--- /dev/null
+From c281a47bd697868a364cb1578ee4b0502d8ab299 Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Mon, 12 Aug 2024 10:43:48 -0400
+Subject: Bluetooth: HCI: Invert LE State quirk to be opt-out rather then
+ opt-in
+
+From: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
+
+[ Upstream commit aae6b81260fd9a7224f7eb4fc440d625852245bb ]
+
+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>
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ 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 93900c37349c1..c084dc88d3d91 100644
+--- a/drivers/bluetooth/btintel.c
++++ b/drivers/bluetooth/btintel.c
+@@ -2876,9 +2876,6 @@ 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;
+@@ -2887,7 +2884,6 @@ 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
+@@ -2979,9 +2975,6 @@ 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);
+
+@@ -3003,9 +2996,6 @@ 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 b8120b98a2395..1fd3b7073ab90 100644
+--- a/drivers/bluetooth/btintel_pcie.c
++++ b/drivers/bluetooth/btintel_pcie.c
+@@ -1182,9 +1182,6 @@ 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 8ded9ef8089a2..bc4700ed3b782 100644
+--- a/drivers/bluetooth/btmtksdio.c
++++ b/drivers/bluetooth/btmtksdio.c
+@@ -1144,9 +1144,6 @@ 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 4f1e37b4f7802..bfcb41a57655f 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 789c492df6fa2..0927f51867c26 100644
+--- a/drivers/bluetooth/btusb.c
++++ b/drivers/bluetooth/btusb.c
+@@ -4545,8 +4545,8 @@ 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 9a0bc86f9aace..34c36f0f781ea 100644
+--- a/drivers/bluetooth/hci_qca.c
++++ b/drivers/bluetooth/hci_qca.c
+@@ -2408,8 +2408,8 @@ 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 28750a40f0ed5..b652d68f0ee14 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 e372a88e8c3f6..d1d073089f384 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 b15f51ae3bfd9..c97ff64c9189f 100644
+--- a/include/net/bluetooth/hci_core.h
++++ b/include/net/bluetooth/hci_core.h
+@@ -826,7 +826,7 @@ 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 a78f6d706cd43..59d9086db75fe 100644
+--- a/net/bluetooth/hci_event.c
++++ b/net/bluetooth/hci_event.c
+@@ -5921,7 +5921,7 @@ 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;
+
+--
+2.43.0
+
--- /dev/null
+From 9f527be1d77a2aa27d37e75f8a45d7c3d2768010 Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Mon, 12 Aug 2024 11:22:08 -0400
+Subject: Bluetooth: hci_core: Fix LE quote calculation
+
+From: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
+
+[ Upstream commit 932021a11805b9da4bd6abf66fe233cccd59fe0e ]
+
+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>
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ 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 6ecb110bf46bc..b488d0742c966 100644
+--- a/net/bluetooth/hci_core.c
++++ b/net/bluetooth/hci_core.c
+@@ -3674,19 +3674,19 @@ 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, "e))) {
++ tmp = *cnt;
++ while (*cnt && (chan = hci_chan_sent(hdev, LE_LINK, "e))) {
+ 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,
+@@ -3701,7 +3701,7 @@ 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++;
+
+@@ -3711,12 +3711,7 @@ 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);
+ }
+
+--
+2.43.0
+
--- /dev/null
+From 1bdbb0effbb15fc185d424e70f8fcaf2d861c64a Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Wed, 30 Aug 2023 15:08:06 -0700
+Subject: Bluetooth: SMP: Fix assumption of Central always being Initiator
+
+From: Luiz Augusto von Dentz <luiz.von.dentz@intel.com>
+
+[ Upstream commit 28cd47f75185c4818b0fb1b46f2f02faaba96376 ]
+
+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>
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ net/bluetooth/smp.c | 144 ++++++++++++++++++++++----------------------
+ 1 file changed, 72 insertions(+), 72 deletions(-)
+
+diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c
+index 1e7ea3a4b7ef3..4f9fdf400584e 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;
+@@ -2347,16 +2365,20 @@ 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_send_pairing_req(smp, auth);
+
+- smp->preq[0] = SMP_CMD_PAIRING_REQ;
+- memcpy(&smp->preq[1], &cp, sizeof(cp));
++ return 0;
++}
+
+- smp_send_cmd(conn, SMP_CMD_PAIRING_REQ, sizeof(cp), &cp);
+- SMP_ALLOW_CMD(smp, SMP_CMD_PAIRING_RSP);
++static void smp_send_security_req(struct smp_chan *smp, __u8 auth)
++{
++ struct smp_cmd_security_req cp;
+
+- return 0;
++ 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)
+@@ -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;
+-
+- 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);
+- }
++ if (hcon->role == HCI_ROLE_MASTER)
++ smp_send_pairing_req(smp, authreq);
++ else
++ smp_send_security_req(smp, authreq);
+
+- 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)
+--
+2.43.0
+
--- /dev/null
+From 4805ced0781d9aae13b104073e7d4ba25077c997 Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Tue, 20 Aug 2024 13:34:15 -0700
+Subject: bnxt_en: Fix double DMA unmapping for XDP_REDIRECT
+
+From: Somnath Kotur <somnath.kotur@broadcom.com>
+
+[ Upstream commit 8baeef7616d5194045c5a6b97fd1246b87c55b13 ]
+
+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>
+Signed-off-by: Sasha Levin <sashal@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 345681d5007e3..f88b641533fcc 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)) {
+--
+2.43.0
+
--- /dev/null
+From 4401fb20cb40e9d4f2022978d55b0784271f32ac Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Fri, 16 Aug 2024 14:48:10 +0300
+Subject: bonding: fix bond_ipsec_offload_ok return type
+
+From: Nikolay Aleksandrov <razor@blackwall.org>
+
+[ Upstream commit fc59b9a5f7201b9f7272944596113a82cc7773d5 ]
+
+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>
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ 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 2ed0da0684906..2370da4632149 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 = {
+--
+2.43.0
+
--- /dev/null
+From 479ae8c19f2767c574c65cc3a7b01cffd8bcbc3e Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Fri, 16 Aug 2024 14:48:11 +0300
+Subject: bonding: fix null pointer deref in bond_ipsec_offload_ok
+
+From: Nikolay Aleksandrov <razor@blackwall.org>
+
+[ Upstream commit 95c90e4ad89d493a7a14fa200082e466e2548f9d ]
+
+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>
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ 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 2370da4632149..55841a0e05a47 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)
+--
+2.43.0
+
--- /dev/null
+From 5313cbd7c550cc39c0baa92b84b65c6e799dc7e0 Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Fri, 16 Aug 2024 14:48:12 +0300
+Subject: bonding: fix xfrm real_dev null pointer dereference
+
+From: Nikolay Aleksandrov <razor@blackwall.org>
+
+[ Upstream commit f8cde9805981c50d0c029063dc7d82821806fc44 ]
+
+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>
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ 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 55841a0e05a47..b257504a85347 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();
+--
+2.43.0
+
--- /dev/null
+From 87d1dc17d774430eeb14d20d59f42e3e2fde9cae Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Fri, 16 Aug 2024 14:48:13 +0300
+Subject: bonding: fix xfrm state handling when clearing active slave
+
+From: Nikolay Aleksandrov <razor@blackwall.org>
+
+[ Upstream commit c4c5c5d2ef40a9f67a9241dc5422eac9ffe19547 ]
+
+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>
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ 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 bc80fb6397dcd..95d59a18c0223 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);
+--
+2.43.0
+
--- /dev/null
+From 82a745183ce0a37eefc6e573b89912465cbbab21 Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Sat, 17 Aug 2024 09:52:46 +0300
+Subject: dpaa2-switch: Fix error checking in dpaa2_switch_seed_bp()
+
+From: Dan Carpenter <dan.carpenter@linaro.org>
+
+[ Upstream commit c50e7475961c36ec4d21d60af055b32f9436b431 ]
+
+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>
+Signed-off-by: Sasha Levin <sashal@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 a71f848adc054..a293b08f36d46 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 = ðsw->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;
+ }
+
+--
+2.43.0
+
--- /dev/null
+From 8b7c750b70953443f77dfd6397a78fcd04fe6076 Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Wed, 7 Aug 2024 12:53:25 +0200
+Subject: ice: fix ICE_LAST_OFFSET formula
+
+From: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
+
+[ Upstream commit b966ad832942b5a11e002f9b5ef102b08425b84a ]
+
+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>
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ 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 50211188c1a7a..4b690952bb403 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) */
+--
+2.43.0
+
--- /dev/null
+From 94ba4374aa43bc774ffb15deb2a1e7cc8ecf3307 Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Wed, 7 Aug 2024 12:53:24 +0200
+Subject: ice: fix page reuse when PAGE_SIZE is over 8k
+
+From: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
+
+[ Upstream commit 50b2143356e888777fc5bca023c39f34f404613a ]
+
+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>
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ 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 8d25b69812698..50211188c1a7a 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)
+--
+2.43.0
+
--- /dev/null
+From 19b37d22ee90822aa0bfd3ba23f3e1d8640377a1 Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Wed, 7 Aug 2024 12:53:26 +0200
+Subject: ice: fix truesize operations for PAGE_SIZE >= 8192
+
+From: Maciej Fijalkowski <maciej.fijalkowski@intel.com>
+
+[ Upstream commit d53d4dcce69be5773e2d0878c9899ebfbf58c393 ]
+
+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>
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ 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 1facf179a96fd..f448d3a845642 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 4b690952bb403..c9bc3f1add5d3 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;
+--
+2.43.0
+
--- /dev/null
+From 24a9fcb622a058a15eb86f2474980f39162f2f61 Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Mon, 19 Aug 2024 09:17:42 +0200
+Subject: ice: use internal pf id instead of function number
+
+From: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
+
+[ Upstream commit 503ab6ee40fc103ea55cc9e50bb879e571d65aac ]
+
+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>
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ 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 13e6790d3cae7..afcf64dab48a1 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.
+@@ -399,7 +399,7 @@ 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);
+--
+2.43.0
+
--- /dev/null
+From 56511d3763ed54c73d1b3071758fa92fdcecaa49 Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Fri, 16 Aug 2024 17:20:34 +0200
+Subject: igb: cope with large MAX_SKB_FRAGS
+
+From: Paolo Abeni <pabeni@redhat.com>
+
+[ Upstream commit 8aba27c4a5020abdf60149239198297f88338a8d ]
+
+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>
+Signed-off-by: Sasha Levin <sashal@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 fce2930ae6af7..b6aa449aa56af 100644
+--- a/drivers/net/ethernet/intel/igb/igb_main.c
++++ b/drivers/net/ethernet/intel/igb/igb_main.c
+@@ -4809,6 +4809,7 @@ 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
+--
+2.43.0
+
--- /dev/null
+From 0d35f7a9c39f366ff172759cf4ba354dd6c7d219 Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Thu, 15 Aug 2024 17:14:16 +0200
+Subject: ip6_tunnel: Fix broken GRO
+
+From: Thomas Bogendoerfer <tbogendoerfer@suse.de>
+
+[ Upstream commit 4b3e33fcc38f7750604b065c55a43e94c5bc3145 ]
+
+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>
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ 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 9dee0c1279554..87dfb565a9f81 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);
+--
+2.43.0
+
--- /dev/null
+From 295a8962a274b6976931e900d2cd396af38dfb82 Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Tue, 20 Aug 2024 16:08:58 +0000
+Subject: ipv6: fix possible UAF in ip6_finish_output2()
+
+From: Eric Dumazet <edumazet@google.com>
+
+[ Upstream commit da273b377ae0d9bd255281ed3c2adb228321687b ]
+
+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>
+Signed-off-by: Sasha Levin <sashal@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 d44ddce4c9f4d..8778431acffda 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);
+--
+2.43.0
+
--- /dev/null
+From ad3870bc1793d5e5b1a2b6e3935aab2d764e9153 Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Tue, 20 Aug 2024 16:08:59 +0000
+Subject: ipv6: prevent possible UAF in ip6_xmit()
+
+From: Eric Dumazet <edumazet@google.com>
+
+[ Upstream commit 2d5ff7e339d04622d8282661df36151906d0e1c7 ]
+
+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>
+Signed-off-by: Sasha Levin <sashal@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 8778431acffda..c49344d8311ab 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) {
+--
+2.43.0
+
--- /dev/null
+From 3e66009a64d62ea6af5afbbc917c01f8313e4297 Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Tue, 20 Aug 2024 16:08:57 +0000
+Subject: ipv6: prevent UAF in ip6_send_skb()
+
+From: Eric Dumazet <edumazet@google.com>
+
+[ Upstream commit faa389b2fbaaec7fd27a390b4896139f9da662e3 ]
+
+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>
+Signed-off-by: Sasha Levin <sashal@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 784424ac41477..d44ddce4c9f4d 100644
+--- a/net/ipv6/ip6_output.c
++++ b/net/ipv6/ip6_output.c
+@@ -1953,6 +1953,7 @@ 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)
+@@ -1962,6 +1963,7 @@ int ip6_send_skb(struct sk_buff *skb)
+ IPSTATS_MIB_OUTDISCARDS);
+ }
+
++ rcu_read_unlock();
+ return err;
+ }
+
+--
+2.43.0
+
--- /dev/null
+From 9e3b43301f8476032de326616a1be2a46a7d9a07 Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Thu, 8 Aug 2024 03:03:00 +0900
+Subject: kbuild: avoid scripts/kallsyms parsing /dev/null
+
+From: Masahiro Yamada <masahiroy@kernel.org>
+
+[ Upstream commit 1472464c6248575bf2d01c7f076b94704bb32c95 ]
+
+On macOS, as reported by Daniel Gomez, getline() sets ENOTTY to errno
+if it is requested to read from /dev/null.
+
+If this is worth fixing, I would rather pass an empty file to
+scripts/kallsyms instead of adding the ugly #ifdef __APPLE__.
+
+Fixes: c442db3f49f2 ("kbuild: remove PROVIDE() for kallsyms symbols")
+Reported-by: Daniel Gomez <da.gomez@samsung.com>
+Closes: https://lore.kernel.org/all/20240807-macos-build-support-v1-12-4cd1ded85694@samsung.com/
+Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
+Reviewed-by: Nicolas Schier <nicolas@fjasle.eu>
+Reviewed-by: Daniel Gomez <da.gomez@samsung.com>
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ scripts/link-vmlinux.sh | 3 ++-
+ 1 file changed, 2 insertions(+), 1 deletion(-)
+
+diff --git a/scripts/link-vmlinux.sh b/scripts/link-vmlinux.sh
+index 22d0bc8439863..070a319140e89 100755
+--- a/scripts/link-vmlinux.sh
++++ b/scripts/link-vmlinux.sh
+@@ -215,7 +215,8 @@ kallsymso=
+ strip_debug=
+
+ if is_enabled CONFIG_KALLSYMS; then
+- kallsyms /dev/null .tmp_vmlinux0.kallsyms
++ truncate -s0 .tmp_vmlinux.kallsyms0.syms
++ kallsyms .tmp_vmlinux.kallsyms0.syms .tmp_vmlinux0.kallsyms
+ fi
+
+ if is_enabled CONFIG_KALLSYMS || is_enabled CONFIG_DEBUG_INFO_BTF; then
+--
+2.43.0
+
--- /dev/null
+From e4aefbe760ecd3041f053b0ab3341d2a72346940 Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Mon, 10 Jun 2024 20:25:18 +0900
+Subject: kbuild: merge temporary vmlinux for BTF and kallsyms
+
+From: Masahiro Yamada <masahiroy@kernel.org>
+
+[ Upstream commit b1a9a5e04767e2a78783e19c9e55c25812ceccc3 ]
+
+CONFIG_DEBUG_INFO_BTF=y requires one additional link step.
+(.tmp_vmlinux.btf)
+
+CONFIG_KALLSYMS=y requires two additional link steps.
+(.tmp_vmlinux.kallsyms1 and .tmp_vmlinux.kallsyms2)
+
+Enabling both requires three additional link steps.
+
+When CONFIG_DEBUG_INFO_BTF=y and CONFIG_KALLSYMS=y, the current build
+process is as follows:
+
+ KSYMS .tmp_vmlinux.kallsyms0.S
+ AS .tmp_vmlinux.kallsyms0.o
+ LD .tmp_vmlinux.btf # temporary vmlinux for BTF
+ BTF .btf.vmlinux.bin.o
+ LD .tmp_vmlinux.kallsyms1 # temporary vmlinux for kallsyms step 1
+ NM .tmp_vmlinux.kallsyms1.syms
+ KSYMS .tmp_vmlinux.kallsyms1.S
+ AS .tmp_vmlinux.kallsyms1.o
+ LD .tmp_vmlinux.kallsyms2 # temporary vmlinux for kallsyms step 2
+ NM .tmp_vmlinux.kallsyms2.syms
+ KSYMS .tmp_vmlinux.kallsyms2.S
+ AS .tmp_vmlinux.kallsyms2.o
+ LD vmlinux # final vmlinux
+
+This is redundant because the BTF generation and the kallsyms step 1 can
+be performed against the same temporary vmlinux.
+
+When both CONFIG_DEBUG_INFO_BTF and CONFIG_KALLSYMS are enabled, we can
+reduce the number of link steps by one.
+
+This commit changes the build process as follows:
+
+ KSYMS .tmp_vmlinux0.kallsyms.S
+ AS .tmp_vmlinux0.kallsyms.o
+ LD .tmp_vmlinux1 # temporary vmlinux for BTF and kallsyms step 1
+ BTF .tmp_vmlinux1.btf.o
+ NM .tmp_vmlinux1.syms
+ KSYMS .tmp_vmlinux1.kallsyms.S
+ AS .tmp_vmlinux1.kallsyms.o
+ LD .tmp_vmlinux2 # temporary vmlinux for kallsyms step 2
+ NM .tmp_vmlinux2.syms
+ KSYMS .tmp_vmlinux2.kallsyms.S
+ AS .tmp_vmlinux2.kallsyms.o
+ LD vmlinux # final vmlinux
+
+Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
+Acked-by: Andrii Nakryiko <andrii@kernel.org>
+Stable-dep-of: 1472464c6248 ("kbuild: avoid scripts/kallsyms parsing /dev/null")
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ scripts/link-vmlinux.sh | 41 ++++++++++++++++++++++++-----------------
+ 1 file changed, 24 insertions(+), 17 deletions(-)
+
+diff --git a/scripts/link-vmlinux.sh b/scripts/link-vmlinux.sh
+index 1e41b330550e6..22d0bc8439863 100755
+--- a/scripts/link-vmlinux.sh
++++ b/scripts/link-vmlinux.sh
+@@ -105,11 +105,10 @@ vmlinux_link()
+
+ # generate .BTF typeinfo from DWARF debuginfo
+ # ${1} - vmlinux image
+-# ${2} - file to dump raw BTF data into
+ gen_btf()
+ {
+ local pahole_ver
+- local btf_data=${2}
++ local btf_data=${1}.btf.o
+
+ if ! [ -x "$(command -v ${PAHOLE})" ]; then
+ echo >&2 "BTF: ${1}: pahole (${PAHOLE}) is not available"
+@@ -122,8 +121,6 @@ gen_btf()
+ return 1
+ fi
+
+- vmlinux_link ${1}
+-
+ info BTF "${btf_data}"
+ LLVM_OBJCOPY="${OBJCOPY}" ${PAHOLE} -J ${PAHOLE_FLAGS} ${1}
+
+@@ -169,15 +166,13 @@ kallsyms()
+ kallsymso=${2}.o
+ }
+
+-# Perform one step in kallsyms generation, including temporary linking of
+-# vmlinux.
+-kallsyms_step()
++# Perform kallsyms for the given temporary vmlinux.
++sysmap_and_kallsyms()
+ {
+- kallsyms_vmlinux=.tmp_vmlinux.kallsyms${1}
++ mksysmap "${1}" "${1}.syms"
++ kallsyms "${1}.syms" "${1}.kallsyms"
+
+- vmlinux_link "${kallsyms_vmlinux}"
+- mksysmap "${kallsyms_vmlinux}" "${kallsyms_vmlinux}.syms"
+- kallsyms "${kallsyms_vmlinux}.syms" "${kallsyms_vmlinux}"
++ kallsyms_sysmap=${1}.syms
+ }
+
+ # Create map file with all symbols from ${1}
+@@ -220,11 +215,21 @@ kallsymso=
+ strip_debug=
+
+ if is_enabled CONFIG_KALLSYMS; then
+- kallsyms /dev/null .tmp_vmlinux.kallsyms0
++ kallsyms /dev/null .tmp_vmlinux0.kallsyms
++fi
++
++if is_enabled CONFIG_KALLSYMS || is_enabled CONFIG_DEBUG_INFO_BTF; then
++
++ # The kallsyms linking does not need debug symbols, but the BTF does.
++ if ! is_enabled CONFIG_DEBUG_INFO_BTF; then
++ strip_debug=1
++ fi
++
++ vmlinux_link .tmp_vmlinux1
+ fi
+
+ if is_enabled CONFIG_DEBUG_INFO_BTF; then
+- if ! gen_btf .tmp_vmlinux.btf .btf.vmlinux.bin.o ; then
++ if ! gen_btf .tmp_vmlinux1; then
+ echo >&2 "Failed to generate BTF for vmlinux"
+ echo >&2 "Try to disable CONFIG_DEBUG_INFO_BTF"
+ exit 1
+@@ -260,14 +265,16 @@ if is_enabled CONFIG_KALLSYMS; then
+ # The kallsyms linking does not need debug symbols included.
+ strip_debug=1
+
+- kallsyms_step 1
++ sysmap_and_kallsyms .tmp_vmlinux1
+ size1=$(${CONFIG_SHELL} "${srctree}/scripts/file-size.sh" ${kallsymso})
+
+- kallsyms_step 2
++ vmlinux_link .tmp_vmlinux2
++ sysmap_and_kallsyms .tmp_vmlinux2
+ size2=$(${CONFIG_SHELL} "${srctree}/scripts/file-size.sh" ${kallsymso})
+
+ if [ $size1 -ne $size2 ] || [ -n "${KALLSYMS_EXTRA_PASS}" ]; then
+- kallsyms_step 3
++ vmlinux_link .tmp_vmlinux3
++ sysmap_and_kallsyms .tmp_vmlinux3
+ fi
+ fi
+
+@@ -293,7 +300,7 @@ fi
+
+ # step a (see comment above)
+ if is_enabled CONFIG_KALLSYMS; then
+- if ! cmp -s System.map ${kallsyms_vmlinux}.syms; then
++ if ! cmp -s System.map "${kallsyms_sysmap}"; then
+ echo >&2 Inconsistent kallsyms data
+ echo >&2 'Try "make KALLSYMS_EXTRA_PASS=1" as a workaround'
+ exit 1
+--
+2.43.0
+
--- /dev/null
+From 5a74a5df2363ccb3208481a0779c374f91901428 Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Thu, 15 Aug 2024 15:04:37 -0700
+Subject: kcm: Serialise kcm_sendmsg() for the same socket.
+
+From: Kuniyuki Iwashima <kuniyu@amazon.com>
+
+[ Upstream commit 807067bf014d4a3ae2cc55bd3de16f22a01eb580 ]
+
+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>
+Signed-off-by: Sasha Levin <sashal@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 90279e5e09a5c..441e993be634c 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 2f191e50d4fc9..d4118c796290e 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);
+--
+2.43.0
+
--- /dev/null
+From a4e5db2e003a6b34d6a65561179d99432616cada Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Sun, 4 Aug 2024 14:50:57 +0900
+Subject: Makefile: add $(srctree) to dependency of compile_commands.json
+ target
+
+From: Alexandre Courbot <gnurou@gmail.com>
+
+[ Upstream commit 6fc9aacad49e3fbecd270c266850d50c453d52ef ]
+
+When trying to build compile_commands.json for an external module against
+the kernel built in a separate output directory, the following error is
+displayed:
+
+ make[1]: *** No rule to make target 'scripts/clang-tools/gen_compile_commands.py',
+ needed by 'compile_commands.json'. Stop.
+
+This is because gen_compile_commands.py was previously looked up using a
+relative path to $(srctree), but commit b1992c3772e6 ("kbuild: use
+$(src) instead of $(srctree)/$(src) for source directory") stopped
+defining VPATH for external module builds.
+
+Prefixing gen_compile_commands.py with $(srctree) fixes the problem.
+
+Fixes: b1992c3772e6 ("kbuild: use $(src) instead of $(srctree)/$(src) for source directory")
+Signed-off-by: Alexandre Courbot <gnurou@gmail.com>
+Reviewed-by: Nicolas Schier <nicolas@fjasle.eu>
+Signed-off-by: Masahiro Yamada <masahiroy@kernel.org>
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ Makefile | 2 +-
+ 1 file changed, 1 insertion(+), 1 deletion(-)
+
+diff --git a/Makefile b/Makefile
+index 361a70264e1fb..194841a4efde9 100644
+--- a/Makefile
++++ b/Makefile
+@@ -1986,7 +1986,7 @@ nsdeps: modules
+ quiet_cmd_gen_compile_commands = GEN $@
+ cmd_gen_compile_commands = $(PYTHON3) $< -a $(AR) -o $@ $(filter-out $<, $(real-prereqs))
+
+-$(extmod_prefix)compile_commands.json: scripts/clang-tools/gen_compile_commands.py \
++$(extmod_prefix)compile_commands.json: $(srctree)/scripts/clang-tools/gen_compile_commands.py \
+ $(if $(KBUILD_EXTMOD),, vmlinux.a $(KBUILD_VMLINUX_LIBS)) \
+ $(if $(CONFIG_MODULES), $(MODORDER)) FORCE
+ $(call if_changed,gen_compile_commands)
+--
+2.43.0
+
--- /dev/null
+From e824326b868c630ae7789b334f71992a005bf4c2 Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Mon, 19 Aug 2024 19:52:50 -0400
+Subject: net: dsa: mv88e6xxx: Fix out-of-bound access
+
+From: Joseph Huang <Joseph.Huang@garmin.com>
+
+[ Upstream commit 528876d867a23b5198022baf2e388052ca67c952 ]
+
+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>
+Signed-off-by: Sasha Levin <sashal@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 ce3b3690c3c05..c47f068f56b32 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;
+--
+2.43.0
+
--- /dev/null
+From b778edf298c0814e2a69c380c697a11bad708bd3 Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Fri, 16 Aug 2024 18:29:17 +0800
+Subject: net: mctp: test: Use correct skb for route input check
+
+From: Jeremy Kerr <jk@codeconstruct.com.au>
+
+[ Upstream commit ce335db0621648472f9bb4b7191eb2e13a5793cf ]
+
+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>
+Signed-off-by: Sasha Levin <sashal@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 77e5dd4222580..8551dab1d1e69 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);
+
+--
+2.43.0
+
--- /dev/null
+From bfe6b85bdd5c6e3ba5e84f5cd0cafe3387abe1ac Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Thu, 15 Aug 2024 10:16:11 +0300
+Subject: net/mlx5: Fix IPsec RoCE MPV trace call
+
+From: Patrisious Haddad <phaddad@nvidia.com>
+
+[ Upstream commit 607e1df7bd47fe91cab85a97f57870a26d066137 ]
+
+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>
+Signed-off-by: Sasha Levin <sashal@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 234cd00f71a1c..b7d4b1a2baf2e 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;
+ }
+--
+2.43.0
+
--- /dev/null
+From 719bf7a59f333580ab4d1907a975900474f66bda Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Thu, 15 Aug 2024 10:16:10 +0300
+Subject: net/mlx5e: XPS, Fix oversight of Multi-PF Netdev changes
+
+From: Carolina Jubran <cjubran@nvidia.com>
+
+[ Upstream commit a07e953dafe5ebd88942dc861dfb06eaf055fb07 ]
+
+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>
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ drivers/net/ethernet/mellanox/mlx5/core/en_main.c | 13 ++++++++-----
+ 1 file changed, 8 insertions(+), 5 deletions(-)
+
+diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+index eedbcba226894..409f525f1703c 100644
+--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
++++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+@@ -3005,15 +3005,18 @@ 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++) {
++ int num_comp_vectors, irq, vec_ix;
++ struct mlx5_core_dev *mdev;
++
++ 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 = ix; irq < num_comp_vectors; irq += params->num_channels) {
++ 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);
+--
+2.43.0
+
--- /dev/null
+From ad01d9077e049d77e52e61f98ad750c52b779804 Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Thu, 15 Aug 2024 03:07:03 +0300
+Subject: net: mscc: ocelot: fix QoS class for injected packets with
+ "ocelot-8021q"
+
+From: Vladimir Oltean <vladimir.oltean@nxp.com>
+
+[ Upstream commit e1b9e80236c540fa85d76e2d510d1b38e1968c5d ]
+
+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>
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ 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 69a4e5a90475b..9301716e21d58 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 87b59cc5e4416..00326ae8c708b 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;
+--
+2.43.0
+
--- /dev/null
+From 1dc1be717800969117335feb2edbb9668f57f804 Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Thu, 15 Aug 2024 03:07:04 +0300
+Subject: net: mscc: ocelot: serialize access to the injection/extraction
+ groups
+
+From: Vladimir Oltean <vladimir.oltean@nxp.com>
+
+[ Upstream commit c5e12ac3beb0dd3a718296b2d8af5528e9ab728e ]
+
+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>
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ 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 61e95487732dc..f5d26e724ae65 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;
+ }
+@@ -1504,6 +1506,8 @@ 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;
+@@ -1512,6 +1516,7 @@ 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);
+@@ -1521,6 +1526,8 @@ 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);
+ }
+@@ -1671,6 +1678,8 @@ 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;
+@@ -1707,6 +1716,8 @@ 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 9301716e21d58..f4e027a6fe955 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 993212c3a7da6..c09dd2e3343cb 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 0297bc2277927..846132ca5503d 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);
+--
+2.43.0
+
--- /dev/null
+From 232e4900f7ba50db6b627f9fd74dede2a2ddd58c Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Thu, 15 Aug 2024 03:07:02 +0300
+Subject: net: mscc: ocelot: use ocelot_xmit_get_vlan_info() also for FDMA and
+ register injection
+
+From: Vladimir Oltean <vladimir.oltean@nxp.com>
+
+[ Upstream commit 67c3ca2c5cfe6a50772514e3349b5e7b3b0fac03 ]
+
+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>
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ 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 ed2fb44500b0c..69a4e5a90475b 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 312a468321544..87b59cc5e4416 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 dca2969015d80..6fbfbde68a37c 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 1e1b40f4e664e..0297bc2277927 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 e0e4300bfbd3f..bf6608fc6be70 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;
+--
+2.43.0
+
--- /dev/null
+From a5b60cf3a5ad1de04ea545cc4c6d007054c2cb5e Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Wed, 21 Aug 2024 20:32:52 +0800
+Subject: net: ovs: fix ovs_drop_reasons error
+
+From: Menglong Dong <menglong8.dong@gmail.com>
+
+[ Upstream commit 57fb67783c4011581882f32e656d738da1f82042 ]
+
+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>
+Signed-off-by: Sasha Levin <sashal@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 99d72543abd3a..78d9961fcd446 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
+ };
+--
+2.43.0
+
--- /dev/null
+From d480c09a8698f6ae2c1bf9c71f1fddff0dbe587a Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Thu, 22 Aug 2024 11:40:55 -0400
+Subject: net: xilinx: axienet: Always disable promiscuous mode
+
+From: Sean Anderson <sean.anderson@linux.dev>
+
+[ Upstream commit 4ae738dfef2c0323752ab81786e2d298c9939321 ]
+
+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>
+Signed-off-by: Sasha Levin <sashal@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 fa510f4e26008..b2e4d0b11a7d7 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)
+--
+2.43.0
+
--- /dev/null
+From 7e80bdd7a6b251d69d53e81524c22cdae9936687 Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Thu, 22 Aug 2024 11:40:56 -0400
+Subject: net: xilinx: axienet: Fix dangling multicast addresses
+
+From: Sean Anderson <sean.anderson@linux.dev>
+
+[ Upstream commit 797a68c9de0f5a5447baf4bd3bb9c10a3993435b ]
+
+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>
+Signed-off-by: Sasha Levin <sashal@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 c7d9221fafdcb..09c9f9787180b 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 b2e4d0b11a7d7..559c0d60d9483 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);
++ }
+ }
+
+ /**
+--
+2.43.0
+
--- /dev/null
+From e7f7d0ab9d1ad1ddcdc77307df8a5eade691c212 Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Mon, 19 Aug 2024 10:56:45 -0700
+Subject: netem: fix return value if duplicate enqueue fails
+
+From: Stephen Hemminger <stephen@networkplumber.org>
+
+[ Upstream commit c07ff8592d57ed258afee5a5e04991a48dbaf382 ]
+
+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>
+Signed-off-by: Sasha Levin <sashal@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 edc72962ae63a..0f8d581438c39 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;
+--
+2.43.0
+
--- /dev/null
+From 65ae68542a51a7afcf43c158a3032d551c406dc0 Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Tue, 13 Aug 2024 12:39:46 +0200
+Subject: netfilter: flowtable: validate vlan header
+
+From: Pablo Neira Ayuso <pablo@netfilter.org>
+
+[ Upstream commit 6ea14ccb60c8ab829349979b22b58a941ec4a3ee ]
+
+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>
+Signed-off-by: Sasha Levin <sashal@kernel.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 6eef15648b7b0..b0f1991719324 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 c2c005234dcd3..98edcaa37b38d 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;
+--
+2.43.0
+
--- /dev/null
+From 6dcacb7d0302ddf19d191b698e8f5a36d72ce9d1 Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Tue, 20 Aug 2024 09:54:30 +0200
+Subject: netfilter: nft_counter: Disable BH in nft_counter_offload_stats().
+
+From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
+
+[ Upstream commit 1eacdd71b3436b54d5fc8218c4bb0187d92a6892 ]
+
+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>
+Signed-off-by: Sasha Levin <sashal@kernel.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 291ed2026367e..16f40b503d379 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)
+--
+2.43.0
+
--- /dev/null
+From 502f5b25dd123cd3b7e4bab6f1b6cf84c05c0d87 Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Tue, 20 Aug 2024 09:54:31 +0200
+Subject: netfilter: nft_counter: Synchronize nft_counter_reset() against
+ reader.
+
+From: Sebastian Andrzej Siewior <bigeasy@linutronix.de>
+
+[ Upstream commit a0b39e2dc7017ac667b70bdeee5293e410fab2fb ]
+
+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>
+Signed-off-by: Sasha Levin <sashal@kernel.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 16f40b503d379..eab0dc66bee6b 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();
+ }
+
+--
+2.43.0
+
--- /dev/null
+From f5c51c75acbf2bb8582dd9b3256ed9547c619713 Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Wed, 21 Aug 2024 12:35:58 +0530
+Subject: octeontx2-af: Fix CPT AF register offset calculation
+
+From: Bharat Bhushan <bbhushan2@marvell.com>
+
+[ Upstream commit af688a99eb1fc7ef69774665d61e6be51cea627a ]
+
+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>
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ .../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 3e09d22858147..daf4b951e9059 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;
+
+--
+2.43.0
+
--- /dev/null
+From 2fddac94d8d189dd3b73536556261d3f5af81968 Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Wed, 21 Aug 2024 11:13:37 +0200
+Subject: s390/iucv: Fix vargs handling in iucv_alloc_device()
+
+From: Alexandra Winter <wintera@linux.ibm.com>
+
+[ Upstream commit 0124fb0ebf3b0ef89892d42147c9387be3105318 ]
+
+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>
+Signed-off-by: Sasha Levin <sashal@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 b7bf34a5eb37a..1235307020075 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;
+--
+2.43.0
+
--- /dev/null
+From ff1f338f1729343fea294a70aeff4c8c1d0522f8 Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Tue, 20 Aug 2024 12:53:47 +0200
+Subject: selftests: mlxsw: ethtool_lanes: Source ethtool lib from correct path
+
+From: Ido Schimmel <idosch@nvidia.com>
+
+[ Upstream commit f8669d7b5f5d2d88959456ae9123d8bb6fdc1ebe ]
+
+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>
+Signed-off-by: Sasha Levin <sashal@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 877cd6df94a10..fe905a7f34b3c 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()
+ {
+--
+2.43.0
+
--- /dev/null
+From 33efe9cbe41850fe89a226ed16c07525c810c2ad Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Thu, 15 Aug 2024 15:59:51 +0800
+Subject: selftests: udpgro: no need to load xdp for gro
+MIME-Version: 1.0
+Content-Type: text/plain; charset=UTF-8
+Content-Transfer-Encoding: 8bit
+
+From: Hangbin Liu <liuhangbin@gmail.com>
+
+[ Upstream commit d7818402b1d80347c764001583f6d63fa68c2e1a ]
+
+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>
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ 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 4659cf01e4384..d5ffd8c9172e1 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
+--
+2.43.0
+
--- /dev/null
+From 5aebb126154a4e2300680d11cd7409d2e6723e63 Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Thu, 15 Aug 2024 15:59:50 +0800
+Subject: selftests: udpgro: report error when receive failed
+
+From: Hangbin Liu <liuhangbin@gmail.com>
+
+[ Upstream commit 7167395a4be7930ecac6a33b4e54d7e3dd9ee209 ]
+
+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 $?
+ 1
+
+Fixes: 3327a9c46352 ("selftests: add functionals test for UDP GRO")
+Suggested-by: Paolo Abeni <pabeni@redhat.com>
+Signed-off-by: Hangbin Liu <liuhangbin@gmail.com>
+Signed-off-by: David S. Miller <davem@davemloft.net>
+Signed-off-by: Sasha Levin <sashal@kernel.org>
+---
+ tools/testing/selftests/net/udpgro.sh | 44 ++++++++++++++++-----------
+ 1 file changed, 27 insertions(+), 17 deletions(-)
+
+diff --git a/tools/testing/selftests/net/udpgro.sh b/tools/testing/selftests/net/udpgro.sh
+index 11a1ebda564fd..4659cf01e4384 100755
+--- a/tools/testing/selftests/net/udpgro.sh
++++ b/tools/testing/selftests/net/udpgro.sh
+@@ -46,17 +46,19 @@ run_one() {
+ local -r all="$@"
+ 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
+ }
+
+--
+2.43.0
+
wifi-ath12k-use-128-bytes-aligned-iova-in-transmit-p.patch
platform-surface-aggregator-fix-warning-when-control.patch
alsa-hda-tas2781-use-correct-endian-conversion.patch
+makefile-add-srctree-to-dependency-of-compile_comman.patch
+kbuild-merge-temporary-vmlinux-for-btf-and-kallsyms.patch
+kbuild-avoid-scripts-kallsyms-parsing-dev-null.patch
+bluetooth-hci-invert-le-state-quirk-to-be-opt-out-ra.patch
+bluetooth-hci_core-fix-le-quote-calculation.patch
+bluetooth-smp-fix-assumption-of-central-always-being.patch
+net-mscc-ocelot-use-ocelot_xmit_get_vlan_info-also-f.patch
+net-mscc-ocelot-fix-qos-class-for-injected-packets-w.patch
+net-mscc-ocelot-serialize-access-to-the-injection-ex.patch
+net-mlx5e-xps-fix-oversight-of-multi-pf-netdev-chang.patch
+net-mlx5-fix-ipsec-roce-mpv-trace-call.patch
+tc-testing-don-t-access-non-existent-variable-on-exc.patch
+selftests-udpgro-report-error-when-receive-failed.patch
+selftests-udpgro-no-need-to-load-xdp-for-gro.patch
+tcp-prevent-concurrent-execution-of-tcp_sk_exit_batc.patch
+net-mctp-test-use-correct-skb-for-route-input-check.patch
+kcm-serialise-kcm_sendmsg-for-the-same-socket.patch
+netfilter-nft_counter-disable-bh-in-nft_counter_offl.patch
+netfilter-nft_counter-synchronize-nft_counter_reset-.patch
+ip6_tunnel-fix-broken-gro.patch
+bonding-fix-bond_ipsec_offload_ok-return-type.patch
+bonding-fix-null-pointer-deref-in-bond_ipsec_offload.patch
+bonding-fix-xfrm-real_dev-null-pointer-dereference.patch
+bonding-fix-xfrm-state-handling-when-clearing-active.patch
+ice-fix-page-reuse-when-page_size-is-over-8k.patch
+ice-fix-ice_last_offset-formula.patch
+ice-fix-truesize-operations-for-page_size-8192.patch
+ice-use-internal-pf-id-instead-of-function-number.patch
+dpaa2-switch-fix-error-checking-in-dpaa2_switch_seed.patch
+igb-cope-with-large-max_skb_frags.patch
+net-dsa-mv88e6xxx-fix-out-of-bound-access.patch
+netem-fix-return-value-if-duplicate-enqueue-fails.patch
+udp-fix-receiving-fraglist-gso-packets.patch
+selftests-mlxsw-ethtool_lanes-source-ethtool-lib-fro.patch
+ipv6-prevent-uaf-in-ip6_send_skb.patch
+ipv6-fix-possible-uaf-in-ip6_finish_output2.patch
+ipv6-prevent-possible-uaf-in-ip6_xmit.patch
+bnxt_en-fix-double-dma-unmapping-for-xdp_redirect.patch
+netfilter-flowtable-validate-vlan-header.patch
+octeontx2-af-fix-cpt-af-register-offset-calculation.patch
+net-xilinx-axienet-always-disable-promiscuous-mode.patch
+net-xilinx-axienet-fix-dangling-multicast-addresses.patch
+net-ovs-fix-ovs_drop_reasons-error.patch
+s390-iucv-fix-vargs-handling-in-iucv_alloc_device.patch
--- /dev/null
+From 926e02ac826d2f93c0895913c4b76b82228ecd27 Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Thu, 15 Aug 2024 16:37:13 +0100
+Subject: tc-testing: don't access non-existent variable on exception
+
+From: Simon Horman <horms@kernel.org>
+
+[ Upstream commit a0c9fe5eecc97680323ee83780ea3eaf440ba1b7 ]
+
+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>
+Signed-off-by: Sasha Levin <sashal@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 ee349187636fc..4f255cec0c22e 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
+
+--
+2.43.0
+
--- /dev/null
+From eb6ee959c67ab0e02e6d4d5cca23715bcb918c8f Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Tue, 13 Aug 2024 00:28:25 +0200
+Subject: tcp: prevent concurrent execution of tcp_sk_exit_batch
+
+From: Florian Westphal <fw@strlen.de>
+
+[ Upstream commit 565d121b69980637f040eb4d84289869cdaabedf ]
+
+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>
+Signed-off-by: Sasha Levin <sashal@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 a541659b6562b..8f8f93716ff85 100644
+--- a/net/ipv4/tcp_ipv4.c
++++ b/net/ipv4/tcp_ipv4.c
+@@ -95,6 +95,8 @@ EXPORT_SYMBOL(tcp_hashinfo);
+
+ static DEFINE_PER_CPU(struct sock *, ipv4_tcp_sk);
+
++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,
+@@ -3509,6 +3511,16 @@ 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) {
+@@ -3516,6 +3528,8 @@ 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 = {
+--
+2.43.0
+
--- /dev/null
+From 439f79c5bfece2c5a901518acabe9170b6d6e991 Mon Sep 17 00:00:00 2001
+From: Sasha Levin <sashal@kernel.org>
+Date: Mon, 19 Aug 2024 17:06:21 +0200
+Subject: udp: fix receiving fraglist GSO packets
+
+From: Felix Fietkau <nbd@nbd.name>
+
+[ Upstream commit b128ed5ab27330deeeaf51ea8bb69f1442a96f7f ]
+
+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>
+Signed-off-by: Sasha Levin <sashal@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 ee9af921556a7..5b54f4f32b1cd 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);
+
+ if (skb_gso_ok(gso_skb, features | NETIF_F_GSO_ROBUST)) {
+--
+2.43.0
+
projects / thirdparty / kernel / stable-queue.git / commitdiff
