Merge tag 'net-6.15-rc4' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull networking fixes from Paolo Abeni: "No fixes from any subtree. Current release - regressions: - net: fix the missing unlock for detached devices Previous releases - regressions: - sched: fix UAF vulnerability in HFSC qdisc - lwtunnel: disable BHs when required - mptcp: pm: defer freeing of MPTCP userspace path manager entries - tipc: fix NULL pointer dereference in tipc_mon_reinit_self() - eth: virtio-net: disable delayed refill when pausing rx Previous releases - always broken: - phylink: fix suspend/resume with WoL enabled and link down - eth: - mlx5: fix null-ptr-deref in mlx5_create_{inner_,}ttc_table() - xen-netfront: handle NULL returned by xdp_convert_buff_to_frame() - enetc: fix frame corruption on bpf_xdp_adjust_head/tail() and XDP_PASS - stmmac: fix dwmac1000 ptp timestamp status offset - pds_core: prevent possible adminq overflow/stuck condition Misc: - a bunch of MAINTAINERS updates" * tag 'net-6.15-rc4' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (32 commits) net: stmmac: fix multiplication overflow when reading timestamp net: stmmac: fix dwmac1000 ptp timestamp status offset net: dp83822: Fix OF_MDIO config check pds_core: make wait_context part of q_info pds_core: Remove unnecessary check in pds_client_adminq_cmd() pds_core: handle unsupported PDS_CORE_CMD_FW_CONTROL result pds_core: Prevent possible adminq overflow/stuck condition net: dsa: mt7530: sync driver-specific behavior of MT7531 variants selftests/tc-testing: Add test for HFSC queue emptying during peek operation net_sched: hfsc: Fix a potential UAF in hfsc_dequeue() too net_sched: hfsc: Fix a UAF vulnerability in class handling selftests: mptcp: diag: use mptcp_lib_get_info_value mptcp: pm: Defer freeing of MPTCP userspace path manager entries net: ethernet: mtk_eth_soc: net: revise NETSYSv3 hardware configuration tipc: fix NULL pointer dereference in tipc_mon_reinit_self() virtio-net: disable delayed refill when pausing rx net: phy: leds: fix memory leak net: phylink: mac_link_(up|down)() clarifications net: phylink: fix suspend/resume with WoL enabled and link down net: lwtunnel: disable BHs when required ...
2025-04-24 09:14:50 -07:00
parent 288537d9c9 cc0dec3f65
commit e72e9e6933
29 changed files with 345 additions and 196 deletions
@@ -3191,6 +3191,12 @@ M:	Dinh Nguyen <dinguyen@kernel.org>
 S:	Maintained
 F:	drivers/clk/socfpga/

+ARM/SOCFPGA DWMAC GLUE LAYER
+M:	Maxime Chevallier <maxime.chevallier@bootlin.com>
+S:	Maintained
+F:	Documentation/devicetree/bindings/net/socfpga-dwmac.txt
+F:	drivers/net/ethernet/stmicro/stmmac/dwmac-socfpga.c
+
 ARM/SOCFPGA EDAC BINDINGS
 M:	Matthew Gerlach <matthew.gerlach@altera.com>
 S:	Maintained
@@ -16812,6 +16818,7 @@ F:	Documentation/networking/net_cachelines/net_device.rst
 F:	drivers/connector/
 F:	drivers/net/
 F:	drivers/ptp/
+F:	drivers/s390/net/
 F:	include/dt-bindings/net/
 F:	include/linux/cn_proc.h
 F:	include/linux/etherdevice.h
@@ -16821,6 +16828,7 @@ F:	include/linux/fddidevice.h
 F:	include/linux/hippidevice.h
 F:	include/linux/if_*
 F:	include/linux/inetdevice.h
+F:	include/linux/ism.h
 F:	include/linux/netdev*
 F:	include/linux/platform_data/wiznet.h
 F:	include/uapi/linux/cn_proc.h
@@ -21312,6 +21320,7 @@ L:	linux-s390@vger.kernel.org
 L:	netdev@vger.kernel.org
 S:	Supported
 F:	drivers/s390/net/
+F:	include/linux/ism.h

 S390 PCI SUBSYSTEM
 M:	Niklas Schnelle <schnelle@linux.ibm.com>
@@ -2419,6 +2419,9 @@ mt7531_setup_common(struct dsa_switch *ds)
 	struct mt7530_priv *priv = ds->priv;
 	int ret, i;

+	ds->assisted_learning_on_cpu_port = true;
+	ds->mtu_enforcement_ingress = true;
+
 	mt753x_trap_frames(priv);

 	/* Enable and reset MIB counters */
@@ -2571,9 +2574,6 @@ mt7531_setup(struct dsa_switch *ds)
 	if (ret)
 		return ret;

-	ds->assisted_learning_on_cpu_port = true;
-	ds->mtu_enforcement_ingress = true;
-
 	return 0;
 }

@@ -5,11 +5,6 @@

 #include "core.h"

-struct pdsc_wait_context {
-	struct pdsc_qcq *qcq;
-	struct completion wait_completion;
-};
-
 static int pdsc_process_notifyq(struct pdsc_qcq *qcq)
 {
 	union pds_core_notifyq_comp *comp;
@@ -109,10 +104,10 @@ void pdsc_process_adminq(struct pdsc_qcq *qcq)
 		q_info = &q->info[q->tail_idx];
 		q->tail_idx = (q->tail_idx + 1) & (q->num_descs - 1);

-		/* Copy out the completion data */
-		memcpy(q_info->dest, comp, sizeof(*comp));
-
-		complete_all(&q_info->wc->wait_completion);
+		if (!completion_done(&q_info->completion)) {
+			memcpy(q_info->dest, comp, sizeof(*comp));
+			complete(&q_info->completion);
+		}

 		if (cq->tail_idx == cq->num_descs - 1)
 			cq->done_color = !cq->done_color;
@@ -162,8 +157,7 @@ irqreturn_t pdsc_adminq_isr(int irq, void *data)
 static int __pdsc_adminq_post(struct pdsc *pdsc,
 			      struct pdsc_qcq *qcq,
 			      union pds_core_adminq_cmd *cmd,
-			      union pds_core_adminq_comp *comp,
-			      struct pdsc_wait_context *wc)
+			      union pds_core_adminq_comp *comp)
 {
 	struct pdsc_queue *q = &qcq->q;
 	struct pdsc_q_info *q_info;
@@ -205,9 +199,9 @@ static int __pdsc_adminq_post(struct pdsc *pdsc,
 	/* Post the request */
 	index = q->head_idx;
 	q_info = &q->info[index];
-	q_info->wc = wc;
 	q_info->dest = comp;
 	memcpy(q_info->desc, cmd, sizeof(*cmd));
+	reinit_completion(&q_info->completion);

 	dev_dbg(pdsc->dev, "head_idx %d tail_idx %d\n",
 		q->head_idx, q->tail_idx);
@@ -231,16 +225,13 @@ int pdsc_adminq_post(struct pdsc *pdsc,
 		     union pds_core_adminq_comp *comp,
 		     bool fast_poll)
 {
-	struct pdsc_wait_context wc = {
-		.wait_completion =
-			COMPLETION_INITIALIZER_ONSTACK(wc.wait_completion),
-	};
 	unsigned long poll_interval = 1;
 	unsigned long poll_jiffies;
 	unsigned long time_limit;
 	unsigned long time_start;
 	unsigned long time_done;
 	unsigned long remaining;
+	struct completion *wc;
 	int err = 0;
 	int index;

@@ -250,20 +241,19 @@ int pdsc_adminq_post(struct pdsc *pdsc,
 		return -ENXIO;
 	}

-	wc.qcq = &pdsc->adminqcq;
-	index = __pdsc_adminq_post(pdsc, &pdsc->adminqcq, cmd, comp, &wc);
+	index = __pdsc_adminq_post(pdsc, &pdsc->adminqcq, cmd, comp);
 	if (index < 0) {
 		err = index;
 		goto err_out;
 	}

+	wc = &pdsc->adminqcq.q.info[index].completion;
 	time_start = jiffies;
 	time_limit = time_start + HZ * pdsc->devcmd_timeout;
 	do {
 		/* Timeslice the actual wait to catch IO errors etc early */
 		poll_jiffies = msecs_to_jiffies(poll_interval);
-		remaining = wait_for_completion_timeout(&wc.wait_completion,
-							poll_jiffies);
+		remaining = wait_for_completion_timeout(wc, poll_jiffies);
 		if (remaining)
 			break;

@@ -292,9 +282,11 @@ int pdsc_adminq_post(struct pdsc *pdsc,
 	dev_dbg(pdsc->dev, "%s: elapsed %d msecs\n",
 		__func__, jiffies_to_msecs(time_done - time_start));

-	/* Check the results */
-	if (time_after_eq(time_done, time_limit))
+	/* Check the results and clear an un-completed timeout */
+	if (time_after_eq(time_done, time_limit) && !completion_done(wc)) {
 		err = -ETIMEDOUT;
+		complete(wc);
+	}

 	dev_dbg(pdsc->dev, "read admin queue completion idx %d:\n", index);
 	dynamic_hex_dump("comp ", DUMP_PREFIX_OFFSET, 16, 1,
@@ -107,9 +107,6 @@ int pds_client_adminq_cmd(struct pds_auxiliary_dev *padev,
 	dev_dbg(pf->dev, "%s: %s opcode %d\n",
 		__func__, dev_name(&padev->aux_dev.dev), req->opcode);

-	if (pf->state)
-		return -ENXIO;
-
 	/* Wrap the client's request */
 	cmd.client_request.opcode = PDS_AQ_CMD_CLIENT_CMD;
 	cmd.client_request.client_id = cpu_to_le16(padev->client_id);
@@ -167,8 +167,10 @@ static void pdsc_q_map(struct pdsc_queue *q, void *base, dma_addr_t base_pa)
 	q->base = base;
 	q->base_pa = base_pa;

-	for (i = 0, cur = q->info; i < q->num_descs; i++, cur++)
+	for (i = 0, cur = q->info; i < q->num_descs; i++, cur++) {
 		cur->desc = base + (i * q->desc_size);
+		init_completion(&cur->completion);
+	}
 }

 static void pdsc_cq_map(struct pdsc_cq *cq, void *base, dma_addr_t base_pa)
@@ -325,10 +327,7 @@ static int pdsc_core_init(struct pdsc *pdsc)
 	size_t sz;
 	int err;

-	/* Scale the descriptor ring length based on number of CPUs and VFs */
-	numdescs = max_t(int, PDSC_ADMINQ_MIN_LENGTH, num_online_cpus());
-	numdescs += 2 * pci_sriov_get_totalvfs(pdsc->pdev);
-	numdescs = roundup_pow_of_two(numdescs);
+	numdescs = PDSC_ADMINQ_MAX_LENGTH;
 	err = pdsc_qcq_alloc(pdsc, PDS_CORE_QTYPE_ADMINQ, 0, "adminq",
 			     PDS_CORE_QCQ_F_CORE | PDS_CORE_QCQ_F_INTR,
 			     numdescs,
@@ -16,7 +16,7 @@

 #define PDSC_WATCHDOG_SECS	5
 #define PDSC_QUEUE_NAME_MAX_SZ  16
-#define PDSC_ADMINQ_MIN_LENGTH	16	/* must be a power of two */
+#define PDSC_ADMINQ_MAX_LENGTH	16	/* must be a power of two */
 #define PDSC_NOTIFYQ_LENGTH	64	/* must be a power of two */
 #define PDSC_TEARDOWN_RECOVERY	false
 #define PDSC_TEARDOWN_REMOVING	true
@@ -96,7 +96,7 @@ struct pdsc_q_info {
 	unsigned int bytes;
 	unsigned int nbufs;
 	struct pdsc_buf_info bufs[PDS_CORE_MAX_FRAGS];
-	struct pdsc_wait_context *wc;
+	struct completion completion;
 	void *dest;
 };

@@ -105,7 +105,7 @@ int pdsc_dl_info_get(struct devlink *dl, struct devlink_info_req *req,
 		.fw_control.opcode = PDS_CORE_CMD_FW_CONTROL,
 		.fw_control.oper = PDS_CORE_FW_GET_LIST,
 	};
-	struct pds_core_fw_list_info fw_list;
+	struct pds_core_fw_list_info fw_list = {};
 	struct pdsc *pdsc = devlink_priv(dl);
 	union pds_core_dev_comp comp;
 	char buf[32];
@@ -118,8 +118,6 @@ int pdsc_dl_info_get(struct devlink *dl, struct devlink_info_req *req,
 	if (!err)
 		memcpy_fromio(&fw_list, pdsc->cmd_regs->data, sizeof(fw_list));
 	mutex_unlock(&pdsc->devcmd_lock);
-	if (err && err != -EIO)
-		return err;

 	listlen = min(fw_list.num_fw_slots, ARRAY_SIZE(fw_list.fw_names));
 	for (i = 0; i < listlen; i++) {
@@ -1850,6 +1850,16 @@ static void enetc_xdp_drop(struct enetc_bdr *rx_ring, int rx_ring_first,
 	}
 }

+static void enetc_bulk_flip_buff(struct enetc_bdr *rx_ring, int rx_ring_first,
+				 int rx_ring_last)
+{
+	while (rx_ring_first != rx_ring_last) {
+		enetc_flip_rx_buff(rx_ring,
+				   &rx_ring->rx_swbd[rx_ring_first]);
+		enetc_bdr_idx_inc(rx_ring, &rx_ring_first);
+	}
+}
+
 static int enetc_clean_rx_ring_xdp(struct enetc_bdr *rx_ring,
 				   struct napi_struct *napi, int work_limit,
 				   struct bpf_prog *prog)
@@ -1868,11 +1878,10 @@ static int enetc_clean_rx_ring_xdp(struct enetc_bdr *rx_ring,

 	while (likely(rx_frm_cnt < work_limit)) {
 		union enetc_rx_bd *rxbd, *orig_rxbd;
-		int orig_i, orig_cleaned_cnt;
 		struct xdp_buff xdp_buff;
 		struct sk_buff *skb;
+		int orig_i, err;
 		u32 bd_status;
-		int err;

 		rxbd = enetc_rxbd(rx_ring, i);
 		bd_status = le32_to_cpu(rxbd->r.lstatus);
@@ -1887,7 +1896,6 @@ static int enetc_clean_rx_ring_xdp(struct enetc_bdr *rx_ring,
 			break;

 		orig_rxbd = rxbd;
-		orig_cleaned_cnt = cleaned_cnt;
 		orig_i = i;

 		enetc_build_xdp_buff(rx_ring, bd_status, &rxbd, &i,
@@ -1915,15 +1923,21 @@ static int enetc_clean_rx_ring_xdp(struct enetc_bdr *rx_ring,
 			rx_ring->stats.xdp_drops++;
 			break;
 		case XDP_PASS:
-			rxbd = orig_rxbd;
-			cleaned_cnt = orig_cleaned_cnt;
-			i = orig_i;
-
-			skb = enetc_build_skb(rx_ring, bd_status, &rxbd,
-					      &i, &cleaned_cnt,
-					      ENETC_RXB_DMA_SIZE_XDP);
-			if (unlikely(!skb))
+			skb = xdp_build_skb_from_buff(&xdp_buff);
+			/* Probably under memory pressure, stop NAPI */
+			if (unlikely(!skb)) {
+				enetc_xdp_drop(rx_ring, orig_i, i);
+				rx_ring->stats.xdp_drops++;
 				goto out;
+			}
+
+			enetc_get_offloads(rx_ring, orig_rxbd, skb);
+
+			/* These buffers are about to be owned by the stack.
+			 * Update our buffer cache (the rx_swbd array elements)
+			 * with their other page halves.
+			 */
+			enetc_bulk_flip_buff(rx_ring, orig_i, i);

 			napi_gro_receive(napi, skb);
 			break;
@@ -1965,11 +1979,7 @@ static int enetc_clean_rx_ring_xdp(struct enetc_bdr *rx_ring,
 				enetc_xdp_drop(rx_ring, orig_i, i);
 				rx_ring->stats.xdp_redirect_failures++;
 			} else {
-				while (orig_i != i) {
-					enetc_flip_rx_buff(rx_ring,
-							   &rx_ring->rx_swbd[orig_i]);
-					enetc_bdr_idx_inc(rx_ring, &orig_i);
-				}
+				enetc_bulk_flip_buff(rx_ring, orig_i, i);
 				xdp_redirect_frm_cnt++;
 				rx_ring->stats.xdp_redirect++;
 			}
@@ -3362,7 +3372,8 @@ static int enetc_int_vector_init(struct enetc_ndev_priv *priv, int i,
 	bdr->buffer_offset = ENETC_RXB_PAD;
 	priv->rx_ring[i] = bdr;

-	err = xdp_rxq_info_reg(&bdr->xdp.rxq, priv->ndev, i, 0);
+	err = __xdp_rxq_info_reg(&bdr->xdp.rxq, priv->ndev, i, 0,
+				 ENETC_RXB_DMA_SIZE_XDP);
 	if (err)
 		goto free_vector;

@@ -4043,11 +4043,27 @@ static int mtk_hw_init(struct mtk_eth *eth, bool reset)
 	mtk_w32(eth, 0x21021000, MTK_FE_INT_GRP);

 	if (mtk_is_netsys_v3_or_greater(eth)) {
-		/* PSE should not drop port1, port8 and port9 packets */
-		mtk_w32(eth, 0x00000302, PSE_DROP_CFG);
+		/* PSE dummy page mechanism */
+		mtk_w32(eth, PSE_DUMMY_WORK_GDM(1) | PSE_DUMMY_WORK_GDM(2) |
+			PSE_DUMMY_WORK_GDM(3) | DUMMY_PAGE_THR, PSE_DUMY_REQ);
+
+		/* PSE free buffer drop threshold */
+		mtk_w32(eth, 0x00600009, PSE_IQ_REV(8));
+
+		/* PSE should not drop port8, port9 and port13 packets from
+		 * WDMA Tx
+		 */
+		mtk_w32(eth, 0x00002300, PSE_DROP_CFG);
+
+		/* PSE should drop packets to port8, port9 and port13 on WDMA Rx
+		 * ring full
+		 */
+		mtk_w32(eth, 0x00002300, PSE_PPE_DROP(0));
+		mtk_w32(eth, 0x00002300, PSE_PPE_DROP(1));
+		mtk_w32(eth, 0x00002300, PSE_PPE_DROP(2));

 		/* GDM and CDM Threshold */
-		mtk_w32(eth, 0x00000707, MTK_CDMW0_THRES);
+		mtk_w32(eth, 0x08000707, MTK_CDMW0_THRES);
 		mtk_w32(eth, 0x00000077, MTK_CDMW1_THRES);

 		/* Disable GDM1 RX CRC stripping */
@@ -4064,7 +4080,7 @@ static int mtk_hw_init(struct mtk_eth *eth, bool reset)
 		mtk_w32(eth, 0x00000300, PSE_DROP_CFG);

 		/* PSE should drop packets to port 8/9 on WDMA Rx ring full */
-		mtk_w32(eth, 0x00000300, PSE_PPE0_DROP);
+		mtk_w32(eth, 0x00000300, PSE_PPE_DROP(0));

 		/* PSE Free Queue Flow Control  */
 		mtk_w32(eth, 0x01fa01f4, PSE_FQFC_CFG2);
@@ -151,7 +151,15 @@
 #define PSE_FQFC_CFG1		0x100
 #define PSE_FQFC_CFG2		0x104
 #define PSE_DROP_CFG		0x108
-#define PSE_PPE0_DROP		0x110
+#define PSE_PPE_DROP(x)		(0x110 + ((x) * 0x4))
+
+/* PSE Last FreeQ Page Request Control */
+#define PSE_DUMY_REQ		0x10C
+/* PSE_DUMY_REQ is not a typo but actually called like that also in
+ * MediaTek's datasheet
+ */
+#define PSE_DUMMY_WORK_GDM(x)	BIT(16 + (x))
+#define DUMMY_PAGE_THR		0x1

 /* PSE Input Queue Reservation Register*/
 #define PSE_IQ_REV(x)		(0x140 + (((x) - 1) << 2))
@@ -637,10 +637,6 @@ struct mlx5_ttc_table *mlx5_create_inner_ttc_table(struct mlx5_core_dev *dev,
 	bool use_l4_type;
 	int err;

-	ttc = kvzalloc(sizeof(*ttc), GFP_KERNEL);
-	if (!ttc)
-		return ERR_PTR(-ENOMEM);
-
 	switch (params->ns_type) {
 	case MLX5_FLOW_NAMESPACE_PORT_SEL:
 		use_l4_type = MLX5_CAP_GEN_2(dev, pcc_ifa2) &&
@@ -654,7 +650,16 @@ struct mlx5_ttc_table *mlx5_create_inner_ttc_table(struct mlx5_core_dev *dev,
 		return ERR_PTR(-EINVAL);
 	}

+	ttc = kvzalloc(sizeof(*ttc), GFP_KERNEL);
+	if (!ttc)
+		return ERR_PTR(-ENOMEM);
+
 	ns = mlx5_get_flow_namespace(dev, params->ns_type);
+	if (!ns) {
+		kvfree(ttc);
+		return ERR_PTR(-EOPNOTSUPP);
+	}
+
 	groups = use_l4_type ? &inner_ttc_groups[TTC_GROUPS_USE_L4_TYPE] :
 			       &inner_ttc_groups[TTC_GROUPS_DEFAULT];

@@ -710,10 +715,6 @@ struct mlx5_ttc_table *mlx5_create_ttc_table(struct mlx5_core_dev *dev,
 	bool use_l4_type;
 	int err;

-	ttc = kvzalloc(sizeof(*ttc), GFP_KERNEL);
-	if (!ttc)
-		return ERR_PTR(-ENOMEM);
-
 	switch (params->ns_type) {
 	case MLX5_FLOW_NAMESPACE_PORT_SEL:
 		use_l4_type = MLX5_CAP_GEN_2(dev, pcc_ifa2) &&
@@ -727,7 +728,16 @@ struct mlx5_ttc_table *mlx5_create_ttc_table(struct mlx5_core_dev *dev,
 		return ERR_PTR(-EINVAL);
 	}

+	ttc = kvzalloc(sizeof(*ttc), GFP_KERNEL);
+	if (!ttc)
+		return ERR_PTR(-ENOMEM);
+
 	ns = mlx5_get_flow_namespace(dev, params->ns_type);
+	if (!ns) {
+		kvfree(ttc);
+		return ERR_PTR(-EOPNOTSUPP);
+	}
+
 	groups = use_l4_type ? &ttc_groups[TTC_GROUPS_USE_L4_TYPE] :
 			       &ttc_groups[TTC_GROUPS_DEFAULT];

@@ -320,8 +320,8 @@ enum rtc_control {

 /* PTP and timestamping registers */

-#define GMAC3_X_ATSNS       GENMASK(19, 16)
-#define GMAC3_X_ATSNS_SHIFT 16
+#define GMAC3_X_ATSNS       GENMASK(29, 25)
+#define GMAC3_X_ATSNS_SHIFT 25

 #define GMAC_PTP_TCR_ATSFC	BIT(24)
 #define GMAC_PTP_TCR_ATSEN0	BIT(25)
@@ -553,7 +553,7 @@ void dwmac1000_get_ptptime(void __iomem *ptpaddr, u64 *ptp_time)
 	u64 ns;

 	ns = readl(ptpaddr + GMAC_PTP_ATNR);
-	ns += readl(ptpaddr + GMAC_PTP_ATSR) * NSEC_PER_SEC;
+	ns += (u64)readl(ptpaddr + GMAC_PTP_ATSR) * NSEC_PER_SEC;

 	*ptp_time = ns;
 }
@@ -222,7 +222,7 @@ static void get_ptptime(void __iomem *ptpaddr, u64 *ptp_time)
 	u64 ns;

 	ns = readl(ptpaddr + PTP_ATNR);
-	ns += readl(ptpaddr + PTP_ATSR) * NSEC_PER_SEC;
+	ns += (u64)readl(ptpaddr + PTP_ATSR) * NSEC_PER_SEC;

 	*ptp_time = ns;
 }
@@ -730,7 +730,7 @@ static int dp83822_phy_reset(struct phy_device *phydev)
 	return phydev->drv->config_init(phydev);
 }

-#ifdef CONFIG_OF_MDIO
+#if IS_ENABLED(CONFIG_OF_MDIO)
 static const u32 tx_amplitude_100base_tx_gain[] = {
 	80, 82, 83, 85, 87, 88, 90, 92,
 	93, 95, 97, 98, 100, 102, 103, 105,
@@ -37,47 +37,6 @@ static int lan88xx_write_page(struct phy_device *phydev, int page)
 	return __phy_write(phydev, LAN88XX_EXT_PAGE_ACCESS, page);
 }

-static int lan88xx_phy_config_intr(struct phy_device *phydev)
-{
-	int rc;
-
-	if (phydev->interrupts == PHY_INTERRUPT_ENABLED) {
-		/* unmask all source and clear them before enable */
-		rc = phy_write(phydev, LAN88XX_INT_MASK, 0x7FFF);
-		rc = phy_read(phydev, LAN88XX_INT_STS);
-		rc = phy_write(phydev, LAN88XX_INT_MASK,
-			       LAN88XX_INT_MASK_MDINTPIN_EN_ |
-			       LAN88XX_INT_MASK_LINK_CHANGE_);
-	} else {
-		rc = phy_write(phydev, LAN88XX_INT_MASK, 0);
-		if (rc)
-			return rc;
-
-		/* Ack interrupts after they have been disabled */
-		rc = phy_read(phydev, LAN88XX_INT_STS);
-	}
-
-	return rc < 0 ? rc : 0;
-}
-
-static irqreturn_t lan88xx_handle_interrupt(struct phy_device *phydev)
-{
-	int irq_status;
-
-	irq_status = phy_read(phydev, LAN88XX_INT_STS);
-	if (irq_status < 0) {
-		phy_error(phydev);
-		return IRQ_NONE;
-	}
-
-	if (!(irq_status & LAN88XX_INT_STS_LINK_CHANGE_))
-		return IRQ_NONE;
-
-	phy_trigger_machine(phydev);
-
-	return IRQ_HANDLED;
-}
-
 static int lan88xx_suspend(struct phy_device *phydev)
 {
 	struct lan88xx_priv *priv = phydev->priv;
@@ -528,8 +487,9 @@ static struct phy_driver microchip_phy_driver[] = {
 	.config_aneg	= lan88xx_config_aneg,
 	.link_change_notify = lan88xx_link_change_notify,

-	.config_intr	= lan88xx_phy_config_intr,
-	.handle_interrupt = lan88xx_handle_interrupt,
+	/* Interrupt handling is broken, do not define related
+	 * functions to force polling.
+	 */

 	.suspend	= lan88xx_suspend,
 	.resume		= genphy_resume,
@@ -93,9 +93,8 @@ int phy_led_triggers_register(struct phy_device *phy)
 	if (!phy->phy_num_led_triggers)
 		return 0;

-	phy->led_link_trigger = devm_kzalloc(&phy->mdio.dev,
-					     sizeof(*phy->led_link_trigger),
-					     GFP_KERNEL);
+	phy->led_link_trigger = kzalloc(sizeof(*phy->led_link_trigger),
+					GFP_KERNEL);
 	if (!phy->led_link_trigger) {
 		err = -ENOMEM;
 		goto out_clear;
@@ -105,10 +104,9 @@ int phy_led_triggers_register(struct phy_device *phy)
 	if (err)
 		goto out_free_link;

-	phy->phy_led_triggers = devm_kcalloc(&phy->mdio.dev,
-					    phy->phy_num_led_triggers,
-					    sizeof(struct phy_led_trigger),
-					    GFP_KERNEL);
+	phy->phy_led_triggers = kcalloc(phy->phy_num_led_triggers,
+					sizeof(struct phy_led_trigger),
+					GFP_KERNEL);
 	if (!phy->phy_led_triggers) {
 		err = -ENOMEM;
 		goto out_unreg_link;
@@ -129,11 +127,11 @@ int phy_led_triggers_register(struct phy_device *phy)
 out_unreg:
 	while (i--)
 		phy_led_trigger_unregister(&phy->phy_led_triggers[i]);
-	devm_kfree(&phy->mdio.dev, phy->phy_led_triggers);
+	kfree(phy->phy_led_triggers);
 out_unreg_link:
 	phy_led_trigger_unregister(phy->led_link_trigger);
 out_free_link:
-	devm_kfree(&phy->mdio.dev, phy->led_link_trigger);
+	kfree(phy->led_link_trigger);
 	phy->led_link_trigger = NULL;
 out_clear:
 	phy->phy_num_led_triggers = 0;
@@ -147,8 +145,13 @@ void phy_led_triggers_unregister(struct phy_device *phy)

 	for (i = 0; i < phy->phy_num_led_triggers; i++)
 		phy_led_trigger_unregister(&phy->phy_led_triggers[i]);
+	kfree(phy->phy_led_triggers);
+	phy->phy_led_triggers = NULL;

-	if (phy->led_link_trigger)
+	if (phy->led_link_trigger) {
 		phy_led_trigger_unregister(phy->led_link_trigger);
+		kfree(phy->led_link_trigger);
+		phy->led_link_trigger = NULL;
+	}
 }
 EXPORT_SYMBOL_GPL(phy_led_triggers_unregister);
@@ -81,6 +81,7 @@ struct phylink {
 	unsigned int pcs_state;

 	bool link_failed;
+	bool suspend_link_up;
 	bool major_config_failed;
 	bool mac_supports_eee_ops;
 	bool mac_supports_eee;
@@ -2545,14 +2546,16 @@ void phylink_suspend(struct phylink *pl, bool mac_wol)
 		/* Stop the resolver bringing the link up */
 		__set_bit(PHYLINK_DISABLE_MAC_WOL, &pl->phylink_disable_state);

-		/* Disable the carrier, to prevent transmit timeouts,
-		 * but one would hope all packets have been sent. This
-		 * also means phylink_resolve() will do nothing.
-		 */
-		if (pl->netdev)
-			netif_carrier_off(pl->netdev);
-		else
+		pl->suspend_link_up = phylink_link_is_up(pl);
+		if (pl->suspend_link_up) {
+			/* Disable the carrier, to prevent transmit timeouts,
+			 * but one would hope all packets have been sent. This
+			 * also means phylink_resolve() will do nothing.
+			 */
+			if (pl->netdev)
+				netif_carrier_off(pl->netdev);
 			pl->old_link_state = false;
+		}

 		/* We do not call mac_link_down() here as we want the
 		 * link to remain up to receive the WoL packets.
@@ -2603,15 +2606,18 @@ void phylink_resume(struct phylink *pl)
 	if (test_bit(PHYLINK_DISABLE_MAC_WOL, &pl->phylink_disable_state)) {
 		/* Wake-on-Lan enabled, MAC handling */

-		/* Call mac_link_down() so we keep the overall state balanced.
-		 * Do this under the state_mutex lock for consistency. This
-		 * will cause a "Link Down" message to be printed during
-		 * resume, which is harmless - the true link state will be
-		 * printed when we run a resolve.
-		 */
-		mutex_lock(&pl->state_mutex);
-		phylink_link_down(pl);
-		mutex_unlock(&pl->state_mutex);
+		if (pl->suspend_link_up) {
+			/* Call mac_link_down() so we keep the overall state
+			 * balanced. Do this under the state_mutex lock for
+			 * consistency. This will cause a "Link Down" message
+			 * to be printed during resume, which is harmless -
+			 * the true link state will be printed when we run a
+			 * resolve.
+			 */
+			mutex_lock(&pl->state_mutex);
+			phylink_link_down(pl);
+			mutex_unlock(&pl->state_mutex);
+		}

 		/* Re-apply the link parameters so that all the settings get
 		 * restored to the MAC.
@@ -3342,7 +3342,8 @@ static netdev_tx_t start_xmit(struct sk_buff *skb, struct net_device *dev)
 	return NETDEV_TX_OK;
 }

-static void virtnet_rx_pause(struct virtnet_info *vi, struct receive_queue *rq)
+static void __virtnet_rx_pause(struct virtnet_info *vi,
+			       struct receive_queue *rq)
 {
 	bool running = netif_running(vi->dev);

@@ -3352,17 +3353,63 @@ static void virtnet_rx_pause(struct virtnet_info *vi, struct receive_queue *rq)
 	}
 }

-static void virtnet_rx_resume(struct virtnet_info *vi, struct receive_queue *rq)
+static void virtnet_rx_pause_all(struct virtnet_info *vi)
+{
+	int i;
+
+	/*
+	 * Make sure refill_work does not run concurrently to
+	 * avoid napi_disable race which leads to deadlock.
+	 */
+	disable_delayed_refill(vi);
+	cancel_delayed_work_sync(&vi->refill);
+	for (i = 0; i < vi->max_queue_pairs; i++)
+		__virtnet_rx_pause(vi, &vi->rq[i]);
+}
+
+static void virtnet_rx_pause(struct virtnet_info *vi, struct receive_queue *rq)
+{
+	/*
+	 * Make sure refill_work does not run concurrently to
+	 * avoid napi_disable race which leads to deadlock.
+	 */
+	disable_delayed_refill(vi);
+	cancel_delayed_work_sync(&vi->refill);
+	__virtnet_rx_pause(vi, rq);
+}
+
+static void __virtnet_rx_resume(struct virtnet_info *vi,
+				struct receive_queue *rq,
+				bool refill)
 {
 	bool running = netif_running(vi->dev);

-	if (!try_fill_recv(vi, rq, GFP_KERNEL))
+	if (refill && !try_fill_recv(vi, rq, GFP_KERNEL))
 		schedule_delayed_work(&vi->refill, 0);

 	if (running)
 		virtnet_napi_enable(rq);
 }

+static void virtnet_rx_resume_all(struct virtnet_info *vi)
+{
+	int i;
+
+	enable_delayed_refill(vi);
+	for (i = 0; i < vi->max_queue_pairs; i++) {
+		if (i < vi->curr_queue_pairs)
+			__virtnet_rx_resume(vi, &vi->rq[i], true);
+		else
+			__virtnet_rx_resume(vi, &vi->rq[i], false);
+	}
+}
+
+static void virtnet_rx_resume(struct virtnet_info *vi, struct receive_queue *rq)
+{
+	enable_delayed_refill(vi);
+	__virtnet_rx_resume(vi, rq, true);
+}
+
 static int virtnet_rx_resize(struct virtnet_info *vi,
 			     struct receive_queue *rq, u32 ring_num)
 {
@@ -5959,12 +6006,12 @@ static int virtnet_xdp_set(struct net_device *dev, struct bpf_prog *prog,
 	if (prog)
 		bpf_prog_add(prog, vi->max_queue_pairs - 1);

+	virtnet_rx_pause_all(vi);
+
 	/* Make sure NAPI is not using any XDP TX queues for RX. */
 	if (netif_running(dev)) {
-		for (i = 0; i < vi->max_queue_pairs; i++) {
-			virtnet_napi_disable(&vi->rq[i]);
+		for (i = 0; i < vi->max_queue_pairs; i++)
 			virtnet_napi_tx_disable(&vi->sq[i]);
-		}
 	}

 	if (!prog) {
@@ -5996,13 +6043,12 @@ static int virtnet_xdp_set(struct net_device *dev, struct bpf_prog *prog,
 		vi->xdp_enabled = false;
 	}

+	virtnet_rx_resume_all(vi);
 	for (i = 0; i < vi->max_queue_pairs; i++) {
 		if (old_prog)
 			bpf_prog_put(old_prog);
-		if (netif_running(dev)) {
-			virtnet_napi_enable(&vi->rq[i]);
+		if (netif_running(dev))
 			virtnet_napi_tx_enable(&vi->sq[i]);
-		}
 	}

 	return 0;
@@ -6014,11 +6060,10 @@ err:
 			rcu_assign_pointer(vi->rq[i].xdp_prog, old_prog);
 	}

+	virtnet_rx_resume_all(vi);
 	if (netif_running(dev)) {
-		for (i = 0; i < vi->max_queue_pairs; i++) {
-			virtnet_napi_enable(&vi->rq[i]);
+		for (i = 0; i < vi->max_queue_pairs; i++)
 			virtnet_napi_tx_enable(&vi->sq[i]);
-		}
 	}
 	if (prog)
 		bpf_prog_sub(prog, vi->max_queue_pairs - 1);
@@ -985,20 +985,27 @@ static u32 xennet_run_xdp(struct netfront_queue *queue, struct page *pdata,
 	act = bpf_prog_run_xdp(prog, xdp);
 	switch (act) {
 	case XDP_TX:
-		get_page(pdata);
 		xdpf = xdp_convert_buff_to_frame(xdp);
-		err = xennet_xdp_xmit(queue->info->netdev, 1, &xdpf, 0);
-		if (unlikely(!err))
-			xdp_return_frame_rx_napi(xdpf);
-		else if (unlikely(err < 0))
+		if (unlikely(!xdpf)) {
 			trace_xdp_exception(queue->info->netdev, prog, act);
+			break;
+		}
+		get_page(pdata);
+		err = xennet_xdp_xmit(queue->info->netdev, 1, &xdpf, 0);
+		if (unlikely(err <= 0)) {
+			if (err < 0)
+				trace_xdp_exception(queue->info->netdev, prog, act);
+			xdp_return_frame_rx_napi(xdpf);
+		}
 		break;
 	case XDP_REDIRECT:
 		get_page(pdata);
 		err = xdp_do_redirect(queue->info->netdev, xdp, prog);
 		*need_xdp_flush = true;
-		if (unlikely(err))
+		if (unlikely(err)) {
 			trace_xdp_exception(queue->info->netdev, prog, act);
+			xdp_return_buff(xdp);
+		}
 		break;
 	case XDP_PASS:
 	case XDP_DROP:
@@ -361,23 +361,29 @@ int mac_finish(struct phylink_config *config, unsigned int mode,
 		phy_interface_t iface);

 /**
- * mac_link_down() - take the link down
+ * mac_link_down() - notification that the link has gone down
 * @config: a pointer to a &struct phylink_config.
 * @mode: link autonegotiation mode
 * @interface: link &typedef phy_interface_t mode
 *
- * If @mode is not an in-band negotiation mode (as defined by
- * phylink_autoneg_inband()), force the link down and disable any
- * Energy Efficient Ethernet MAC configuration. Interface type
- * selection must be done in mac_config().
+ * Notifies the MAC that the link has gone down. This will not be called
+ * unless mac_link_up() has been previously called.
+ *
+ * The MAC should stop processing packets for transmission and reception.
+ * phylink will have called netif_carrier_off() to notify the networking
+ * stack that the link has gone down, so MAC drivers should not make this
+ * call.
+ *
+ * If @mode is %MLO_AN_INBAND, then this function must not prevent the
+ * link coming up.
 */
 void mac_link_down(struct phylink_config *config, unsigned int mode,
 		   phy_interface_t interface);

 /**
- * mac_link_up() - allow the link to come up
+ * mac_link_up() - notification that the link has come up
 * @config: a pointer to a &struct phylink_config.
- * @phy: any attached phy
+ * @phy: any attached phy (deprecated - please use LPI interfaces)
 * @mode: link autonegotiation mode
 * @interface: link &typedef phy_interface_t mode
 * @speed: link speed
@@ -385,7 +391,10 @@ void mac_link_down(struct phylink_config *config, unsigned int mode,
 * @tx_pause: link transmit pause enablement status
 * @rx_pause: link receive pause enablement status
 *
- * Configure the MAC for an established link.
+ * Notifies the MAC that the link has come up, and the parameters of the
+ * link as seen from the MACs point of view. If mac_link_up() has been
+ * called previously, there will be an intervening call to mac_link_down()
+ * before this method will be subsequently called.
 *
 * @speed, @duplex, @tx_pause and @rx_pause indicate the finalised link
 * settings, and should be used to configure the MAC block appropriately
@@ -397,9 +406,9 @@ void mac_link_down(struct phylink_config *config, unsigned int mode,
 * that the user wishes to override the pause settings, and this should
 * be allowed when considering the implementation of this method.
 *
- * If in-band negotiation mode is disabled, allow the link to come up. If
- * @phy is non-%NULL, configure Energy Efficient Ethernet by calling
- * phy_init_eee() and perform appropriate MAC configuration for EEE.
+ * Once configured, the MAC may begin to process packets for transmission
+ * and reception.
+ *
 * Interface type selection must be done in mac_config().
 */
 void mac_link_up(struct phylink_config *config, struct phy_device *phy,
@@ -333,6 +333,8 @@ int lwtunnel_output(struct net *net, struct sock *sk, struct sk_buff *skb)
 	struct dst_entry *dst;
 	int ret;

+	local_bh_disable();
+
 	if (dev_xmit_recursion()) {
 		net_crit_ratelimited("%s(): recursion limit reached on datapath\n",
 				     __func__);
@@ -348,8 +350,10 @@ int lwtunnel_output(struct net *net, struct sock *sk, struct sk_buff *skb)
 	lwtstate = dst->lwtstate;

 	if (lwtstate->type == LWTUNNEL_ENCAP_NONE ||
-	    lwtstate->type > LWTUNNEL_ENCAP_MAX)
-		return 0;
+	    lwtstate->type > LWTUNNEL_ENCAP_MAX) {
+		ret = 0;
+		goto out;
+	}

 	ret = -EOPNOTSUPP;
 	rcu_read_lock();
@@ -364,11 +368,13 @@ int lwtunnel_output(struct net *net, struct sock *sk, struct sk_buff *skb)
 	if (ret == -EOPNOTSUPP)
 		goto drop;

-	return ret;
+	goto out;

 drop:
 	kfree_skb(skb);

+out:
+	local_bh_enable();
 	return ret;
 }
 EXPORT_SYMBOL_GPL(lwtunnel_output);
@@ -380,6 +386,8 @@ int lwtunnel_xmit(struct sk_buff *skb)
 	struct dst_entry *dst;
 	int ret;

+	local_bh_disable();
+
 	if (dev_xmit_recursion()) {
 		net_crit_ratelimited("%s(): recursion limit reached on datapath\n",
 				     __func__);
@@ -396,8 +404,10 @@ int lwtunnel_xmit(struct sk_buff *skb)
 	lwtstate = dst->lwtstate;

 	if (lwtstate->type == LWTUNNEL_ENCAP_NONE ||
-	    lwtstate->type > LWTUNNEL_ENCAP_MAX)
-		return 0;
+	    lwtstate->type > LWTUNNEL_ENCAP_MAX) {
+		ret = 0;
+		goto out;
+	}

 	ret = -EOPNOTSUPP;
 	rcu_read_lock();
@@ -412,11 +422,13 @@ int lwtunnel_xmit(struct sk_buff *skb)
 	if (ret == -EOPNOTSUPP)
 		goto drop;

-	return ret;
+	goto out;

 drop:
 	kfree_skb(skb);

+out:
+	local_bh_enable();
 	return ret;
 }
 EXPORT_SYMBOL_GPL(lwtunnel_xmit);
@@ -428,6 +440,8 @@ int lwtunnel_input(struct sk_buff *skb)
 	struct dst_entry *dst;
 	int ret;

+	DEBUG_NET_WARN_ON_ONCE(!in_softirq());
+
 	if (dev_xmit_recursion()) {
 		net_crit_ratelimited("%s(): recursion limit reached on datapath\n",
 				     __func__);
@@ -861,14 +861,17 @@ int netdev_nl_bind_rx_doit(struct sk_buff *skb, struct genl_info *info)

 	mutex_lock(&priv->lock);

+	err = 0;
 	netdev = netdev_get_by_index_lock(genl_info_net(info), ifindex);
-	if (!netdev || !netif_device_present(netdev)) {
+	if (!netdev) {
 		err = -ENODEV;
 		goto err_unlock_sock;
 	}
-
-	if (!netdev_need_ops_lock(netdev)) {
+	if (!netif_device_present(netdev))
+		err = -ENODEV;
+	else if (!netdev_need_ops_lock(netdev))
 		err = -EOPNOTSUPP;
+	if (err) {
 		NL_SET_BAD_ATTR(info->extack,
 				info->attrs[NETDEV_A_DEV_IFINDEX]);
 		goto err_unlock;
@@ -100,10 +100,10 @@ static struct sk_buff *net_test_get_skb(struct net_device *ndev,
 	ehdr->h_proto = htons(ETH_P_IP);

 	if (attr->tcp) {
+		memset(thdr, 0, sizeof(*thdr));
 		thdr->source = htons(attr->sport);
 		thdr->dest = htons(attr->dport);
 		thdr->doff = sizeof(struct tcphdr) / 4;
-		thdr->check = 0;
 	} else {
 		uhdr->source = htons(attr->sport);
 		uhdr->dest = htons(attr->dport);
@@ -144,10 +144,18 @@ static struct sk_buff *net_test_get_skb(struct net_device *ndev,
 	attr->id = net_test_next_id;
 	shdr->id = net_test_next_id++;

-	if (attr->size)
-		skb_put(skb, attr->size);
-	if (attr->max_size && attr->max_size > skb->len)
-		skb_put(skb, attr->max_size - skb->len);
+	if (attr->size) {
+		void *payload = skb_put(skb, attr->size);
+
+		memset(payload, 0, attr->size);
+	}
+
+	if (attr->max_size && attr->max_size > skb->len) {
+		size_t pad_len = attr->max_size - skb->len;
+		void *pad = skb_put(skb, pad_len);
+
+		memset(pad, 0, pad_len);
+	}

 	skb->csum = 0;
 	skb->ip_summed = CHECKSUM_PARTIAL;
@@ -337,7 +337,11 @@ int mptcp_pm_nl_remove_doit(struct sk_buff *skb, struct genl_info *info)

 	release_sock(sk);

-	sock_kfree_s(sk, match, sizeof(*match));
+	kfree_rcu_mightsleep(match);
+	/* Adjust sk_omem_alloc like sock_kfree_s() does, to match
+	 * with allocation of this memory by sock_kmemdup()
+	 */
+	atomic_sub(sizeof(*match), &sk->sk_omem_alloc);

 	err = 0;
 out:
@@ -961,6 +961,7 @@ hfsc_change_class(struct Qdisc *sch, u32 classid, u32 parentid,

 	if (cl != NULL) {
 		int old_flags;
+		int len = 0;

 		if (parentid) {
 			if (cl->cl_parent &&
@@ -991,9 +992,13 @@ hfsc_change_class(struct Qdisc *sch, u32 classid, u32 parentid,
 		if (usc != NULL)
 			hfsc_change_usc(cl, usc, cur_time);

+		if (cl->qdisc->q.qlen != 0)
+			len = qdisc_peek_len(cl->qdisc);
+		/* Check queue length again since some qdisc implementations
+		 * (e.g., netem/codel) might empty the queue during the peek
+		 * operation.
+		 */
 		if (cl->qdisc->q.qlen != 0) {
-			int len = qdisc_peek_len(cl->qdisc);
-
 			if (cl->cl_flags & HFSC_RSC) {
 				if (old_flags & HFSC_RSC)
 					update_ed(cl, len);
@@ -1636,10 +1641,16 @@ hfsc_dequeue(struct Qdisc *sch)
 		if (cl->qdisc->q.qlen != 0) {
 			/* update ed */
 			next_len = qdisc_peek_len(cl->qdisc);
-			if (realtime)
-				update_ed(cl, next_len);
-			else
-				update_d(cl, next_len);
+			/* Check queue length again since some qdisc implementations
+			 * (e.g., netem/codel) might empty the queue during the peek
+			 * operation.
+			 */
+			if (cl->qdisc->q.qlen != 0) {
+				if (realtime)
+					update_ed(cl, next_len);
+				else
+					update_d(cl, next_len);
+			}
 		} else {
 			/* the class becomes passive */
 			eltree_remove(cl);
@@ -716,7 +716,8 @@ void tipc_mon_reinit_self(struct net *net)
 		if (!mon)
 			continue;
 		write_lock_bh(&mon->lock);
-		mon->self->addr = tipc_own_addr(net);
+		if (mon->self)
+			mon->self->addr = tipc_own_addr(net);
 		write_unlock_bh(&mon->lock);
 	}
 }
@@ -206,9 +206,8 @@ chk_dump_one()
 	local token
 	local msg

-	ss_token="$(ss -inmHMN $ns | grep 'token:' |\
-		    head -n 1 |\
-		    sed 's/.*token:\([0-9a-f]*\).*/\1/')"
+	ss_token="$(ss -inmHMN $ns |
+		    mptcp_lib_get_info_value "token" "token")"

 	token="$(ip netns exec $ns ./mptcp_diag -t $ss_token |\
 		 awk -F':[ \t]+' '/^token/ {print $2}')"
@@ -313,5 +313,44 @@
            "$TC qdisc del dev $DUMMY handle 1: root",
            "$IP addr del 10.10.10.10/24 dev $DUMMY || true"
        ]
+    },
+    {
+        "id": "a4c3",
+        "name": "Test HFSC with netem/blackhole - queue emptying during peek operation",
+        "category": [
+            "qdisc",
+            "hfsc",
+            "netem",
+            "blackhole"
+        ],
+        "plugins": {
+            "requires": "nsPlugin"
+        },
+        "setup": [
+            "$IP link set dev $DUMMY up || true",
+            "$IP addr add 10.10.10.10/24 dev $DUMMY || true",
+            "$TC qdisc add dev $DUMMY handle 1:0 root drr",
+            "$TC class add dev $DUMMY parent 1:0 classid 1:1 drr",
+            "$TC class add dev $DUMMY parent 1:0 classid 1:2 drr",
+            "$TC qdisc add dev $DUMMY parent 1:1 handle 2:0 plug limit 1024",
+            "$TC qdisc add dev $DUMMY parent 1:2 handle 3:0 hfsc default 1",
+            "$TC class add dev $DUMMY parent 3:0 classid 3:1 hfsc rt m1 5Mbit d 10ms m2 10Mbit",
+            "$TC qdisc add dev $DUMMY parent 3:1 handle 4:0 netem delay 1ms",
+            "$TC qdisc add dev $DUMMY parent 4:1 handle 5:0 blackhole",
+            "ping -c 3 -W 0.01 -i 0.001 -s 1 10.10.10.10 -I $DUMMY > /dev/null 2>&1 || true",
+            "$TC class change dev $DUMMY parent 3:0 classid 3:1 hfsc sc m1 5Mbit d 10ms m2 10Mbit",
+            "$TC class del dev $DUMMY parent 3:0 classid 3:1",
+            "$TC class add dev $DUMMY parent 3:0 classid 3:1 hfsc rt m1 5Mbit d 10ms m2 10Mbit",
+            "ping -c 3 -W 0.01 -i 0.001 -s 1 10.10.10.10 -I $DUMMY > /dev/null 2>&1 || true"
+        ],
+        "cmdUnderTest": "$TC class change dev $DUMMY parent 3:0 classid 3:1 hfsc sc m1 5Mbit d 10ms m2 10Mbit",
+        "expExitCode": "0",
+        "verifyCmd": "$TC -s qdisc show dev $DUMMY",
+        "matchPattern": "qdisc hfsc 3:.*parent 1:2.*default 1",
+        "matchCount": "1",
+        "teardown": [
+            "$TC qdisc del dev $DUMMY handle 1:0 root",
+            "$IP addr del 10.10.10.10/24 dev $DUMMY || true"
+        ]
    }
 ]