Including fixes from netfilter.

As Paolo promised we continue to hammer out issues in our selftests.
 This is not the end but probably the peak.
 
 Current release - regressions:
 
  - smc: fix incorrect SMC-D link group matching logic
 
 Current release - new code bugs:
 
  - eth: bnxt: silence WARN() when device skips a timestamp, it happens
 
 Previous releases - regressions:
 
  - ipmr: fix null-deref when forwarding mcast packets
 
  - conntrack: evaluate window negotiation only for packets in the REPLY
    direction, otherwise SYN retransmissions trigger incorrect window
    scale negotiation
 
  - ipset: fix performance regression in swap operation
 
 Previous releases - always broken:
 
  - tcp: add sanity checks to types of pages getting into
    the rx zerocopy path, we only support basic NIC -> user,
    no page cache pages etc.
 
  - ip6_tunnel: make sure to pull inner header in __ip6_tnl_rcv()
 
  - nt_tables: more input sanitization changes
 
  - dsa: mt7530: fix 10M/100M speed on MediaTek MT7988 switch
 
  - bridge: mcast: fix loss of snooping after long uptime,
    jiffies do wrap on 32bit
 
  - xen-netback: properly sync TX responses, protect with locking
 
  - phy: mediatek-ge-soc: sync calibration values with MediaTek SDK,
    increase connection stability
 
  - eth: pds: fixes for various teardown, and reset races
 
 Misc:
 
  - hsr: silence WARN() if we can't alloc supervision frame, it happens
 
 Signed-off-by: Jakub Kicinski <kuba@kernel.org>
 -----BEGIN PGP SIGNATURE-----
 
 iQIzBAABCAAdFiEE6jPA+I1ugmIBA4hXMUZtbf5SIrsFAmW74qQACgkQMUZtbf5S
 Irv8BxAAvGQ8js+HyzDsQ8RYLLzKP+YZbMDwQdpZYSXBEskLSxdEn/SoD+2VOtfD
 5op+ZOusE098Zppj9XEdQoqLDpTuOK5+mVA/85PUVuumz+nh/PfXNDPKO0M6V+pO
 iNq/qR6/gScwPFOzkrNXQaH3gOO1CfFW1Khwf8SPPWx+qCgNQZw3HI6yncukdx/K
 TLLM9LOgOJkhLCjMc7o2zpySQA9ctnVQB/Z6iT+j9EDvB30eyv+gSTT0OJQdMgod
 HpIXh0En52Ndt1Z32vKNoxEIgEWDylgoFUMTTTbJ/mKTwCfseC7PXPs6Kv9CxTJr
 aqFXNJkkF1Lzj09QMtBnfqprST7LEmvdQvOX0B8CT6fdQg0o3l6oz2WiTcpBKV7H
 ArlLLSWq9ABJZZcElR8ESkK3zg1YT42VaXfHsOCduMN1pV+5BbMl0xNSkTJpj+QC
 +r1h/hd09dp+pehJmcT2Coi7kXT2VWJvyqGLWZU7bxmc9wYM/63WHUIWdFAirmRq
 8i2e9WHH6lqmjtzKG2CUpjg92NTpkEPkUDUjpMc+VbUYo583AFt2noNpGvDRZgcq
 3WtcDyyfmX1bOHbagVidtphyQpPki9xt6ZxfgMkIqjNq2qSAr8fWj+cxjSSQvZjR
 +XEc/2NKedXcSnMXSFitsZ4wPJpgCRs2oLBtLQ9SDq4/p6uBSF4=
 =UJVq
 -----END PGP SIGNATURE-----

Merge tag 'net-6.8-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull networking fixes from Jakub Kicinski:
 "Including fixes from netfilter.

  As Paolo promised we continue to hammer out issues in our selftests.
  This is not the end but probably the peak.

  Current release - regressions:

   - smc: fix incorrect SMC-D link group matching logic

  Current release - new code bugs:

   - eth: bnxt: silence WARN() when device skips a timestamp, it happens

  Previous releases - regressions:

   - ipmr: fix null-deref when forwarding mcast packets

   - conntrack: evaluate window negotiation only for packets in the
     REPLY direction, otherwise SYN retransmissions trigger incorrect
     window scale negotiation

   - ipset: fix performance regression in swap operation

  Previous releases - always broken:

   - tcp: add sanity checks to types of pages getting into the rx
     zerocopy path, we only support basic NIC -> user, no page cache
     pages etc.

   - ip6_tunnel: make sure to pull inner header in __ip6_tnl_rcv()

   - nt_tables: more input sanitization changes

   - dsa: mt7530: fix 10M/100M speed on MediaTek MT7988 switch

   - bridge: mcast: fix loss of snooping after long uptime, jiffies do
     wrap on 32bit

   - xen-netback: properly sync TX responses, protect with locking

   - phy: mediatek-ge-soc: sync calibration values with MediaTek SDK,
     increase connection stability

   - eth: pds: fixes for various teardown, and reset races

  Misc:

   - hsr: silence WARN() if we can't alloc supervision frame, it
     happens"

* tag 'net-6.8-rc3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (82 commits)
  doc/netlink/specs: Add missing attr in rt_link spec
  idpf: avoid compiler padding in virtchnl2_ptype struct
  selftests: mptcp: join: stop transfer when check is done (part 2)
  selftests: mptcp: join: stop transfer when check is done (part 1)
  selftests: mptcp: allow changing subtests prefix
  selftests: mptcp: decrease BW in simult flows
  selftests: mptcp: increase timeout to 30 min
  selftests: mptcp: add missing kconfig for NF Mangle
  selftests: mptcp: add missing kconfig for NF Filter in v6
  selftests: mptcp: add missing kconfig for NF Filter
  mptcp: fix data re-injection from stale subflow
  selftests: net: enable some more knobs
  selftests: net: add missing config for NF_TARGET_TTL
  selftests: forwarding: List helper scripts in TEST_FILES Makefile variable
  selftests: net: List helper scripts in TEST_FILES Makefile variable
  selftests: net: Remove executable bits from library scripts
  selftests: bonding: Check initial state
  selftests: team: Add missing config options
  hv_netvsc: Fix race condition between netvsc_probe and netvsc_remove
  xen-netback: properly sync TX responses
  ...

Documentation/ABI/testing/sysfs-class-net-queues

@@ -1,4 +1,4 @@
-What:		/sys/class/<iface>/queues/rx-<queue>/rps_cpus
+What:		/sys/class/net/<iface>/queues/rx-<queue>/rps_cpus
 Date:		March 2010
 KernelVersion:	2.6.35
 Contact:	netdev@vger.kernel.org
@@ -8,7 +8,7 @@ Description:
 		network device queue. Possible values depend on the number
 		of available CPU(s) in the system.
 
-What:		/sys/class/<iface>/queues/rx-<queue>/rps_flow_cnt
+What:		/sys/class/net/<iface>/queues/rx-<queue>/rps_flow_cnt
 Date:		April 2010
 KernelVersion:	2.6.35
 Contact:	netdev@vger.kernel.org
@@ -16,7 +16,7 @@ Description:
 		Number of Receive Packet Steering flows being currently
 		processed by this particular network device receive queue.
 
-What:		/sys/class/<iface>/queues/tx-<queue>/tx_timeout
+What:		/sys/class/net/<iface>/queues/tx-<queue>/tx_timeout
 Date:		November 2011
 KernelVersion:	3.3
 Contact:	netdev@vger.kernel.org
@@ -24,7 +24,7 @@ Description:
 		Indicates the number of transmit timeout events seen by this
 		network interface transmit queue.
 
-What:		/sys/class/<iface>/queues/tx-<queue>/tx_maxrate
+What:		/sys/class/net/<iface>/queues/tx-<queue>/tx_maxrate
 Date:		March 2015
 KernelVersion:	4.1
 Contact:	netdev@vger.kernel.org
@@ -32,7 +32,7 @@ Description:
 		A Mbps max-rate set for the queue, a value of zero means disabled,
 		default is disabled.
 
-What:		/sys/class/<iface>/queues/tx-<queue>/xps_cpus
+What:		/sys/class/net/<iface>/queues/tx-<queue>/xps_cpus
 Date:		November 2010
 KernelVersion:	2.6.38
 Contact:	netdev@vger.kernel.org
@@ -42,7 +42,7 @@ Description:
 		network device transmit queue. Possible values depend on the
 		number of available CPU(s) in the system.
 
-What:		/sys/class/<iface>/queues/tx-<queue>/xps_rxqs
+What:		/sys/class/net/<iface>/queues/tx-<queue>/xps_rxqs
 Date:		June 2018
 KernelVersion:	4.18.0
 Contact:	netdev@vger.kernel.org
@@ -53,7 +53,7 @@ Description:
 		number of available receive queue(s) in the network device.
 		Default is disabled.
 
-What:		/sys/class/<iface>/queues/tx-<queue>/byte_queue_limits/hold_time
+What:		/sys/class/net/<iface>/queues/tx-<queue>/byte_queue_limits/hold_time
 Date:		November 2011
 KernelVersion:	3.3
 Contact:	netdev@vger.kernel.org
@@ -62,7 +62,7 @@ Description:
 		of this particular network device transmit queue.
 		Default value is 1000.
 
-What:		/sys/class/<iface>/queues/tx-<queue>/byte_queue_limits/inflight
+What:		/sys/class/net/<iface>/queues/tx-<queue>/byte_queue_limits/inflight
 Date:		November 2011
 KernelVersion:	3.3
 Contact:	netdev@vger.kernel.org
@@ -70,7 +70,7 @@ Description:
 		Indicates the number of bytes (objects) in flight on this
 		network device transmit queue.
 
-What:		/sys/class/<iface>/queues/tx-<queue>/byte_queue_limits/limit
+What:		/sys/class/net/<iface>/queues/tx-<queue>/byte_queue_limits/limit
 Date:		November 2011
 KernelVersion:	3.3
 Contact:	netdev@vger.kernel.org
@@ -79,7 +79,7 @@ Description:
 		on this network device transmit queue. This value is clamped
 		to be within the bounds defined by limit_max and limit_min.
 
-What:		/sys/class/<iface>/queues/tx-<queue>/byte_queue_limits/limit_max
+What:		/sys/class/net/<iface>/queues/tx-<queue>/byte_queue_limits/limit_max
 Date:		November 2011
 KernelVersion:	3.3
 Contact:	netdev@vger.kernel.org
@@ -88,7 +88,7 @@ Description:
 		queued on this network device transmit queue. See
 		include/linux/dynamic_queue_limits.h for the default value.
 
-What:		/sys/class/<iface>/queues/tx-<queue>/byte_queue_limits/limit_min
+What:		/sys/class/net/<iface>/queues/tx-<queue>/byte_queue_limits/limit_min
 Date:		November 2011
 KernelVersion:	3.3
 Contact:	netdev@vger.kernel.org

Documentation/netlink/specs/rt_link.yaml

@@ -942,6 +942,10 @@ attribute-sets:
       -
         name: gro-ipv4-max-size
         type: u32
+      -
+        name: dpll-pin
+        type: nest
+        nested-attributes: link-dpll-pin-attrs
   -
     name: af-spec-attrs
     attributes:
@@ -1627,6 +1631,12 @@ attribute-sets:
       -
         name: used
         type: u8
+  -
+    name: link-dpll-pin-attrs
+    attributes:
+      -
+        name: id
+        type: u32
 
 sub-messages:
   -

MAINTAINERS

@@ -15181,6 +15181,7 @@ F:	Documentation/networking/net_cachelines/net_device.rst
 F:	drivers/connector/
 F:	drivers/net/
 F:	include/dt-bindings/net/
+F:	include/linux/cn_proc.h
 F:	include/linux/etherdevice.h
 F:	include/linux/fcdevice.h
 F:	include/linux/fddidevice.h
@@ -15188,6 +15189,7 @@ F:	include/linux/hippidevice.h
 F:	include/linux/if_*
 F:	include/linux/inetdevice.h
 F:	include/linux/netdevice.h
+F:	include/uapi/linux/cn_proc.h
 F:	include/uapi/linux/if_*
 F:	include/uapi/linux/netdevice.h
 X:	drivers/net/wireless/
@@ -18085,7 +18087,6 @@ F:	drivers/net/ethernet/qualcomm/emac/
 
 QUALCOMM ETHQOS ETHERNET DRIVER
 M:	Vinod Koul <vkoul@kernel.org>
-R:	Bhupesh Sharma <bhupesh.sharma@linaro.org>
 L:	netdev@vger.kernel.org
 L:	linux-arm-msm@vger.kernel.org
 S:	Maintained

drivers/net/dsa/mt7530.c

@@ -2838,8 +2838,7 @@ static void mt753x_phylink_mac_link_up(struct dsa_switch *ds, int port,
 	/* MT753x MAC works in 1G full duplex mode for all up-clocked
 	 * variants.
 	 */
-	if (interface == PHY_INTERFACE_MODE_INTERNAL ||
+	if (interface == PHY_INTERFACE_MODE_TRGMII ||
-	    interface == PHY_INTERFACE_MODE_TRGMII ||
 	    (phy_interface_mode_is_8023z(interface))) {
 		speed = SPEED_1000;
 		duplex = DUPLEX_FULL;

drivers/net/dsa/mv88e6xxx/chip.c

@@ -3659,7 +3659,7 @@ static int mv88e6xxx_mdio_read_c45(struct mii_bus *bus, int phy, int devad,
 	int err;
 
 	if (!chip->info->ops->phy_read_c45)
-		return -EOPNOTSUPP;
+		return 0xffff;
 
 	mv88e6xxx_reg_lock(chip);
 	err = chip->info->ops->phy_read_c45(chip, bus, phy, devad, reg, &val);

drivers/net/dsa/qca/qca8k-8xxx.c

@@ -2051,12 +2051,11 @@ qca8k_sw_probe(struct mdio_device *mdiodev)
 	priv->info = of_device_get_match_data(priv->dev);
 
 	priv->reset_gpio = devm_gpiod_get_optional(priv->dev, "reset",
-						   GPIOD_ASIS);
+						   GPIOD_OUT_HIGH);
 	if (IS_ERR(priv->reset_gpio))
 		return PTR_ERR(priv->reset_gpio);
 
 	if (priv->reset_gpio) {
-		gpiod_set_value_cansleep(priv->reset_gpio, 1);
 		/* The active low duration must be greater than 10 ms
 		 * and checkpatch.pl wants 20 ms.
 		 */

drivers/net/ethernet/amd/pds_core/adminq.c

@@ -63,6 +63,15 @@ static int pdsc_process_notifyq(struct pdsc_qcq *qcq)
 	return nq_work;
 }
 
+static bool pdsc_adminq_inc_if_up(struct pdsc *pdsc)
+{
+	if (pdsc->state & BIT_ULL(PDSC_S_STOPPING_DRIVER) ||
+	    pdsc->state & BIT_ULL(PDSC_S_FW_DEAD))
+		return false;
+
+	return refcount_inc_not_zero(&pdsc->adminq_refcnt);
+}
+
 void pdsc_process_adminq(struct pdsc_qcq *qcq)
 {
 	union pds_core_adminq_comp *comp;
@@ -75,9 +84,9 @@ void pdsc_process_adminq(struct pdsc_qcq *qcq)
 	int aq_work = 0;
 	int credits;
 
-	/* Don't process AdminQ when shutting down */
+	/* Don't process AdminQ when it's not up */
-	if (pdsc->state & BIT_ULL(PDSC_S_STOPPING_DRIVER)) {
+	if (!pdsc_adminq_inc_if_up(pdsc)) {
-		dev_err(pdsc->dev, "%s: called while PDSC_S_STOPPING_DRIVER\n",
+		dev_err(pdsc->dev, "%s: called while adminq is unavailable\n",
 			__func__);
 		return;
 	}
@@ -124,6 +133,7 @@ void pdsc_process_adminq(struct pdsc_qcq *qcq)
 		pds_core_intr_credits(&pdsc->intr_ctrl[qcq->intx],
 				      credits,
 				      PDS_CORE_INTR_CRED_REARM);
+	refcount_dec(&pdsc->adminq_refcnt);
 }
 
 void pdsc_work_thread(struct work_struct *work)
@@ -135,18 +145,20 @@ void pdsc_work_thread(struct work_struct *work)
 
 irqreturn_t pdsc_adminq_isr(int irq, void *data)
 {
-	struct pdsc_qcq *qcq = data;
+	struct pdsc *pdsc = data;
-	struct pdsc *pdsc = qcq->pdsc;
+	struct pdsc_qcq *qcq;
 
-	/* Don't process AdminQ when shutting down */
+	/* Don't process AdminQ when it's not up */
-	if (pdsc->state & BIT_ULL(PDSC_S_STOPPING_DRIVER)) {
+	if (!pdsc_adminq_inc_if_up(pdsc)) {
-		dev_err(pdsc->dev, "%s: called while PDSC_S_STOPPING_DRIVER\n",
+		dev_err(pdsc->dev, "%s: called while adminq is unavailable\n",
 			__func__);
 		return IRQ_HANDLED;
 	}
 
+	qcq = &pdsc->adminqcq;
 	queue_work(pdsc->wq, &qcq->work);
 	pds_core_intr_mask(&pdsc->intr_ctrl[qcq->intx], PDS_CORE_INTR_MASK_CLEAR);
+	refcount_dec(&pdsc->adminq_refcnt);
 
 	return IRQ_HANDLED;
 }
@@ -179,10 +191,16 @@ static int __pdsc_adminq_post(struct pdsc *pdsc,
 
 	/* Check that the FW is running */
 	if (!pdsc_is_fw_running(pdsc)) {
-		u8 fw_status = ioread8(&pdsc->info_regs->fw_status);
+		if (pdsc->info_regs) {
+			u8 fw_status =
+				ioread8(&pdsc->info_regs->fw_status);
 
 			dev_info(pdsc->dev, "%s: post failed - fw not running %#02x:\n",
 				 __func__, fw_status);
+		} else {
+			dev_info(pdsc->dev, "%s: post failed - BARs not setup\n",
+				 __func__);
+		}
 		ret = -ENXIO;
 
 		goto err_out_unlock;
@@ -230,6 +248,12 @@ int pdsc_adminq_post(struct pdsc *pdsc,
 	int err = 0;
 	int index;
 
+	if (!pdsc_adminq_inc_if_up(pdsc)) {
+		dev_dbg(pdsc->dev, "%s: preventing adminq cmd %u\n",
+			__func__, cmd->opcode);
+		return -ENXIO;
+	}
+
 	wc.qcq = &pdsc->adminqcq;
 	index = __pdsc_adminq_post(pdsc, &pdsc->adminqcq, cmd, comp, &wc);
 	if (index < 0) {
@@ -248,10 +272,16 @@ int pdsc_adminq_post(struct pdsc *pdsc,
 			break;
 
 		if (!pdsc_is_fw_running(pdsc)) {
-			u8 fw_status = ioread8(&pdsc->info_regs->fw_status);
+			if (pdsc->info_regs) {
+				u8 fw_status =
+					ioread8(&pdsc->info_regs->fw_status);
 
 				dev_dbg(pdsc->dev, "%s: post wait failed - fw not running %#02x:\n",
 					__func__, fw_status);
+			} else {
+				dev_dbg(pdsc->dev, "%s: post wait failed - BARs not setup\n",
+					__func__);
+			}
 			err = -ENXIO;
 			break;
 		}
@@ -285,6 +315,8 @@ int pdsc_adminq_post(struct pdsc *pdsc,
 			queue_work(pdsc->wq, &pdsc->health_work);
 	}
 
+	refcount_dec(&pdsc->adminq_refcnt);
+
 	return err;
 }
 EXPORT_SYMBOL_GPL(pdsc_adminq_post);

drivers/net/ethernet/amd/pds_core/core.c

@@ -125,7 +125,7 @@ static int pdsc_qcq_intr_alloc(struct pdsc *pdsc, struct pdsc_qcq *qcq)
 
 	snprintf(name, sizeof(name), "%s-%d-%s",
 		 PDS_CORE_DRV_NAME, pdsc->pdev->bus->number, qcq->q.name);
-	index = pdsc_intr_alloc(pdsc, name, pdsc_adminq_isr, qcq);
+	index = pdsc_intr_alloc(pdsc, name, pdsc_adminq_isr, pdsc);
 	if (index < 0)
 		return index;
 	qcq->intx = index;
@@ -404,10 +404,7 @@ int pdsc_setup(struct pdsc *pdsc, bool init)
 	int numdescs;
 	int err;
 
-	if (init)
 	err = pdsc_dev_init(pdsc);
-	else
-		err = pdsc_dev_reinit(pdsc);
 	if (err)
 		return err;
 
@@ -450,6 +447,7 @@ int pdsc_setup(struct pdsc *pdsc, bool init)
 		pdsc_debugfs_add_viftype(pdsc);
 	}
 
+	refcount_set(&pdsc->adminq_refcnt, 1);
 	clear_bit(PDSC_S_FW_DEAD, &pdsc->state);
 	return 0;
 
@@ -464,6 +462,8 @@ void pdsc_teardown(struct pdsc *pdsc, bool removing)
 
 	if (!pdsc->pdev->is_virtfn)
 		pdsc_devcmd_reset(pdsc);
+	if (pdsc->adminqcq.work.func)
+		cancel_work_sync(&pdsc->adminqcq.work);
 	pdsc_qcq_free(pdsc, &pdsc->notifyqcq);
 	pdsc_qcq_free(pdsc, &pdsc->adminqcq);
 
@@ -476,10 +476,9 @@ void pdsc_teardown(struct pdsc *pdsc, bool removing)
 		for (i = 0; i < pdsc->nintrs; i++)
 			pdsc_intr_free(pdsc, i);
 
-		if (removing) {
 		kfree(pdsc->intr_info);
 		pdsc->intr_info = NULL;
-		}
+		pdsc->nintrs = 0;
 	}
 
 	if (pdsc->kern_dbpage) {
@@ -487,6 +486,7 @@ void pdsc_teardown(struct pdsc *pdsc, bool removing)
 		pdsc->kern_dbpage = NULL;
 	}
 
+	pci_free_irq_vectors(pdsc->pdev);
 	set_bit(PDSC_S_FW_DEAD, &pdsc->state);
 }
 
@@ -512,6 +512,24 @@ void pdsc_stop(struct pdsc *pdsc)
 					   PDS_CORE_INTR_MASK_SET);
 }
 
+static void pdsc_adminq_wait_and_dec_once_unused(struct pdsc *pdsc)
+{
+	/* The driver initializes the adminq_refcnt to 1 when the adminq is
+	 * allocated and ready for use. Other users/requesters will increment
+	 * the refcnt while in use. If the refcnt is down to 1 then the adminq
+	 * is not in use and the refcnt can be cleared and adminq freed. Before
+	 * calling this function the driver will set PDSC_S_FW_DEAD, which
+	 * prevent subsequent attempts to use the adminq and increment the
+	 * refcnt to fail. This guarantees that this function will eventually
+	 * exit.
+	 */
+	while (!refcount_dec_if_one(&pdsc->adminq_refcnt)) {
+		dev_dbg_ratelimited(pdsc->dev, "%s: adminq in use\n",
+				    __func__);
+		cpu_relax();
+	}
+}
+
 void pdsc_fw_down(struct pdsc *pdsc)
 {
 	union pds_core_notifyq_comp reset_event = {
@@ -527,6 +545,8 @@ void pdsc_fw_down(struct pdsc *pdsc)
 	if (pdsc->pdev->is_virtfn)
 		return;
 
+	pdsc_adminq_wait_and_dec_once_unused(pdsc);
+
 	/* Notify clients of fw_down */
 	if (pdsc->fw_reporter)
 		devlink_health_report(pdsc->fw_reporter, "FW down reported", pdsc);
@@ -577,7 +597,13 @@ void pdsc_fw_up(struct pdsc *pdsc)
 
 static void pdsc_check_pci_health(struct pdsc *pdsc)
 {
-	u8 fw_status = ioread8(&pdsc->info_regs->fw_status);
+	u8 fw_status;
+
+	/* some sort of teardown already in progress */
+	if (!pdsc->info_regs)
+		return;
+
+	fw_status = ioread8(&pdsc->info_regs->fw_status);
 
 	/* is PCI broken? */
 	if (fw_status != PDS_RC_BAD_PCI)

drivers/net/ethernet/amd/pds_core/core.h

@@ -184,6 +184,7 @@ struct pdsc {
 	struct mutex devcmd_lock;	/* lock for dev_cmd operations */
 	struct mutex config_lock;	/* lock for configuration operations */
 	spinlock_t adminq_lock;		/* lock for adminq operations */
+	refcount_t adminq_refcnt;
 	struct pds_core_dev_info_regs __iomem *info_regs;
 	struct pds_core_dev_cmd_regs __iomem *cmd_regs;
 	struct pds_core_intr __iomem *intr_ctrl;
@@ -280,7 +281,6 @@ int pdsc_devcmd_locked(struct pdsc *pdsc, union pds_core_dev_cmd *cmd,
 		       union pds_core_dev_comp *comp, int max_seconds);
 int pdsc_devcmd_init(struct pdsc *pdsc);
 int pdsc_devcmd_reset(struct pdsc *pdsc);
-int pdsc_dev_reinit(struct pdsc *pdsc);
 int pdsc_dev_init(struct pdsc *pdsc);
 
 void pdsc_reset_prepare(struct pci_dev *pdev);

drivers/net/ethernet/amd/pds_core/debugfs.c

@@ -64,6 +64,10 @@ DEFINE_SHOW_ATTRIBUTE(identity);
 
 void pdsc_debugfs_add_ident(struct pdsc *pdsc)
 {
+	/* This file will already exist in the reset flow */
+	if (debugfs_lookup("identity", pdsc->dentry))
+		return;
+
 	debugfs_create_file("identity", 0400, pdsc->dentry,
 			    pdsc, &identity_fops);
 }

drivers/net/ethernet/amd/pds_core/dev.c

@@ -57,6 +57,9 @@ int pdsc_err_to_errno(enum pds_core_status_code code)
 
 bool pdsc_is_fw_running(struct pdsc *pdsc)
 {
+	if (!pdsc->info_regs)
+		return false;
+
 	pdsc->fw_status = ioread8(&pdsc->info_regs->fw_status);
 	pdsc->last_fw_time = jiffies;
 	pdsc->last_hb = ioread32(&pdsc->info_regs->fw_heartbeat);
@@ -182,13 +185,17 @@ int pdsc_devcmd_locked(struct pdsc *pdsc, union pds_core_dev_cmd *cmd,
 {
 	int err;
 
+	if (!pdsc->cmd_regs)
+		return -ENXIO;
+
 	memcpy_toio(&pdsc->cmd_regs->cmd, cmd, sizeof(*cmd));
 	pdsc_devcmd_dbell(pdsc);
 	err = pdsc_devcmd_wait(pdsc, cmd->opcode, max_seconds);
-	memcpy_fromio(comp, &pdsc->cmd_regs->comp, sizeof(*comp));
 
 	if ((err == -ENXIO || err == -ETIMEDOUT) && pdsc->wq)
 		queue_work(pdsc->wq, &pdsc->health_work);
+	else
+		memcpy_fromio(comp, &pdsc->cmd_regs->comp, sizeof(*comp));
 
 	return err;
 }
@@ -309,13 +316,6 @@ static int pdsc_identify(struct pdsc *pdsc)
 	return 0;
 }
 
-int pdsc_dev_reinit(struct pdsc *pdsc)
-{
-	pdsc_init_devinfo(pdsc);
-
-	return pdsc_identify(pdsc);
-}
-
 int pdsc_dev_init(struct pdsc *pdsc)
 {
 	unsigned int nintrs;

drivers/net/ethernet/amd/pds_core/devlink.c

@@ -111,6 +111,7 @@ int pdsc_dl_info_get(struct devlink *dl, struct devlink_info_req *req,
 
 	mutex_lock(&pdsc->devcmd_lock);
 	err = pdsc_devcmd_locked(pdsc, &cmd, &comp, pdsc->devcmd_timeout * 2);
+	if (!err)
 		memcpy_fromio(&fw_list, pdsc->cmd_regs->data, sizeof(fw_list));
 	mutex_unlock(&pdsc->devcmd_lock);
 	if (err && err != -EIO)

drivers/net/ethernet/amd/pds_core/fw.c

@@ -107,6 +107,9 @@ int pdsc_firmware_update(struct pdsc *pdsc, const struct firmware *fw,
 
 	dev_info(pdsc->dev, "Installing firmware\n");
 
+	if (!pdsc->cmd_regs)
+		return -ENXIO;
+
 	dl = priv_to_devlink(pdsc);
 	devlink_flash_update_status_notify(dl, "Preparing to flash",
 					   NULL, 0, 0);

drivers/net/ethernet/amd/pds_core/main.c

@@ -37,6 +37,11 @@ static void pdsc_unmap_bars(struct pdsc *pdsc)
 	struct pdsc_dev_bar *bars = pdsc->bars;
 	unsigned int i;
 
+	pdsc->info_regs = NULL;
+	pdsc->cmd_regs = NULL;
+	pdsc->intr_status = NULL;
+	pdsc->intr_ctrl = NULL;
+
 	for (i = 0; i < PDS_CORE_BARS_MAX; i++) {
 		if (bars[i].vaddr)
 			pci_iounmap(pdsc->pdev, bars[i].vaddr);
@@ -293,7 +298,7 @@ static int pdsc_init_pf(struct pdsc *pdsc)
 err_out_teardown:
 	pdsc_teardown(pdsc, PDSC_TEARDOWN_REMOVING);
 err_out_unmap_bars:
-	del_timer_sync(&pdsc->wdtimer);
+	timer_shutdown_sync(&pdsc->wdtimer);
 	if (pdsc->wq)
 		destroy_workqueue(pdsc->wq);
 	mutex_destroy(&pdsc->config_lock);
@@ -420,7 +425,7 @@ static void pdsc_remove(struct pci_dev *pdev)
 		 */
 		pdsc_sriov_configure(pdev, 0);
 
-		del_timer_sync(&pdsc->wdtimer);
+		timer_shutdown_sync(&pdsc->wdtimer);
 		if (pdsc->wq)
 			destroy_workqueue(pdsc->wq);
 
@@ -433,7 +438,6 @@ static void pdsc_remove(struct pci_dev *pdev)
 		mutex_destroy(&pdsc->config_lock);
 		mutex_destroy(&pdsc->devcmd_lock);
 
-		pci_free_irq_vectors(pdev);
 		pdsc_unmap_bars(pdsc);
 		pci_release_regions(pdev);
 	}
@@ -445,13 +449,26 @@ static void pdsc_remove(struct pci_dev *pdev)
 	devlink_free(dl);
 }
 
+static void pdsc_stop_health_thread(struct pdsc *pdsc)
+{
+	timer_shutdown_sync(&pdsc->wdtimer);
+	if (pdsc->health_work.func)
+		cancel_work_sync(&pdsc->health_work);
+}
+
+static void pdsc_restart_health_thread(struct pdsc *pdsc)
+{
+	timer_setup(&pdsc->wdtimer, pdsc_wdtimer_cb, 0);
+	mod_timer(&pdsc->wdtimer, jiffies + 1);
+}
+
 void pdsc_reset_prepare(struct pci_dev *pdev)
 {
 	struct pdsc *pdsc = pci_get_drvdata(pdev);
 
+	pdsc_stop_health_thread(pdsc);
 	pdsc_fw_down(pdsc);
 
-	pci_free_irq_vectors(pdev);
 	pdsc_unmap_bars(pdsc);
 	pci_release_regions(pdev);
 	pci_disable_device(pdev);
@@ -486,6 +503,7 @@ void pdsc_reset_done(struct pci_dev *pdev)
 	}
 
 	pdsc_fw_up(pdsc);
+	pdsc_restart_health_thread(pdsc);
 }
 
 static const struct pci_error_handlers pdsc_err_handler = {

drivers/net/ethernet/broadcom/bnxt/bnxt_ptp.c

@@ -684,7 +684,7 @@ static void bnxt_stamp_tx_skb(struct bnxt *bp, struct sk_buff *skb)
 		timestamp.hwtstamp = ns_to_ktime(ns);
 		skb_tstamp_tx(ptp->tx_skb, &timestamp);
 	} else {
-		netdev_WARN_ONCE(bp->dev,
+		netdev_warn_once(bp->dev,
 				 "TS query for TX timer failed rc = %x\n", rc);
 	}
 

drivers/net/ethernet/google/gve/gve_rx.c

@@ -356,7 +356,7 @@ static enum pkt_hash_types gve_rss_type(__be16 pkt_flags)
 
 static struct sk_buff *gve_rx_add_frags(struct napi_struct *napi,
 					struct gve_rx_slot_page_info *page_info,
-					u16 packet_buffer_size, u16 len,
+					unsigned int truesize, u16 len,
 					struct gve_rx_ctx *ctx)
 {
 	u32 offset = page_info->page_offset + page_info->pad;
@@ -389,10 +389,10 @@ static struct sk_buff *gve_rx_add_frags(struct napi_struct *napi,
 	if (skb != ctx->skb_head) {
 		ctx->skb_head->len += len;
 		ctx->skb_head->data_len += len;
-		ctx->skb_head->truesize += packet_buffer_size;
+		ctx->skb_head->truesize += truesize;
 	}
 	skb_add_rx_frag(skb, num_frags, page_info->page,
-			offset, len, packet_buffer_size);
+			offset, len, truesize);
 
 	return ctx->skb_head;
 }
@@ -486,7 +486,7 @@ static struct sk_buff *gve_rx_copy_to_pool(struct gve_rx_ring *rx,
 
 		memcpy(alloc_page_info.page_address, src, page_info->pad + len);
 		skb = gve_rx_add_frags(napi, &alloc_page_info,
-				       rx->packet_buffer_size,
+				       PAGE_SIZE,
 				       len, ctx);
 
 		u64_stats_update_begin(&rx->statss);

drivers/net/ethernet/intel/e1000e/e1000.h

@@ -360,23 +360,43 @@ s32 e1000e_get_base_timinca(struct e1000_adapter *adapter, u32 *timinca);
  * As a result, a shift of INCVALUE_SHIFT_n is used to fit a value of
  * INCVALUE_n into the TIMINCA register allowing 32+8+(24-INCVALUE_SHIFT_n)
  * bits to count nanoseconds leaving the rest for fractional nonseconds.
+ *
+ * Any given INCVALUE also has an associated maximum adjustment value. This
+ * maximum adjustment value is the largest increase (or decrease) which can be
+ * safely applied without overflowing the INCVALUE. Since INCVALUE has
+ * a maximum range of 24 bits, its largest value is 0xFFFFFF.
+ *
+ * To understand where the maximum value comes from, consider the following
+ * equation:
+ *
+ *   new_incval = base_incval + (base_incval * adjustment) / 1billion
+ *
+ * To avoid overflow that means:
+ *   max_incval = base_incval + (base_incval * max_adj) / billion
+ *
+ * Re-arranging:
+ *   max_adj = floor(((max_incval - base_incval) * 1billion) / 1billion)
  */
 #define INCVALUE_96MHZ		125
 #define INCVALUE_SHIFT_96MHZ	17
 #define INCPERIOD_SHIFT_96MHZ	2
 #define INCPERIOD_96MHZ		(12 >> INCPERIOD_SHIFT_96MHZ)
+#define MAX_PPB_96MHZ		23999900 /* 23,999,900 ppb */
 
 #define INCVALUE_25MHZ		40
 #define INCVALUE_SHIFT_25MHZ	18
 #define INCPERIOD_25MHZ		1
+#define MAX_PPB_25MHZ		599999900 /* 599,999,900 ppb */
 
 #define INCVALUE_24MHZ		125
 #define INCVALUE_SHIFT_24MHZ	14
 #define INCPERIOD_24MHZ		3
+#define MAX_PPB_24MHZ		999999999 /* 999,999,999 ppb */
 
 #define INCVALUE_38400KHZ	26
 #define INCVALUE_SHIFT_38400KHZ	19
 #define INCPERIOD_38400KHZ	1
+#define MAX_PPB_38400KHZ	230769100 /* 230,769,100 ppb */
 
 /* Another drawback of scaling the incvalue by a large factor is the
  * 64-bit SYSTIM register overflows more quickly.  This is dealt with

drivers/net/ethernet/intel/e1000e/ptp.c

@@ -280,8 +280,17 @@ void e1000e_ptp_init(struct e1000_adapter *adapter)
 
 	switch (hw->mac.type) {
 	case e1000_pch2lan:
+		adapter->ptp_clock_info.max_adj = MAX_PPB_96MHZ;
+		break;
 	case e1000_pch_lpt:
+		if (er32(TSYNCRXCTL) & E1000_TSYNCRXCTL_SYSCFI)
+			adapter->ptp_clock_info.max_adj = MAX_PPB_96MHZ;
+		else
+			adapter->ptp_clock_info.max_adj = MAX_PPB_25MHZ;
+		break;
 	case e1000_pch_spt:
+		adapter->ptp_clock_info.max_adj = MAX_PPB_24MHZ;
+		break;
 	case e1000_pch_cnp:
 	case e1000_pch_tgp:
 	case e1000_pch_adp:
@@ -289,15 +298,14 @@ void e1000e_ptp_init(struct e1000_adapter *adapter)
 	case e1000_pch_lnp:
 	case e1000_pch_ptp:
 	case e1000_pch_nvp:
-		if ((hw->mac.type < e1000_pch_lpt) ||
+		if (er32(TSYNCRXCTL) & E1000_TSYNCRXCTL_SYSCFI)
-		    (er32(TSYNCRXCTL) & E1000_TSYNCRXCTL_SYSCFI)) {
+			adapter->ptp_clock_info.max_adj = MAX_PPB_24MHZ;
-			adapter->ptp_clock_info.max_adj = 24000000 - 1;
+		else
+			adapter->ptp_clock_info.max_adj = MAX_PPB_38400KHZ;
 		break;
-		}
-		fallthrough;
 	case e1000_82574:
 	case e1000_82583:
-		adapter->ptp_clock_info.max_adj = 600000000 - 1;
+		adapter->ptp_clock_info.max_adj = MAX_PPB_25MHZ;
 		break;
 	default:
 		break;

drivers/net/ethernet/intel/idpf/virtchnl2.h

@@ -978,7 +978,7 @@ struct virtchnl2_ptype {
 	u8 proto_id_count;
 	__le16 pad;
 	__le16 proto_id[];
-};
+} __packed __aligned(2);
 VIRTCHNL2_CHECK_STRUCT_LEN(6, virtchnl2_ptype);
 
 /**

drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c

@@ -716,7 +716,8 @@ static s32 ixgbe_read_iosf_sb_reg_x550(struct ixgbe_hw *hw, u32 reg_addr,
 	if ((command & IXGBE_SB_IOSF_CTRL_RESP_STAT_MASK) != 0) {
 		error = FIELD_GET(IXGBE_SB_IOSF_CTRL_CMPL_ERR_MASK, command);
 		hw_dbg(hw, "Failed to read, error %x\n", error);
-		return -EIO;
+		ret = -EIO;
+		goto out;
 	}
 
 	if (!ret)

drivers/net/ethernet/marvell/octeontx2/nic/otx2_ethtool.c

@@ -314,7 +314,6 @@ static int otx2_set_channels(struct net_device *dev,
 	pfvf->hw.tx_queues = channel->tx_count;
 	if (pfvf->xdp_prog)
 		pfvf->hw.xdp_queues = channel->rx_count;
-	pfvf->hw.non_qos_queues =  pfvf->hw.tx_queues + pfvf->hw.xdp_queues;
 
 	if (if_up)
 		err = dev->netdev_ops->ndo_open(dev);

drivers/net/ethernet/marvell/octeontx2/nic/otx2_pf.c

@@ -1744,6 +1744,7 @@ int otx2_open(struct net_device *netdev)
 	/* RQ and SQs are mapped to different CQs,
 	 * so find out max CQ IRQs (i.e CINTs) needed.
 	 */
+	pf->hw.non_qos_queues =  pf->hw.tx_queues + pf->hw.xdp_queues;
 	pf->hw.cint_cnt = max3(pf->hw.rx_queues, pf->hw.tx_queues,
 			       pf->hw.tc_tx_queues);
 
@@ -2643,8 +2644,6 @@ static int otx2_xdp_setup(struct otx2_nic *pf, struct bpf_prog *prog)
 		xdp_features_clear_redirect_target(dev);
 	}
 
-	pf->hw.non_qos_queues += pf->hw.xdp_queues;
-
 	if (if_up)
 		otx2_open(pf->netdev);
 

drivers/net/ethernet/marvell/octeontx2/nic/otx2_txrx.c

@@ -1403,7 +1403,7 @@ static bool otx2_xdp_rcv_pkt_handler(struct otx2_nic *pfvf,
 				     struct otx2_cq_queue *cq,
 				     bool *need_xdp_flush)
 {
-	unsigned char *hard_start, *data;
+	unsigned char *hard_start;
 	int qidx = cq->cq_idx;
 	struct xdp_buff xdp;
 	struct page *page;
@@ -1417,9 +1417,8 @@ static bool otx2_xdp_rcv_pkt_handler(struct otx2_nic *pfvf,
 
 	xdp_init_buff(&xdp, pfvf->rbsize, &cq->xdp_rxq);
 
-	data = (unsigned char *)phys_to_virt(pa);
+	hard_start = (unsigned char *)phys_to_virt(pa);
-	hard_start = page_address(page);
+	xdp_prepare_buff(&xdp, hard_start, OTX2_HEAD_ROOM,
-	xdp_prepare_buff(&xdp, hard_start, data - hard_start,
 			 cqe->sg.seg_size, false);
 
 	act = bpf_prog_run_xdp(prog, &xdp);

drivers/net/ethernet/mediatek/mtk_eth_soc.c

@@ -4761,7 +4761,10 @@ static int mtk_probe(struct platform_device *pdev)
 	}
 
 	if (MTK_HAS_CAPS(eth->soc->caps, MTK_36BIT_DMA)) {
-		err = dma_set_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(36));
+		err = dma_set_mask(&pdev->dev, DMA_BIT_MASK(36));
+		if (!err)
+			err = dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(32));
+
 		if (err) {
 			dev_err(&pdev->dev, "Wrong DMA config\n");
 			return -EINVAL;

drivers/net/ethernet/microchip/lan966x/lan966x_port.c

@@ -168,9 +168,10 @@ static void lan966x_port_link_up(struct lan966x_port *port)
 	lan966x_taprio_speed_set(port, config->speed);
 
 	/* Also the GIGA_MODE_ENA(1) needs to be set regardless of the
-	 * port speed for QSGMII ports.
+	 * port speed for QSGMII or SGMII ports.
 	 */
-	if (phy_interface_num_ports(config->portmode) == 4)
+	if (phy_interface_num_ports(config->portmode) == 4 ||
+	    config->portmode == PHY_INTERFACE_MODE_SGMII)
 		mode = DEV_MAC_MODE_CFG_GIGA_MODE_ENA_SET(1);
 
 	lan_wr(config->duplex | mode,

drivers/net/ethernet/netronome/nfp/flower/conntrack.c

@@ -1424,10 +1424,30 @@ static void nfp_nft_ct_translate_mangle_action(struct flow_action_entry *mangle_
 		mangle_action->mangle.mask = (__force u32)cpu_to_be32(mangle_action->mangle.mask);
 		return;
 
+	/* Both struct tcphdr and struct udphdr start with
+	 *	__be16 source;
+	 *	__be16 dest;
+	 * so we can use the same code for both.
+	 */
 	case FLOW_ACT_MANGLE_HDR_TYPE_TCP:
 	case FLOW_ACT_MANGLE_HDR_TYPE_UDP:
-		mangle_action->mangle.val = (__force u16)cpu_to_be16(mangle_action->mangle.val);
+		if (mangle_action->mangle.offset == offsetof(struct tcphdr, source)) {
-		mangle_action->mangle.mask = (__force u16)cpu_to_be16(mangle_action->mangle.mask);
+			mangle_action->mangle.val =
+				(__force u32)cpu_to_be32(mangle_action->mangle.val << 16);
+			/* The mask of mangle action is inverse mask,
+			 * so clear the dest tp port with 0xFFFF to
+			 * instead of rotate-left operation.
+			 */
+			mangle_action->mangle.mask =
+				(__force u32)cpu_to_be32(mangle_action->mangle.mask << 16 | 0xFFFF);
+		}
+		if (mangle_action->mangle.offset == offsetof(struct tcphdr, dest)) {
+			mangle_action->mangle.offset = 0;
+			mangle_action->mangle.val =
+				(__force u32)cpu_to_be32(mangle_action->mangle.val);
+			mangle_action->mangle.mask =
+				(__force u32)cpu_to_be32(mangle_action->mangle.mask);
+		}
 		return;
 
 	default:
@@ -1864,10 +1884,30 @@ int nfp_fl_ct_handle_post_ct(struct nfp_flower_priv *priv,
 {
 	struct flow_rule *rule = flow_cls_offload_flow_rule(flow);
 	struct nfp_fl_ct_flow_entry *ct_entry;
+	struct flow_action_entry *ct_goto;
 	struct nfp_fl_ct_zone_entry *zt;
+	struct flow_action_entry *act;
 	bool wildcarded = false;
 	struct flow_match_ct ct;
-	struct flow_action_entry *ct_goto;
+	int i;
+
+	flow_action_for_each(i, act, &rule->action) {
+		switch (act->id) {
+		case FLOW_ACTION_REDIRECT:
+		case FLOW_ACTION_REDIRECT_INGRESS:
+		case FLOW_ACTION_MIRRED:
+		case FLOW_ACTION_MIRRED_INGRESS:
+			if (act->dev->rtnl_link_ops &&
+			    !strcmp(act->dev->rtnl_link_ops->kind, "openvswitch")) {
+				NL_SET_ERR_MSG_MOD(extack,
+						   "unsupported offload: out port is openvswitch internal port");
+				return -EOPNOTSUPP;
+			}
+			break;
+		default:
+			break;
+		}
+	}
 
 	flow_rule_match_ct(rule, &ct);
 	if (!ct.mask->ct_zone) {

drivers/net/ethernet/stmicro/stmmac/dwmac-imx.c

@@ -353,6 +353,10 @@ static int imx_dwmac_probe(struct platform_device *pdev)
 	if (data->flags & STMMAC_FLAG_HWTSTAMP_CORRECT_LATENCY)
 		plat_dat->flags |= STMMAC_FLAG_HWTSTAMP_CORRECT_LATENCY;
 
+	/* Default TX Q0 to use TSO and rest TXQ for TBS */
+	for (int i = 1; i < plat_dat->tx_queues_to_use; i++)
+		plat_dat->tx_queues_cfg[i].tbs_en = 1;
+
 	plat_dat->host_dma_width = dwmac->ops->addr_width;
 	plat_dat->init = imx_dwmac_init;
 	plat_dat->exit = imx_dwmac_exit;

drivers/net/ethernet/stmicro/stmmac/stmmac_main.c

@@ -3932,6 +3932,9 @@ static int __stmmac_open(struct net_device *dev,
 	priv->rx_copybreak = STMMAC_RX_COPYBREAK;
 
 	buf_sz = dma_conf->dma_buf_sz;
+	for (int i = 0; i < MTL_MAX_TX_QUEUES; i++)
+		if (priv->dma_conf.tx_queue[i].tbs & STMMAC_TBS_EN)
+			dma_conf->tx_queue[i].tbs = priv->dma_conf.tx_queue[i].tbs;
 	memcpy(&priv->dma_conf, dma_conf, sizeof(*dma_conf));
 
 	stmmac_reset_queues_param(priv);

drivers/net/hyperv/netvsc.c

@@ -708,7 +708,10 @@ void netvsc_device_remove(struct hv_device *device)
 	/* Disable NAPI and disassociate its context from the device. */
 	for (i = 0; i < net_device->num_chn; i++) {
 		/* See also vmbus_reset_channel_cb(). */
+		/* only disable enabled NAPI channel */
+		if (i < ndev->real_num_rx_queues)
 			napi_disable(&net_device->chan_table[i].napi);
+
 		netif_napi_del(&net_device->chan_table[i].napi);
 	}
 

drivers/net/phy/mediatek-ge-soc.c

@@ -489,7 +489,7 @@ static int tx_r50_fill_result(struct phy_device *phydev, u16 tx_r50_cal_val,
 	u16 reg, val;
 
 	if (phydev->drv->phy_id == MTK_GPHY_ID_MT7988)
-		bias = -2;
+		bias = -1;
 
 	val = clamp_val(bias + tx_r50_cal_val, 0, 63);
 
@@ -705,6 +705,11 @@ static int tx_vcm_cal_sw(struct phy_device *phydev, u8 rg_txreserve_x)
 static void mt798x_phy_common_finetune(struct phy_device *phydev)
 {
 	phy_select_page(phydev, MTK_PHY_PAGE_EXTENDED_52B5);
+	/* SlvDSPreadyTime = 24, MasDSPreadyTime = 24 */
+	__phy_write(phydev, 0x11, 0xc71);
+	__phy_write(phydev, 0x12, 0xc);
+	__phy_write(phydev, 0x10, 0x8fae);
+
 	/* EnabRandUpdTrig = 1 */
 	__phy_write(phydev, 0x11, 0x2f00);
 	__phy_write(phydev, 0x12, 0xe);
@@ -715,15 +720,56 @@ static void mt798x_phy_common_finetune(struct phy_device *phydev)
 	__phy_write(phydev, 0x12, 0x0);
 	__phy_write(phydev, 0x10, 0x83aa);
 
-	/* TrFreeze = 0 */
+	/* FfeUpdGainForce = 1(Enable), FfeUpdGainForceVal = 4 */
+	__phy_write(phydev, 0x11, 0x240);
+	__phy_write(phydev, 0x12, 0x0);
+	__phy_write(phydev, 0x10, 0x9680);
+
+	/* TrFreeze = 0 (mt7988 default) */
 	__phy_write(phydev, 0x11, 0x0);
 	__phy_write(phydev, 0x12, 0x0);
 	__phy_write(phydev, 0x10, 0x9686);
 
+	/* SSTrKp100 = 5 */
+	/* SSTrKf100 = 6 */
+	/* SSTrKp1000Mas = 5 */
+	/* SSTrKf1000Mas = 6 */
 	/* SSTrKp1000Slv = 5 */
+	/* SSTrKf1000Slv = 6 */
 	__phy_write(phydev, 0x11, 0xbaef);
 	__phy_write(phydev, 0x12, 0x2e);
 	__phy_write(phydev, 0x10, 0x968c);
+	phy_restore_page(phydev, MTK_PHY_PAGE_STANDARD, 0);
+}
+
+static void mt7981_phy_finetune(struct phy_device *phydev)
+{
+	u16 val[8] = { 0x01ce, 0x01c1,
+		       0x020f, 0x0202,
+		       0x03d0, 0x03c0,
+		       0x0013, 0x0005 };
+	int i, k;
+
+	/* 100M eye finetune:
+	 * Keep middle level of TX MLT3 shapper as default.
+	 * Only change TX MLT3 overshoot level here.
+	 */
+	for (k = 0, i = 1; i < 12; i++) {
+		if (i % 3 == 0)
+			continue;
+		phy_write_mmd(phydev, MDIO_MMD_VEND1, i, val[k++]);
+	}
+
+	phy_select_page(phydev, MTK_PHY_PAGE_EXTENDED_52B5);
+	/* ResetSyncOffset = 6 */
+	__phy_write(phydev, 0x11, 0x600);
+	__phy_write(phydev, 0x12, 0x0);
+	__phy_write(phydev, 0x10, 0x8fc0);
+
+	/* VgaDecRate = 1 */
+	__phy_write(phydev, 0x11, 0x4c2a);
+	__phy_write(phydev, 0x12, 0x3e);
+	__phy_write(phydev, 0x10, 0x8fa4);
 
 	/* MrvlTrFix100Kp = 3, MrvlTrFix100Kf = 2,
 	 * MrvlTrFix1000Kp = 3, MrvlTrFix1000Kf = 2
@@ -738,7 +784,7 @@ static void mt798x_phy_common_finetune(struct phy_device *phydev)
 	__phy_write(phydev, 0x10, 0x8ec0);
 	phy_restore_page(phydev, MTK_PHY_PAGE_STANDARD, 0);
 
-	/* TR_OPEN_LOOP_EN = 1, lpf_x_average = 9*/
+	/* TR_OPEN_LOOP_EN = 1, lpf_x_average = 9 */
 	phy_modify_mmd(phydev, MDIO_MMD_VEND1, MTK_PHY_RG_DEV1E_REG234,
 		       MTK_PHY_TR_OPEN_LOOP_EN_MASK | MTK_PHY_LPF_X_AVERAGE_MASK,
 		       BIT(0) | FIELD_PREP(MTK_PHY_LPF_X_AVERAGE_MASK, 0x9));
@@ -771,48 +817,6 @@ static void mt798x_phy_common_finetune(struct phy_device *phydev)
 	phy_write_mmd(phydev, MDIO_MMD_VEND1, MTK_PHY_LDO_OUTPUT_V, 0x2222);
 }
 
-static void mt7981_phy_finetune(struct phy_device *phydev)
-{
-	u16 val[8] = { 0x01ce, 0x01c1,
-		       0x020f, 0x0202,
-		       0x03d0, 0x03c0,
-		       0x0013, 0x0005 };
-	int i, k;
-
-	/* 100M eye finetune:
-	 * Keep middle level of TX MLT3 shapper as default.
-	 * Only change TX MLT3 overshoot level here.
-	 */
-	for (k = 0, i = 1; i < 12; i++) {
-		if (i % 3 == 0)
-			continue;
-		phy_write_mmd(phydev, MDIO_MMD_VEND1, i, val[k++]);
-	}
-
-	phy_select_page(phydev, MTK_PHY_PAGE_EXTENDED_52B5);
-	/* SlvDSPreadyTime = 24, MasDSPreadyTime = 24 */
-	__phy_write(phydev, 0x11, 0xc71);
-	__phy_write(phydev, 0x12, 0xc);
-	__phy_write(phydev, 0x10, 0x8fae);
-
-	/* ResetSyncOffset = 6 */
-	__phy_write(phydev, 0x11, 0x600);
-	__phy_write(phydev, 0x12, 0x0);
-	__phy_write(phydev, 0x10, 0x8fc0);
-
-	/* VgaDecRate = 1 */
-	__phy_write(phydev, 0x11, 0x4c2a);
-	__phy_write(phydev, 0x12, 0x3e);
-	__phy_write(phydev, 0x10, 0x8fa4);
-
-	/* FfeUpdGainForce = 4 */
-	__phy_write(phydev, 0x11, 0x240);
-	__phy_write(phydev, 0x12, 0x0);
-	__phy_write(phydev, 0x10, 0x9680);
-
-	phy_restore_page(phydev, MTK_PHY_PAGE_STANDARD, 0);
-}
-
 static void mt7988_phy_finetune(struct phy_device *phydev)
 {
 	u16 val[12] = { 0x0187, 0x01cd, 0x01c8, 0x0182,
@@ -827,17 +831,7 @@ static void mt7988_phy_finetune(struct phy_device *phydev)
 	/* TCT finetune */
 	phy_write_mmd(phydev, MDIO_MMD_VEND1, MTK_PHY_RG_TX_FILTER, 0x5);
 
-	/* Disable TX power saving */
-	phy_modify_mmd(phydev, MDIO_MMD_VEND1, MTK_PHY_RXADC_CTRL_RG7,
-		       MTK_PHY_DA_AD_BUF_BIAS_LP_MASK, 0x3 << 8);
-
 	phy_select_page(phydev, MTK_PHY_PAGE_EXTENDED_52B5);
-
-	/* SlvDSPreadyTime = 24, MasDSPreadyTime = 12 */
-	__phy_write(phydev, 0x11, 0x671);
-	__phy_write(phydev, 0x12, 0xc);
-	__phy_write(phydev, 0x10, 0x8fae);
-
 	/* ResetSyncOffset = 5 */
 	__phy_write(phydev, 0x11, 0x500);
 	__phy_write(phydev, 0x12, 0x0);
@@ -845,13 +839,27 @@ static void mt7988_phy_finetune(struct phy_device *phydev)
 
 	/* VgaDecRate is 1 at default on mt7988 */
 
+	/* MrvlTrFix100Kp = 6, MrvlTrFix100Kf = 7,
+	 * MrvlTrFix1000Kp = 6, MrvlTrFix1000Kf = 7
+	 */
+	__phy_write(phydev, 0x11, 0xb90a);
+	__phy_write(phydev, 0x12, 0x6f);
+	__phy_write(phydev, 0x10, 0x8f82);
+
+	/* RemAckCntLimitCtrl = 1 */
+	__phy_write(phydev, 0x11, 0xfbba);
+	__phy_write(phydev, 0x12, 0xc3);
+	__phy_write(phydev, 0x10, 0x87f8);
+
 	phy_restore_page(phydev, MTK_PHY_PAGE_STANDARD, 0);
 
-	phy_select_page(phydev, MTK_PHY_PAGE_EXTENDED_2A30);
+	/* TR_OPEN_LOOP_EN = 1, lpf_x_average = 10 */
-	/* TxClkOffset = 2 */
+	phy_modify_mmd(phydev, MDIO_MMD_VEND1, MTK_PHY_RG_DEV1E_REG234,
-	__phy_modify(phydev, MTK_PHY_ANARG_RG, MTK_PHY_TCLKOFFSET_MASK,
+		       MTK_PHY_TR_OPEN_LOOP_EN_MASK | MTK_PHY_LPF_X_AVERAGE_MASK,
-		     FIELD_PREP(MTK_PHY_TCLKOFFSET_MASK, 0x2));
+		       BIT(0) | FIELD_PREP(MTK_PHY_LPF_X_AVERAGE_MASK, 0xa));
-	phy_restore_page(phydev, MTK_PHY_PAGE_STANDARD, 0);
+
+	/* rg_tr_lpf_cnt_val = 1023 */
+	phy_write_mmd(phydev, MDIO_MMD_VEND1, MTK_PHY_RG_LPF_CNT_VAL, 0x3ff);
 }
 
 static void mt798x_phy_eee(struct phy_device *phydev)
@@ -884,11 +892,11 @@ static void mt798x_phy_eee(struct phy_device *phydev)
 		       MTK_PHY_LPI_SLV_SEND_TX_EN,
 		       FIELD_PREP(MTK_PHY_LPI_SLV_SEND_TX_TIMER_MASK, 0x120));
 
-	phy_modify_mmd(phydev, MDIO_MMD_VEND1, MTK_PHY_RG_DEV1E_REG239,
+	/* Keep MTK_PHY_LPI_SEND_LOC_TIMER as 375 */
-		       MTK_PHY_LPI_SEND_LOC_TIMER_MASK |
+	phy_clear_bits_mmd(phydev, MDIO_MMD_VEND1, MTK_PHY_RG_DEV1E_REG239,
-		       MTK_PHY_LPI_TXPCS_LOC_RCV,
+			   MTK_PHY_LPI_TXPCS_LOC_RCV);
-		       FIELD_PREP(MTK_PHY_LPI_SEND_LOC_TIMER_MASK, 0x117));
 
+	/* This also fixes some IoT issues, such as CH340 */
 	phy_modify_mmd(phydev, MDIO_MMD_VEND1, MTK_PHY_RG_DEV1E_REG2C7,
 		       MTK_PHY_MAX_GAIN_MASK | MTK_PHY_MIN_GAIN_MASK,
 		       FIELD_PREP(MTK_PHY_MAX_GAIN_MASK, 0x8) |
@@ -922,7 +930,7 @@ static void mt798x_phy_eee(struct phy_device *phydev)
 	__phy_write(phydev, 0x12, 0x0);
 	__phy_write(phydev, 0x10, 0x9690);
 
-	/* REG_EEE_st2TrKf1000 = 3 */
+	/* REG_EEE_st2TrKf1000 = 2 */
 	__phy_write(phydev, 0x11, 0x114f);
 	__phy_write(phydev, 0x12, 0x2);
 	__phy_write(phydev, 0x10, 0x969a);
@@ -947,7 +955,7 @@ static void mt798x_phy_eee(struct phy_device *phydev)
 	__phy_write(phydev, 0x12, 0x0);
 	__phy_write(phydev, 0x10, 0x96b8);
 
-	/* REGEEE_wake_slv_tr_wait_dfesigdet_en = 1 */
+	/* REGEEE_wake_slv_tr_wait_dfesigdet_en = 0 */
 	__phy_write(phydev, 0x11, 0x1463);
 	__phy_write(phydev, 0x12, 0x0);
 	__phy_write(phydev, 0x10, 0x96ca);
@@ -1459,6 +1467,13 @@ static int mt7988_phy_probe(struct phy_device *phydev)
 	if (err)
 		return err;
 
+	/* Disable TX power saving at probing to:
+	 * 1. Meet common mode compliance test criteria
+	 * 2. Make sure that TX-VCM calibration works fine
+	 */
+	phy_modify_mmd(phydev, MDIO_MMD_VEND1, MTK_PHY_RXADC_CTRL_RG7,
+		       MTK_PHY_DA_AD_BUF_BIAS_LP_MASK, 0x3 << 8);
+
 	return mt798x_phy_calibration(phydev);
 }
 

drivers/net/xen-netback/netback.c

@@ -104,13 +104,12 @@ bool provides_xdp_headroom = true;
 module_param(provides_xdp_headroom, bool, 0644);
 
 static void xenvif_idx_release(struct xenvif_queue *queue, u16 pending_idx,
-			       u8 status);
+			       s8 status);
 
 static void make_tx_response(struct xenvif_queue *queue,
-			     struct xen_netif_tx_request *txp,
+			     const struct xen_netif_tx_request *txp,
 			     unsigned int extra_count,
-			     s8       st);
+			     s8 status);
-static void push_tx_responses(struct xenvif_queue *queue);
 
 static void xenvif_idx_unmap(struct xenvif_queue *queue, u16 pending_idx);
 
@@ -208,13 +207,9 @@ static void xenvif_tx_err(struct xenvif_queue *queue,
 			  unsigned int extra_count, RING_IDX end)
 {
 	RING_IDX cons = queue->tx.req_cons;
-	unsigned long flags;
 
 	do {
-		spin_lock_irqsave(&queue->response_lock, flags);
 		make_tx_response(queue, txp, extra_count, XEN_NETIF_RSP_ERROR);
-		push_tx_responses(queue);
-		spin_unlock_irqrestore(&queue->response_lock, flags);
 		if (cons == end)
 			break;
 		RING_COPY_REQUEST(&queue->tx, cons++, txp);
@@ -465,12 +460,7 @@ static void xenvif_get_requests(struct xenvif_queue *queue,
 	for (shinfo->nr_frags = 0; nr_slots > 0 && shinfo->nr_frags < MAX_SKB_FRAGS;
 	     nr_slots--) {
 		if (unlikely(!txp->size)) {
-			unsigned long flags;
-
-			spin_lock_irqsave(&queue->response_lock, flags);
 			make_tx_response(queue, txp, 0, XEN_NETIF_RSP_OKAY);
-			push_tx_responses(queue);
-			spin_unlock_irqrestore(&queue->response_lock, flags);
 			++txp;
 			continue;
 		}
@@ -496,14 +486,8 @@ static void xenvif_get_requests(struct xenvif_queue *queue,
 
 		for (shinfo->nr_frags = 0; shinfo->nr_frags < nr_slots; ++txp) {
 			if (unlikely(!txp->size)) {
-				unsigned long flags;
-
-				spin_lock_irqsave(&queue->response_lock, flags);
 				make_tx_response(queue, txp, 0,
 						 XEN_NETIF_RSP_OKAY);
-				push_tx_responses(queue);
-				spin_unlock_irqrestore(&queue->response_lock,
-						       flags);
 				continue;
 			}
 
@@ -995,7 +979,6 @@ static void xenvif_tx_build_gops(struct xenvif_queue *queue,
 					 (ret == 0) ?
 					 XEN_NETIF_RSP_OKAY :
 					 XEN_NETIF_RSP_ERROR);
-			push_tx_responses(queue);
 			continue;
 		}
 
@@ -1007,7 +990,6 @@ static void xenvif_tx_build_gops(struct xenvif_queue *queue,
 
 			make_tx_response(queue, &txreq, extra_count,
 					 XEN_NETIF_RSP_OKAY);
-			push_tx_responses(queue);
 			continue;
 		}
 
@@ -1433,44 +1415,17 @@ int xenvif_tx_action(struct xenvif_queue *queue, int budget)
 	return work_done;
 }
 
-static void xenvif_idx_release(struct xenvif_queue *queue, u16 pending_idx,
+static void _make_tx_response(struct xenvif_queue *queue,
-			       u8 status)
+			     const struct xen_netif_tx_request *txp,
-{
-	struct pending_tx_info *pending_tx_info;
-	pending_ring_idx_t index;
-	unsigned long flags;
-
-	pending_tx_info = &queue->pending_tx_info[pending_idx];
-
-	spin_lock_irqsave(&queue->response_lock, flags);
-
-	make_tx_response(queue, &pending_tx_info->req,
-			 pending_tx_info->extra_count, status);
-
-	/* Release the pending index before pusing the Tx response so
-	 * its available before a new Tx request is pushed by the
-	 * frontend.
-	 */
-	index = pending_index(queue->pending_prod++);
-	queue->pending_ring[index] = pending_idx;
-
-	push_tx_responses(queue);
-
-	spin_unlock_irqrestore(&queue->response_lock, flags);
-}
-
-
-static void make_tx_response(struct xenvif_queue *queue,
-			     struct xen_netif_tx_request *txp,
 			     unsigned int extra_count,
-			     s8       st)
+			     s8 status)
 {
 	RING_IDX i = queue->tx.rsp_prod_pvt;
 	struct xen_netif_tx_response *resp;
 
 	resp = RING_GET_RESPONSE(&queue->tx, i);
 	resp->id     = txp->id;
-	resp->status = st;
+	resp->status = status;
 
 	while (extra_count-- != 0)
 		RING_GET_RESPONSE(&queue->tx, ++i)->status = XEN_NETIF_RSP_NULL;
@@ -1487,6 +1442,47 @@ static void push_tx_responses(struct xenvif_queue *queue)
 		notify_remote_via_irq(queue->tx_irq);
 }
 
+static void xenvif_idx_release(struct xenvif_queue *queue, u16 pending_idx,
+			       s8 status)
+{
+	struct pending_tx_info *pending_tx_info;
+	pending_ring_idx_t index;
+	unsigned long flags;
+
+	pending_tx_info = &queue->pending_tx_info[pending_idx];
+
+	spin_lock_irqsave(&queue->response_lock, flags);
+
+	_make_tx_response(queue, &pending_tx_info->req,
+			  pending_tx_info->extra_count, status);
+
+	/* Release the pending index before pusing the Tx response so
+	 * its available before a new Tx request is pushed by the
+	 * frontend.
+	 */
+	index = pending_index(queue->pending_prod++);
+	queue->pending_ring[index] = pending_idx;
+
+	push_tx_responses(queue);
+
+	spin_unlock_irqrestore(&queue->response_lock, flags);
+}
+
+static void make_tx_response(struct xenvif_queue *queue,
+			     const struct xen_netif_tx_request *txp,
+			     unsigned int extra_count,
+			     s8 status)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&queue->response_lock, flags);
+
+	_make_tx_response(queue, txp, extra_count, status);
+	push_tx_responses(queue);
+
+	spin_unlock_irqrestore(&queue->response_lock, flags);
+}
+
 static void xenvif_idx_unmap(struct xenvif_queue *queue, u16 pending_idx)
 {
 	int ret;

include/linux/netfilter/ipset/ip_set.h

@@ -186,6 +186,8 @@ struct ip_set_type_variant {
 	/* Return true if "b" set is the same as "a"
 	 * according to the create set parameters */
 	bool (*same_set)(const struct ip_set *a, const struct ip_set *b);
+	/* Cancel ongoing garbage collectors before destroying the set*/
+	void (*cancel_gc)(struct ip_set *set);
 	/* Region-locking is used */
 	bool region_lock;
 };
@@ -242,6 +244,8 @@ extern void ip_set_type_unregister(struct ip_set_type *set_type);
 
 /* A generic IP set */
 struct ip_set {
+	/* For call_cru in destroy */
+	struct rcu_head rcu;
 	/* The name of the set */
 	char name[IPSET_MAXNAMELEN];
 	/* Lock protecting the set data */

include/net/af_unix.h

@@ -46,12 +46,6 @@ struct scm_stat {
 
 #define UNIXCB(skb)	(*(struct unix_skb_parms *)&((skb)->cb))
 
-#define unix_state_lock(s)	spin_lock(&unix_sk(s)->lock)
-#define unix_state_unlock(s)	spin_unlock(&unix_sk(s)->lock)
-#define unix_state_lock_nested(s) \
-				spin_lock_nested(&unix_sk(s)->lock, \
-				SINGLE_DEPTH_NESTING)
-
 /* The AF_UNIX socket */
 struct unix_sock {
 	/* WARNING: sk has to be the first member */
@@ -77,6 +71,20 @@ struct unix_sock {
 #define unix_sk(ptr) container_of_const(ptr, struct unix_sock, sk)
 #define unix_peer(sk) (unix_sk(sk)->peer)
 
+#define unix_state_lock(s)	spin_lock(&unix_sk(s)->lock)
+#define unix_state_unlock(s)	spin_unlock(&unix_sk(s)->lock)
+enum unix_socket_lock_class {
+	U_LOCK_NORMAL,
+	U_LOCK_SECOND,	/* for double locking, see unix_state_double_lock(). */
+	U_LOCK_DIAG, /* used while dumping icons, see sk_diag_dump_icons(). */
+};
+
+static inline void unix_state_lock_nested(struct sock *sk,
+				   enum unix_socket_lock_class subclass)
+{
+	spin_lock_nested(&unix_sk(sk)->lock, subclass);
+}
+
 #define peer_wait peer_wq.wait
 
 long unix_inq_len(struct sock *sk);

include/net/ip.h

@@ -767,7 +767,7 @@ int ip_options_rcv_srr(struct sk_buff *skb, struct net_device *dev);
  *	Functions provided by ip_sockglue.c
  */
 
-void ipv4_pktinfo_prepare(const struct sock *sk, struct sk_buff *skb);
+void ipv4_pktinfo_prepare(const struct sock *sk, struct sk_buff *skb, bool drop_dst);
 void ip_cmsg_recv_offset(struct msghdr *msg, struct sock *sk,
 			 struct sk_buff *skb, int tlen, int offset);
 int ip_cmsg_send(struct sock *sk, struct msghdr *msg,

include/net/netfilter/nf_tables.h

@@ -1351,6 +1351,7 @@ void nft_obj_notify(struct net *net, const struct nft_table *table,
  *	@type: stateful object numeric type
  *	@owner: module owner
  *	@maxattr: maximum netlink attribute
+ *	@family: address family for AF-specific object types
  *	@policy: netlink attribute policy
  */
 struct nft_object_type {
@@ -1360,6 +1361,7 @@ struct nft_object_type {
 	struct list_head		list;
 	u32				type;
 	unsigned int                    maxattr;
+	u8				family;
 	struct module			*owner;
 	const struct nla_policy		*policy;
 };

net/batman-adv/multicast.c

@@ -2175,6 +2175,7 @@ void batadv_mcast_free(struct batadv_priv *bat_priv)
 	cancel_delayed_work_sync(&bat_priv->mcast.work);
 
 	batadv_tvlv_container_unregister(bat_priv, BATADV_TVLV_MCAST, 2);
+	batadv_tvlv_handler_unregister(bat_priv, BATADV_TVLV_MCAST_TRACKER, 1);
 	batadv_tvlv_handler_unregister(bat_priv, BATADV_TVLV_MCAST, 2);
 
 	/* safely calling outside of worker, as worker was canceled above */
@@ -2198,6 +2199,8 @@ void batadv_mcast_purge_orig(struct batadv_orig_node *orig)
 				      BATADV_MCAST_WANT_NO_RTR4);
 	batadv_mcast_want_rtr6_update(bat_priv, orig,
 				      BATADV_MCAST_WANT_NO_RTR6);
+	batadv_mcast_have_mc_ptype_update(bat_priv, orig,
+					  BATADV_MCAST_HAVE_MC_PTYPE_CAPA);
 
 	spin_unlock_bh(&orig->mcast_handler_lock);
 }

net/bridge/br_multicast.c

@@ -1762,6 +1762,10 @@ static void br_ip6_multicast_querier_expired(struct timer_list *t)
 }
 #endif
 
+static void br_multicast_query_delay_expired(struct timer_list *t)
+{
+}
+
 static void br_multicast_select_own_querier(struct net_bridge_mcast *brmctx,
 					    struct br_ip *ip,
 					    struct sk_buff *skb)
@@ -3198,7 +3202,7 @@ br_multicast_update_query_timer(struct net_bridge_mcast *brmctx,
 				unsigned long max_delay)
 {
 	if (!timer_pending(&query->timer))
-		query->delay_time = jiffies + max_delay;
+		mod_timer(&query->delay_timer, jiffies + max_delay);
 
 	mod_timer(&query->timer, jiffies + brmctx->multicast_querier_interval);
 }
@@ -4041,13 +4045,11 @@ void br_multicast_ctx_init(struct net_bridge *br,
 	brmctx->multicast_querier_interval = 255 * HZ;
 	brmctx->multicast_membership_interval = 260 * HZ;
 
-	brmctx->ip4_other_query.delay_time = 0;
 	brmctx->ip4_querier.port_ifidx = 0;
 	seqcount_spinlock_init(&brmctx->ip4_querier.seq, &br->multicast_lock);
 	brmctx->multicast_igmp_version = 2;
 #if IS_ENABLED(CONFIG_IPV6)
 	brmctx->multicast_mld_version = 1;
-	brmctx->ip6_other_query.delay_time = 0;
 	brmctx->ip6_querier.port_ifidx = 0;
 	seqcount_spinlock_init(&brmctx->ip6_querier.seq, &br->multicast_lock);
 #endif
@@ -4056,6 +4058,8 @@ void br_multicast_ctx_init(struct net_bridge *br,
 		    br_ip4_multicast_local_router_expired, 0);
 	timer_setup(&brmctx->ip4_other_query.timer,
 		    br_ip4_multicast_querier_expired, 0);
+	timer_setup(&brmctx->ip4_other_query.delay_timer,
+		    br_multicast_query_delay_expired, 0);
 	timer_setup(&brmctx->ip4_own_query.timer,
 		    br_ip4_multicast_query_expired, 0);
 #if IS_ENABLED(CONFIG_IPV6)
@@ -4063,6 +4067,8 @@ void br_multicast_ctx_init(struct net_bridge *br,
 		    br_ip6_multicast_local_router_expired, 0);
 	timer_setup(&brmctx->ip6_other_query.timer,
 		    br_ip6_multicast_querier_expired, 0);
+	timer_setup(&brmctx->ip6_other_query.delay_timer,
+		    br_multicast_query_delay_expired, 0);
 	timer_setup(&brmctx->ip6_own_query.timer,
 		    br_ip6_multicast_query_expired, 0);
 #endif
@@ -4197,10 +4203,12 @@ static void __br_multicast_stop(struct net_bridge_mcast *brmctx)
 {
 	del_timer_sync(&brmctx->ip4_mc_router_timer);
 	del_timer_sync(&brmctx->ip4_other_query.timer);
+	del_timer_sync(&brmctx->ip4_other_query.delay_timer);
 	del_timer_sync(&brmctx->ip4_own_query.timer);
 #if IS_ENABLED(CONFIG_IPV6)
 	del_timer_sync(&brmctx->ip6_mc_router_timer);
 	del_timer_sync(&brmctx->ip6_other_query.timer);
+	del_timer_sync(&brmctx->ip6_other_query.delay_timer);
 	del_timer_sync(&brmctx->ip6_own_query.timer);
 #endif
 }
@@ -4643,13 +4651,15 @@ int br_multicast_set_querier(struct net_bridge_mcast *brmctx, unsigned long val)
 	max_delay = brmctx->multicast_query_response_interval;
 
 	if (!timer_pending(&brmctx->ip4_other_query.timer))
-		brmctx->ip4_other_query.delay_time = jiffies + max_delay;
+		mod_timer(&brmctx->ip4_other_query.delay_timer,
+			  jiffies + max_delay);
 
 	br_multicast_start_querier(brmctx, &brmctx->ip4_own_query);
 
 #if IS_ENABLED(CONFIG_IPV6)
 	if (!timer_pending(&brmctx->ip6_other_query.timer))
-		brmctx->ip6_other_query.delay_time = jiffies + max_delay;
+		mod_timer(&brmctx->ip6_other_query.delay_timer,
+			  jiffies + max_delay);
 
 	br_multicast_start_querier(brmctx, &brmctx->ip6_own_query);
 #endif

net/bridge/br_private.h

@@ -78,7 +78,7 @@ struct bridge_mcast_own_query {
 /* other querier */
 struct bridge_mcast_other_query {
 	struct timer_list		timer;
-	unsigned long			delay_time;
+	struct timer_list		delay_timer;
 };
 
 /* selected querier */
@@ -1159,7 +1159,7 @@ __br_multicast_querier_exists(struct net_bridge_mcast *brmctx,
 		own_querier_enabled = false;
 	}
 
-	return time_is_before_jiffies(querier->delay_time) &&
+	return !timer_pending(&querier->delay_timer) &&
 	       (own_querier_enabled || timer_pending(&querier->timer));
 }
 

net/devlink/port.c

@@ -674,7 +674,7 @@ static int devlink_port_function_validate(struct devlink_port *devlink_port,
 		return -EOPNOTSUPP;
 	}
 	if (tb[DEVLINK_PORT_FN_ATTR_STATE] && !ops->port_fn_state_set) {
-		NL_SET_ERR_MSG_ATTR(extack, tb[DEVLINK_PORT_FUNCTION_ATTR_HW_ADDR],
+		NL_SET_ERR_MSG_ATTR(extack, tb[DEVLINK_PORT_FN_ATTR_STATE],
 				    "Function does not support state setting");
 		return -EOPNOTSUPP;
 	}

net/hsr/hsr_device.c

@@ -308,7 +308,7 @@ static void send_hsr_supervision_frame(struct hsr_port *master,
 
 	skb = hsr_init_skb(master);
 	if (!skb) {
-		WARN_ONCE(1, "HSR: Could not send supervision frame\n");
+		netdev_warn_once(master->dev, "HSR: Could not send supervision frame\n");
 		return;
 	}
 
@@ -355,7 +355,7 @@ static void send_prp_supervision_frame(struct hsr_port *master,
 
 	skb = hsr_init_skb(master);
 	if (!skb) {
-		WARN_ONCE(1, "PRP: Could not send supervision frame\n");
+		netdev_warn_once(master->dev, "PRP: Could not send supervision frame\n");
 		return;
 	}
 

net/ipv4/ip_output.c

@@ -1287,6 +1287,12 @@ static int ip_setup_cork(struct sock *sk, struct inet_cork *cork,
 	if (unlikely(!rt))
 		return -EFAULT;
 
+	cork->fragsize = ip_sk_use_pmtu(sk) ?
+			 dst_mtu(&rt->dst) : READ_ONCE(rt->dst.dev->mtu);
+
+	if (!inetdev_valid_mtu(cork->fragsize))
+		return -ENETUNREACH;
+
 	/*
 	 * setup for corking.
 	 */
@@ -1303,12 +1309,6 @@ static int ip_setup_cork(struct sock *sk, struct inet_cork *cork,
 		cork->addr = ipc->addr;
 	}
 
-	cork->fragsize = ip_sk_use_pmtu(sk) ?
-			 dst_mtu(&rt->dst) : READ_ONCE(rt->dst.dev->mtu);
-
-	if (!inetdev_valid_mtu(cork->fragsize))
-		return -ENETUNREACH;
-
 	cork->gso_size = ipc->gso_size;
 
 	cork->dst = &rt->dst;

net/ipv4/ip_sockglue.c

@@ -1363,12 +1363,13 @@ int do_ip_setsockopt(struct sock *sk, int level, int optname,
  * ipv4_pktinfo_prepare - transfer some info from rtable to skb
  * @sk: socket
  * @skb: buffer
+ * @drop_dst: if true, drops skb dst
  *
  * To support IP_CMSG_PKTINFO option, we store rt_iif and specific
  * destination in skb->cb[] before dst drop.
  * This way, receiver doesn't make cache line misses to read rtable.
  */
-void ipv4_pktinfo_prepare(const struct sock *sk, struct sk_buff *skb)
+void ipv4_pktinfo_prepare(const struct sock *sk, struct sk_buff *skb, bool drop_dst)
 {
 	struct in_pktinfo *pktinfo = PKTINFO_SKB_CB(skb);
 	bool prepare = inet_test_bit(PKTINFO, sk) ||
@@ -1397,6 +1398,7 @@ void ipv4_pktinfo_prepare(const struct sock *sk, struct sk_buff *skb)
 		pktinfo->ipi_ifindex = 0;
 		pktinfo->ipi_spec_dst.s_addr = 0;
 	}
+	if (drop_dst)
 		skb_dst_drop(skb);
 }
 

net/ipv4/ipmr.c

@@ -1073,7 +1073,7 @@ static int ipmr_cache_report(const struct mr_table *mrt,
 		msg = (struct igmpmsg *)skb_network_header(skb);
 		msg->im_vif = vifi;
 		msg->im_vif_hi = vifi >> 8;
-		ipv4_pktinfo_prepare(mroute_sk, pkt);
+		ipv4_pktinfo_prepare(mroute_sk, pkt, false);
 		memcpy(skb->cb, pkt->cb, sizeof(skb->cb));
 		/* Add our header */
 		igmp = skb_put(skb, sizeof(struct igmphdr));

net/ipv4/raw.c

@@ -292,7 +292,7 @@ static int raw_rcv_skb(struct sock *sk, struct sk_buff *skb)
 
 	/* Charge it to the socket. */
 
-	ipv4_pktinfo_prepare(sk, skb);
+	ipv4_pktinfo_prepare(sk, skb, true);
 	if (sock_queue_rcv_skb_reason(sk, skb, &reason) < 0) {
 		kfree_skb_reason(skb, reason);
 		return NET_RX_DROP;

net/ipv4/tcp.c

@@ -1786,7 +1786,17 @@ static skb_frag_t *skb_advance_to_frag(struct sk_buff *skb, u32 offset_skb,
 
 static bool can_map_frag(const skb_frag_t *frag)
 {
-	return skb_frag_size(frag) == PAGE_SIZE && !skb_frag_off(frag);
+	struct page *page;
+
+	if (skb_frag_size(frag) != PAGE_SIZE || skb_frag_off(frag))
+		return false;
+
+	page = skb_frag_page(frag);
+
+	if (PageCompound(page) || page->mapping)
+		return false;
+
+	return true;
 }
 
 static int find_next_mappable_frag(const skb_frag_t *frag,

net/ipv4/udp.c

@@ -2169,7 +2169,7 @@ static int udp_queue_rcv_one_skb(struct sock *sk, struct sk_buff *skb)
 
 	udp_csum_pull_header(skb);
 
-	ipv4_pktinfo_prepare(sk, skb);
+	ipv4_pktinfo_prepare(sk, skb, true);
 	return __udp_queue_rcv_skb(sk, skb);
 
 csum_error:

net/ipv6/addrconf_core.c

@@ -220,19 +220,26 @@ const struct ipv6_stub *ipv6_stub __read_mostly = &(struct ipv6_stub) {
 EXPORT_SYMBOL_GPL(ipv6_stub);
 
 /* IPv6 Wildcard Address and Loopback Address defined by RFC2553 */
-const struct in6_addr in6addr_loopback = IN6ADDR_LOOPBACK_INIT;
+const struct in6_addr in6addr_loopback __aligned(BITS_PER_LONG/8)
+	= IN6ADDR_LOOPBACK_INIT;
 EXPORT_SYMBOL(in6addr_loopback);
-const struct in6_addr in6addr_any = IN6ADDR_ANY_INIT;
+const struct in6_addr in6addr_any __aligned(BITS_PER_LONG/8)
+	= IN6ADDR_ANY_INIT;
 EXPORT_SYMBOL(in6addr_any);
-const struct in6_addr in6addr_linklocal_allnodes = IN6ADDR_LINKLOCAL_ALLNODES_INIT;
+const struct in6_addr in6addr_linklocal_allnodes __aligned(BITS_PER_LONG/8)
+	= IN6ADDR_LINKLOCAL_ALLNODES_INIT;
 EXPORT_SYMBOL(in6addr_linklocal_allnodes);
-const struct in6_addr in6addr_linklocal_allrouters = IN6ADDR_LINKLOCAL_ALLROUTERS_INIT;
+const struct in6_addr in6addr_linklocal_allrouters __aligned(BITS_PER_LONG/8)
+	= IN6ADDR_LINKLOCAL_ALLROUTERS_INIT;
 EXPORT_SYMBOL(in6addr_linklocal_allrouters);
-const struct in6_addr in6addr_interfacelocal_allnodes = IN6ADDR_INTERFACELOCAL_ALLNODES_INIT;
+const struct in6_addr in6addr_interfacelocal_allnodes __aligned(BITS_PER_LONG/8)
+	= IN6ADDR_INTERFACELOCAL_ALLNODES_INIT;
 EXPORT_SYMBOL(in6addr_interfacelocal_allnodes);
-const struct in6_addr in6addr_interfacelocal_allrouters = IN6ADDR_INTERFACELOCAL_ALLROUTERS_INIT;
+const struct in6_addr in6addr_interfacelocal_allrouters __aligned(BITS_PER_LONG/8)
+	= IN6ADDR_INTERFACELOCAL_ALLROUTERS_INIT;
 EXPORT_SYMBOL(in6addr_interfacelocal_allrouters);
-const struct in6_addr in6addr_sitelocal_allrouters = IN6ADDR_SITELOCAL_ALLROUTERS_INIT;
+const struct in6_addr in6addr_sitelocal_allrouters __aligned(BITS_PER_LONG/8)
+	= IN6ADDR_SITELOCAL_ALLROUTERS_INIT;
 EXPORT_SYMBOL(in6addr_sitelocal_allrouters);
 
 static void snmp6_free_dev(struct inet6_dev *idev)

net/ipv6/ip6_tunnel.c

@@ -796,8 +796,8 @@ static int __ip6_tnl_rcv(struct ip6_tnl *tunnel, struct sk_buff *skb,
 						struct sk_buff *skb),
 			 bool log_ecn_err)
 {
-	const struct ipv6hdr *ipv6h = ipv6_hdr(skb);
+	const struct ipv6hdr *ipv6h;
-	int err;
+	int nh, err;
 
 	if ((!(tpi->flags & TUNNEL_CSUM) &&
 	     (tunnel->parms.i_flags & TUNNEL_CSUM)) ||
@@ -829,7 +829,6 @@ static int __ip6_tnl_rcv(struct ip6_tnl *tunnel, struct sk_buff *skb,
 			goto drop;
 		}
 
-		ipv6h = ipv6_hdr(skb);
 		skb->protocol = eth_type_trans(skb, tunnel->dev);
 		skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN);
 	} else {
@@ -837,7 +836,23 @@ static int __ip6_tnl_rcv(struct ip6_tnl *tunnel, struct sk_buff *skb,
 		skb_reset_mac_header(skb);
 	}
 
+	/* Save offset of outer header relative to skb->head,
+	 * because we are going to reset the network header to the inner header
+	 * and might change skb->head.
+	 */
+	nh = skb_network_header(skb) - skb->head;
+
 	skb_reset_network_header(skb);
+
+	if (!pskb_inet_may_pull(skb)) {
+		DEV_STATS_INC(tunnel->dev, rx_length_errors);
+		DEV_STATS_INC(tunnel->dev, rx_errors);
+		goto drop;
+	}
+
+	/* Get the outer header. */
+	ipv6h = (struct ipv6hdr *)(skb->head + nh);
+
 	memset(skb->cb, 0, sizeof(struct inet6_skb_parm));
 
 	__skb_tunnel_rx(skb, tunnel->dev, tunnel->net);

net/llc/af_llc.c

@@ -226,6 +226,8 @@ static int llc_ui_release(struct socket *sock)
 	}
 	netdev_put(llc->dev, &llc->dev_tracker);
 	sock_put(sk);
+	sock_orphan(sk);
+	sock->sk = NULL;
 	llc_sk_free(sk);
 out:
 	return 0;

net/mptcp/protocol.c

@@ -2314,9 +2314,6 @@ bool __mptcp_retransmit_pending_data(struct sock *sk)
 	if (__mptcp_check_fallback(msk))
 		return false;
 
-	if (tcp_rtx_and_write_queues_empty(sk))
-		return false;
-
 	/* the closing socket has some data untransmitted and/or unacked:
 	 * some data in the mptcp rtx queue has not really xmitted yet.
 	 * keep it simple and re-inject the whole mptcp level rtx queue

net/netfilter/ipset/ip_set_bitmap_gen.h

@@ -30,6 +30,7 @@
 #define mtype_del		IPSET_TOKEN(MTYPE, _del)
 #define mtype_list		IPSET_TOKEN(MTYPE, _list)
 #define mtype_gc		IPSET_TOKEN(MTYPE, _gc)
+#define mtype_cancel_gc		IPSET_TOKEN(MTYPE, _cancel_gc)
 #define mtype			MTYPE
 
 #define get_ext(set, map, id)	((map)->extensions + ((set)->dsize * (id)))
@@ -59,9 +60,6 @@ mtype_destroy(struct ip_set *set)
 {
 	struct mtype *map = set->data;
 
-	if (SET_WITH_TIMEOUT(set))
-		del_timer_sync(&map->gc);
-
 	if (set->dsize && set->extensions & IPSET_EXT_DESTROY)
 		mtype_ext_cleanup(set);
 	ip_set_free(map->members);
@@ -290,6 +288,15 @@ mtype_gc(struct timer_list *t)
 	add_timer(&map->gc);
 }
 
+static void
+mtype_cancel_gc(struct ip_set *set)
+{
+	struct mtype *map = set->data;
+
+	if (SET_WITH_TIMEOUT(set))
+		del_timer_sync(&map->gc);
+}
+
 static const struct ip_set_type_variant mtype = {
 	.kadt	= mtype_kadt,
 	.uadt	= mtype_uadt,
@@ -303,6 +310,7 @@ static const struct ip_set_type_variant mtype = {
 	.head	= mtype_head,
 	.list	= mtype_list,
 	.same_set = mtype_same_set,
+	.cancel_gc = mtype_cancel_gc,
 };
 
 #endif /* __IP_SET_BITMAP_IP_GEN_H */

net/netfilter/ipset/ip_set_core.c

@@ -1182,6 +1182,14 @@ ip_set_destroy_set(struct ip_set *set)
 	kfree(set);
 }
 
+static void
+ip_set_destroy_set_rcu(struct rcu_head *head)
+{
+	struct ip_set *set = container_of(head, struct ip_set, rcu);
+
+	ip_set_destroy_set(set);
+}
+
 static int ip_set_destroy(struct sk_buff *skb, const struct nfnl_info *info,
 			  const struct nlattr * const attr[])
 {
@@ -1193,8 +1201,6 @@ static int ip_set_destroy(struct sk_buff *skb, const struct nfnl_info *info,
 	if (unlikely(protocol_min_failed(attr)))
 		return -IPSET_ERR_PROTOCOL;
 
-	/* Must wait for flush to be really finished in list:set */
-	rcu_barrier();
 
 	/* Commands are serialized and references are
 	 * protected by the ip_set_ref_lock.
@@ -1206,8 +1212,10 @@ static int ip_set_destroy(struct sk_buff *skb, const struct nfnl_info *info,
 	 * counter, so if it's already zero, we can proceed
 	 * without holding the lock.
 	 */
-	read_lock_bh(&ip_set_ref_lock);
 	if (!attr[IPSET_ATTR_SETNAME]) {
+		/* Must wait for flush to be really finished in list:set */
+		rcu_barrier();
+		read_lock_bh(&ip_set_ref_lock);
 		for (i = 0; i < inst->ip_set_max; i++) {
 			s = ip_set(inst, i);
 			if (s && (s->ref || s->ref_netlink)) {
@@ -1221,6 +1229,8 @@ static int ip_set_destroy(struct sk_buff *skb, const struct nfnl_info *info,
 			s = ip_set(inst, i);
 			if (s) {
 				ip_set(inst, i) = NULL;
+				/* Must cancel garbage collectors */
+				s->variant->cancel_gc(s);
 				ip_set_destroy_set(s);
 			}
 		}
@@ -1228,6 +1238,9 @@ static int ip_set_destroy(struct sk_buff *skb, const struct nfnl_info *info,
 		inst->is_destroyed = false;
 	} else {
 		u32 flags = flag_exist(info->nlh);
+		u16 features = 0;
+
+		read_lock_bh(&ip_set_ref_lock);
 		s = find_set_and_id(inst, nla_data(attr[IPSET_ATTR_SETNAME]),
 				    &i);
 		if (!s) {
@@ -1238,10 +1251,16 @@ static int ip_set_destroy(struct sk_buff *skb, const struct nfnl_info *info,
 			ret = -IPSET_ERR_BUSY;
 			goto out;
 		}
+		features = s->type->features;
 		ip_set(inst, i) = NULL;
 		read_unlock_bh(&ip_set_ref_lock);
-
+		if (features & IPSET_TYPE_NAME) {
-		ip_set_destroy_set(s);
+			/* Must wait for flush to be really finished  */
+			rcu_barrier();
+		}
+		/* Must cancel garbage collectors */
+		s->variant->cancel_gc(s);
+		call_rcu(&s->rcu, ip_set_destroy_set_rcu);
 	}
 	return 0;
 out:
@@ -1394,9 +1413,6 @@ static int ip_set_swap(struct sk_buff *skb, const struct nfnl_info *info,
 	ip_set(inst, to_id) = from;
 	write_unlock_bh(&ip_set_ref_lock);
 
-	/* Make sure all readers of the old set pointers are completed. */
-	synchronize_rcu();
-
 	return 0;
 }
 
@@ -2409,8 +2425,11 @@ ip_set_fini(void)
 {
 	nf_unregister_sockopt(&so_set);
 	nfnetlink_subsys_unregister(&ip_set_netlink_subsys);
-
 	unregister_pernet_subsys(&ip_set_net_ops);
+
+	/* Wait for call_rcu() in destroy */
+	rcu_barrier();
+
 	pr_debug("these are the famous last words\n");
 }
 

net/netfilter/ipset/ip_set_hash_gen.h

@@ -222,6 +222,7 @@ static const union nf_inet_addr zeromask = {};
 #undef mtype_gc_do
 #undef mtype_gc
 #undef mtype_gc_init
+#undef mtype_cancel_gc
 #undef mtype_variant
 #undef mtype_data_match
 
@@ -266,6 +267,7 @@ static const union nf_inet_addr zeromask = {};
 #define mtype_gc_do		IPSET_TOKEN(MTYPE, _gc_do)
 #define mtype_gc		IPSET_TOKEN(MTYPE, _gc)
 #define mtype_gc_init		IPSET_TOKEN(MTYPE, _gc_init)
+#define mtype_cancel_gc		IPSET_TOKEN(MTYPE, _cancel_gc)
 #define mtype_variant		IPSET_TOKEN(MTYPE, _variant)
 #define mtype_data_match	IPSET_TOKEN(MTYPE, _data_match)
 
@@ -450,9 +452,6 @@ mtype_destroy(struct ip_set *set)
 	struct htype *h = set->data;
 	struct list_head *l, *lt;
 
-	if (SET_WITH_TIMEOUT(set))
-		cancel_delayed_work_sync(&h->gc.dwork);
-
 	mtype_ahash_destroy(set, ipset_dereference_nfnl(h->table), true);
 	list_for_each_safe(l, lt, &h->ad) {
 		list_del(l);
@@ -599,6 +598,15 @@ mtype_gc_init(struct htable_gc *gc)
 	queue_delayed_work(system_power_efficient_wq, &gc->dwork, HZ);
 }
 
+static void
+mtype_cancel_gc(struct ip_set *set)
+{
+	struct htype *h = set->data;
+
+	if (SET_WITH_TIMEOUT(set))
+		cancel_delayed_work_sync(&h->gc.dwork);
+}
+
 static int
 mtype_add(struct ip_set *set, void *value, const struct ip_set_ext *ext,
 	  struct ip_set_ext *mext, u32 flags);
@@ -1441,6 +1449,7 @@ static const struct ip_set_type_variant mtype_variant = {
 	.uref	= mtype_uref,
 	.resize	= mtype_resize,
 	.same_set = mtype_same_set,
+	.cancel_gc = mtype_cancel_gc,
 	.region_lock = true,
 };
 

net/netfilter/ipset/ip_set_list_set.c

@@ -426,9 +426,6 @@ list_set_destroy(struct ip_set *set)
 	struct list_set *map = set->data;
 	struct set_elem *e, *n;
 
-	if (SET_WITH_TIMEOUT(set))
-		timer_shutdown_sync(&map->gc);
-
 	list_for_each_entry_safe(e, n, &map->members, list) {
 		list_del(&e->list);
 		ip_set_put_byindex(map->net, e->id);
@@ -545,6 +542,15 @@ list_set_same_set(const struct ip_set *a, const struct ip_set *b)
 	       a->extensions == b->extensions;
 }
 
+static void
+list_set_cancel_gc(struct ip_set *set)
+{
+	struct list_set *map = set->data;
+
+	if (SET_WITH_TIMEOUT(set))
+		timer_shutdown_sync(&map->gc);
+}
+
 static const struct ip_set_type_variant set_variant = {
 	.kadt	= list_set_kadt,
 	.uadt	= list_set_uadt,
@@ -558,6 +564,7 @@ static const struct ip_set_type_variant set_variant = {
 	.head	= list_set_head,
 	.list	= list_set_list,
 	.same_set = list_set_same_set,
+	.cancel_gc = list_set_cancel_gc,
 };
 
 static void

net/netfilter/nf_conntrack_proto_sctp.c

@@ -283,7 +283,7 @@ sctp_new(struct nf_conn *ct, const struct sk_buff *skb,
 			pr_debug("Setting vtag %x for secondary conntrack\n",
 				 sh->vtag);
 			ct->proto.sctp.vtag[IP_CT_DIR_ORIGINAL] = sh->vtag;
-		} else {
+		} else if (sch->type == SCTP_CID_SHUTDOWN_ACK) {
 		/* If it is a shutdown ack OOTB packet, we expect a return
 		   shutdown complete, otherwise an ABORT Sec 8.4 (5) and (8) */
 			pr_debug("Setting vtag %x for new conn OOTB\n",

net/netfilter/nf_conntrack_proto_tcp.c

@@ -457,7 +457,8 @@ static void tcp_init_sender(struct ip_ct_tcp_state *sender,
 			    const struct sk_buff *skb,
 			    unsigned int dataoff,
 			    const struct tcphdr *tcph,
-			    u32 end, u32 win)
+			    u32 end, u32 win,
+			    enum ip_conntrack_dir dir)
 {
 	/* SYN-ACK in reply to a SYN
 	 * or SYN from reply direction in simultaneous open.
@@ -471,7 +472,8 @@ static void tcp_init_sender(struct ip_ct_tcp_state *sender,
 	 * Both sides must send the Window Scale option
 	 * to enable window scaling in either direction.
 	 */
-	if (!(sender->flags & IP_CT_TCP_FLAG_WINDOW_SCALE &&
+	if (dir == IP_CT_DIR_REPLY &&
+	    !(sender->flags & IP_CT_TCP_FLAG_WINDOW_SCALE &&
 	      receiver->flags & IP_CT_TCP_FLAG_WINDOW_SCALE)) {
 		sender->td_scale = 0;
 		receiver->td_scale = 0;
@@ -542,7 +544,7 @@ tcp_in_window(struct nf_conn *ct, enum ip_conntrack_dir dir,
 		if (tcph->syn) {
 			tcp_init_sender(sender, receiver,
 					skb, dataoff, tcph,
-					end, win);
+					end, win, dir);
 			if (!tcph->ack)
 				/* Simultaneous open */
 				return NFCT_TCP_ACCEPT;
@@ -585,7 +587,7 @@ tcp_in_window(struct nf_conn *ct, enum ip_conntrack_dir dir,
 		 */
 		tcp_init_sender(sender, receiver,
 				skb, dataoff, tcph,
-				end, win);
+				end, win, dir);
 
 		if (dir == IP_CT_DIR_REPLY && !tcph->ack)
 			return NFCT_TCP_ACCEPT;

net/netfilter/nf_log.c

@@ -193,10 +193,11 @@ void nf_logger_put(int pf, enum nf_log_type type)
 		return;
 	}
 
-	BUG_ON(loggers[pf][type] == NULL);
-
 	rcu_read_lock();
 	logger = rcu_dereference(loggers[pf][type]);
+	if (!logger)
+		WARN_ON_ONCE(1);
+	else
 		module_put(logger->me);
 	rcu_read_unlock();
 }

net/netfilter/nf_tables_api.c

@@ -7551,11 +7551,15 @@ static int nft_object_dump(struct sk_buff *skb, unsigned int attr,
 	return -1;
 }
 
-static const struct nft_object_type *__nft_obj_type_get(u32 objtype)
+static const struct nft_object_type *__nft_obj_type_get(u32 objtype, u8 family)
 {
 	const struct nft_object_type *type;
 
 	list_for_each_entry(type, &nf_tables_objects, list) {
+		if (type->family != NFPROTO_UNSPEC &&
+		    type->family != family)
+			continue;
+
 		if (objtype == type->type)
 			return type;
 	}
@@ -7563,11 +7567,11 @@ static const struct nft_object_type *__nft_obj_type_get(u32 objtype)
 }
 
 static const struct nft_object_type *
-nft_obj_type_get(struct net *net, u32 objtype)
+nft_obj_type_get(struct net *net, u32 objtype, u8 family)
 {
 	const struct nft_object_type *type;
 
-	type = __nft_obj_type_get(objtype);
+	type = __nft_obj_type_get(objtype, family);
 	if (type != NULL && try_module_get(type->owner))
 		return type;
 
@@ -7660,7 +7664,7 @@ static int nf_tables_newobj(struct sk_buff *skb, const struct nfnl_info *info,
 		if (info->nlh->nlmsg_flags & NLM_F_REPLACE)
 			return -EOPNOTSUPP;
 
-		type = __nft_obj_type_get(objtype);
+		type = __nft_obj_type_get(objtype, family);
 		if (WARN_ON_ONCE(!type))
 			return -ENOENT;
 
@@ -7674,7 +7678,7 @@ static int nf_tables_newobj(struct sk_buff *skb, const struct nfnl_info *info,
 	if (!nft_use_inc(&table->use))
 		return -EMFILE;
 
-	type = nft_obj_type_get(net, objtype);
+	type = nft_obj_type_get(net, objtype, family);
 	if (IS_ERR(type)) {
 		err = PTR_ERR(type);
 		goto err_type;

net/netfilter/nft_ct.c

@@ -1250,7 +1250,31 @@ static int nft_ct_expect_obj_init(const struct nft_ctx *ctx,
 	if (tb[NFTA_CT_EXPECT_L3PROTO])
 		priv->l3num = ntohs(nla_get_be16(tb[NFTA_CT_EXPECT_L3PROTO]));
 
+	switch (priv->l3num) {
+	case NFPROTO_IPV4:
+	case NFPROTO_IPV6:
+		if (priv->l3num != ctx->family)
+			return -EINVAL;
+
+		fallthrough;
+	case NFPROTO_INET:
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
 	priv->l4proto = nla_get_u8(tb[NFTA_CT_EXPECT_L4PROTO]);
+	switch (priv->l4proto) {
+	case IPPROTO_TCP:
+	case IPPROTO_UDP:
+	case IPPROTO_UDPLITE:
+	case IPPROTO_DCCP:
+	case IPPROTO_SCTP:
+		break;
+	default:
+		return -EOPNOTSUPP;
+	}
+
 	priv->dport = nla_get_be16(tb[NFTA_CT_EXPECT_DPORT]);
 	priv->timeout = nla_get_u32(tb[NFTA_CT_EXPECT_TIMEOUT]);
 	priv->size = nla_get_u8(tb[NFTA_CT_EXPECT_SIZE]);

net/netfilter/nft_tunnel.c

@@ -713,6 +713,7 @@ static const struct nft_object_ops nft_tunnel_obj_ops = {
 
 static struct nft_object_type nft_tunnel_obj_type __read_mostly = {
 	.type		= NFT_OBJECT_TUNNEL,
+	.family		= NFPROTO_NETDEV,
 	.ops		= &nft_tunnel_obj_ops,
 	.maxattr	= NFTA_TUNNEL_KEY_MAX,
 	.policy		= nft_tunnel_key_policy,

net/nfc/nci/core.c

@@ -1208,6 +1208,10 @@ void nci_free_device(struct nci_dev *ndev)
 {
 	nfc_free_device(ndev->nfc_dev);
 	nci_hci_deallocate(ndev);
+
+	/* drop partial rx data packet if present */
+	if (ndev->rx_data_reassembly)
+		kfree_skb(ndev->rx_data_reassembly);
 	kfree(ndev);
 }
 EXPORT_SYMBOL(nci_free_device);

net/smc/smc_core.c

@@ -1877,9 +1877,15 @@ static bool smcd_lgr_match(struct smc_link_group *lgr,
 			   struct smcd_dev *smcismdev,
 			   struct smcd_gid *peer_gid)
 {
-	return lgr->peer_gid.gid == peer_gid->gid && lgr->smcd == smcismdev &&
+	if (lgr->peer_gid.gid != peer_gid->gid ||
-		smc_ism_is_virtual(smcismdev) ?
+	    lgr->smcd != smcismdev)
-		(lgr->peer_gid.gid_ext == peer_gid->gid_ext) : 1;
+		return false;
+
+	if (smc_ism_is_virtual(smcismdev) &&
+	    lgr->peer_gid.gid_ext != peer_gid->gid_ext)
+		return false;
+
+	return true;
 }
 
 /* create a new SMC connection (and a new link group if necessary) */

net/unix/af_unix.c

@@ -1344,13 +1344,11 @@ static void unix_state_double_lock(struct sock *sk1, struct sock *sk2)
 		unix_state_lock(sk1);
 		return;
 	}
-	if (sk1 < sk2) {
+	if (sk1 > sk2)
+		swap(sk1, sk2);
+
 	unix_state_lock(sk1);
-		unix_state_lock_nested(sk2);
+	unix_state_lock_nested(sk2, U_LOCK_SECOND);
-	} else {
-		unix_state_lock(sk2);
-		unix_state_lock_nested(sk1);
-	}
 }
 
 static void unix_state_double_unlock(struct sock *sk1, struct sock *sk2)
@@ -1591,7 +1589,7 @@ static int unix_stream_connect(struct socket *sock, struct sockaddr *uaddr,
 		goto out_unlock;
 	}
 
-	unix_state_lock_nested(sk);
+	unix_state_lock_nested(sk, U_LOCK_SECOND);
 
 	if (sk->sk_state != st) {
 		unix_state_unlock(sk);

net/unix/diag.c

@@ -84,7 +84,7 @@ static int sk_diag_dump_icons(struct sock *sk, struct sk_buff *nlskb)
 			 * queue lock. With the other's queue locked it's
 			 * OK to lock the state.
 			 */
-			unix_state_lock_nested(req);
+			unix_state_lock_nested(req, U_LOCK_DIAG);
 			peer = unix_sk(req)->peer;
 			buf[i++] = (peer ? sock_i_ino(peer) : 0);
 			unix_state_unlock(req);

tools/testing/selftests/drivers/net/bonding/lag_lib.sh

@@ -48,6 +48,17 @@ test_LAG_cleanup()
 	ip link add mv0 link "$name" up address "$ucaddr" type macvlan
 	# Used to test dev->mc handling
 	ip address add "$addr6" dev "$name"
+
+	# Check that addresses were added as expected
+	(grep_bridge_fdb "$ucaddr" bridge fdb show dev dummy1 ||
+		grep_bridge_fdb "$ucaddr" bridge fdb show dev dummy2) >/dev/null
+	check_err $? "macvlan unicast address not found on a slave"
+
+	# mcaddr is added asynchronously by addrconf_dad_work(), use busywait
+	(busywait 10000 grep_bridge_fdb "$mcaddr" bridge fdb show dev dummy1 ||
+		grep_bridge_fdb "$mcaddr" bridge fdb show dev dummy2) >/dev/null
+	check_err $? "IPv6 solicited-node multicast mac address not found on a slave"
+
 	ip link set dev "$name" down
 	ip link del "$name"
 

tools/testing/selftests/drivers/net/team/config

@@ -1,3 +1,5 @@
+CONFIG_DUMMY=y
+CONFIG_IPV6=y
+CONFIG_MACVLAN=y
 CONFIG_NET_TEAM=y
 CONFIG_NET_TEAM_MODE_LOADBALANCE=y
-CONFIG_MACVLAN=y

tools/testing/selftests/net/Makefile

@@ -53,8 +53,7 @@ TEST_PROGS += bind_bhash.sh
 TEST_PROGS += ip_local_port_range.sh
 TEST_PROGS += rps_default_mask.sh
 TEST_PROGS += big_tcp.sh
-TEST_PROGS_EXTENDED := in_netns.sh setup_loopback.sh setup_veth.sh
+TEST_PROGS_EXTENDED := toeplitz_client.sh toeplitz.sh
-TEST_PROGS_EXTENDED += toeplitz_client.sh toeplitz.sh lib.sh
 TEST_GEN_FILES =  socket nettest
 TEST_GEN_FILES += psock_fanout psock_tpacket msg_zerocopy reuseport_addr_any
 TEST_GEN_FILES += tcp_mmap tcp_inq psock_snd txring_overwrite
@@ -84,6 +83,7 @@ TEST_PROGS += sctp_vrf.sh
 TEST_GEN_FILES += sctp_hello
 TEST_GEN_FILES += csum
 TEST_GEN_FILES += nat6to4.o
+TEST_GEN_FILES += xdp_dummy.o
 TEST_GEN_FILES += ip_local_port_range
 TEST_GEN_FILES += bind_wildcard
 TEST_PROGS += test_vxlan_mdb.sh
@@ -95,6 +95,7 @@ TEST_PROGS += fq_band_pktlimit.sh
 TEST_PROGS += vlan_hw_filter.sh
 
 TEST_FILES := settings
+TEST_FILES += in_netns.sh lib.sh net_helper.sh setup_loopback.sh setup_veth.sh
 
 include ../lib.mk
 
@@ -104,7 +105,7 @@ $(OUTPUT)/tcp_inq: LDLIBS += -lpthread
 $(OUTPUT)/bind_bhash: LDLIBS += -lpthread
 $(OUTPUT)/io_uring_zerocopy_tx: CFLAGS += -I../../../include/
 
-# Rules to generate bpf obj nat6to4.o
+# Rules to generate bpf objs
 CLANG ?= clang
 SCRATCH_DIR := $(OUTPUT)/tools
 BUILD_DIR := $(SCRATCH_DIR)/build
@@ -139,7 +140,7 @@ endif
 
 CLANG_SYS_INCLUDES = $(call get_sys_includes,$(CLANG),$(CLANG_TARGET_ARCH))
 
-$(OUTPUT)/nat6to4.o: nat6to4.c $(BPFOBJ) | $(MAKE_DIRS)
+$(OUTPUT)/nat6to4.o $(OUTPUT)/xdp_dummy.o: $(OUTPUT)/%.o : %.c $(BPFOBJ) | $(MAKE_DIRS)
 	$(CLANG) -O2 --target=bpf -c $< $(CCINCLUDE) $(CLANG_SYS_INCLUDES) -o $@
 
 $(BPFOBJ): $(wildcard $(BPFDIR)/*.[ch] $(BPFDIR)/Makefile)		       \

tools/testing/selftests/net/config

@@ -19,8 +19,11 @@ CONFIG_BRIDGE_VLAN_FILTERING=y
 CONFIG_BRIDGE=y
 CONFIG_CRYPTO_CHACHA20POLY1305=m
 CONFIG_VLAN_8021Q=y
+CONFIG_GENEVE=m
 CONFIG_IFB=y
 CONFIG_INET_DIAG=y
+CONFIG_INET_ESP=y
+CONFIG_INET_ESP_OFFLOAD=y
 CONFIG_IP_GRE=m
 CONFIG_NETFILTER=y
 CONFIG_NETFILTER_ADVANCED=y
@@ -29,7 +32,10 @@ CONFIG_NF_NAT=m
 CONFIG_IP6_NF_IPTABLES=m
 CONFIG_IP_NF_IPTABLES=m
 CONFIG_IP6_NF_NAT=m
+CONFIG_IP6_NF_RAW=m
 CONFIG_IP_NF_NAT=m
+CONFIG_IP_NF_RAW=m
+CONFIG_IP_NF_TARGET_TTL=m
 CONFIG_IPV6_GRE=m
 CONFIG_IPV6_SEG6_LWTUNNEL=y
 CONFIG_L2TP_ETH=m
@@ -45,8 +51,14 @@ CONFIG_NF_TABLES=m
 CONFIG_NF_TABLES_IPV6=y
 CONFIG_NF_TABLES_IPV4=y
 CONFIG_NFT_NAT=m
+CONFIG_NETFILTER_XT_MATCH_LENGTH=m
+CONFIG_NET_ACT_CSUM=m
+CONFIG_NET_ACT_CT=m
 CONFIG_NET_ACT_GACT=m
+CONFIG_NET_ACT_PEDIT=m
 CONFIG_NET_CLS_BASIC=m
+CONFIG_NET_CLS_BPF=m
+CONFIG_NET_CLS_MATCHALL=m
 CONFIG_NET_CLS_U32=m
 CONFIG_NET_IPGRE_DEMUX=m
 CONFIG_NET_IPGRE=m
@@ -55,6 +67,9 @@ CONFIG_NET_SCH_HTB=m
 CONFIG_NET_SCH_FQ=m
 CONFIG_NET_SCH_ETF=m
 CONFIG_NET_SCH_NETEM=y
+CONFIG_NET_SCH_PRIO=m
+CONFIG_NFT_COMPAT=m
+CONFIG_NF_FLOW_TABLE=m
 CONFIG_PSAMPLE=m
 CONFIG_TCP_MD5SIG=y
 CONFIG_TEST_BLACKHOLE_DEV=m
@@ -80,3 +95,4 @@ CONFIG_IP_SCTP=m
 CONFIG_NETFILTER_XT_MATCH_POLICY=m
 CONFIG_CRYPTO_ARIA=y
 CONFIG_XFRM_INTERFACE=m
+CONFIG_XFRM_USER=m

tools/testing/selftests/net/forwarding/Makefile

@@ -112,7 +112,7 @@ TEST_PROGS = bridge_fdb_learning_limit.sh \
 	vxlan_symmetric_ipv6.sh \
 	vxlan_symmetric.sh
 
-TEST_PROGS_EXTENDED := devlink_lib.sh \
+TEST_FILES := devlink_lib.sh \
 	ethtool_lib.sh \
 	fib_offload_lib.sh \
 	forwarding.config.sample \

tools/testing/selftests/net/lib.sh

@@ -4,6 +4,9 @@
 ##############################################################################
 # Defines
 
+WAIT_TIMEOUT=${WAIT_TIMEOUT:=20}
+BUSYWAIT_TIMEOUT=$((WAIT_TIMEOUT * 1000)) # ms
+
 # Kselftest framework requirement - SKIP code is 4.
 ksft_skip=4
 # namespace list created by setup_ns
@@ -48,7 +51,7 @@ cleanup_ns()
 
 	for ns in "$@"; do
 		ip netns delete "${ns}" &> /dev/null
-		if ! busywait 2 ip netns list \| grep -vq "^$ns$" &> /dev/null; then
+		if ! busywait $BUSYWAIT_TIMEOUT ip netns list \| grep -vq "^$ns$" &> /dev/null; then
 			echo "Warn: Failed to remove namespace $ns"
 			ret=1
 		fi

tools/testing/selftests/net/mptcp/config

@@ -22,8 +22,11 @@ CONFIG_NFT_TPROXY=m
 CONFIG_NFT_SOCKET=m
 CONFIG_IP_ADVANCED_ROUTER=y
 CONFIG_IP_MULTIPLE_TABLES=y
+CONFIG_IP_NF_FILTER=m
+CONFIG_IP_NF_MANGLE=m
 CONFIG_IP_NF_TARGET_REJECT=m
 CONFIG_IPV6_MULTIPLE_TABLES=y
+CONFIG_IP6_NF_FILTER=m
 CONFIG_NET_ACT_CSUM=m
 CONFIG_NET_ACT_PEDIT=m
 CONFIG_NET_CLS_ACT=y

tools/testing/selftests/net/mptcp/mptcp_join.sh

@@ -643,13 +643,6 @@ kill_events_pids()
 	mptcp_lib_kill_wait $evts_ns2_pid
 }
 
-kill_tests_wait()
-{
-	#shellcheck disable=SC2046
-	kill -SIGUSR1 $(ip netns pids $ns2) $(ip netns pids $ns1)
-	wait
-}
-
 pm_nl_set_limits()
 {
 	local ns=$1
@@ -3453,7 +3446,7 @@ userspace_tests()
 		chk_mptcp_info subflows 0 subflows 0
 		chk_subflows_total 1 1
 		kill_events_pids
-		wait $tests_pid
+		mptcp_lib_kill_wait $tests_pid
 	fi
 
 	# userspace pm create destroy subflow
@@ -3475,7 +3468,7 @@ userspace_tests()
 		chk_mptcp_info subflows 0 subflows 0
 		chk_subflows_total 1 1
 		kill_events_pids
-		wait $tests_pid
+		mptcp_lib_kill_wait $tests_pid
 	fi
 
 	# userspace pm create id 0 subflow
@@ -3494,7 +3487,7 @@ userspace_tests()
 		chk_mptcp_info subflows 1 subflows 1
 		chk_subflows_total 2 2
 		kill_events_pids
-		wait $tests_pid
+		mptcp_lib_kill_wait $tests_pid
 	fi
 
 	# userspace pm remove initial subflow
@@ -3518,7 +3511,7 @@ userspace_tests()
 		chk_mptcp_info subflows 1 subflows 1
 		chk_subflows_total 1 1
 		kill_events_pids
-		wait $tests_pid
+		mptcp_lib_kill_wait $tests_pid
 	fi
 
 	# userspace pm send RM_ADDR for ID 0
@@ -3544,7 +3537,7 @@ userspace_tests()
 		chk_mptcp_info subflows 1 subflows 1
 		chk_subflows_total 1 1
 		kill_events_pids
-		wait $tests_pid
+		mptcp_lib_kill_wait $tests_pid
 	fi
 }
 
@@ -3558,7 +3551,8 @@ endpoint_tests()
 		pm_nl_set_limits $ns2 2 2
 		pm_nl_add_endpoint $ns1 10.0.2.1 flags signal
 		speed=slow \
-			run_tests $ns1 $ns2 10.0.1.1 2>/dev/null &
+			run_tests $ns1 $ns2 10.0.1.1 &
+		local tests_pid=$!
 
 		wait_mpj $ns1
 		pm_nl_check_endpoint "creation" \
@@ -3573,7 +3567,7 @@ endpoint_tests()
 		pm_nl_add_endpoint $ns2 10.0.2.2 flags signal
 		pm_nl_check_endpoint "modif is allowed" \
 			$ns2 10.0.2.2 id 1 flags signal
-		kill_tests_wait
+		mptcp_lib_kill_wait $tests_pid
 	fi
 
 	if reset "delete and re-add" &&
@@ -3582,7 +3576,8 @@ endpoint_tests()
 		pm_nl_set_limits $ns2 1 1
 		pm_nl_add_endpoint $ns2 10.0.2.2 id 2 dev ns2eth2 flags subflow
 		test_linkfail=4 speed=20 \
-			run_tests $ns1 $ns2 10.0.1.1 2>/dev/null &
+			run_tests $ns1 $ns2 10.0.1.1 &
+		local tests_pid=$!
 
 		wait_mpj $ns2
 		chk_subflow_nr "before delete" 2
@@ -3597,7 +3592,7 @@ endpoint_tests()
 		wait_mpj $ns2
 		chk_subflow_nr "after re-add" 2
 		chk_mptcp_info subflows 1 subflows 1
-		kill_tests_wait
+		mptcp_lib_kill_wait $tests_pid
 	fi
 }
 

tools/testing/selftests/net/mptcp/mptcp_lib.sh

@@ -6,7 +6,7 @@ readonly KSFT_FAIL=1
 readonly KSFT_SKIP=4
 
 # shellcheck disable=SC2155 # declare and assign separately
-readonly KSFT_TEST=$(basename "${0}" | sed 's/\.sh$//g')
+readonly KSFT_TEST="${MPTCP_LIB_KSFT_TEST:-$(basename "${0}" .sh)}"
 
 MPTCP_LIB_SUBTESTS=()
 

tools/testing/selftests/net/mptcp/settings

@@ -1 +1 @@
-timeout=1200
+timeout=1800

tools/testing/selftests/net/mptcp/simult_flows.sh

@@ -284,12 +284,12 @@ done
 
 setup
 run_test 10 10 0 0 "balanced bwidth"
-run_test 10 10 1 50 "balanced bwidth with unbalanced delay"
+run_test 10 10 1 25 "balanced bwidth with unbalanced delay"
 
 # we still need some additional infrastructure to pass the following test-cases
-run_test 30 10 0 0 "unbalanced bwidth"
+run_test 10 3 0 0 "unbalanced bwidth"
-run_test 30 10 1 50 "unbalanced bwidth with unbalanced delay"
+run_test 10 3 1 25 "unbalanced bwidth with unbalanced delay"
-run_test 30 10 50 1 "unbalanced bwidth with opposed, unbalanced delay"
+run_test 10 3 25 1 "unbalanced bwidth with opposed, unbalanced delay"
 
 mptcp_lib_result_print_all_tap
 exit $ret

tools/testing/selftests/net/pmtu.sh

@@ -707,22 +707,22 @@ setup_xfrm6() {
 }
 
 setup_xfrm4udp() {
-	setup_xfrm 4 ${veth4_a_addr} ${veth4_b_addr} "encap espinudp 4500 4500 0.0.0.0"
+	setup_xfrm 4 ${veth4_a_addr} ${veth4_b_addr} "encap espinudp 4500 4500 0.0.0.0" && \
 		setup_nettest_xfrm 4 4500
 }
 
 setup_xfrm6udp() {
-	setup_xfrm 6 ${veth6_a_addr} ${veth6_b_addr} "encap espinudp 4500 4500 0.0.0.0"
+	setup_xfrm 6 ${veth6_a_addr} ${veth6_b_addr} "encap espinudp 4500 4500 0.0.0.0" && \
 		setup_nettest_xfrm 6 4500
 }
 
 setup_xfrm4udprouted() {
-	setup_xfrm 4 ${prefix4}.${a_r1}.1 ${prefix4}.${b_r1}.1 "encap espinudp 4500 4500 0.0.0.0"
+	setup_xfrm 4 ${prefix4}.${a_r1}.1 ${prefix4}.${b_r1}.1 "encap espinudp 4500 4500 0.0.0.0" && \
 		setup_nettest_xfrm 4 4500
 }
 
 setup_xfrm6udprouted() {
-	setup_xfrm 6 ${prefix6}:${a_r1}::1 ${prefix6}:${b_r1}::1 "encap espinudp 4500 4500 0.0.0.0"
+	setup_xfrm 6 ${prefix6}:${a_r1}::1 ${prefix6}:${b_r1}::1 "encap espinudp 4500 4500 0.0.0.0" && \
 		setup_nettest_xfrm 6 4500
 }
 
@@ -1339,7 +1339,7 @@ test_pmtu_ipvX_over_bridged_vxlanY_or_geneveY_exception() {
 
 		sleep 1
 
-		dd if=/dev/zero of=/dev/stdout status=none bs=1M count=1 | ${target} socat -T 3 -u STDIN $TCPDST,connect-timeout=3
+		dd if=/dev/zero status=none bs=1M count=1 | ${target} socat -T 3 -u STDIN $TCPDST,connect-timeout=3
 
 		size=$(du -sb $tmpoutfile)
 		size=${size%%/tmp/*}

tools/testing/selftests/net/setup_veth.sh

@@ -11,7 +11,7 @@ setup_veth_ns() {
 	local -r ns_mac="$4"
 
 	[[ -e /var/run/netns/"${ns_name}" ]] || ip netns add "${ns_name}"
-	echo 100000 > "/sys/class/net/${ns_dev}/gro_flush_timeout"
+	echo 1000000 > "/sys/class/net/${ns_dev}/gro_flush_timeout"
 	ip link set dev "${ns_dev}" netns "${ns_name}" mtu 65535
 	ip -netns "${ns_name}" link set dev "${ns_dev}" up
 

tools/testing/selftests/net/tcp_ao/config

@@ -0,0 +1,10 @@
+CONFIG_CRYPTO_HMAC=y
+CONFIG_CRYPTO_RMD160=y
+CONFIG_CRYPTO_SHA1=y
+CONFIG_IPV6_MULTIPLE_TABLES=y
+CONFIG_IPV6=y
+CONFIG_NET_L3_MASTER_DEV=y
+CONFIG_NET_VRF=y
+CONFIG_TCP_AO=y
+CONFIG_TCP_MD5SIG=y
+CONFIG_VETH=m

tools/testing/selftests/net/tcp_ao/key-management.c

@@ -417,9 +417,9 @@ struct test_key {
 		matches_vrf		: 1,
 		is_current		: 1,
 		is_rnext		: 1,
-		used_on_handshake	: 1,
+		used_on_server_tx	: 1,
-		used_after_accept	: 1,
+		used_on_client_tx	: 1,
-		used_on_client		: 1;
+		skip_counters_checks	: 1;
 };
 
 struct key_collection {
@@ -609,16 +609,14 @@ static int key_collection_socket(bool server, unsigned int port)
 				addr = &this_ip_dest;
 			sndid = key->client_keyid;
 			rcvid = key->server_keyid;
-			set_current = key->is_current;
+			key->used_on_client_tx = set_current = key->is_current;
-			set_rnext = key->is_rnext;
+			key->used_on_server_tx = set_rnext = key->is_rnext;
 		}
 
 		if (test_add_key_cr(sk, key->password, key->len,
 				    *addr, vrf, sndid, rcvid, key->maclen,
 				    key->alg, set_current, set_rnext))
 			test_key_error("setsockopt(TCP_AO_ADD_KEY)", key);
-		if (set_current || set_rnext)
-			key->used_on_handshake = 1;
 #ifdef DEBUG
 		test_print("%s [%u/%u] key: { %s, %u:%u, %u, %u:%u:%u:%u (%u)}",
 			   server ? "server" : "client", i, collection.nr_keys,
@@ -640,22 +638,22 @@ static void verify_counters(const char *tst_name, bool is_listen_sk, bool server
 	for (i = 0; i < collection.nr_keys; i++) {
 		struct test_key *key = &collection.keys[i];
 		uint8_t sndid, rcvid;
-		bool was_used;
+		bool rx_cnt_expected;
 
+		if (key->skip_counters_checks)
+			continue;
 		if (server) {
 			sndid = key->server_keyid;
 			rcvid = key->client_keyid;
-			if (is_listen_sk)
+			rx_cnt_expected = key->used_on_client_tx;
-				was_used = key->used_on_handshake;
-			else
-				was_used = key->used_after_accept;
 		} else {
 			sndid = key->client_keyid;
 			rcvid = key->server_keyid;
-			was_used = key->used_on_client;
+			rx_cnt_expected = key->used_on_server_tx;
 		}
 
-		test_tcp_ao_key_counters_cmp(tst_name, a, b, was_used,
+		test_tcp_ao_key_counters_cmp(tst_name, a, b,
+					     rx_cnt_expected ? TEST_CNT_KEY_GOOD : 0,
 					     sndid, rcvid);
 	}
 	test_tcp_ao_counters_free(a);
@@ -843,7 +841,7 @@ static void end_server(const char *tst_name, int sk,
 	synchronize_threads(); /* 4: verified => closed */
 	close(sk);
 
-	verify_counters(tst_name, true, false, begin, &end);
+	verify_counters(tst_name, false, true, begin, &end);
 	synchronize_threads(); /* 5: counters */
 }
 
@@ -916,9 +914,8 @@ static int run_client(const char *tst_name, unsigned int port,
 		current_index = nr_keys - 1;
 	if (rnext_index < 0)
 		rnext_index = nr_keys - 1;
-	collection.keys[current_index].used_on_handshake = 1;
+	collection.keys[current_index].used_on_client_tx = 1;
-	collection.keys[rnext_index].used_after_accept = 1;
+	collection.keys[rnext_index].used_on_server_tx = 1;
-	collection.keys[rnext_index].used_on_client = 1;
 
 	synchronize_threads(); /* 3: accepted => send data */
 	if (test_client_verify(sk, msg_sz, msg_nr, TEST_TIMEOUT_SEC)) {
@@ -1059,7 +1056,16 @@ static void check_current_back(const char *tst_name, unsigned int port,
 		test_error("Can't change the current key");
 	if (test_client_verify(sk, msg_len, nr_packets, TEST_TIMEOUT_SEC))
 		test_fail("verify failed");
-	collection.keys[rotate_to_index].used_after_accept = 1;
+	/* There is a race here: between setting the current_key with
+	 * setsockopt(TCP_AO_INFO) and starting to send some data - there
+	 * might have been a segment received with the desired
+	 * RNext_key set. In turn that would mean that the first outgoing
+	 * segment will have the desired current_key (flipped back).
+	 * Which is what the user/test wants. As it's racy, skip checking
+	 * the counters, yet check what are the resulting current/rnext
+	 * keys on both sides.
+	 */
+	collection.keys[rotate_to_index].skip_counters_checks = 1;
 
 	end_client(tst_name, sk, nr_keys, current_index, rnext_index, &tmp);
 }
@@ -1089,7 +1095,7 @@ static void roll_over_keys(const char *tst_name, unsigned int port,
 		}
 		verify_current_rnext(tst_name, sk, -1,
 				     collection.keys[i].server_keyid);
-		collection.keys[i].used_on_client = 1;
+		collection.keys[i].used_on_server_tx = 1;
 		synchronize_threads(); /* verify current/rnext */
 	}
 	end_client(tst_name, sk, nr_keys, current_index, rnext_index, &tmp);

tools/testing/selftests/net/tcp_ao/lib/sock.c

@@ -62,7 +62,9 @@ int test_wait_fd(int sk, time_t sec, bool write)
 		return -ETIMEDOUT;
 	}
 
-	if (getsockopt(sk, SOL_SOCKET, SO_ERROR, &ret, &slen) || ret)
+	if (getsockopt(sk, SOL_SOCKET, SO_ERROR, &ret, &slen))
+		return -errno;
+	if (ret)
 		return -ret;
 	return 0;
 }
@@ -584,9 +586,11 @@ int test_client_verify(int sk, const size_t msg_len, const size_t nr,
 {
 	size_t buf_sz = msg_len * nr;
 	char *buf = alloca(buf_sz);
+	ssize_t ret;
 
 	randomize_buffer(buf, buf_sz);
-	if (test_client_loop(sk, buf, buf_sz, msg_len, timeout_sec) != buf_sz)
+	ret = test_client_loop(sk, buf, buf_sz, msg_len, timeout_sec);
-		return -1;
+	if (ret < 0)
-	return 0;
+		return (int)ret;
+	return ret != buf_sz ? -1 : 0;
 }

tools/testing/selftests/net/tcp_ao/rst.c

@@ -1,10 +1,33 @@
 // SPDX-License-Identifier: GPL-2.0
-/* Author: Dmitry Safonov <dima@arista.com> */
+/*
+ * The test checks that both active and passive reset have correct TCP-AO
+ * signature. An "active" reset (abort) here is procured from closing
+ * listen() socket with non-accepted connections in the queue:
+ * inet_csk_listen_stop() => inet_child_forget() =>
+ *                        => tcp_disconnect() => tcp_send_active_reset()
+ *
+ * The passive reset is quite hard to get on established TCP connections.
+ * It could be procured from non-established states, but the synchronization
+ * part from userspace in order to reliably get RST seems uneasy.
+ * So, instead it's procured by corrupting SEQ number on TIMED-WAIT state.
+ *
+ * It's important to test both passive and active RST as they go through
+ * different code-paths:
+ * - tcp_send_active_reset() makes no-data skb, sends it with tcp_transmit_skb()
+ * - tcp_v*_send_reset() create their reply skbs and send them with
+ *   ip_send_unicast_reply()
+ *
+ * In both cases TCP-AO signatures have to be correct, which is verified by
+ * (1) checking that the TCP-AO connection was reset and (2) TCP-AO counters.
+ *
+ * Author: Dmitry Safonov <dima@arista.com>
+ */
 #include <inttypes.h>
 #include "../../../../include/linux/kernel.h"
 #include "aolib.h"
 
 const size_t quota = 1000;
+const size_t packet_sz = 100;
 /*
  * Backlog == 0 means 1 connection in queue, see:
  * commit 64a146513f8f ("[NET]: Revert incorrect accept queue...")
@@ -59,26 +82,6 @@ static void close_forced(int sk)
 	close(sk);
 }
 
-static int test_wait_for_exception(int sk, time_t sec)
-{
-	struct timeval tv = { .tv_sec = sec };
-	struct timeval *ptv = NULL;
-	fd_set efds;
-	int ret;
-
-	FD_ZERO(&efds);
-	FD_SET(sk, &efds);
-
-	if (sec)
-		ptv = &tv;
-
-	errno = 0;
-	ret = select(sk + 1, NULL, NULL, &efds, ptv);
-	if (ret < 0)
-		return -errno;
-	return ret ? sk : 0;
-}
-
 static void test_server_active_rst(unsigned int port)
 {
 	struct tcp_ao_counters cnt1, cnt2;
@@ -155,17 +158,16 @@ static void test_server_passive_rst(unsigned int port)
 			test_fail("server returned %zd", bytes);
 	}
 
-	synchronize_threads(); /* 3: chekpoint/restore the connection */
+	synchronize_threads(); /* 3: checkpoint the client */
+	synchronize_threads(); /* 4: close the server, creating twsk */
 	if (test_get_tcp_ao_counters(sk, &ao2))
 		test_error("test_get_tcp_ao_counters()");
-
-	synchronize_threads(); /* 4: terminate server + send more on client */
-	bytes = test_server_run(sk, quota, TEST_RETRANSMIT_SEC);
 	close(sk);
+
+	synchronize_threads(); /* 5: restore the socket, send more data */
 	test_tcp_ao_counters_cmp("passive RST server", &ao1, &ao2, TEST_CNT_GOOD);
 
-	synchronize_threads(); /* 5: verified => closed */
+	synchronize_threads(); /* 6: server exits */
-	close(sk);
 }
 
 static void *server_fn(void *arg)
@@ -284,7 +286,7 @@ static void test_client_active_rst(unsigned int port)
 		test_error("test_wait_fds(): %d", err);
 
 	synchronize_threads(); /* 3: close listen socket */
-	if (test_client_verify(sk[0], 100, quota / 100, TEST_TIMEOUT_SEC))
+	if (test_client_verify(sk[0], packet_sz, quota / packet_sz, TEST_TIMEOUT_SEC))
 		test_fail("Failed to send data on connected socket");
 	else
 		test_ok("Verified established tcp connection");
@@ -323,7 +325,6 @@ static void test_client_passive_rst(unsigned int port)
 	struct tcp_sock_state img;
 	sockaddr_af saddr;
 	int sk, err;
-	socklen_t slen = sizeof(err);
 
 	sk = socket(test_family, SOCK_STREAM, IPPROTO_TCP);
 	if (sk < 0)
@@ -337,18 +338,51 @@ static void test_client_passive_rst(unsigned int port)
 		test_error("failed to connect()");
 
 	synchronize_threads(); /* 2: accepted => send data */
-	if (test_client_verify(sk, 100, quota / 100, TEST_TIMEOUT_SEC))
+	if (test_client_verify(sk, packet_sz, quota / packet_sz, TEST_TIMEOUT_SEC))
 		test_fail("Failed to send data on connected socket");
 	else
 		test_ok("Verified established tcp connection");
 
-	synchronize_threads(); /* 3: chekpoint/restore the connection */
+	synchronize_threads(); /* 3: checkpoint the client */
 	test_enable_repair(sk);
 	test_sock_checkpoint(sk, &img, &saddr);
 	test_ao_checkpoint(sk, &ao_img);
-	test_kill_sk(sk);
+	test_disable_repair(sk);
 
-	img.out.seq += quota;
+	synchronize_threads(); /* 4: close the server, creating twsk */
+
+	/*
+	 * The "corruption" in SEQ has to be small enough to fit into TCP
+	 * window, see tcp_timewait_state_process() for out-of-window
+	 * segments.
+	 */
+	img.out.seq += 5; /* 5 is more noticeable in tcpdump than 1 */
+
+	/*
+	 * FIXME: This is kind-of ugly and dirty, but it works.
+	 *
+	 * At this moment, the server has close'ed(sk).
+	 * The passive RST that is being targeted here is new data after
+	 * half-duplex close, see tcp_timewait_state_process() => TCP_TW_RST
+	 *
+	 * What is needed here is:
+	 * (1) wait for FIN from the server
+	 * (2) make sure that the ACK from the client went out
+	 * (3) make sure that the ACK was received and processed by the server
+	 *
+	 * Otherwise, the data that will be sent from "repaired" socket
+	 * post SEQ corruption may get to the server before it's in
+	 * TCP_FIN_WAIT2.
+	 *
+	 * (1) is easy with select()/poll()
+	 * (2) is possible by polling tcpi_state from TCP_INFO
+	 * (3) is quite complex: as server's socket was already closed,
+	 *     probably the way to do it would be tcp-diag.
+	 */
+	sleep(TEST_RETRANSMIT_SEC);
+
+	synchronize_threads(); /* 5: restore the socket, send more data */
+	test_kill_sk(sk);
 
 	sk = socket(test_family, SOCK_STREAM, IPPROTO_TCP);
 	if (sk < 0)
@@ -366,25 +400,33 @@ static void test_client_passive_rst(unsigned int port)
 	test_disable_repair(sk);
 	test_sock_state_free(&img);
 
-	synchronize_threads(); /* 4: terminate server + send more on client */
+	/*
-	if (test_client_verify(sk, 100, quota / 100, 2 * TEST_TIMEOUT_SEC))
+	 * This is how "passive reset" is acquired in this test from TCP_TW_RST:
-		test_ok("client connection broken post-seq-adjust");
+	 *
+	 * IP 10.0.254.1.7011 > 10.0.1.1.59772: Flags [P.], seq 901:1001, ack 1001, win 249,
+	 *    options [tcp-ao keyid 100 rnextkeyid 100 mac 0x10217d6c36a22379086ef3b1], length 100
+	 * IP 10.0.254.1.7011 > 10.0.1.1.59772: Flags [F.], seq 1001, ack 1001, win 249,
+	 *    options [tcp-ao keyid 100 rnextkeyid 100 mac 0x104ffc99b98c10a5298cc268], length 0
+	 * IP 10.0.1.1.59772 > 10.0.254.1.7011: Flags [.], ack 1002, win 251,
+	 *    options [tcp-ao keyid 100 rnextkeyid 100 mac 0xe496dd4f7f5a8a66873c6f93,nop,nop,sack 1 {1001:1002}], length 0
+	 * IP 10.0.1.1.59772 > 10.0.254.1.7011: Flags [P.], seq 1006:1106, ack 1001, win 251,
+	 *    options [tcp-ao keyid 100 rnextkeyid 100 mac 0x1b5f3330fb23fbcd0c77d0ca], length 100
+	 * IP 10.0.254.1.7011 > 10.0.1.1.59772: Flags [R], seq 3215596252, win 0,
+	 *    options [tcp-ao keyid 100 rnextkeyid 100 mac 0x0bcfbbf497bce844312304b2], length 0
+	 */
+	err = test_client_verify(sk, packet_sz, quota / packet_sz, 2 * TEST_TIMEOUT_SEC);
+	/* Make sure that the connection was reset, not timeouted */
+	if (err && err == -ECONNRESET)
+		test_ok("client sock was passively reset post-seq-adjust");
+	else if (err)
+		test_fail("client sock was not reset post-seq-adjust: %d", err);
 	else
-		test_fail("client connection still works post-seq-adjust");
+		test_fail("client sock is yet connected post-seq-adjust");
-
-	test_wait_for_exception(sk, TEST_TIMEOUT_SEC);
-
-	if (getsockopt(sk, SOL_SOCKET, SO_ERROR, &err, &slen))
-		test_error("getsockopt()");
-	if (err != ECONNRESET && err != EPIPE)
-		test_fail("client connection was not reset: %d", err);
-	else
-		test_ok("client connection was reset");
 
 	if (test_get_tcp_ao_counters(sk, &ao2))
 		test_error("test_get_tcp_ao_counters()");
 
-	synchronize_threads(); /* 5: verified => closed */
+	synchronize_threads(); /* 6: server exits */
 	close(sk);
 	test_tcp_ao_counters_cmp("client passive RST", &ao1, &ao2, TEST_CNT_GOOD);
 }
@@ -410,6 +452,6 @@ static void *client_fn(void *arg)
 
 int main(int argc, char *argv[])
 {
-	test_init(15, server_fn, client_fn);
+	test_init(14, server_fn, client_fn);
 	return 0;
 }

tools/testing/selftests/net/tcp_ao/settings

@@ -0,0 +1 @@
+timeout=120

tools/testing/selftests/net/udpgro.sh

@@ -7,7 +7,7 @@ source net_helper.sh
 
 readonly PEER_NS="ns-peer-$(mktemp -u XXXXXX)"
 
-BPF_FILE="../bpf/xdp_dummy.bpf.o"
+BPF_FILE="xdp_dummy.o"
 
 # set global exit status, but never reset nonzero one.
 check_err()
@@ -197,7 +197,7 @@ run_all() {
 }
 
 if [ ! -f ${BPF_FILE} ]; then
-	echo "Missing ${BPF_FILE}. Build bpf selftest first"
+	echo "Missing ${BPF_FILE}. Run 'make' first"
 	exit -1
 fi
 

tools/testing/selftests/net/udpgro_bench.sh

@@ -7,7 +7,7 @@ source net_helper.sh
 
 readonly PEER_NS="ns-peer-$(mktemp -u XXXXXX)"
 
-BPF_FILE="../bpf/xdp_dummy.bpf.o"
+BPF_FILE="xdp_dummy.o"
 
 cleanup() {
 	local -r jobs="$(jobs -p)"
@@ -84,7 +84,7 @@ run_all() {
 }
 
 if [ ! -f ${BPF_FILE} ]; then
-	echo "Missing ${BPF_FILE}. Build bpf selftest first"
+	echo "Missing ${BPF_FILE}. Run 'make' first"
 	exit -1
 fi
 

tools/testing/selftests/net/udpgro_frglist.sh

@@ -7,7 +7,7 @@ source net_helper.sh
 
 readonly PEER_NS="ns-peer-$(mktemp -u XXXXXX)"
 
-BPF_FILE="../bpf/xdp_dummy.bpf.o"
+BPF_FILE="xdp_dummy.o"
 
 cleanup() {
 	local -r jobs="$(jobs -p)"
@@ -85,12 +85,12 @@ run_all() {
 }
 
 if [ ! -f ${BPF_FILE} ]; then
-	echo "Missing ${BPF_FILE}. Build bpf selftest first"
+	echo "Missing ${BPF_FILE}. Run 'make' first"
 	exit -1
 fi
 
 if [ ! -f nat6to4.o ]; then
-	echo "Missing nat6to4 helper. Build bpf nat6to4.o selftest first"
+	echo "Missing nat6to4 helper. Run 'make' first"
 	exit -1
 fi
 

tools/testing/selftests/net/udpgro_fwd.sh

@@ -1,7 +1,9 @@
 #!/bin/bash
 # SPDX-License-Identifier: GPL-2.0
 
-BPF_FILE="../bpf/xdp_dummy.bpf.o"
+source net_helper.sh
+
+BPF_FILE="xdp_dummy.o"
 readonly BASE="ns-$(mktemp -u XXXXXX)"
 readonly SRC=2
 readonly DST=1
@@ -119,7 +121,7 @@ run_test() {
 	ip netns exec $NS_DST $ipt -A INPUT -p udp --dport 8000
 	ip netns exec $NS_DST ./udpgso_bench_rx -C 1000 -R 10 -n 10 -l 1300 $rx_args &
 	local spid=$!
-	sleep 0.1
+	wait_local_port_listen "$NS_DST" 8000 udp
 	ip netns exec $NS_SRC ./udpgso_bench_tx $family -M 1 -s 13000 -S 1300 -D $dst
 	local retc=$?
 	wait $spid
@@ -168,7 +170,7 @@ run_bench() {
 	ip netns exec $NS_DST bash -c "echo 2 > /sys/class/net/veth$DST/queues/rx-0/rps_cpus"
 	ip netns exec $NS_DST taskset 0x2 ./udpgso_bench_rx -C 1000 -R 10  &
 	local spid=$!
-	sleep 0.1
+	wait_local_port_listen "$NS_DST" 8000 udp
 	ip netns exec $NS_SRC taskset 0x1 ./udpgso_bench_tx $family -l 3 -S 1300 -D $dst
 	local retc=$?
 	wait $spid

tools/testing/selftests/net/veth.sh

@@ -1,7 +1,7 @@
 #!/bin/sh
 # SPDX-License-Identifier: GPL-2.0
 
-BPF_FILE="../bpf/xdp_dummy.bpf.o"
+BPF_FILE="xdp_dummy.o"
 readonly STATS="$(mktemp -p /tmp ns-XXXXXX)"
 readonly BASE=`basename $STATS`
 readonly SRC=2
@@ -218,7 +218,7 @@ while getopts "hs:" option; do
 done
 
 if [ ! -f ${BPF_FILE} ]; then
-	echo "Missing ${BPF_FILE}. Build bpf selftest first"
+	echo "Missing ${BPF_FILE}. Run 'make' first"
 	exit 1
 fi
 

tools/testing/selftests/net/xdp_dummy.c

@@ -0,0 +1,13 @@
+// SPDX-License-Identifier: GPL-2.0
+
+#define KBUILD_MODNAME "xdp_dummy"
+#include <linux/bpf.h>
+#include <bpf/bpf_helpers.h>
+
+SEC("xdp")
+int xdp_dummy_prog(struct xdp_md *ctx)
+{
+	return XDP_PASS;
+}
+
+char _license[] SEC("license") = "GPL";