpt_rd_wr_register(struct rvu *rvu,
 	    !is_cpt_vf(rvu, req->hdr.pcifunc))
 		return CPT_AF_ERR_ACCESS_DENIED;
 
-	if (!is_valid_offset(rvu, req))
+	if (!validate_and_update_reg_offset(rvu, req, &offset))
 		return CPT_AF_ERR_ACCESS_DENIED;
 
-	/* Translate local LF used by VFs to global CPT LF */
-	lf = rvu_get_lf(rvu, &rvu->hw->block[blkaddr], req->hdr.pcifunc,
-			(offset & 0xFFF) >> 3);
-
-	/* Translate local LF's offset to global CPT LF's offset */
-	offset &= 0xFF000;
-	offset += lf << 3;
-
-	rsp->reg_offset = offset;
+	rsp->reg_offset = req->reg_offset;
 	rsp->ret_val = req->ret_val;
 	rsp->is_write = req->is_write;
 

From 1ac66c4960e1c735eb6edfd3e6d52bebb2aa347e Mon Sep 17 00:00:00 2001
From: Simon Horman <horms@kernel.org>
Date: Wed, 21 Aug 2024 09:46:44 +0100
Subject: [PATCH 74/82] MAINTAINERS: Add sonet.h to ATM section of MAINTAINERS

This is part of an effort to assign a section in MAINTAINERS to header
files that relate to Networking. In this case the files with "net" in
their name.

It seems that sonet.h is included in ATM related source files,
and thus that ATM is the most relevant section for these files.

Cc: Chas Williams <3chas3@gmail.com>
Signed-off-by: Simon Horman <horms@kernel.org>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 MAINTAINERS | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/MAINTAINERS b/MAINTAINERS
index a964a34651f5..c682203915a2 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -3504,7 +3504,9 @@ S:	Maintained
 W:	http://linux-atm.sourceforge.net
 F:	drivers/atm/
 F:	include/linux/atm*
+F:	include/linux/sonet.h
 F:	include/uapi/linux/atm*
+F:	include/uapi/linux/sonet.h
 
 ATMEL MACB ETHERNET DRIVER
 M:	Nicolas Ferre <nicolas.ferre@microchip.com>

From eb208fecd77d898709c25af680487289fd5f3e16 Mon Sep 17 00:00:00 2001
From: Simon Horman <horms@kernel.org>
Date: Wed, 21 Aug 2024 09:46:45 +0100
Subject: [PATCH 75/82] MAINTAINERS: Add net_tstamp.h to SOCKET TIMESTAMPING
 section

This is part of an effort to assign a section in MAINTAINERS to header
files that relate to Networking. In this case the files with "net" in
their name.

Cc: Richard Cochran <richardcochran@gmail.com>
Cc: Willem de Bruijn <willemdebruijn.kernel@gmail.com>
Signed-off-by: Simon Horman <horms@kernel.org>
Acked-by: Willem de Bruijn <willemb@google.com>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 MAINTAINERS | 1 +
 1 file changed, 1 insertion(+)

diff --git a/MAINTAINERS b/MAINTAINERS
index c682203915a2..e5b9a4d9bc21 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -21057,6 +21057,7 @@ SOCKET TIMESTAMPING
 M:	Willem de Bruijn <willemdebruijn.kernel@gmail.com>
 S:	Maintained
 F:	Documentation/networking/timestamping.rst
+F:	include/linux/net_tstamp.h
 F:	include/uapi/linux/net_tstamp.h
 F:	tools/testing/selftests/net/so_txtime.c
 

From 8cb0a938d90b25f123fcb2e24bbda9eaabd79c9e Mon Sep 17 00:00:00 2001
From: Simon Horman <horms@kernel.org>
Date: Wed, 21 Aug 2024 09:46:46 +0100
Subject: [PATCH 76/82] MAINTAINERS: Add limited globs for Networking headers

This aims to add limited globs to improve the coverage of header files
in the NETWORKING DRIVERS and NETWORKING [GENERAL] sections.

It is done so in a minimal way to exclude overlap with other sections.
And so as not to require "X" entries to exclude files otherwise
matched by these new globs.

While imperfect, due to it's limited nature, this does extend coverage
of header files by these sections. And aims to automatically cover
new files that seem very likely belong to these sections.

The include/linux/netdev* glob (both sections)
+ Subsumes the entries for:
  - include/linux/netdevice.h
+ Extends the sections to cover
  - include/linux/netdevice_xmit.h
  - include/linux/netdev_features.h

The include/uapi/linux/netdev* globs: (both sections)
+ Subsumes the entries for:
  - include/linux/netdevice.h
+ Extends the sections to cover
  - include/linux/netdev.h

The include/linux/skbuff* glob (NETWORKING [GENERAL] section only):
+ Subsumes the entry for:
  - include/linux/skbuff.h
+ Extends the section to cover
  - include/linux/skbuff_ref.h

A include/uapi/linux/net_* glob was not added to the NETWORKING [GENERAL]
section. Although it would subsume the entry for
include/uapi/linux/net_namespace.h, which is fine, it would also extend
coverage to:
- include/uapi/linux/net_dropmon.h, which belongs to the
   NETWORK DROP MONITOR section
- include/uapi/linux/net_tstamp.h which, as per an earlier patch in this
  series, belongs to the SOCKET TIMESTAMPING section

Signed-off-by: Simon Horman <horms@kernel.org>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 MAINTAINERS | 10 +++++-----
 1 file changed, 5 insertions(+), 5 deletions(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index e5b9a4d9bc21..03d571b131eb 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -15884,10 +15884,10 @@ F:	include/linux/fddidevice.h
 F:	include/linux/hippidevice.h
 F:	include/linux/if_*
 F:	include/linux/inetdevice.h
-F:	include/linux/netdevice.h
+F:	include/linux/netdev*
 F:	include/uapi/linux/cn_proc.h
 F:	include/uapi/linux/if_*
-F:	include/uapi/linux/netdevice.h
+F:	include/uapi/linux/netdev*
 F:	tools/testing/selftests/drivers/net/
 X:	drivers/net/wireless/
 
@@ -15940,13 +15940,13 @@ F:	include/linux/framer/framer.h
 F:	include/linux/in.h
 F:	include/linux/indirect_call_wrapper.h
 F:	include/linux/net.h
-F:	include/linux/netdevice.h
-F:	include/linux/skbuff.h
+F:	include/linux/netdev*
+F:	include/linux/skbuff*
 F:	include/net/
 F:	include/uapi/linux/in.h
 F:	include/uapi/linux/net.h
 F:	include/uapi/linux/net_namespace.h
-F:	include/uapi/linux/netdevice.h
+F:	include/uapi/linux/netdev*
 F:	lib/net_utils.c
 F:	lib/random32.c
 F:	net/

From f2d20c9b97f0df64841b89fa1ad3e9c92f7377ae Mon Sep 17 00:00:00 2001
From: Simon Horman <horms@kernel.org>
Date: Wed, 21 Aug 2024 09:46:47 +0100
Subject: [PATCH 77/82] MAINTAINERS: Add header files to NETWORKING sections

This is part of an effort to assign a section in MAINTAINERS to header
files that relate to Networking. In this case the files with "net" or
"skbuff" in their name.

This patch adds a number of such files to the NETWORKING DRIVERS
and NETWORKING [GENERAL] sections.

Signed-off-by: Simon Horman <horms@kernel.org>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 MAINTAINERS | 17 +++++++++++++++++
 1 file changed, 17 insertions(+)

diff --git a/MAINTAINERS b/MAINTAINERS
index 03d571b131eb..798f1ffcbbaa 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -15879,13 +15879,16 @@ F:	drivers/net/
 F:	include/dt-bindings/net/
 F:	include/linux/cn_proc.h
 F:	include/linux/etherdevice.h
+F:	include/linux/ethtool_netlink.h
 F:	include/linux/fcdevice.h
 F:	include/linux/fddidevice.h
 F:	include/linux/hippidevice.h
 F:	include/linux/if_*
 F:	include/linux/inetdevice.h
 F:	include/linux/netdev*
+F:	include/linux/platform_data/wiznet.h
 F:	include/uapi/linux/cn_proc.h
+F:	include/uapi/linux/ethtool_netlink.h
 F:	include/uapi/linux/if_*
 F:	include/uapi/linux/netdev*
 F:	tools/testing/selftests/drivers/net/
@@ -15939,14 +15942,28 @@ F:	include/linux/framer/framer-provider.h
 F:	include/linux/framer/framer.h
 F:	include/linux/in.h
 F:	include/linux/indirect_call_wrapper.h
+F:	include/linux/inet.h
+F:	include/linux/inet_diag.h
 F:	include/linux/net.h
 F:	include/linux/netdev*
+F:	include/linux/netlink.h
+F:	include/linux/netpoll.h
+F:	include/linux/rtnetlink.h
+F:	include/linux/seq_file_net.h
 F:	include/linux/skbuff*
 F:	include/net/
+F:	include/uapi/linux/genetlink.h
+F:	include/uapi/linux/hsr_netlink.h
 F:	include/uapi/linux/in.h
+F:	include/uapi/linux/inet_diag.h
+F:	include/uapi/linux/nbd-netlink.h
 F:	include/uapi/linux/net.h
 F:	include/uapi/linux/net_namespace.h
+F:	include/uapi/linux/netconf.h
 F:	include/uapi/linux/netdev*
+F:	include/uapi/linux/netlink.h
+F:	include/uapi/linux/netlink_diag.h
+F:	include/uapi/linux/rtnetlink.h
 F:	lib/net_utils.c
 F:	lib/random32.c
 F:	net/

From 46097a92662496394628cb41138e681d6074cce7 Mon Sep 17 00:00:00 2001
From: Simon Horman <horms@kernel.org>
Date: Wed, 21 Aug 2024 09:46:48 +0100
Subject: [PATCH 78/82] MAINTAINERS: Mark JME Network Driver as Odd Fixes

This driver only appears to have received sporadic clean-ups, typically
part of some tree-wide activity, and fixes for quite some time.  And
according to the maintainer, Guo-Fu Tseng, the device has been EOLed for
a long time (see Link).

Accordingly, it seems appropriate to mark this driver as odd fixes.

Cc: Moon Yeounsu <yyyynoom@gmail.com>
Cc: Guo-Fu Tseng <cooldavid@cooldavid.org>
Link: https://lore.kernel.org/netdev/20240805003139.M94125@cooldavid.org/
Signed-off-by: Simon Horman <horms@kernel.org>
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 MAINTAINERS | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/MAINTAINERS b/MAINTAINERS
index 798f1ffcbbaa..0c94ec0ca478 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -11995,7 +11995,7 @@ F:	fs/jfs/
 JME NETWORK DRIVER
 M:	Guo-Fu Tseng <cooldavid@cooldavid.org>
 L:	netdev@vger.kernel.org
-S:	Maintained
+S:	Odd Fixes
 F:	drivers/net/ethernet/jme.*
 
 JOURNALLING FLASH FILE SYSTEM V2 (JFFS2)

From 4ae738dfef2c0323752ab81786e2d298c9939321 Mon Sep 17 00:00:00 2001
From: Sean Anderson <sean.anderson@linux.dev>
Date: Thu, 22 Aug 2024 11:40:55 -0400
Subject: [PATCH 79/82] net: xilinx: axienet: Always disable promiscuous mode

If promiscuous mode is disabled when there are fewer than four multicast
addresses, then it will not be reflected in the hardware. Fix this by
always clearing the promiscuous mode flag even when we program multicast
addresses.

Fixes: 8a3b7a252dca ("drivers/net/ethernet/xilinx: added Xilinx AXI Ethernet driver")
Signed-off-by: Sean Anderson <sean.anderson@linux.dev>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20240822154059.1066595-2-sean.anderson@linux.dev
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/xilinx/xilinx_axienet_main.c | 4 ++++
 1 file changed, 4 insertions(+)

diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
index 02fdf66e07fa..163d05248007 100644
--- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
+++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
@@ -450,6 +450,10 @@ static void axienet_set_multicast_list(struct net_device *ndev)
 	} else if (!netdev_mc_empty(ndev)) {
 		struct netdev_hw_addr *ha;
 
+		reg = axienet_ior(lp, XAE_FMI_OFFSET);
+		reg &= ~XAE_FMI_PM_MASK;
+		axienet_iow(lp, XAE_FMI_OFFSET, reg);
+
 		i = 0;
 		netdev_for_each_mc_addr(ha, ndev) {
 			if (i >= XAE_MULTICAST_CAM_TABLE_NUM)

From 797a68c9de0f5a5447baf4bd3bb9c10a3993435b Mon Sep 17 00:00:00 2001
From: Sean Anderson <sean.anderson@linux.dev>
Date: Thu, 22 Aug 2024 11:40:56 -0400
Subject: [PATCH 80/82] net: xilinx: axienet: Fix dangling multicast addresses

If a multicast address is removed but there are still some multicast
addresses, that address would remain programmed into the frame filter.
Fix this by explicitly setting the enable bit for each filter.

Fixes: 8a3b7a252dca ("drivers/net/ethernet/xilinx: added Xilinx AXI Ethernet driver")
Signed-off-by: Sean Anderson <sean.anderson@linux.dev>
Reviewed-by: Simon Horman <horms@kernel.org>
Link: https://patch.msgid.link/20240822154059.1066595-3-sean.anderson@linux.dev
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/xilinx/xilinx_axienet.h  |  1 +
 .../net/ethernet/xilinx/xilinx_axienet_main.c | 21 ++++++++-----------
 2 files changed, 10 insertions(+), 12 deletions(-)

diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet.h b/drivers/net/ethernet/xilinx/xilinx_axienet.h
index c7d9221fafdc..09c9f9787180 100644
--- a/drivers/net/ethernet/xilinx/xilinx_axienet.h
+++ b/drivers/net/ethernet/xilinx/xilinx_axienet.h
@@ -170,6 +170,7 @@
 #define XAE_UAW0_OFFSET		0x00000700 /* Unicast address word 0 */
 #define XAE_UAW1_OFFSET		0x00000704 /* Unicast address word 1 */
 #define XAE_FMI_OFFSET		0x00000708 /* Frame Filter Control */
+#define XAE_FFE_OFFSET		0x0000070C /* Frame Filter Enable */
 #define XAE_AF0_OFFSET		0x00000710 /* Address Filter 0 */
 #define XAE_AF1_OFFSET		0x00000714 /* Address Filter 1 */
 
diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
index 163d05248007..9aeb7b9f3ae4 100644
--- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
+++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
@@ -432,7 +432,7 @@ static int netdev_set_mac_address(struct net_device *ndev, void *p)
  */
 static void axienet_set_multicast_list(struct net_device *ndev)
 {
-	int i;
+	int i = 0;
 	u32 reg, af0reg, af1reg;
 	struct axienet_local *lp = netdev_priv(ndev);
 
@@ -454,7 +454,6 @@ static void axienet_set_multicast_list(struct net_device *ndev)
 		reg &= ~XAE_FMI_PM_MASK;
 		axienet_iow(lp, XAE_FMI_OFFSET, reg);
 
-		i = 0;
 		netdev_for_each_mc_addr(ha, ndev) {
 			if (i >= XAE_MULTICAST_CAM_TABLE_NUM)
 				break;
@@ -473,6 +472,7 @@ static void axienet_set_multicast_list(struct net_device *ndev)
 			axienet_iow(lp, XAE_FMI_OFFSET, reg);
 			axienet_iow(lp, XAE_AF0_OFFSET, af0reg);
 			axienet_iow(lp, XAE_AF1_OFFSET, af1reg);
+			axienet_iow(lp, XAE_FFE_OFFSET, 1);
 			i++;
 		}
 	} else {
@@ -480,18 +480,15 @@ static void axienet_set_multicast_list(struct net_device *ndev)
 		reg &= ~XAE_FMI_PM_MASK;
 
 		axienet_iow(lp, XAE_FMI_OFFSET, reg);
-
-		for (i = 0; i < XAE_MULTICAST_CAM_TABLE_NUM; i++) {
-			reg = axienet_ior(lp, XAE_FMI_OFFSET) & 0xFFFFFF00;
-			reg |= i;
-
-			axienet_iow(lp, XAE_FMI_OFFSET, reg);
-			axienet_iow(lp, XAE_AF0_OFFSET, 0);
-			axienet_iow(lp, XAE_AF1_OFFSET, 0);
-		}
-
 		dev_info(&ndev->dev, "Promiscuous mode disabled.\n");
 	}
+
+	for (; i < XAE_MULTICAST_CAM_TABLE_NUM; i++) {
+		reg = axienet_ior(lp, XAE_FMI_OFFSET) & 0xFFFFFF00;
+		reg |= i;
+		axienet_iow(lp, XAE_FMI_OFFSET, reg);
+		axienet_iow(lp, XAE_FFE_OFFSET, 0);
+	}
 }
 
 /**

From 57fb67783c4011581882f32e656d738da1f82042 Mon Sep 17 00:00:00 2001
From: Menglong Dong <menglong8.dong@gmail.com>
Date: Wed, 21 Aug 2024 20:32:52 +0800
Subject: [PATCH 81/82] net: ovs: fix ovs_drop_reasons error

There is something wrong with ovs_drop_reasons. ovs_drop_reasons[0] is
"OVS_DROP_LAST_ACTION", but OVS_DROP_LAST_ACTION == __OVS_DROP_REASON + 1,
which means that ovs_drop_reasons[1] should be "OVS_DROP_LAST_ACTION".

And as Adrian tested, without the patch, adding flow to drop packets
results in:

drop at: do_execute_actions+0x197/0xb20 [openvsw (0xffffffffc0db6f97)
origin: software
input port ifindex: 8
timestamp: Tue Aug 20 10:19:17 2024 859853461 nsec
protocol: 0x800
length: 98
original length: 98
drop reason: OVS_DROP_ACTION_ERROR

With the patch, the same results in:

drop at: do_execute_actions+0x197/0xb20 [openvsw (0xffffffffc0db6f97)
origin: software
input port ifindex: 8
timestamp: Tue Aug 20 10:16:13 2024 475856608 nsec
protocol: 0x800
length: 98
original length: 98
drop reason: OVS_DROP_LAST_ACTION

Fix this by initializing ovs_drop_reasons with index.

Fixes: 9d802da40b7c ("net: openvswitch: add last-action drop reason")
Signed-off-by: Menglong Dong <dongml2@chinatelecom.cn>
Tested-by: Adrian Moreno <amorenoz@redhat.com>
Reviewed-by: Adrian Moreno <amorenoz@redhat.com>
Link: https://patch.msgid.link/20240821123252.186305-1-dongml2@chinatelecom.cn
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/openvswitch/datapath.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
index 99d72543abd3..78d9961fcd44 100644
--- a/net/openvswitch/datapath.c
+++ b/net/openvswitch/datapath.c
@@ -2706,7 +2706,7 @@ static struct pernet_operations ovs_net_ops = {
 };
 
 static const char * const ovs_drop_reasons[] = {
-#define S(x)	(#x),
+#define S(x) [(x) & ~SKB_DROP_REASON_SUBSYS_MASK] = (#x),
 	OVS_DROP_REASONS(S)
 #undef S
 };

From 0124fb0ebf3b0ef89892d42147c9387be3105318 Mon Sep 17 00:00:00 2001
From: Alexandra Winter <wintera@linux.ibm.com>
Date: Wed, 21 Aug 2024 11:13:37 +0200
Subject: [PATCH 82/82] s390/iucv: Fix vargs handling in iucv_alloc_device()

iucv_alloc_device() gets a format string and a varying number of
arguments. This is incorrectly forwarded by calling dev_set_name() with
the format string and a va_list, while dev_set_name() expects also a
varying number of arguments.

Symptoms:
Corrupted iucv device names, which can result in log messages like:
sysfs: cannot create duplicate filename '/devices/iucv/hvc_iucv1827699952'

Fixes: 4452e8ef8c36 ("s390/iucv: Provide iucv_alloc_device() / iucv_release_device()")
Link: https://bugzilla.suse.com/show_bug.cgi?id=1228425
Signed-off-by: Alexandra Winter <wintera@linux.ibm.com>
Reviewed-by: Thorsten Winkler <twinkler@linux.ibm.com>
Reviewed-by: Przemek Kitszel <przemyslaw.kitszel@intel.com>
Link: https://patch.msgid.link/20240821091337.3627068-1-wintera@linux.ibm.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/iucv/iucv.c | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/net/iucv/iucv.c b/net/iucv/iucv.c
index 1e42e13ad24e..d3e9efab7f4b 100644
--- a/net/iucv/iucv.c
+++ b/net/iucv/iucv.c
@@ -86,13 +86,15 @@ struct device *iucv_alloc_device(const struct attribute_group **attrs,
 {
 	struct device *dev;
 	va_list vargs;
+	char buf[20];
 	int rc;
 
 	dev = kzalloc(sizeof(*dev), GFP_KERNEL);
 	if (!dev)
 		goto out_error;
 	va_start(vargs, fmt);
-	rc = dev_set_name(dev, fmt, vargs);
+	vsnprintf(buf, sizeof(buf), fmt, vargs);
+	rc = dev_set_name(dev, "%s", buf);
 	va_end(vargs);
 	if (rc)
 		goto out_error;