From 9facce84f4062f782ebde18daa7006a23d40b607 Mon Sep 17 00:00:00 2001
From: MD Danish Anwar <danishanwar@ti.com>
Date: Mon, 23 Dec 2024 20:45:49 +0530
Subject: [PATCH 01/16] net: ti: icssg-prueth: Fix firmware load sequence.

Timesync related operations are ran in PRU0 cores for both ICSSG SLICE0
and SLICE1. Currently whenever any ICSSG interface comes up we load the
respective firmwares to PRU cores and whenever interface goes down, we
stop the resective cores. Due to this, when SLICE0 goes down while
SLICE1 is still active, PRU0 firmwares are unloaded and PRU0 core is
stopped. This results in clock jump for SLICE1 interface as the timesync
related operations are no longer running.

As there are interdependencies between SLICE0 and SLICE1 firmwares,
fix this by running both PRU0 and PRU1 firmwares as long as at least 1
ICSSG interface is up. Add new flag in prueth struct to check if all
firmwares are running and remove the old flag (fw_running).

Use emacs_initialized as reference count to load the firmwares for the
first and last interface up/down. Moving init_emac_mode and fw_offload_mode
API outside of icssg_config to icssg_common_start API as they need
to be called only once per firmware boot.

Change prueth_emac_restart() to return error code and add error prints
inside the caller of this functions in case of any failures.

Move prueth_emac_stop() from common to sr1 driver.
sr1 and sr2 drivers have different logic handling for stopping
the firmwares. While sr1 driver is dependent on emac structure
to stop the corresponding pru cores for that slice, for sr2
all the pru cores of both the slices are stopped and is not
dependent on emac. So the prueth_emac_stop() function is no
longer common and can be moved to sr1 driver.

Fixes: c1e0230eeaab ("net: ti: icss-iep: Add IEP driver")
Signed-off-by: MD Danish Anwar <danishanwar@ti.com>
Signed-off-by: Meghana Malladi <m-malladi@ti.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/ti/icssg/icssg_common.c  |  25 --
 drivers/net/ethernet/ti/icssg/icssg_config.c  |  41 ++-
 drivers/net/ethernet/ti/icssg/icssg_config.h  |   1 +
 drivers/net/ethernet/ti/icssg/icssg_prueth.c  | 261 ++++++++++++------
 drivers/net/ethernet/ti/icssg/icssg_prueth.h  |   5 +-
 .../net/ethernet/ti/icssg/icssg_prueth_sr1.c  |  24 +-
 6 files changed, 236 insertions(+), 121 deletions(-)

diff --git a/drivers/net/ethernet/ti/icssg/icssg_common.c b/drivers/net/ethernet/ti/icssg/icssg_common.c
index fdebeb2f84e0..74f0f200a89d 100644
--- a/drivers/net/ethernet/ti/icssg/icssg_common.c
+++ b/drivers/net/ethernet/ti/icssg/icssg_common.c
@@ -855,31 +855,6 @@ irqreturn_t prueth_rx_irq(int irq, void *dev_id)
 }
 EXPORT_SYMBOL_GPL(prueth_rx_irq);
 
-void prueth_emac_stop(struct prueth_emac *emac)
-{
-	struct prueth *prueth = emac->prueth;
-	int slice;
-
-	switch (emac->port_id) {
-	case PRUETH_PORT_MII0:
-		slice = ICSS_SLICE0;
-		break;
-	case PRUETH_PORT_MII1:
-		slice = ICSS_SLICE1;
-		break;
-	default:
-		netdev_err(emac->ndev, "invalid port\n");
-		return;
-	}
-
-	emac->fw_running = 0;
-	if (!emac->is_sr1)
-		rproc_shutdown(prueth->txpru[slice]);
-	rproc_shutdown(prueth->rtu[slice]);
-	rproc_shutdown(prueth->pru[slice]);
-}
-EXPORT_SYMBOL_GPL(prueth_emac_stop);
-
 void prueth_cleanup_tx_ts(struct prueth_emac *emac)
 {
 	int i;
diff --git a/drivers/net/ethernet/ti/icssg/icssg_config.c b/drivers/net/ethernet/ti/icssg/icssg_config.c
index 5d2491c2943a..ddfd1c02a885 100644
--- a/drivers/net/ethernet/ti/icssg/icssg_config.c
+++ b/drivers/net/ethernet/ti/icssg/icssg_config.c
@@ -397,7 +397,7 @@ static int prueth_emac_buffer_setup(struct prueth_emac *emac)
 	return 0;
 }
 
-static void icssg_init_emac_mode(struct prueth *prueth)
+void icssg_init_emac_mode(struct prueth *prueth)
 {
 	/* When the device is configured as a bridge and it is being brought
 	 * back to the emac mode, the host mac address has to be set as 0.
@@ -406,9 +406,6 @@ static void icssg_init_emac_mode(struct prueth *prueth)
 	int i;
 	u8 mac[ETH_ALEN] = { 0 };
 
-	if (prueth->emacs_initialized)
-		return;
-
 	/* Set VLAN TABLE address base */
 	regmap_update_bits(prueth->miig_rt, FDB_GEN_CFG1, SMEM_VLAN_OFFSET_MASK,
 			   addr <<  SMEM_VLAN_OFFSET);
@@ -423,15 +420,13 @@ static void icssg_init_emac_mode(struct prueth *prueth)
 	/* Clear host MAC address */
 	icssg_class_set_host_mac_addr(prueth->miig_rt, mac);
 }
+EXPORT_SYMBOL_GPL(icssg_init_emac_mode);
 
-static void icssg_init_fw_offload_mode(struct prueth *prueth)
+void icssg_init_fw_offload_mode(struct prueth *prueth)
 {
 	u32 addr = prueth->shram.pa + EMAC_ICSSG_SWITCH_DEFAULT_VLAN_TABLE_OFFSET;
 	int i;
 
-	if (prueth->emacs_initialized)
-		return;
-
 	/* Set VLAN TABLE address base */
 	regmap_update_bits(prueth->miig_rt, FDB_GEN_CFG1, SMEM_VLAN_OFFSET_MASK,
 			   addr <<  SMEM_VLAN_OFFSET);
@@ -448,6 +443,7 @@ static void icssg_init_fw_offload_mode(struct prueth *prueth)
 		icssg_class_set_host_mac_addr(prueth->miig_rt, prueth->hw_bridge_dev->dev_addr);
 	icssg_set_pvid(prueth, prueth->default_vlan, PRUETH_PORT_HOST);
 }
+EXPORT_SYMBOL_GPL(icssg_init_fw_offload_mode);
 
 int icssg_config(struct prueth *prueth, struct prueth_emac *emac, int slice)
 {
@@ -455,11 +451,6 @@ int icssg_config(struct prueth *prueth, struct prueth_emac *emac, int slice)
 	struct icssg_flow_cfg __iomem *flow_cfg;
 	int ret;
 
-	if (prueth->is_switch_mode || prueth->is_hsr_offload_mode)
-		icssg_init_fw_offload_mode(prueth);
-	else
-		icssg_init_emac_mode(prueth);
-
 	memset_io(config, 0, TAS_GATE_MASK_LIST0);
 	icssg_miig_queues_init(prueth, slice);
 
@@ -786,3 +777,27 @@ void icssg_set_pvid(struct prueth *prueth, u8 vid, u8 port)
 		writel(pvid, prueth->shram.va + EMAC_ICSSG_SWITCH_PORT0_DEFAULT_VLAN_OFFSET);
 }
 EXPORT_SYMBOL_GPL(icssg_set_pvid);
+
+int emac_fdb_flow_id_updated(struct prueth_emac *emac)
+{
+	struct mgmt_cmd_rsp fdb_cmd_rsp = { 0 };
+	int slice = prueth_emac_slice(emac);
+	struct mgmt_cmd fdb_cmd = { 0 };
+	int ret;
+
+	fdb_cmd.header = ICSSG_FW_MGMT_CMD_HEADER;
+	fdb_cmd.type   = ICSSG_FW_MGMT_FDB_CMD_TYPE_RX_FLOW;
+	fdb_cmd.seqnum = ++(emac->prueth->icssg_hwcmdseq);
+	fdb_cmd.param  = 0;
+
+	fdb_cmd.param |= (slice << 4);
+	fdb_cmd.cmd_args[0] = 0;
+
+	ret = icssg_send_fdb_msg(emac, &fdb_cmd, &fdb_cmd_rsp);
+	if (ret)
+		return ret;
+
+	WARN_ON(fdb_cmd.seqnum != fdb_cmd_rsp.seqnum);
+	return fdb_cmd_rsp.status == 1 ? 0 : -EINVAL;
+}
+EXPORT_SYMBOL_GPL(emac_fdb_flow_id_updated);
diff --git a/drivers/net/ethernet/ti/icssg/icssg_config.h b/drivers/net/ethernet/ti/icssg/icssg_config.h
index 92c2deaa3068..c884e9fa099e 100644
--- a/drivers/net/ethernet/ti/icssg/icssg_config.h
+++ b/drivers/net/ethernet/ti/icssg/icssg_config.h
@@ -55,6 +55,7 @@ struct icssg_rxq_ctx {
 #define ICSSG_FW_MGMT_FDB_CMD_TYPE	0x03
 #define ICSSG_FW_MGMT_CMD_TYPE		0x04
 #define ICSSG_FW_MGMT_PKT		0x80000000
+#define ICSSG_FW_MGMT_FDB_CMD_TYPE_RX_FLOW	0x05
 
 struct icssg_r30_cmd {
 	u32 cmd[4];
diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth.c b/drivers/net/ethernet/ti/icssg/icssg_prueth.c
index c568c84a032b..d76fe6d05e10 100644
--- a/drivers/net/ethernet/ti/icssg/icssg_prueth.c
+++ b/drivers/net/ethernet/ti/icssg/icssg_prueth.c
@@ -164,11 +164,26 @@ static struct icssg_firmwares icssg_emac_firmwares[] = {
 	}
 };
 
-static int prueth_emac_start(struct prueth *prueth, struct prueth_emac *emac)
+static int prueth_start(struct rproc *rproc, const char *fw_name)
+{
+	int ret;
+
+	ret = rproc_set_firmware(rproc, fw_name);
+	if (ret)
+		return ret;
+	return rproc_boot(rproc);
+}
+
+static void prueth_shutdown(struct rproc *rproc)
+{
+	rproc_shutdown(rproc);
+}
+
+static int prueth_emac_start(struct prueth *prueth)
 {
 	struct icssg_firmwares *firmwares;
 	struct device *dev = prueth->dev;
-	int slice, ret;
+	int ret, slice;
 
 	if (prueth->is_switch_mode)
 		firmwares = icssg_switch_firmwares;
@@ -177,49 +192,126 @@ static int prueth_emac_start(struct prueth *prueth, struct prueth_emac *emac)
 	else
 		firmwares = icssg_emac_firmwares;
 
-	slice = prueth_emac_slice(emac);
-	if (slice < 0) {
-		netdev_err(emac->ndev, "invalid port\n");
-		return -EINVAL;
+	for (slice = 0; slice < PRUETH_NUM_MACS; slice++) {
+		ret = prueth_start(prueth->pru[slice], firmwares[slice].pru);
+		if (ret) {
+			dev_err(dev, "failed to boot PRU%d: %d\n", slice, ret);
+			goto unwind_slices;
+		}
+
+		ret = prueth_start(prueth->rtu[slice], firmwares[slice].rtu);
+		if (ret) {
+			dev_err(dev, "failed to boot RTU%d: %d\n", slice, ret);
+			rproc_shutdown(prueth->pru[slice]);
+			goto unwind_slices;
+		}
+
+		ret = prueth_start(prueth->txpru[slice], firmwares[slice].txpru);
+		if (ret) {
+			dev_err(dev, "failed to boot TX_PRU%d: %d\n", slice, ret);
+			rproc_shutdown(prueth->rtu[slice]);
+			rproc_shutdown(prueth->pru[slice]);
+			goto unwind_slices;
+		}
 	}
 
-	ret = icssg_config(prueth, emac, slice);
-	if (ret)
-		return ret;
+	return 0;
 
-	ret = rproc_set_firmware(prueth->pru[slice], firmwares[slice].pru);
-	ret = rproc_boot(prueth->pru[slice]);
-	if (ret) {
-		dev_err(dev, "failed to boot PRU%d: %d\n", slice, ret);
-		return -EINVAL;
+unwind_slices:
+	while (--slice >= 0) {
+		prueth_shutdown(prueth->txpru[slice]);
+		prueth_shutdown(prueth->rtu[slice]);
+		prueth_shutdown(prueth->pru[slice]);
 	}
 
-	ret = rproc_set_firmware(prueth->rtu[slice], firmwares[slice].rtu);
-	ret = rproc_boot(prueth->rtu[slice]);
-	if (ret) {
-		dev_err(dev, "failed to boot RTU%d: %d\n", slice, ret);
-		goto halt_pru;
+	return ret;
+}
+
+static void prueth_emac_stop(struct prueth *prueth)
+{
+	int slice;
+
+	for (slice = 0; slice < PRUETH_NUM_MACS; slice++) {
+		prueth_shutdown(prueth->txpru[slice]);
+		prueth_shutdown(prueth->rtu[slice]);
+		prueth_shutdown(prueth->pru[slice]);
 	}
+}
+
+static int prueth_emac_common_start(struct prueth *prueth)
+{
+	struct prueth_emac *emac;
+	int ret = 0;
+	int slice;
+
+	if (!prueth->emac[ICSS_SLICE0] && !prueth->emac[ICSS_SLICE1])
+		return -EINVAL;
+
+	/* clear SMEM and MSMC settings for all slices */
+	memset_io(prueth->msmcram.va, 0, prueth->msmcram.size);
+	memset_io(prueth->shram.va, 0, ICSSG_CONFIG_OFFSET_SLICE1 * PRUETH_NUM_MACS);
+
+	icssg_class_default(prueth->miig_rt, ICSS_SLICE0, 0, false);
+	icssg_class_default(prueth->miig_rt, ICSS_SLICE1, 0, false);
+
+	if (prueth->is_switch_mode || prueth->is_hsr_offload_mode)
+		icssg_init_fw_offload_mode(prueth);
+	else
+		icssg_init_emac_mode(prueth);
+
+	for (slice = 0; slice < PRUETH_NUM_MACS; slice++) {
+		emac = prueth->emac[slice];
+		if (!emac)
+			continue;
+		ret = icssg_config(prueth, emac, slice);
+		if (ret)
+			goto disable_class;
+	}
+
+	ret = prueth_emac_start(prueth);
+	if (ret)
+		goto disable_class;
 
-	ret = rproc_set_firmware(prueth->txpru[slice], firmwares[slice].txpru);
-	ret = rproc_boot(prueth->txpru[slice]);
+	emac = prueth->emac[ICSS_SLICE0] ? prueth->emac[ICSS_SLICE0] :
+	       prueth->emac[ICSS_SLICE1];
+	ret = icss_iep_init(emac->iep, &prueth_iep_clockops,
+			    emac, IEP_DEFAULT_CYCLE_TIME_NS);
 	if (ret) {
-		dev_err(dev, "failed to boot TX_PRU%d: %d\n", slice, ret);
-		goto halt_rtu;
+		dev_err(prueth->dev, "Failed to initialize IEP module\n");
+		goto stop_pruss;
 	}
 
-	emac->fw_running = 1;
 	return 0;
 
-halt_rtu:
-	rproc_shutdown(prueth->rtu[slice]);
+stop_pruss:
+	prueth_emac_stop(prueth);
 
-halt_pru:
-	rproc_shutdown(prueth->pru[slice]);
+disable_class:
+	icssg_class_disable(prueth->miig_rt, ICSS_SLICE0);
+	icssg_class_disable(prueth->miig_rt, ICSS_SLICE1);
 
 	return ret;
 }
 
+static int prueth_emac_common_stop(struct prueth *prueth)
+{
+	struct prueth_emac *emac;
+
+	if (!prueth->emac[ICSS_SLICE0] && !prueth->emac[ICSS_SLICE1])
+		return -EINVAL;
+
+	icssg_class_disable(prueth->miig_rt, ICSS_SLICE0);
+	icssg_class_disable(prueth->miig_rt, ICSS_SLICE1);
+
+	prueth_emac_stop(prueth);
+
+	emac = prueth->emac[ICSS_SLICE0] ? prueth->emac[ICSS_SLICE0] :
+	       prueth->emac[ICSS_SLICE1];
+	icss_iep_exit(emac->iep);
+
+	return 0;
+}
+
 /* called back by PHY layer if there is change in link state of hw port*/
 static void emac_adjust_link(struct net_device *ndev)
 {
@@ -374,9 +466,6 @@ static void prueth_iep_settime(void *clockops_data, u64 ns)
 	u32 cycletime;
 	int timeout;
 
-	if (!emac->fw_running)
-		return;
-
 	sc_descp = emac->prueth->shram.va + TIMESYNC_FW_WC_SETCLOCK_DESC_OFFSET;
 
 	cycletime = IEP_DEFAULT_CYCLE_TIME_NS;
@@ -543,23 +632,17 @@ static int emac_ndo_open(struct net_device *ndev)
 {
 	struct prueth_emac *emac = netdev_priv(ndev);
 	int ret, i, num_data_chn = emac->tx_ch_num;
+	struct icssg_flow_cfg __iomem *flow_cfg;
 	struct prueth *prueth = emac->prueth;
 	int slice = prueth_emac_slice(emac);
 	struct device *dev = prueth->dev;
 	int max_rx_flows;
 	int rx_flow;
 
-	/* clear SMEM and MSMC settings for all slices */
-	if (!prueth->emacs_initialized) {
-		memset_io(prueth->msmcram.va, 0, prueth->msmcram.size);
-		memset_io(prueth->shram.va, 0, ICSSG_CONFIG_OFFSET_SLICE1 * PRUETH_NUM_MACS);
-	}
-
 	/* set h/w MAC as user might have re-configured */
 	ether_addr_copy(emac->mac_addr, ndev->dev_addr);
 
 	icssg_class_set_mac_addr(prueth->miig_rt, slice, emac->mac_addr);
-	icssg_class_default(prueth->miig_rt, slice, 0, false);
 	icssg_ft1_set_mac_addr(prueth->miig_rt, slice, emac->mac_addr);
 
 	/* Notify the stack of the actual queue counts. */
@@ -597,18 +680,23 @@ static int emac_ndo_open(struct net_device *ndev)
 		goto cleanup_napi;
 	}
 
-	/* reset and start PRU firmware */
-	ret = prueth_emac_start(prueth, emac);
-	if (ret)
-		goto free_rx_irq;
+	if (!prueth->emacs_initialized) {
+		ret = prueth_emac_common_start(prueth);
+		if (ret)
+			goto free_rx_irq;
+	}
 
-	icssg_mii_update_mtu(prueth->mii_rt, slice, ndev->max_mtu);
+	flow_cfg = emac->dram.va + ICSSG_CONFIG_OFFSET + PSI_L_REGULAR_FLOW_ID_BASE_OFFSET;
+	writew(emac->rx_flow_id_base, &flow_cfg->rx_base_flow);
+	ret = emac_fdb_flow_id_updated(emac);
 
-	if (!prueth->emacs_initialized) {
-		ret = icss_iep_init(emac->iep, &prueth_iep_clockops,
-				    emac, IEP_DEFAULT_CYCLE_TIME_NS);
+	if (ret) {
+		netdev_err(ndev, "Failed to update Rx Flow ID %d", ret);
+		goto stop;
 	}
 
+	icssg_mii_update_mtu(prueth->mii_rt, slice, ndev->max_mtu);
+
 	ret = request_threaded_irq(emac->tx_ts_irq, NULL, prueth_tx_ts_irq,
 				   IRQF_ONESHOT, dev_name(dev), emac);
 	if (ret)
@@ -653,7 +741,8 @@ reset_rx_chn:
 free_tx_ts_irq:
 	free_irq(emac->tx_ts_irq, emac);
 stop:
-	prueth_emac_stop(emac);
+	if (!prueth->emacs_initialized)
+		prueth_emac_common_stop(prueth);
 free_rx_irq:
 	free_irq(emac->rx_chns.irq[rx_flow], emac);
 cleanup_napi:
@@ -689,8 +778,6 @@ static int emac_ndo_stop(struct net_device *ndev)
 	if (ndev->phydev)
 		phy_stop(ndev->phydev);
 
-	icssg_class_disable(prueth->miig_rt, prueth_emac_slice(emac));
-
 	if (emac->prueth->is_hsr_offload_mode)
 		__dev_mc_unsync(ndev, icssg_prueth_hsr_del_mcast);
 	else
@@ -728,11 +815,9 @@ static int emac_ndo_stop(struct net_device *ndev)
 	/* Destroying the queued work in ndo_stop() */
 	cancel_delayed_work_sync(&emac->stats_work);
 
-	if (prueth->emacs_initialized == 1)
-		icss_iep_exit(emac->iep);
-
 	/* stop PRUs */
-	prueth_emac_stop(emac);
+	if (prueth->emacs_initialized == 1)
+		prueth_emac_common_stop(prueth);
 
 	free_irq(emac->tx_ts_irq, emac);
 
@@ -1053,10 +1138,11 @@ static void prueth_offload_fwd_mark_update(struct prueth *prueth)
 	}
 }
 
-static void prueth_emac_restart(struct prueth *prueth)
+static int prueth_emac_restart(struct prueth *prueth)
 {
 	struct prueth_emac *emac0 = prueth->emac[PRUETH_MAC0];
 	struct prueth_emac *emac1 = prueth->emac[PRUETH_MAC1];
+	int ret;
 
 	/* Detach the net_device for both PRUeth ports*/
 	if (netif_running(emac0->ndev))
@@ -1065,36 +1151,46 @@ static void prueth_emac_restart(struct prueth *prueth)
 		netif_device_detach(emac1->ndev);
 
 	/* Disable both PRUeth ports */
-	icssg_set_port_state(emac0, ICSSG_EMAC_PORT_DISABLE);
-	icssg_set_port_state(emac1, ICSSG_EMAC_PORT_DISABLE);
+	ret = icssg_set_port_state(emac0, ICSSG_EMAC_PORT_DISABLE);
+	ret |= icssg_set_port_state(emac1, ICSSG_EMAC_PORT_DISABLE);
+	if (ret)
+		return ret;
 
 	/* Stop both pru cores for both PRUeth ports*/
-	prueth_emac_stop(emac0);
-	prueth->emacs_initialized--;
-	prueth_emac_stop(emac1);
-	prueth->emacs_initialized--;
+	ret = prueth_emac_common_stop(prueth);
+	if (ret) {
+		dev_err(prueth->dev, "Failed to stop the firmwares");
+		return ret;
+	}
 
 	/* Start both pru cores for both PRUeth ports */
-	prueth_emac_start(prueth, emac0);
-	prueth->emacs_initialized++;
-	prueth_emac_start(prueth, emac1);
-	prueth->emacs_initialized++;
+	ret = prueth_emac_common_start(prueth);
+	if (ret) {
+		dev_err(prueth->dev, "Failed to start the firmwares");
+		return ret;
+	}
 
 	/* Enable forwarding for both PRUeth ports */
-	icssg_set_port_state(emac0, ICSSG_EMAC_PORT_FORWARD);
-	icssg_set_port_state(emac1, ICSSG_EMAC_PORT_FORWARD);
+	ret = icssg_set_port_state(emac0, ICSSG_EMAC_PORT_FORWARD);
+	ret |= icssg_set_port_state(emac1, ICSSG_EMAC_PORT_FORWARD);
 
 	/* Attache net_device for both PRUeth ports */
 	netif_device_attach(emac0->ndev);
 	netif_device_attach(emac1->ndev);
+
+	return ret;
 }
 
 static void icssg_change_mode(struct prueth *prueth)
 {
 	struct prueth_emac *emac;
-	int mac;
+	int mac, ret;
 
-	prueth_emac_restart(prueth);
+	ret = prueth_emac_restart(prueth);
+	if (ret) {
+		dev_err(prueth->dev, "Failed to restart the firmwares, aborting the process");
+		return;
+	}
 
 	for (mac = PRUETH_MAC0; mac < PRUETH_NUM_MACS; mac++) {
 		emac = prueth->emac[mac];
@@ -1173,13 +1269,18 @@ static void prueth_netdevice_port_unlink(struct net_device *ndev)
 {
 	struct prueth_emac *emac = netdev_priv(ndev);
 	struct prueth *prueth = emac->prueth;
+	int ret;
 
 	prueth->br_members &= ~BIT(emac->port_id);
 
 	if (prueth->is_switch_mode) {
 		prueth->is_switch_mode = false;
 		emac->port_vlan = 0;
-		prueth_emac_restart(prueth);
+		ret = prueth_emac_restart(prueth);
+		if (ret) {
+			dev_err(prueth->dev, "Failed to restart the firmwares, aborting the process");
+			return;
+		}
 	}
 
 	prueth_offload_fwd_mark_update(prueth);
@@ -1228,6 +1329,7 @@ static void prueth_hsr_port_unlink(struct net_device *ndev)
 	struct prueth *prueth = emac->prueth;
 	struct prueth_emac *emac0;
 	struct prueth_emac *emac1;
+	int ret;
 
 	emac0 = prueth->emac[PRUETH_MAC0];
 	emac1 = prueth->emac[PRUETH_MAC1];
@@ -1238,7 +1340,11 @@ static void prueth_hsr_port_unlink(struct net_device *ndev)
 		emac0->port_vlan = 0;
 		emac1->port_vlan = 0;
 		prueth->hsr_dev = NULL;
-		prueth_emac_restart(prueth);
+		ret = prueth_emac_restart(prueth);
+		if (ret) {
+			dev_err(prueth->dev, "Failed to restart the firmwares, aborting the process");
+			return;
+		}
 		netdev_dbg(ndev, "Disabling HSR Offload mode\n");
 	}
 }
@@ -1413,13 +1519,10 @@ static int prueth_probe(struct platform_device *pdev)
 		prueth->pa_stats = NULL;
 	}
 
-	if (eth0_node) {
+	if (eth0_node || eth1_node) {
 		ret = prueth_get_cores(prueth, ICSS_SLICE0, false);
 		if (ret)
 			goto put_cores;
-	}
-
-	if (eth1_node) {
 		ret = prueth_get_cores(prueth, ICSS_SLICE1, false);
 		if (ret)
 			goto put_cores;
@@ -1618,14 +1721,12 @@ put_pruss:
 	pruss_put(prueth->pruss);
 
 put_cores:
-	if (eth1_node) {
-		prueth_put_cores(prueth, ICSS_SLICE1);
-		of_node_put(eth1_node);
-	}
-
-	if (eth0_node) {
+	if (eth0_node || eth1_node) {
 		prueth_put_cores(prueth, ICSS_SLICE0);
 		of_node_put(eth0_node);
+
+		prueth_put_cores(prueth, ICSS_SLICE1);
+		of_node_put(eth1_node);
 	}
 
 	return ret;
diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth.h b/drivers/net/ethernet/ti/icssg/icssg_prueth.h
index f5c1d473e9f9..5473315ea204 100644
--- a/drivers/net/ethernet/ti/icssg/icssg_prueth.h
+++ b/drivers/net/ethernet/ti/icssg/icssg_prueth.h
@@ -140,7 +140,6 @@ struct prueth_rx_chn {
 /* data for each emac port */
 struct prueth_emac {
 	bool is_sr1;
-	bool fw_running;
 	struct prueth *prueth;
 	struct net_device *ndev;
 	u8 mac_addr[6];
@@ -361,6 +360,8 @@ int icssg_set_port_state(struct prueth_emac *emac,
 			 enum icssg_port_state_cmd state);
 void icssg_config_set_speed(struct prueth_emac *emac);
 void icssg_config_half_duplex(struct prueth_emac *emac);
+void icssg_init_emac_mode(struct prueth *prueth);
+void icssg_init_fw_offload_mode(struct prueth *prueth);
 
 /* Buffer queue helpers */
 int icssg_queue_pop(struct prueth *prueth, u8 queue);
@@ -377,6 +378,7 @@ void icssg_vtbl_modify(struct prueth_emac *emac, u8 vid, u8 port_mask,
 		       u8 untag_mask, bool add);
 u16 icssg_get_pvid(struct prueth_emac *emac);
 void icssg_set_pvid(struct prueth *prueth, u8 vid, u8 port);
+int emac_fdb_flow_id_updated(struct prueth_emac *emac);
 #define prueth_napi_to_tx_chn(pnapi) \
 	container_of(pnapi, struct prueth_tx_chn, napi_tx)
 
@@ -407,7 +409,6 @@ void emac_rx_timestamp(struct prueth_emac *emac,
 		       struct sk_buff *skb, u32 *psdata);
 enum netdev_tx icssg_ndo_start_xmit(struct sk_buff *skb, struct net_device *ndev);
 irqreturn_t prueth_rx_irq(int irq, void *dev_id);
-void prueth_emac_stop(struct prueth_emac *emac);
 void prueth_cleanup_tx_ts(struct prueth_emac *emac);
 int icssg_napi_rx_poll(struct napi_struct *napi_rx, int budget);
 int prueth_prepare_rx_chan(struct prueth_emac *emac,
diff --git a/drivers/net/ethernet/ti/icssg/icssg_prueth_sr1.c b/drivers/net/ethernet/ti/icssg/icssg_prueth_sr1.c
index 5024f0647a0d..3dc86397c367 100644
--- a/drivers/net/ethernet/ti/icssg/icssg_prueth_sr1.c
+++ b/drivers/net/ethernet/ti/icssg/icssg_prueth_sr1.c
@@ -440,7 +440,6 @@ static int prueth_emac_start(struct prueth *prueth, struct prueth_emac *emac)
 		goto halt_pru;
 	}
 
-	emac->fw_running = 1;
 	return 0;
 
 halt_pru:
@@ -449,6 +448,29 @@ halt_pru:
 	return ret;
 }
 
+static void prueth_emac_stop(struct prueth_emac *emac)
+{
+	struct prueth *prueth = emac->prueth;
+	int slice;
+
+	switch (emac->port_id) {
+	case PRUETH_PORT_MII0:
+		slice = ICSS_SLICE0;
+		break;
+	case PRUETH_PORT_MII1:
+		slice = ICSS_SLICE1;
+		break;
+	default:
+		netdev_err(emac->ndev, "invalid port\n");
+		return;
+	}
+
+	if (!emac->is_sr1)
+		rproc_shutdown(prueth->txpru[slice]);
+	rproc_shutdown(prueth->rtu[slice]);
+	rproc_shutdown(prueth->pru[slice]);
+}
+
 /**
  * emac_ndo_open - EMAC device open
  * @ndev: network adapter device
-- 
2.51.0


From 9b115361248dc6cce182a2dc030c1c70b0a9639e Mon Sep 17 00:00:00 2001
From: Meghana Malladi <m-malladi@ti.com>
Date: Mon, 23 Dec 2024 20:45:50 +0530
Subject: [PATCH 02/16] net: ti: icssg-prueth: Fix clearing of IEP_CMP_CFG
 registers during iep_init

When ICSSG interfaces are brought down and brought up again, the
pru cores are shut down and booted again, flushing out all the memories
and start again in a clean state. Hence it is expected that the
IEP_CMP_CFG register needs to be flushed during iep_init() to ensure
that the existing residual configuration doesn't cause any unusual
behavior. If the register is not cleared, existing IEP_CMP_CFG set for
CMP1 will result in SYNC0_OUT signal based on the SYNC_OUT register values.

After bringing the interface up, calling PPS enable doesn't work as
the driver believes PPS is already enabled, (iep->pps_enabled is not
cleared during interface bring down) and driver will just return true
even though there is no signal. Fix this by disabling pps and perout.

Fixes: c1e0230eeaab ("net: ti: icss-iep: Add IEP driver")
Signed-off-by: Meghana Malladi <m-malladi@ti.com>
Reviewed-by: Roger Quadros <rogerq@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>
---
 drivers/net/ethernet/ti/icssg/icss_iep.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/drivers/net/ethernet/ti/icssg/icss_iep.c b/drivers/net/ethernet/ti/icssg/icss_iep.c
index 5d6d1cf78e93..768578c0d958 100644
--- a/drivers/net/ethernet/ti/icssg/icss_iep.c
+++ b/drivers/net/ethernet/ti/icssg/icss_iep.c
@@ -215,6 +215,9 @@ static void icss_iep_enable_shadow_mode(struct icss_iep *iep)
 	for (cmp = IEP_MIN_CMP; cmp < IEP_MAX_CMP; cmp++) {
 		regmap_update_bits(iep->map, ICSS_IEP_CMP_STAT_REG,
 				   IEP_CMP_STATUS(cmp), IEP_CMP_STATUS(cmp));
+
+		regmap_update_bits(iep->map, ICSS_IEP_CMP_CFG_REG,
+				   IEP_CMP_CFG_CMP_EN(cmp), 0);
 	}
 
 	/* enable reset counter on CMP0 event */
@@ -780,6 +783,11 @@ int icss_iep_exit(struct icss_iep *iep)
 	}
 	icss_iep_disable(iep);
 
+	if (iep->pps_enabled)
+		icss_iep_pps_enable(iep, false);
+	else if (iep->perout_enabled)
+		icss_iep_perout_enable(iep, NULL, false);
+
 	return 0;
 }
 EXPORT_SYMBOL_GPL(icss_iep_exit);
-- 
2.51.0


From 45d339fefaa3dcd237038769e0d34584fb867390 Mon Sep 17 00:00:00 2001
From: Mark Zhang <markzhang@nvidia.com>
Date: Thu, 19 Dec 2024 14:23:36 +0200
Subject: [PATCH 03/16] RDMA/mlx5: Enable multiplane mode only when it is
 supported

Driver queries vport_cxt.num_plane and enables multiplane when it is
greater then 0, but some old FWs (versions from x.40.1000 till x.42.1000),
report vport_cxt.num_plane = 1 unexpectedly.

Fix it by querying num_plane only when HCA_CAP2.multiplane bit is set.

Fixes: 2a5db20fa532 ("RDMA/mlx5: Add support to multi-plane device and port")
Link: https://patch.msgid.link/r/1ef901acdf564716fcf550453cf5e94f343777ec.1734610916.git.leon@kernel.org
Cc: stable@vger.kernel.org
Reported-by: Francesco Poli <invernomuto@paranoici.org>
Closes: https://lore.kernel.org/all/nvs4i2v7o6vn6zhmtq4sgazy2hu5kiulukxcntdelggmznnl7h@so3oul6uwgbl/
Signed-off-by: Mark Zhang <markzhang@nvidia.com>
Signed-off-by: Leon Romanovsky <leonro@nvidia.com>
Reviewed-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>
---
 drivers/infiniband/hw/mlx5/main.c | 2 +-
 include/linux/mlx5/mlx5_ifc.h     | 4 +++-
 2 files changed, 4 insertions(+), 2 deletions(-)

diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
index c2314797afc9..f5b59d02f4d3 100644
--- a/drivers/infiniband/hw/mlx5/main.c
+++ b/drivers/infiniband/hw/mlx5/main.c
@@ -2839,7 +2839,7 @@ static int mlx5_ib_get_plane_num(struct mlx5_core_dev *mdev, u8 *num_plane)
 	int err;
 
 	*num_plane = 0;
-	if (!MLX5_CAP_GEN(mdev, ib_virt))
+	if (!MLX5_CAP_GEN(mdev, ib_virt) || !MLX5_CAP_GEN_2(mdev, multiplane))
 		return 0;
 
 	err = mlx5_query_hca_vport_context(mdev, 0, 1, 0, &vport_ctx);
diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
index 4fbbcf35498b..48d47181c7cd 100644
--- a/include/linux/mlx5/mlx5_ifc.h
+++ b/include/linux/mlx5/mlx5_ifc.h
@@ -2119,7 +2119,9 @@ struct mlx5_ifc_cmd_hca_cap_2_bits {
 	u8	   migration_in_chunks[0x1];
 	u8	   reserved_at_d1[0x1];
 	u8	   sf_eq_usage[0x1];
-	u8	   reserved_at_d3[0xd];
+	u8	   reserved_at_d3[0x5];
+	u8	   multiplane[0x1];
+	u8	   reserved_at_d9[0x7];
 
 	u8	   cross_vhca_object_to_object_supported[0x20];
 
-- 
2.51.0


From 1e9b0e1c550c42c13c111d1a31e822057232abc4 Mon Sep 17 00:00:00 2001
From: Antonio Pastor <antonio.pastor@gmail.com>
Date: Thu, 2 Jan 2025 20:23:00 -0500
Subject: [PATCH 04/16] net: 802: LLC+SNAP OID:PID lookup on start of skb data

802.2+LLC+SNAP frames received by napi_complete_done() with GRO and DSA
have skb->transport_header set two bytes short, or pointing 2 bytes
before network_header & skb->data. This was an issue as snap_rcv()
expected offset to point to SNAP header (OID:PID), causing packet to
be dropped.

A fix at llc_fixup_skb() (a024e377efed) resets transport_header for any
LLC consumers that may care about it, and stops SNAP packets from being
dropped, but doesn't fix the problem which is that LLC and SNAP should
not use transport_header offset.

Ths patch eliminates the use of transport_header offset for SNAP lookup
of OID:PID so that SNAP does not rely on the offset at all.
The offset is reset after pull for any SNAP packet consumers that may
(but shouldn't) use it.

Fixes: fda55eca5a33 ("net: introduce skb_transport_header_was_set()")
Signed-off-by: Antonio Pastor <antonio.pastor@gmail.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20250103012303.746521-1-antonio.pastor@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/802/psnap.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/net/802/psnap.c b/net/802/psnap.c
index fca9d454905f..389df460c8c4 100644
--- a/net/802/psnap.c
+++ b/net/802/psnap.c
@@ -55,11 +55,11 @@ static int snap_rcv(struct sk_buff *skb, struct net_device *dev,
 		goto drop;
 
 	rcu_read_lock();
-	proto = find_snap_client(skb_transport_header(skb));
+	proto = find_snap_client(skb->data);
 	if (proto) {
 		/* Pass the frame on. */
-		skb->transport_header += 5;
 		skb_pull_rcsum(skb, 5);
+		skb_reset_transport_header(skb);
 		rc = proto->rcvfunc(skb, dev, &snap_packet_type, orig_dev);
 	}
 	rcu_read_unlock();
-- 
2.51.0


From 3479c7549fb1dfa7a1db4efb7347c7b8ef50de4b Mon Sep 17 00:00:00 2001
From: Zhongqiu Duan <dzq.aishenghu0@gmail.com>
Date: Thu, 2 Jan 2025 17:14:26 +0000
Subject: [PATCH 05/16] tcp/dccp: allow a connection when sk_max_ack_backlog is
 zero

If the backlog of listen() is set to zero, sk_acceptq_is_full() allows
one connection to be made, but inet_csk_reqsk_queue_is_full() does not.
When the net.ipv4.tcp_syncookies is zero, inet_csk_reqsk_queue_is_full()
will cause an immediate drop before the sk_acceptq_is_full() check in
tcp_conn_request(), resulting in no connection can be made.

This patch tries to keep consistent with 64a146513f8f ("[NET]: Revert
incorrect accept queue backlog changes.").

Link: https://lore.kernel.org/netdev/20250102080258.53858-1-kuniyu@amazon.com/
Fixes: ef547f2ac16b ("tcp: remove max_qlen_log")
Signed-off-by: Zhongqiu Duan <dzq.aishenghu0@gmail.com>
Reviewed-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Reviewed-by: Jason Xing <kerneljasonxing@gmail.com>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20250102171426.915276-1-dzq.aishenghu0@gmail.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 include/net/inet_connection_sock.h | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h
index 3c82fad904d4..c7f42844c79a 100644
--- a/include/net/inet_connection_sock.h
+++ b/include/net/inet_connection_sock.h
@@ -282,7 +282,7 @@ static inline int inet_csk_reqsk_queue_len(const struct sock *sk)
 
 static inline int inet_csk_reqsk_queue_is_full(const struct sock *sk)
 {
-	return inet_csk_reqsk_queue_len(sk) >= READ_ONCE(sk->sk_max_ack_backlog);
+	return inet_csk_reqsk_queue_len(sk) > READ_ONCE(sk->sk_max_ack_backlog);
 }
 
 bool inet_csk_reqsk_queue_drop(struct sock *sk, struct request_sock *req);
-- 
2.51.0


From a039e54397c6a75b713b9ce7894a62e06956aa92 Mon Sep 17 00:00:00 2001
From: Eric Dumazet <edumazet@google.com>
Date: Fri, 3 Jan 2025 10:45:46 +0000
Subject: [PATCH 06/16] net_sched: cls_flow: validate TCA_FLOW_RSHIFT attribute

syzbot found that TCA_FLOW_RSHIFT attribute was not validated.
Right shitfing a 32bit integer is undefined for large shift values.

UBSAN: shift-out-of-bounds in net/sched/cls_flow.c:329:23
shift exponent 9445 is too large for 32-bit type 'u32' (aka 'unsigned int')
CPU: 1 UID: 0 PID: 54 Comm: kworker/u8:3 Not tainted 6.13.0-rc3-syzkaller-00180-g4f619d518db9 #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 09/13/2024
Workqueue: ipv6_addrconf addrconf_dad_work
Call Trace:
 <TASK>
  __dump_stack lib/dump_stack.c:94 [inline]
  dump_stack_lvl+0x241/0x360 lib/dump_stack.c:120
  ubsan_epilogue lib/ubsan.c:231 [inline]
  __ubsan_handle_shift_out_of_bounds+0x3c8/0x420 lib/ubsan.c:468
  flow_classify+0x24d5/0x25b0 net/sched/cls_flow.c:329
  tc_classify include/net/tc_wrapper.h:197 [inline]
  __tcf_classify net/sched/cls_api.c:1771 [inline]
  tcf_classify+0x420/0x1160 net/sched/cls_api.c:1867
  sfb_classify net/sched/sch_sfb.c:260 [inline]
  sfb_enqueue+0x3ad/0x18b0 net/sched/sch_sfb.c:318
  dev_qdisc_enqueue+0x4b/0x290 net/core/dev.c:3793
  __dev_xmit_skb net/core/dev.c:3889 [inline]
  __dev_queue_xmit+0xf0e/0x3f50 net/core/dev.c:4400
  dev_queue_xmit include/linux/netdevice.h:3168 [inline]
  neigh_hh_output include/net/neighbour.h:523 [inline]
  neigh_output include/net/neighbour.h:537 [inline]
  ip_finish_output2+0xd41/0x1390 net/ipv4/ip_output.c:236
  iptunnel_xmit+0x55d/0x9b0 net/ipv4/ip_tunnel_core.c:82
  udp_tunnel_xmit_skb+0x262/0x3b0 net/ipv4/udp_tunnel_core.c:173
  geneve_xmit_skb drivers/net/geneve.c:916 [inline]
  geneve_xmit+0x21dc/0x2d00 drivers/net/geneve.c:1039
  __netdev_start_xmit include/linux/netdevice.h:5002 [inline]
  netdev_start_xmit include/linux/netdevice.h:5011 [inline]
  xmit_one net/core/dev.c:3590 [inline]
  dev_hard_start_xmit+0x27a/0x7d0 net/core/dev.c:3606
  __dev_queue_xmit+0x1b73/0x3f50 net/core/dev.c:4434

Fixes: e5dfb815181f ("[NET_SCHED]: Add flow classifier")
Reported-by: syzbot+1dbb57d994e54aaa04d2@syzkaller.appspotmail.com
Closes: https://lore.kernel.org/netdev/6777bf49.050a0220.178762.0040.GAE@google.com/T/#u
Signed-off-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20250103104546.3714168-1-edumazet@google.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/sched/cls_flow.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/net/sched/cls_flow.c b/net/sched/cls_flow.c
index 5502998aace7..5c2580a07530 100644
--- a/net/sched/cls_flow.c
+++ b/net/sched/cls_flow.c
@@ -356,7 +356,8 @@ static const struct nla_policy flow_policy[TCA_FLOW_MAX + 1] = {
 	[TCA_FLOW_KEYS]		= { .type = NLA_U32 },
 	[TCA_FLOW_MODE]		= { .type = NLA_U32 },
 	[TCA_FLOW_BASECLASS]	= { .type = NLA_U32 },
-	[TCA_FLOW_RSHIFT]	= { .type = NLA_U32 },
+	[TCA_FLOW_RSHIFT]	= NLA_POLICY_MAX(NLA_U32,
+						 31 /* BITS_PER_U32 - 1 */),
 	[TCA_FLOW_ADDEND]	= { .type = NLA_U32 },
 	[TCA_FLOW_MASK]		= { .type = NLA_U32 },
 	[TCA_FLOW_XOR]		= { .type = NLA_U32 },
-- 
2.51.0


From e95274dfe86490ec2a5633035c24b2de6722841f Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Fri, 3 Jan 2025 10:24:58 -0800
Subject: [PATCH 07/16] selftests: tc-testing: reduce rshift value

After previous change rshift >= 32 is no longer allowed.
Modify the test to use 31, the test doesn't seem to send
any traffic so the exact value shouldn't matter.

Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20250103182458.1213486-1-kuba@kernel.org
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 tools/testing/selftests/tc-testing/tc-tests/filters/flow.json | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/tools/testing/selftests/tc-testing/tc-tests/filters/flow.json b/tools/testing/selftests/tc-testing/tc-tests/filters/flow.json
index 996448afe31b..91d120548bf5 100644
--- a/tools/testing/selftests/tc-testing/tc-tests/filters/flow.json
+++ b/tools/testing/selftests/tc-testing/tc-tests/filters/flow.json
@@ -78,10 +78,10 @@
         "setup": [
             "$TC qdisc add dev $DEV1 ingress"
         ],
-        "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 prio 1 protocol ip flow map key dst rshift 0xff",
+        "cmdUnderTest": "$TC filter add dev $DEV1 parent ffff: handle 1 prio 1 protocol ip flow map key dst rshift 0x1f",
         "expExitCode": "0",
         "verifyCmd": "$TC filter get dev $DEV1 parent ffff: handle 1 protocol ip prio 1 flow",
-        "matchPattern": "filter parent ffff: protocol ip pref 1 flow chain [0-9]+ handle 0x1 map keys dst rshift 255 baseclass",
+        "matchPattern": "filter parent ffff: protocol ip pref 1 flow chain [0-9]+ handle 0x1 map keys dst rshift 31 baseclass",
         "matchCount": "1",
         "teardown": [
             "$TC qdisc del dev $DEV1 ingress"
-- 
2.51.0


From 8ce4f287524c74a118b0af1eebd4b24a8efca57a Mon Sep 17 00:00:00 2001
From: Jiawen Wu <jiawenwu@trustnetic.com>
Date: Fri, 3 Jan 2025 16:10:13 +0800
Subject: [PATCH 08/16] net: libwx: fix firmware mailbox abnormal return

The existing SW-FW interaction flow on the driver is wrong. Follow this
wrong flow, driver would never return error if there is a unknown command.
Since firmware writes back 'firmware ready' and 'unknown command' in the
mailbox message if there is an unknown command sent by driver. So reading
'firmware ready' does not timeout. Then driver would mistakenly believe
that the interaction has completed successfully.

It tends to happen with the use of custom firmware. Move the check for
'unknown command' out of the poll timeout for 'firmware ready'. And adjust
the debug log so that mailbox messages are always printed when commands
timeout.

Fixes: 1efa9bfe58c5 ("net: libwx: Implement interaction with firmware")
Signed-off-by: Jiawen Wu <jiawenwu@trustnetic.com>
Link: https://patch.msgid.link/20250103081013.1995939-1-jiawenwu@trustnetic.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/wangxun/libwx/wx_hw.c | 24 ++++++++++------------
 1 file changed, 11 insertions(+), 13 deletions(-)

diff --git a/drivers/net/ethernet/wangxun/libwx/wx_hw.c b/drivers/net/ethernet/wangxun/libwx/wx_hw.c
index 1bf9c38e4125..deaf670c160e 100644
--- a/drivers/net/ethernet/wangxun/libwx/wx_hw.c
+++ b/drivers/net/ethernet/wangxun/libwx/wx_hw.c
@@ -334,27 +334,25 @@ int wx_host_interface_command(struct wx *wx, u32 *buffer,
 	status = read_poll_timeout(rd32, hicr, hicr & WX_MNG_MBOX_CTL_FWRDY, 1000,
 				   timeout * 1000, false, wx, WX_MNG_MBOX_CTL);
 
+	buf[0] = rd32(wx, WX_MNG_MBOX);
+	if ((buf[0] & 0xff0000) >> 16 == 0x80) {
+		wx_err(wx, "Unknown FW command: 0x%x\n", buffer[0] & 0xff);
+		status = -EINVAL;
+		goto rel_out;
+	}
+
 	/* Check command completion */
 	if (status) {
-		wx_dbg(wx, "Command has failed with no status valid.\n");
-
-		buf[0] = rd32(wx, WX_MNG_MBOX);
-		if ((buffer[0] & 0xff) != (~buf[0] >> 24)) {
-			status = -EINVAL;
-			goto rel_out;
-		}
-		if ((buf[0] & 0xff0000) >> 16 == 0x80) {
-			wx_dbg(wx, "It's unknown cmd.\n");
-			status = -EINVAL;
-			goto rel_out;
-		}
-
+		wx_err(wx, "Command has failed with no status valid.\n");
 		wx_dbg(wx, "write value:\n");
 		for (i = 0; i < dword_len; i++)
 			wx_dbg(wx, "%x ", buffer[i]);
 		wx_dbg(wx, "read value:\n");
 		for (i = 0; i < dword_len; i++)
 			wx_dbg(wx, "%x ", buf[i]);
+		wx_dbg(wx, "\ncheck: %x %x\n", buffer[0] & 0xff, ~buf[0] >> 24);
+
+		goto rel_out;
 	}
 
 	if (!return_data)
-- 
2.51.0


From 8c817eb26230dc0ae553cee16ff43a4a895f6756 Mon Sep 17 00:00:00 2001
From: Shannon Nelson <shannon.nelson@amd.com>
Date: Fri, 3 Jan 2025 11:51:47 -0800
Subject: [PATCH 09/16] pds_core: limit loop over fw name list

Add an array size limit to the for-loop to be sure we don't try
to reference a fw_version string off the end of the fw info names
array.  We know that our firmware only has a limited number
of firmware slot names, but we shouldn't leave this unchecked.

Fixes: 45d76f492938 ("pds_core: set up device and adminq")
Signed-off-by: Shannon Nelson <shannon.nelson@amd.com>
Reviewed-by: Simon Horman <horms@kernel.org>
Reviewed-by: Brett Creeley <brett.creeley@amd.com>
Reviewed-by: Jacob Keller <jacob.e.keller@intel.com>
Link: https://patch.msgid.link/20250103195147.7408-1-shannon.nelson@amd.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/amd/pds_core/devlink.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/amd/pds_core/devlink.c b/drivers/net/ethernet/amd/pds_core/devlink.c
index 2681889162a2..44971e71991f 100644
--- a/drivers/net/ethernet/amd/pds_core/devlink.c
+++ b/drivers/net/ethernet/amd/pds_core/devlink.c
@@ -118,7 +118,7 @@ int pdsc_dl_info_get(struct devlink *dl, struct devlink_info_req *req,
 	if (err && err != -EIO)
 		return err;
 
-	listlen = fw_list.num_fw_slots;
+	listlen = min(fw_list.num_fw_slots, ARRAY_SIZE(fw_list.fw_names));
 	for (i = 0; i < listlen; i++) {
 		if (i < ARRAY_SIZE(fw_slotnames))
 			strscpy(buf, fw_slotnames[i], sizeof(buf));
-- 
2.51.0


From c8dafb0e4398dacc362832098a04b97da3b0395b Mon Sep 17 00:00:00 2001
From: Kalesh AP <kalesh-anakkur.purayil@broadcom.com>
Date: Fri, 3 Jan 2025 20:38:47 -0800
Subject: [PATCH 10/16] bnxt_en: Fix possible memory leak when hwrm_req_replace
 fails

When hwrm_req_replace() fails, the driver is not invoking bnxt_req_drop()
which could cause a memory leak.

Fixes: bbf33d1d9805 ("bnxt_en: update all firmware calls to use the new APIs")
Reviewed-by: Pavan Chebbi <pavan.chebbi@broadcom.com>
Signed-off-by: Kalesh AP <kalesh-anakkur.purayil@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Link: https://patch.msgid.link/20250104043849.3482067-2-michael.chan@broadcom.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c | 3 ++-
 1 file changed, 2 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c
index b771c84cdd89..0ed26e3a28f4 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ulp.c
@@ -208,7 +208,7 @@ int bnxt_send_msg(struct bnxt_en_dev *edev,
 
 	rc = hwrm_req_replace(bp, req, fw_msg->msg, fw_msg->msg_len);
 	if (rc)
-		return rc;
+		goto drop_req;
 
 	hwrm_req_timeout(bp, req, fw_msg->timeout);
 	resp = hwrm_req_hold(bp, req);
@@ -220,6 +220,7 @@ int bnxt_send_msg(struct bnxt_en_dev *edev,
 
 		memcpy(fw_msg->resp, resp, resp_len);
 	}
+drop_req:
 	hwrm_req_drop(bp, req);
 	return rc;
 }
-- 
2.51.0


From 40452969a50652e3cbf89dac83d54eebf2206d27 Mon Sep 17 00:00:00 2001
From: Michael Chan <michael.chan@broadcom.com>
Date: Fri, 3 Jan 2025 20:38:48 -0800
Subject: [PATCH 11/16] bnxt_en: Fix DIM shutdown

DIM work will call the firmware to adjust the coalescing parameters on
the RX rings.  We should cancel DIM work before we call the firmware
to free the RX rings.  Otherwise, FW will reject the call from DIM
work if the RX ring has been freed.  This will generate an error
message like this:

bnxt_en 0000:21:00.1 ens2f1np1: hwrm req_type 0x53 seq id 0x6fca error 0x2

and cause unnecessary concern for the user.  It is also possible to
modify the coalescing parameters of the wrong ring if the ring has
been re-allocated.

To prevent this, cancel DIM work right before freeing the RX rings.
We also have to add a check in NAPI poll to not schedule DIM if the
RX rings are shutting down.  Check that the VNIC is active before we
schedule DIM.  The VNIC is always disabled before we free the RX rings.

Fixes: 0bc0b97fca73 ("bnxt_en: cleanup DIM work on device shutdown")
Reviewed-by: Hongguang Gao <hongguang.gao@broadcom.com>
Reviewed-by: Kalesh AP <kalesh-anakkur.purayil@broadcom.com>
Reviewed-by: Somnath Kotur <somnath.kotur@broadcom.com>
Signed-off-by: Michael Chan <michael.chan@broadcom.com>
Link: https://patch.msgid.link/20250104043849.3482067-3-michael.chan@broadcom.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/broadcom/bnxt/bnxt.c | 38 ++++++++++++++++++++---
 1 file changed, 33 insertions(+), 5 deletions(-)

diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
index b86f980fa7ea..aeaa74f03046 100644
--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
@@ -2897,6 +2897,13 @@ static int bnxt_hwrm_handler(struct bnxt *bp, struct tx_cmp *txcmp)
 	return 0;
 }
 
+static bool bnxt_vnic_is_active(struct bnxt *bp)
+{
+	struct bnxt_vnic_info *vnic = &bp->vnic_info[0];
+
+	return vnic->fw_vnic_id != INVALID_HW_RING_ID && vnic->mru > 0;
+}
+
 static irqreturn_t bnxt_msix(int irq, void *dev_instance)
 {
 	struct bnxt_napi *bnapi = dev_instance;
@@ -3164,7 +3171,7 @@ static int bnxt_poll(struct napi_struct *napi, int budget)
 			break;
 		}
 	}
-	if (bp->flags & BNXT_FLAG_DIM) {
+	if ((bp->flags & BNXT_FLAG_DIM) && bnxt_vnic_is_active(bp)) {
 		struct dim_sample dim_sample = {};
 
 		dim_update_sample(cpr->event_ctr,
@@ -3295,7 +3302,7 @@ static int bnxt_poll_p5(struct napi_struct *napi, int budget)
 poll_done:
 	cpr_rx = &cpr->cp_ring_arr[0];
 	if (cpr_rx->cp_ring_type == BNXT_NQ_HDL_TYPE_RX &&
-	    (bp->flags & BNXT_FLAG_DIM)) {
+	    (bp->flags & BNXT_FLAG_DIM) && bnxt_vnic_is_active(bp)) {
 		struct dim_sample dim_sample = {};
 
 		dim_update_sample(cpr->event_ctr,
@@ -7266,6 +7273,26 @@ err_out:
 	return rc;
 }
 
+static void bnxt_cancel_dim(struct bnxt *bp)
+{
+	int i;
+
+	/* DIM work is initialized in bnxt_enable_napi().  Proceed only
+	 * if NAPI is enabled.
+	 */
+	if (!bp->bnapi || test_bit(BNXT_STATE_NAPI_DISABLED, &bp->state))
+		return;
+
+	/* Make sure NAPI sees that the VNIC is disabled */
+	synchronize_net();
+	for (i = 0; i < bp->rx_nr_rings; i++) {
+		struct bnxt_rx_ring_info *rxr = &bp->rx_ring[i];
+		struct bnxt_napi *bnapi = rxr->bnapi;
+
+		cancel_work_sync(&bnapi->cp_ring.dim.work);
+	}
+}
+
 static int hwrm_ring_free_send_msg(struct bnxt *bp,
 				   struct bnxt_ring_struct *ring,
 				   u32 ring_type, int cmpl_ring_id)
@@ -7366,6 +7393,7 @@ static void bnxt_hwrm_ring_free(struct bnxt *bp, bool close_path)
 		}
 	}
 
+	bnxt_cancel_dim(bp);
 	for (i = 0; i < bp->rx_nr_rings; i++) {
 		bnxt_hwrm_rx_ring_free(bp, &bp->rx_ring[i], close_path);
 		bnxt_hwrm_rx_agg_ring_free(bp, &bp->rx_ring[i], close_path);
@@ -11309,8 +11337,6 @@ static void bnxt_disable_napi(struct bnxt *bp)
 		if (bnapi->in_reset)
 			cpr->sw_stats->rx.rx_resets++;
 		napi_disable(&bnapi->napi);
-		if (bnapi->rx_ring)
-			cancel_work_sync(&cpr->dim.work);
 	}
 }
 
@@ -15572,8 +15598,10 @@ static int bnxt_queue_stop(struct net_device *dev, void *qmem, int idx)
 		bnxt_hwrm_vnic_update(bp, vnic,
 				      VNIC_UPDATE_REQ_ENABLES_MRU_VALID);
 	}
-
+	/* Make sure NAPI sees that the VNIC is disabled */
+	synchronize_net();
 	rxr = &bp->rx_ring[idx];
+	cancel_work_sync(&rxr->bnapi->cp_ring.dim.work);
 	bnxt_hwrm_rx_ring_free(bp, rxr, false);
 	bnxt_hwrm_rx_agg_ring_free(bp, rxr, false);
 	rxr->rx_next_cons = 0;
-- 
2.51.0


From 4c1224501e9d6c5fd12d83752f1c1b444e0e3418 Mon Sep 17 00:00:00 2001
From: Anumula Murali Mohan Reddy <anumula@chelsio.com>
Date: Fri, 3 Jan 2025 14:53:27 +0530
Subject: [PATCH 12/16] cxgb4: Avoid removal of uninserted tid

During ARP failure, tid is not inserted but _c4iw_free_ep()
attempts to remove tid which results in error.
This patch fixes the issue by avoiding removal of uninserted tid.

Fixes: 59437d78f088 ("cxgb4/chtls: fix ULD connection failures due to wrong TID base")
Signed-off-by: Anumula Murali Mohan Reddy <anumula@chelsio.com>
Signed-off-by: Potnuri Bharat Teja <bharat@chelsio.com>
Link: https://patch.msgid.link/20250103092327.1011925-1-anumula@chelsio.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
index bc3af0054406..604dcfd49aa4 100644
--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
+++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c
@@ -1799,7 +1799,10 @@ void cxgb4_remove_tid(struct tid_info *t, unsigned int chan, unsigned int tid,
 	struct adapter *adap = container_of(t, struct adapter, tids);
 	struct sk_buff *skb;
 
-	WARN_ON(tid_out_of_range(&adap->tids, tid));
+	if (tid_out_of_range(&adap->tids, tid)) {
+		dev_err(adap->pdev_dev, "tid %d out of range\n", tid);
+		return;
+	}
 
 	if (t->tid_tab[tid - adap->tids.tid_base]) {
 		t->tid_tab[tid - adap->tids.tid_base] = NULL;
-- 
2.51.0


From fd48f071a3d6d51e737e953bb43fe69785cf59a9 Mon Sep 17 00:00:00 2001
From: Jakub Kicinski <kuba@kernel.org>
Date: Fri, 3 Jan 2025 10:32:07 -0800
Subject: [PATCH 13/16] net: don't dump Tx and uninitialized NAPIs

We use NAPI ID as the key for continuing dumps. We also depend
on the NAPIs being sorted by ID within the driver list. Tx NAPIs
(which don't have an ID assigned) break this expectation, it's
not currently possible to dump them reliably. Since Tx NAPIs
are relatively rare, and can't be used in doit (GET or SET)
hide them from the dump API as well.

Fixes: 27f91aaf49b3 ("netdev-genl: Add netlink framework functions for napi")
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
Reviewed-by: Eric Dumazet <edumazet@google.com>
Link: https://patch.msgid.link/20250103183207.1216004-1-kuba@kernel.org
Signed-off-by: Paolo Abeni <pabeni@redhat.com>
---
 net/core/netdev-genl.c | 5 +++--
 1 file changed, 3 insertions(+), 2 deletions(-)

diff --git a/net/core/netdev-genl.c b/net/core/netdev-genl.c
index b0772d135efb..125b660004d3 100644
--- a/net/core/netdev-genl.c
+++ b/net/core/netdev-genl.c
@@ -176,8 +176,7 @@ netdev_nl_napi_fill_one(struct sk_buff *rsp, struct napi_struct *napi,
 	if (!hdr)
 		return -EMSGSIZE;
 
-	if (napi->napi_id >= MIN_NAPI_ID &&
-	    nla_put_u32(rsp, NETDEV_A_NAPI_ID, napi->napi_id))
+	if (nla_put_u32(rsp, NETDEV_A_NAPI_ID, napi->napi_id))
 		goto nla_put_failure;
 
 	if (nla_put_u32(rsp, NETDEV_A_NAPI_IFINDEX, napi->dev->ifindex))
@@ -272,6 +271,8 @@ netdev_nl_napi_dump_one(struct net_device *netdev, struct sk_buff *rsp,
 		return err;
 
 	list_for_each_entry(napi, &netdev->napi_list, dev_list) {
+		if (napi->napi_id < MIN_NAPI_ID)
+			continue;
 		if (ctx->napi_id && napi->napi_id >= ctx->napi_id)
 			continue;
 
-- 
2.51.0


From 95978931d55fb7685f8c0b2598d6c12a9b6bc82a Mon Sep 17 00:00:00 2001
From: Su Hui <suhui@nfschina.com>
Date: Mon, 6 Jan 2025 10:36:48 +0800
Subject: [PATCH 14/16] eth: fbnic: Revert "eth: fbnic: Add hardware monitoring
 support via HWMON interface"

There is a garbage value problem in fbnic_mac_get_sensor_asic(). 'fw_cmpl'
is uninitialized which makes 'sensor' and '*val' to be stored garbage
value. Revert commit d85ebade02e8 ("eth: fbnic: Add hardware monitoring
support via HWMON interface") to avoid this problem.

Fixes: d85ebade02e8 ("eth: fbnic: Add hardware monitoring support via HWMON interface")
Signed-off-by: Su Hui <suhui@nfschina.com>
Suggested-by: Jakub Kicinski <kuba@kernel.org>
Suggested-by: Michal Swiatkowski <michal.swiatkowski@linux.intel.com>
Link: https://patch.msgid.link/20250106023647.47756-1-suhui@nfschina.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 drivers/net/ethernet/meta/fbnic/Makefile      |  1 -
 drivers/net/ethernet/meta/fbnic/fbnic.h       |  5 --
 drivers/net/ethernet/meta/fbnic/fbnic_fw.h    |  7 --
 drivers/net/ethernet/meta/fbnic/fbnic_hwmon.c | 81 -------------------
 drivers/net/ethernet/meta/fbnic/fbnic_mac.c   | 22 -----
 drivers/net/ethernet/meta/fbnic/fbnic_mac.h   |  7 --
 drivers/net/ethernet/meta/fbnic/fbnic_pci.c   |  3 -
 7 files changed, 126 deletions(-)
 delete mode 100644 drivers/net/ethernet/meta/fbnic/fbnic_hwmon.c

diff --git a/drivers/net/ethernet/meta/fbnic/Makefile b/drivers/net/ethernet/meta/fbnic/Makefile
index 239b2258ec65..ea6214ca48e7 100644
--- a/drivers/net/ethernet/meta/fbnic/Makefile
+++ b/drivers/net/ethernet/meta/fbnic/Makefile
@@ -13,7 +13,6 @@ fbnic-y := fbnic_csr.o \
 	   fbnic_ethtool.o \
 	   fbnic_fw.o \
 	   fbnic_hw_stats.o \
-	   fbnic_hwmon.o \
 	   fbnic_irq.o \
 	   fbnic_mac.o \
 	   fbnic_netdev.o \
diff --git a/drivers/net/ethernet/meta/fbnic/fbnic.h b/drivers/net/ethernet/meta/fbnic/fbnic.h
index 706ae6104c8e..744eb0d95449 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic.h
+++ b/drivers/net/ethernet/meta/fbnic/fbnic.h
@@ -20,7 +20,6 @@ struct fbnic_dev {
 	struct device *dev;
 	struct net_device *netdev;
 	struct dentry *dbg_fbd;
-	struct device *hwmon;
 
 	u32 __iomem *uc_addr0;
 	u32 __iomem *uc_addr4;
@@ -33,7 +32,6 @@ struct fbnic_dev {
 
 	struct fbnic_fw_mbx mbx[FBNIC_IPC_MBX_INDICES];
 	struct fbnic_fw_cap fw_cap;
-	struct fbnic_fw_completion *cmpl_data;
 	/* Lock protecting Tx Mailbox queue to prevent possible races */
 	spinlock_t fw_tx_lock;
 
@@ -142,9 +140,6 @@ void fbnic_devlink_unregister(struct fbnic_dev *fbd);
 int fbnic_fw_enable_mbx(struct fbnic_dev *fbd);
 void fbnic_fw_disable_mbx(struct fbnic_dev *fbd);
 
-void fbnic_hwmon_register(struct fbnic_dev *fbd);
-void fbnic_hwmon_unregister(struct fbnic_dev *fbd);
-
 int fbnic_pcs_irq_enable(struct fbnic_dev *fbd);
 void fbnic_pcs_irq_disable(struct fbnic_dev *fbd);
 
diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_fw.h b/drivers/net/ethernet/meta/fbnic/fbnic_fw.h
index 7cd8841920e4..221faf8c6756 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_fw.h
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_fw.h
@@ -44,13 +44,6 @@ struct fbnic_fw_cap {
 	u8	link_fec;
 };
 
-struct fbnic_fw_completion {
-	struct {
-		s32 millivolts;
-		s32 millidegrees;
-	} tsene;
-};
-
 void fbnic_mbx_init(struct fbnic_dev *fbd);
 void fbnic_mbx_clean(struct fbnic_dev *fbd);
 void fbnic_mbx_poll(struct fbnic_dev *fbd);
diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_hwmon.c b/drivers/net/ethernet/meta/fbnic/fbnic_hwmon.c
deleted file mode 100644
index bcd1086e3768..000000000000
--- a/drivers/net/ethernet/meta/fbnic/fbnic_hwmon.c
+++ /dev/null
@@ -1,81 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/* Copyright (c) Meta Platforms, Inc. and affiliates. */
-
-#include <linux/hwmon.h>
-
-#include "fbnic.h"
-#include "fbnic_mac.h"
-
-static int fbnic_hwmon_sensor_id(enum hwmon_sensor_types type)
-{
-	if (type == hwmon_temp)
-		return FBNIC_SENSOR_TEMP;
-	if (type == hwmon_in)
-		return FBNIC_SENSOR_VOLTAGE;
-
-	return -EOPNOTSUPP;
-}
-
-static umode_t fbnic_hwmon_is_visible(const void *drvdata,
-				      enum hwmon_sensor_types type,
-				      u32 attr, int channel)
-{
-	if (type == hwmon_temp && attr == hwmon_temp_input)
-		return 0444;
-	if (type == hwmon_in && attr == hwmon_in_input)
-		return 0444;
-
-	return 0;
-}
-
-static int fbnic_hwmon_read(struct device *dev, enum hwmon_sensor_types type,
-			    u32 attr, int channel, long *val)
-{
-	struct fbnic_dev *fbd = dev_get_drvdata(dev);
-	const struct fbnic_mac *mac = fbd->mac;
-	int id;
-
-	id = fbnic_hwmon_sensor_id(type);
-	return id < 0 ? id : mac->get_sensor(fbd, id, val);
-}
-
-static const struct hwmon_ops fbnic_hwmon_ops = {
-	.is_visible = fbnic_hwmon_is_visible,
-	.read = fbnic_hwmon_read,
-};
-
-static const struct hwmon_channel_info *fbnic_hwmon_info[] = {
-	HWMON_CHANNEL_INFO(temp, HWMON_T_INPUT),
-	HWMON_CHANNEL_INFO(in, HWMON_I_INPUT),
-	NULL
-};
-
-static const struct hwmon_chip_info fbnic_chip_info = {
-	.ops = &fbnic_hwmon_ops,
-	.info = fbnic_hwmon_info,
-};
-
-void fbnic_hwmon_register(struct fbnic_dev *fbd)
-{
-	if (!IS_REACHABLE(CONFIG_HWMON))
-		return;
-
-	fbd->hwmon = hwmon_device_register_with_info(fbd->dev, "fbnic",
-						     fbd, &fbnic_chip_info,
-						     NULL);
-	if (IS_ERR(fbd->hwmon)) {
-		dev_notice(fbd->dev,
-			   "Failed to register hwmon device %pe\n",
-			fbd->hwmon);
-		fbd->hwmon = NULL;
-	}
-}
-
-void fbnic_hwmon_unregister(struct fbnic_dev *fbd)
-{
-	if (!IS_REACHABLE(CONFIG_HWMON) || !fbd->hwmon)
-		return;
-
-	hwmon_device_unregister(fbd->hwmon);
-	fbd->hwmon = NULL;
-}
diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_mac.c b/drivers/net/ethernet/meta/fbnic/fbnic_mac.c
index 80b82ff12c4d..7b654d0a6dac 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_mac.c
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_mac.c
@@ -686,27 +686,6 @@ fbnic_mac_get_eth_mac_stats(struct fbnic_dev *fbd, bool reset,
 			    MAC_STAT_TX_BROADCAST);
 }
 
-static int fbnic_mac_get_sensor_asic(struct fbnic_dev *fbd, int id, long *val)
-{
-	struct fbnic_fw_completion fw_cmpl;
-	s32 *sensor;
-
-	switch (id) {
-	case FBNIC_SENSOR_TEMP:
-		sensor = &fw_cmpl.tsene.millidegrees;
-		break;
-	case FBNIC_SENSOR_VOLTAGE:
-		sensor = &fw_cmpl.tsene.millivolts;
-		break;
-	default:
-		return -EINVAL;
-	}
-
-	*val = *sensor;
-
-	return 0;
-}
-
 static const struct fbnic_mac fbnic_mac_asic = {
 	.init_regs = fbnic_mac_init_regs,
 	.pcs_enable = fbnic_pcs_enable_asic,
@@ -716,7 +695,6 @@ static const struct fbnic_mac fbnic_mac_asic = {
 	.get_eth_mac_stats = fbnic_mac_get_eth_mac_stats,
 	.link_down = fbnic_mac_link_down_asic,
 	.link_up = fbnic_mac_link_up_asic,
-	.get_sensor = fbnic_mac_get_sensor_asic,
 };
 
 /**
diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_mac.h b/drivers/net/ethernet/meta/fbnic/fbnic_mac.h
index 05a591653e09..476239a9d381 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_mac.h
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_mac.h
@@ -47,11 +47,6 @@ enum {
 #define FBNIC_LINK_MODE_PAM4	(FBNIC_LINK_50R1)
 #define FBNIC_LINK_MODE_MASK	(FBNIC_LINK_AUTO - 1)
 
-enum fbnic_sensor_id {
-	FBNIC_SENSOR_TEMP,		/* Temp in millidegrees Centigrade */
-	FBNIC_SENSOR_VOLTAGE,		/* Voltage in millivolts */
-};
-
 /* This structure defines the interface hooks for the MAC. The MAC hooks
  * will be configured as a const struct provided with a set of function
  * pointers.
@@ -88,8 +83,6 @@ struct fbnic_mac {
 
 	void (*link_down)(struct fbnic_dev *fbd);
 	void (*link_up)(struct fbnic_dev *fbd, bool tx_pause, bool rx_pause);
-
-	int (*get_sensor)(struct fbnic_dev *fbd, int id, long *val);
 };
 
 int fbnic_mac_init(struct fbnic_dev *fbd);
diff --git a/drivers/net/ethernet/meta/fbnic/fbnic_pci.c b/drivers/net/ethernet/meta/fbnic/fbnic_pci.c
index 32702dc4a066..7ccf192f13d5 100644
--- a/drivers/net/ethernet/meta/fbnic/fbnic_pci.c
+++ b/drivers/net/ethernet/meta/fbnic/fbnic_pci.c
@@ -296,8 +296,6 @@ static int fbnic_probe(struct pci_dev *pdev, const struct pci_device_id *ent)
 	/* Capture snapshot of hardware stats so netdev can calculate delta */
 	fbnic_reset_hw_stats(fbd);
 
-	fbnic_hwmon_register(fbd);
-
 	if (!fbd->dsn) {
 		dev_warn(&pdev->dev, "Reading serial number failed\n");
 		goto init_failure_mode;
@@ -360,7 +358,6 @@ static void fbnic_remove(struct pci_dev *pdev)
 		fbnic_netdev_free(fbd);
 	}
 
-	fbnic_hwmon_unregister(fbd);
 	fbnic_dbg_fbd_exit(fbd);
 	fbnic_devlink_unregister(fbd);
 	fbnic_fw_disable_mbx(fbd);
-- 
2.51.0


From b341ca51d2679829d26a3f6a4aa9aee9abd94f92 Mon Sep 17 00:00:00 2001
From: Benjamin Coddington <bcodding@redhat.com>
Date: Sat, 4 Jan 2025 10:29:45 -0500
Subject: [PATCH 15/16] tls: Fix tls_sw_sendmsg error handling

We've noticed that NFS can hang when using RPC over TLS on an unstable
connection, and investigation shows that the RPC layer is stuck in a tight
loop attempting to transmit, but forever getting -EBADMSG back from the
underlying network.  The loop begins when tcp_sendmsg_locked() returns
-EPIPE to tls_tx_records(), but that error is converted to -EBADMSG when
calling the socket's error reporting handler.

Instead of converting errors from tcp_sendmsg_locked(), let's pass them
along in this path.  The RPC layer handles -EPIPE by reconnecting the
transport, which prevents the endless attempts to transmit on a broken
connection.

Signed-off-by: Benjamin Coddington <bcodding@redhat.com>
Fixes: a42055e8d2c3 ("net/tls: Add support for async encryption of records for performance")
Link: https://patch.msgid.link/9594185559881679d81f071b181a10eb07cd079f.1736004079.git.bcodding@redhat.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/tls/tls_sw.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c
index bbf26cc4f6ee..7bcc9b4408a2 100644
--- a/net/tls/tls_sw.c
+++ b/net/tls/tls_sw.c
@@ -458,7 +458,7 @@ int tls_tx_records(struct sock *sk, int flags)
 
 tx_err:
 	if (rc < 0 && rc != -EAGAIN)
-		tls_err_abort(sk, -EBADMSG);
+		tls_err_abort(sk, rc);
 
 	return rc;
 }
-- 
2.51.0


From cb358ff94154774d031159b018adf45e17673941 Mon Sep 17 00:00:00 2001
From: Kuniyuki Iwashima <kuniyu@amazon.com>
Date: Mon, 6 Jan 2025 16:19:11 +0900
Subject: [PATCH 16/16] ipvlan: Fix use-after-free in ipvlan_get_iflink().

syzbot presented an use-after-free report [0] regarding ipvlan and
linkwatch.

ipvlan does not hold a refcnt of the lower device unlike vlan and
macvlan.

If the linkwatch work is triggered for the ipvlan dev, the lower dev
might have already been freed, resulting in UAF of ipvlan->phy_dev in
ipvlan_get_iflink().

We can delay the lower dev unregistration like vlan and macvlan by
holding the lower dev's refcnt in dev->netdev_ops->ndo_init() and
releasing it in dev->priv_destructor().

Jakub pointed out calling .ndo_XXX after unregister_netdevice() has
returned is error prone and suggested [1] addressing this UAF in the
core by taking commit 750e51603395 ("net: avoid potential UAF in
default_operstate()") further.

Let's assume unregistering devices DOWN and use RCU protection in
default_operstate() not to race with the device unregistration.

[0]:
BUG: KASAN: slab-use-after-free in ipvlan_get_iflink+0x84/0x88 drivers/net/ipvlan/ipvlan_main.c:353
Read of size 4 at addr ffff0000d768c0e0 by task kworker/u8:35/6944

CPU: 0 UID: 0 PID: 6944 Comm: kworker/u8:35 Not tainted 6.13.0-rc2-g9bc5c9515b48 #12 4c3cb9e8b4565456f6a355f312ff91f4f29b3c47
Hardware name: linux,dummy-virt (DT)
Workqueue: events_unbound linkwatch_event
Call trace:
 show_stack+0x38/0x50 arch/arm64/kernel/stacktrace.c:484 (C)
 __dump_stack lib/dump_stack.c:94 [inline]
 dump_stack_lvl+0xbc/0x108 lib/dump_stack.c:120
 print_address_description mm/kasan/report.c:378 [inline]
 print_report+0x16c/0x6f0 mm/kasan/report.c:489
 kasan_report+0xc0/0x120 mm/kasan/report.c:602
 __asan_report_load4_noabort+0x20/0x30 mm/kasan/report_generic.c:380
 ipvlan_get_iflink+0x84/0x88 drivers/net/ipvlan/ipvlan_main.c:353
 dev_get_iflink+0x7c/0xd8 net/core/dev.c:674
 default_operstate net/core/link_watch.c:45 [inline]
 rfc2863_policy+0x144/0x360 net/core/link_watch.c:72
 linkwatch_do_dev+0x60/0x228 net/core/link_watch.c:175
 __linkwatch_run_queue+0x2f4/0x5b8 net/core/link_watch.c:239
 linkwatch_event+0x64/0xa8 net/core/link_watch.c:282
 process_one_work+0x700/0x1398 kernel/workqueue.c:3229
 process_scheduled_works kernel/workqueue.c:3310 [inline]
 worker_thread+0x8c4/0xe10 kernel/workqueue.c:3391
 kthread+0x2b0/0x360 kernel/kthread.c:389
 ret_from_fork+0x10/0x20 arch/arm64/kernel/entry.S:862

Allocated by task 9303:
 kasan_save_stack mm/kasan/common.c:47 [inline]
 kasan_save_track+0x30/0x68 mm/kasan/common.c:68
 kasan_save_alloc_info+0x44/0x58 mm/kasan/generic.c:568
 poison_kmalloc_redzone mm/kasan/common.c:377 [inline]
 __kasan_kmalloc+0x84/0xa0 mm/kasan/common.c:394
 kasan_kmalloc include/linux/kasan.h:260 [inline]
 __do_kmalloc_node mm/slub.c:4283 [inline]
 __kmalloc_node_noprof+0x2a0/0x560 mm/slub.c:4289
 __kvmalloc_node_noprof+0x9c/0x230 mm/util.c:650
 alloc_netdev_mqs+0xb4/0x1118 net/core/dev.c:11209
 rtnl_create_link+0x2b8/0xb60 net/core/rtnetlink.c:3595
 rtnl_newlink_create+0x19c/0x868 net/core/rtnetlink.c:3771
 __rtnl_newlink net/core/rtnetlink.c:3896 [inline]
 rtnl_newlink+0x122c/0x15c0 net/core/rtnetlink.c:4011
 rtnetlink_rcv_msg+0x61c/0x918 net/core/rtnetlink.c:6901
 netlink_rcv_skb+0x1dc/0x398 net/netlink/af_netlink.c:2542
 rtnetlink_rcv+0x34/0x50 net/core/rtnetlink.c:6928
 netlink_unicast_kernel net/netlink/af_netlink.c:1321 [inline]
 netlink_unicast+0x618/0x838 net/netlink/af_netlink.c:1347
 netlink_sendmsg+0x5fc/0x8b0 net/netlink/af_netlink.c:1891
 sock_sendmsg_nosec net/socket.c:711 [inline]
 __sock_sendmsg net/socket.c:726 [inline]
 __sys_sendto+0x2ec/0x438 net/socket.c:2197
 __do_sys_sendto net/socket.c:2204 [inline]
 __se_sys_sendto net/socket.c:2200 [inline]
 __arm64_sys_sendto+0xe4/0x110 net/socket.c:2200
 __invoke_syscall arch/arm64/kernel/syscall.c:35 [inline]
 invoke_syscall+0x90/0x278 arch/arm64/kernel/syscall.c:49
 el0_svc_common+0x13c/0x250 arch/arm64/kernel/syscall.c:132
 do_el0_svc+0x54/0x70 arch/arm64/kernel/syscall.c:151
 el0_svc+0x4c/0xa8 arch/arm64/kernel/entry-common.c:744
 el0t_64_sync_handler+0x78/0x108 arch/arm64/kernel/entry-common.c:762
 el0t_64_sync+0x198/0x1a0 arch/arm64/kernel/entry.S:600

Freed by task 10200:
 kasan_save_stack mm/kasan/common.c:47 [inline]
 kasan_save_track+0x30/0x68 mm/kasan/common.c:68
 kasan_save_free_info+0x58/0x70 mm/kasan/generic.c:582
 poison_slab_object mm/kasan/common.c:247 [inline]
 __kasan_slab_free+0x48/0x68 mm/kasan/common.c:264
 kasan_slab_free include/linux/kasan.h:233 [inline]
 slab_free_hook mm/slub.c:2338 [inline]
 slab_free mm/slub.c:4598 [inline]
 kfree+0x140/0x420 mm/slub.c:4746
 kvfree+0x4c/0x68 mm/util.c:693
 netdev_release+0x94/0xc8 net/core/net-sysfs.c:2034
 device_release+0x98/0x1c0
 kobject_cleanup lib/kobject.c:689 [inline]
 kobject_release lib/kobject.c:720 [inline]
 kref_put include/linux/kref.h:65 [inline]
 kobject_put+0x2b0/0x438 lib/kobject.c:737
 netdev_run_todo+0xdd8/0xf48 net/core/dev.c:10924
 rtnl_unlock net/core/rtnetlink.c:152 [inline]
 rtnl_net_unlock net/core/rtnetlink.c:209 [inline]
 rtnl_dellink+0x484/0x680 net/core/rtnetlink.c:3526
 rtnetlink_rcv_msg+0x61c/0x918 net/core/rtnetlink.c:6901
 netlink_rcv_skb+0x1dc/0x398 net/netlink/af_netlink.c:2542
 rtnetlink_rcv+0x34/0x50 net/core/rtnetlink.c:6928
 netlink_unicast_kernel net/netlink/af_netlink.c:1321 [inline]
 netlink_unicast+0x618/0x838 net/netlink/af_netlink.c:1347
 netlink_sendmsg+0x5fc/0x8b0 net/netlink/af_netlink.c:1891
 sock_sendmsg_nosec net/socket.c:711 [inline]
 __sock_sendmsg net/socket.c:726 [inline]
 ____sys_sendmsg+0x410/0x708 net/socket.c:2583
 ___sys_sendmsg+0x178/0x1d8 net/socket.c:2637
 __sys_sendmsg net/socket.c:2669 [inline]
 __do_sys_sendmsg net/socket.c:2674 [inline]
 __se_sys_sendmsg net/socket.c:2672 [inline]
 __arm64_sys_sendmsg+0x12c/0x1c8 net/socket.c:2672
 __invoke_syscall arch/arm64/kernel/syscall.c:35 [inline]
 invoke_syscall+0x90/0x278 arch/arm64/kernel/syscall.c:49
 el0_svc_common+0x13c/0x250 arch/arm64/kernel/syscall.c:132
 do_el0_svc+0x54/0x70 arch/arm64/kernel/syscall.c:151
 el0_svc+0x4c/0xa8 arch/arm64/kernel/entry-common.c:744
 el0t_64_sync_handler+0x78/0x108 arch/arm64/kernel/entry-common.c:762
 el0t_64_sync+0x198/0x1a0 arch/arm64/kernel/entry.S:600

The buggy address belongs to the object at ffff0000d768c000
 which belongs to the cache kmalloc-cg-4k of size 4096
The buggy address is located 224 bytes inside of
 freed 4096-byte region [ffff0000d768c000, ffff0000d768d000)

The buggy address belongs to the physical page:
page: refcount:1 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x117688
head: order:3 mapcount:0 entire_mapcount:0 nr_pages_mapped:0 pincount:0
memcg:ffff0000c77ef981
flags: 0xbfffe0000000040(head|node=0|zone=2|lastcpupid=0x1ffff)
page_type: f5(slab)
raw: 0bfffe0000000040 ffff0000c000f500 dead000000000100 dead000000000122
raw: 0000000000000000 0000000000040004 00000001f5000000 ffff0000c77ef981
head: 0bfffe0000000040 ffff0000c000f500 dead000000000100 dead000000000122
head: 0000000000000000 0000000000040004 00000001f5000000 ffff0000c77ef981
head: 0bfffe0000000003 fffffdffc35da201 ffffffffffffffff 0000000000000000
head: 0000000000000008 0000000000000000 00000000ffffffff 0000000000000000
page dumped because: kasan: bad access detected

Memory state around the buggy address:
 ffff0000d768bf80: fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc fc
 ffff0000d768c000: fa fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
>ffff0000d768c080: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
                                                       ^
 ffff0000d768c100: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb
 ffff0000d768c180: fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb fb

Fixes: 8c55facecd7a ("net: linkwatch: only report IF_OPER_LOWERLAYERDOWN if iflink is actually down")
Reported-by: syzkaller <syzkaller@googlegroups.com>
Suggested-by: Jakub Kicinski <kuba@kernel.org>
Link: https://lore.kernel.org/netdev/20250102174400.085fd8ac@kernel.org/ [1]
Signed-off-by: Kuniyuki Iwashima <kuniyu@amazon.com>
Link: https://patch.msgid.link/20250106071911.64355-1-kuniyu@amazon.com
Signed-off-by: Jakub Kicinski <kuba@kernel.org>
---
 net/core/link_watch.c | 10 +++++++---
 1 file changed, 7 insertions(+), 3 deletions(-)

diff --git a/net/core/link_watch.c b/net/core/link_watch.c
index 1b4d39e38084..cb04ef2b9807 100644
--- a/net/core/link_watch.c
+++ b/net/core/link_watch.c
@@ -42,14 +42,18 @@ static unsigned int default_operstate(const struct net_device *dev)
 	 * first check whether lower is indeed the source of its down state.
 	 */
 	if (!netif_carrier_ok(dev)) {
-		int iflink = dev_get_iflink(dev);
 		struct net_device *peer;
+		int iflink;
 
 		/* If called from netdev_run_todo()/linkwatch_sync_dev(),
 		 * dev_net(dev) can be already freed, and RTNL is not held.
 		 */
-		if (dev->reg_state == NETREG_UNREGISTERED ||
-		    iflink == dev->ifindex)
+		if (dev->reg_state <= NETREG_REGISTERED)
+			iflink = dev_get_iflink(dev);
+		else
+			iflink = dev->ifindex;
+
+		if (iflink == dev->ifindex)
 			return IF_OPER_DOWN;
 
 		ASSERT_RTNL();
-- 
2.51.0