Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net

Pull networking fixes from David Miller:
 "What better way to start off a weekend than with some networking bug
  fixes:

  1) net namespace leak in dump filtering code of ipv4 and ipv6, fixed
     by David Ahern and Bjørn Mork.

  2) Handle bad checksums from hardware when using CHECKSUM_COMPLETE
     properly in UDP, from Sean Tranchetti.

  3) Remove TCA_OPTIONS from policy validation, it turns out we don't
     consistently use nested attributes for this across all packet
     schedulers. From David Ahern.

  4) Fix SKB corruption in cadence driver, from Tristram Ha.

  5) Fix broken WoL handling in r8169 driver, from Heiner Kallweit.

  6) Fix OOPS in pneigh_dump_table(), from Eric Dumazet"

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net: (28 commits)
  net/neigh: fix NULL deref in pneigh_dump_table()
  net: allow traceroute with a specified interface in a vrf
  bridge: do not add port to router list when receives query with source 0.0.0.0
  net/smc: fix smc_buf_unuse to use the lgr pointer
  ipv6/ndisc: Preserve IPv6 control buffer if protocol error handlers are called
  net/{ipv4,ipv6}: Do not put target net if input nsid is invalid
  lan743x: Remove SPI dependency from Microchip group.
  drivers: net: remove <net/busy_poll.h> inclusion when not needed
  net: phy: genphy_10g_driver: Avoid NULL pointer dereference
  r8169: fix broken Wake-on-LAN from S5 (poweroff)
  octeontx2-af: Use GFP_ATOMIC under spin lock
  net: ethernet: cadence: fix socket buffer corruption problem
  net/ipv6: Allow onlink routes to have a device mismatch if it is the default route
  net: sched: Remove TCA_OPTIONS from policy
  ice: Poll for link status change
  ice: Allocate VF interrupts and set queue map
  ice: Introduce ice_dev_onetime_setup
  net: hns3: Fix for warning uninitialized symbol hw_err_lst3
  octeontx2-af: Copy the right amount of memory
  net: udp: fix handling of CHECKSUM_COMPLETE packets
  ...

drivers/net/ethernet/amd/xgbe/xgbe-drv.c

@@ -119,7 +119,6 @@
 #include <linux/tcp.h>
 #include <linux/if_vlan.h>
 #include <linux/interrupt.h>
-#include <net/busy_poll.h>
 #include <linux/clk.h>
 #include <linux/if_ether.h>
 #include <linux/net_tstamp.h>

drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c

@@ -27,7 +27,6 @@
 #include <net/tcp.h>
 #include <net/ipv6.h>
 #include <net/ip6_checksum.h>
-#include <net/busy_poll.h>
 #include <linux/prefetch.h>
 #include "bnx2x_cmn.h"
 #include "bnx2x_init.h"

drivers/net/ethernet/cadence/macb_main.c

@@ -1684,7 +1684,7 @@ static int macb_pad_and_fcs(struct sk_buff **skb, struct net_device *ndev)
 			padlen = 0;
 		/* No room for FCS, need to reallocate skb. */
 		else
-			padlen = ETH_FCS_LEN - tailroom;
+			padlen = ETH_FCS_LEN;
 	} else {
 		/* Add room for FCS. */
 		padlen += ETH_FCS_LEN;

drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c

@@ -859,10 +859,12 @@ static int hclge_log_and_clear_ppp_error(struct hclge_dev *hdev, u32 cmd,
 		reset_level = HNAE3_FUNC_RESET;
 	}
 
-	err_sts = (le32_to_cpu(desc[0].data[4]) >> 8) & 0x3;
-	if (err_sts) {
-		hclge_log_error(dev, hw_err_lst3, err_sts);
-		reset_level = HNAE3_FUNC_RESET;
+	if (cmd == HCLGE_PPP_CMD0_INT_CMD) {
+		err_sts = (le32_to_cpu(desc[0].data[4]) >> 8) & 0x3;
+		if (err_sts) {
+			hclge_log_error(dev, hw_err_lst3, err_sts);
+			reset_level = HNAE3_FUNC_RESET;
+		}
 	}
 
 	/* clear PPP INT */

drivers/net/ethernet/intel/i40e/i40e_txrx.c

@@ -2,7 +2,6 @@
 /* Copyright(c) 2013 - 2018 Intel Corporation. */
 
 #include <linux/prefetch.h>
-#include <net/busy_poll.h>
 #include <linux/bpf_trace.h>
 #include <net/xdp.h>
 #include "i40e.h"

drivers/net/ethernet/intel/iavf/iavf_txrx.c

@@ -2,7 +2,6 @@
 /* Copyright(c) 2013 - 2018 Intel Corporation. */
 
 #include <linux/prefetch.h>
-#include <net/busy_poll.h>
 
 #include "iavf.h"
 #include "iavf_trace.h"

drivers/net/ethernet/intel/ice/ice_common.c

@@ -42,6 +42,23 @@ static enum ice_status ice_set_mac_type(struct ice_hw *hw)
 	return 0;
 }
 
+/**
+ * ice_dev_onetime_setup - Temporary HW/FW workarounds
+ * @hw: pointer to the HW structure
+ *
+ * This function provides temporary workarounds for certain issues
+ * that are expected to be fixed in the HW/FW.
+ */
+void ice_dev_onetime_setup(struct ice_hw *hw)
+{
+	/* configure Rx - set non pxe mode */
+	wr32(hw, GLLAN_RCTL_0, 0x1);
+
+#define MBX_PF_VT_PFALLOC	0x00231E80
+	/* set VFs per PF */
+	wr32(hw, MBX_PF_VT_PFALLOC, rd32(hw, PF_VT_PFALLOC_HIF));
+}
+
 /**
  * ice_clear_pf_cfg - Clear PF configuration
  * @hw: pointer to the hardware structure
@@ -218,7 +235,7 @@ static enum ice_media_type ice_get_media_type(struct ice_port_info *pi)
  *
  * Get Link Status (0x607). Returns the link status of the adapter.
  */
-enum ice_status
+static enum ice_status
 ice_aq_get_link_info(struct ice_port_info *pi, bool ena_lse,
 		     struct ice_link_status *link, struct ice_sq_cd *cd)
 {
@@ -740,6 +757,8 @@ enum ice_status ice_init_hw(struct ice_hw *hw)
 	if (status)
 		goto err_unroll_sched;
 
+	ice_dev_onetime_setup(hw);
+
 	/* Get MAC information */
 	/* A single port can report up to two (LAN and WoL) addresses */
 	mac_buf = devm_kcalloc(ice_hw_to_dev(hw), 2,
@@ -1531,9 +1550,7 @@ ice_aq_discover_caps(struct ice_hw *hw, void *buf, u16 buf_size, u32 *cap_count,
 	if (!status)
 		ice_parse_caps(hw, buf, le32_to_cpu(cmd->count), opc);
 	else if (hw->adminq.sq_last_status == ICE_AQ_RC_ENOMEM)
-		*cap_count =
-			DIV_ROUND_UP(le16_to_cpu(desc.datalen),
-				     sizeof(struct ice_aqc_list_caps_elem));
+		*cap_count = le32_to_cpu(cmd->count);
 	return status;
 }
 
@@ -1987,33 +2004,6 @@ ice_aq_set_link_restart_an(struct ice_port_info *pi, bool ena_link,
 	return ice_aq_send_cmd(pi->hw, &desc, NULL, 0, cd);
 }
 
-/**
- * ice_aq_set_event_mask
- * @hw: pointer to the hw struct
- * @port_num: port number of the physical function
- * @mask: event mask to be set
- * @cd: pointer to command details structure or NULL
- *
- * Set event mask (0x0613)
- */
-enum ice_status
-ice_aq_set_event_mask(struct ice_hw *hw, u8 port_num, u16 mask,
-		      struct ice_sq_cd *cd)
-{
-	struct ice_aqc_set_event_mask *cmd;
-	struct ice_aq_desc desc;
-
-	cmd = &desc.params.set_event_mask;
-
-	ice_fill_dflt_direct_cmd_desc(&desc, ice_aqc_opc_set_event_mask);
-
-	cmd->lport_num = port_num;
-
-	cmd->event_mask = cpu_to_le16(mask);
-
-	return ice_aq_send_cmd(hw, &desc, NULL, 0, cd);
-}
-
 /**
  * __ice_aq_get_set_rss_lut
  * @hw: pointer to the hardware structure

drivers/net/ethernet/intel/ice/ice_common.h

@@ -34,6 +34,9 @@ ice_sq_send_cmd(struct ice_hw *hw, struct ice_ctl_q_info *cq,
 		struct ice_sq_cd *cd);
 void ice_clear_pxe_mode(struct ice_hw *hw);
 enum ice_status ice_get_caps(struct ice_hw *hw);
+
+void ice_dev_onetime_setup(struct ice_hw *hw);
+
 enum ice_status
 ice_write_rxq_ctx(struct ice_hw *hw, struct ice_rlan_ctx *rlan_ctx,
 		  u32 rxq_index);
@@ -83,12 +86,6 @@ enum ice_status
 ice_aq_set_link_restart_an(struct ice_port_info *pi, bool ena_link,
 			   struct ice_sq_cd *cd);
 enum ice_status
-ice_aq_get_link_info(struct ice_port_info *pi, bool ena_lse,
-		     struct ice_link_status *link, struct ice_sq_cd *cd);
-enum ice_status
-ice_aq_set_event_mask(struct ice_hw *hw, u8 port_num, u16 mask,
-		      struct ice_sq_cd *cd);
-enum ice_status
 ice_dis_vsi_txq(struct ice_port_info *pi, u8 num_queues, u16 *q_ids,
 		u32 *q_teids, enum ice_disq_rst_src rst_src, u16 vmvf_num,
 		struct ice_sq_cd *cmd_details);

drivers/net/ethernet/intel/ice/ice_controlq.h

@@ -19,11 +19,10 @@
 
 /* Defines that help manage the driver vs FW API checks.
  * Take a look at ice_aq_ver_check in ice_controlq.c for actual usage.
- *
  */
 #define EXP_FW_API_VER_BRANCH		0x00
-#define EXP_FW_API_VER_MAJOR		0x00
-#define EXP_FW_API_VER_MINOR		0x01
+#define EXP_FW_API_VER_MAJOR		0x01
+#define EXP_FW_API_VER_MINOR		0x03
 
 /* Different control queue types: These are mainly for SW consumption. */
 enum ice_ctl_q {

drivers/net/ethernet/intel/ice/ice_devids.h

@@ -6,10 +6,10 @@
 
 /* Device IDs */
 /* Intel(R) Ethernet Controller E810-C for backplane */
-#define ICE_DEV_ID_C810_BACKPLANE	0x1591
+#define ICE_DEV_ID_E810C_BACKPLANE	0x1591
 /* Intel(R) Ethernet Controller E810-C for QSFP */
-#define ICE_DEV_ID_C810_QSFP		0x1592
+#define ICE_DEV_ID_E810C_QSFP		0x1592
 /* Intel(R) Ethernet Controller E810-C for SFP */
-#define ICE_DEV_ID_C810_SFP		0x1593
+#define ICE_DEV_ID_E810C_SFP		0x1593
 
 #endif /* _ICE_DEVIDS_H_ */

drivers/net/ethernet/intel/ice/ice_hw_autogen.h

@@ -157,6 +157,13 @@
 #define VPINT_ALLOC_LAST_S			12
 #define VPINT_ALLOC_LAST_M			ICE_M(0x7FF, 12)
 #define VPINT_ALLOC_VALID_M			BIT(31)
+#define VPINT_ALLOC_PCI(_VF)			(0x0009D000 + ((_VF) * 4))
+#define VPINT_ALLOC_PCI_FIRST_S			0
+#define VPINT_ALLOC_PCI_FIRST_M			ICE_M(0x7FF, 0)
+#define VPINT_ALLOC_PCI_LAST_S			12
+#define VPINT_ALLOC_PCI_LAST_M			ICE_M(0x7FF, 12)
+#define VPINT_ALLOC_PCI_VALID_M			BIT(31)
+#define GLLAN_RCTL_0				0x002941F8
 #define QRX_CONTEXT(_i, _QRX)			(0x00280000 + ((_i) * 8192 + (_QRX) * 4))
 #define QRX_CTRL(_QRX)				(0x00120000 + ((_QRX) * 4))
 #define QRX_CTRL_MAX_INDEX			2047
@@ -320,6 +327,7 @@
 #define GLV_UPRCL(_i)				(0x003B2000 + ((_i) * 8))
 #define GLV_UPTCH(_i)				(0x0030A004 + ((_i) * 8))
 #define GLV_UPTCL(_i)				(0x0030A000 + ((_i) * 8))
+#define PF_VT_PFALLOC_HIF			0x0009DD80
 #define VSIQF_HKEY_MAX_INDEX			12
 #define VSIQF_HLUT_MAX_INDEX			15
 #define VFINT_DYN_CTLN(_i)			(0x00003800 + ((_i) * 4))

drivers/net/ethernet/intel/ice/ice_lib.c

@@ -433,7 +433,7 @@ int ice_vsi_clear(struct ice_vsi *vsi)
  * @irq: interrupt number
  * @data: pointer to a q_vector
  */
-irqreturn_t ice_msix_clean_rings(int __always_unused irq, void *data)
+static irqreturn_t ice_msix_clean_rings(int __always_unused irq, void *data)
 {
 	struct ice_q_vector *q_vector = (struct ice_q_vector *)data;
 
@@ -2529,6 +2529,7 @@ int ice_vsi_rebuild(struct ice_vsi *vsi)
 	vsi->hw_base_vector = 0;
 	ice_vsi_clear_rings(vsi);
 	ice_vsi_free_arrays(vsi, false);
+	ice_dev_onetime_setup(&vsi->back->hw);
 	ice_vsi_set_num_qs(vsi);
 
 	/* Initialize VSI struct elements and create VSI in FW */

drivers/net/ethernet/intel/ice/ice_lib.h

@@ -73,5 +73,4 @@ int ice_vsi_cfg_tc(struct ice_vsi *vsi, u8 ena_tc);
 
 int ice_vsi_manage_rss_lut(struct ice_vsi *vsi, bool ena);
 
-irqreturn_t ice_msix_clean_rings(int __always_unused irq, void *data);
 #endif /* !_ICE_LIB_H_ */

drivers/net/ethernet/intel/ice/ice_main.c

@@ -456,35 +456,6 @@ static void ice_reset_subtask(struct ice_pf *pf)
 	}
 }
 
-/**
- * ice_watchdog_subtask - periodic tasks not using event driven scheduling
- * @pf: board private structure
- */
-static void ice_watchdog_subtask(struct ice_pf *pf)
-{
-	int i;
-
-	/* if interface is down do nothing */
-	if (test_bit(__ICE_DOWN, pf->state) ||
-	    test_bit(__ICE_CFG_BUSY, pf->state))
-		return;
-
-	/* make sure we don't do these things too often */
-	if (time_before(jiffies,
-			pf->serv_tmr_prev + pf->serv_tmr_period))
-		return;
-
-	pf->serv_tmr_prev = jiffies;
-
-	/* Update the stats for active netdevs so the network stack
-	 * can look at updated numbers whenever it cares to
-	 */
-	ice_update_pf_stats(pf);
-	for (i = 0; i < pf->num_alloc_vsi; i++)
-		if (pf->vsi[i] && pf->vsi[i]->netdev)
-			ice_update_vsi_stats(pf->vsi[i]);
-}
-
 /**
  * ice_print_link_msg - print link up or down message
  * @vsi: the VSI whose link status is being queried
@@ -554,36 +525,6 @@ void ice_print_link_msg(struct ice_vsi *vsi, bool isup)
 		    speed, fc);
 }
 
-/**
- * ice_init_link_events - enable/initialize link events
- * @pi: pointer to the port_info instance
- *
- * Returns -EIO on failure, 0 on success
- */
-static int ice_init_link_events(struct ice_port_info *pi)
-{
-	u16 mask;
-
-	mask = ~((u16)(ICE_AQ_LINK_EVENT_UPDOWN | ICE_AQ_LINK_EVENT_MEDIA_NA |
-		       ICE_AQ_LINK_EVENT_MODULE_QUAL_FAIL));
-
-	if (ice_aq_set_event_mask(pi->hw, pi->lport, mask, NULL)) {
-		dev_dbg(ice_hw_to_dev(pi->hw),
-			"Failed to set link event mask for port %d\n",
-			pi->lport);
-		return -EIO;
-	}
-
-	if (ice_aq_get_link_info(pi, true, NULL, NULL)) {
-		dev_dbg(ice_hw_to_dev(pi->hw),
-			"Failed to enable link events for port %d\n",
-			pi->lport);
-		return -EIO;
-	}
-
-	return 0;
-}
-
 /**
  * ice_vsi_link_event - update the vsi's netdev
  * @vsi: the vsi on which the link event occurred
@@ -671,27 +612,35 @@ ice_link_event(struct ice_pf *pf, struct ice_port_info *pi)
 }
 
 /**
- * ice_handle_link_event - handle link event via ARQ
- * @pf: pf that the link event is associated with
- *
- * Return -EINVAL if port_info is null
- * Return status on succes
+ * ice_watchdog_subtask - periodic tasks not using event driven scheduling
+ * @pf: board private structure
  */
-static int ice_handle_link_event(struct ice_pf *pf)
+static void ice_watchdog_subtask(struct ice_pf *pf)
 {
-	struct ice_port_info *port_info;
-	int status;
+	int i;
 
-	port_info = pf->hw.port_info;
-	if (!port_info)
-		return -EINVAL;
+	/* if interface is down do nothing */
+	if (test_bit(__ICE_DOWN, pf->state) ||
+	    test_bit(__ICE_CFG_BUSY, pf->state))
+		return;
 
-	status = ice_link_event(pf, port_info);
-	if (status)
-		dev_dbg(&pf->pdev->dev,
-			"Could not process link event, error %d\n", status);
+	/* make sure we don't do these things too often */
+	if (time_before(jiffies,
+			pf->serv_tmr_prev + pf->serv_tmr_period))
+		return;
 
-	return status;
+	pf->serv_tmr_prev = jiffies;
+
+	if (ice_link_event(pf, pf->hw.port_info))
+		dev_dbg(&pf->pdev->dev, "ice_link_event failed\n");
+
+	/* Update the stats for active netdevs so the network stack
+	 * can look at updated numbers whenever it cares to
+	 */
+	ice_update_pf_stats(pf);
+	for (i = 0; i < pf->num_alloc_vsi; i++)
+		if (pf->vsi[i] && pf->vsi[i]->netdev)
+			ice_update_vsi_stats(pf->vsi[i]);
 }
 
 /**
@@ -797,11 +746,6 @@ static int __ice_clean_ctrlq(struct ice_pf *pf, enum ice_ctl_q q_type)
 		opcode = le16_to_cpu(event.desc.opcode);
 
 		switch (opcode) {
-		case ice_aqc_opc_get_link_status:
-			if (ice_handle_link_event(pf))
-				dev_err(&pf->pdev->dev,
-					"Could not handle link event\n");
-			break;
 		case ice_mbx_opc_send_msg_to_pf:
 			ice_vc_process_vf_msg(pf, &event);
 			break;
@@ -2207,12 +2151,6 @@ static int ice_probe(struct pci_dev *pdev,
 	/* since everything is good, start the service timer */
 	mod_timer(&pf->serv_tmr, round_jiffies(jiffies + pf->serv_tmr_period));
 
-	err = ice_init_link_events(pf->hw.port_info);
-	if (err) {
-		dev_err(&pdev->dev, "ice_init_link_events failed: %d\n", err);
-		goto err_alloc_sw_unroll;
-	}
-
 	return 0;
 
 err_alloc_sw_unroll:
@@ -2271,9 +2209,9 @@ static void ice_remove(struct pci_dev *pdev)
  *   Class, Class Mask, private data (not used) }
  */
 static const struct pci_device_id ice_pci_tbl[] = {
-	{ PCI_VDEVICE(INTEL, ICE_DEV_ID_C810_BACKPLANE), 0 },
-	{ PCI_VDEVICE(INTEL, ICE_DEV_ID_C810_QSFP), 0 },
-	{ PCI_VDEVICE(INTEL, ICE_DEV_ID_C810_SFP), 0 },
+	{ PCI_VDEVICE(INTEL, ICE_DEV_ID_E810C_BACKPLANE), 0 },
+	{ PCI_VDEVICE(INTEL, ICE_DEV_ID_E810C_QSFP), 0 },
+	{ PCI_VDEVICE(INTEL, ICE_DEV_ID_E810C_SFP), 0 },
 	/* required last entry */
 	{ 0, }
 };

drivers/net/ethernet/intel/ice/ice_virtchnl_pf.c

@@ -173,6 +173,7 @@ static void ice_dis_vf_mappings(struct ice_vf *vf)
 	vsi = pf->vsi[vf->lan_vsi_idx];
 
 	wr32(hw, VPINT_ALLOC(vf->vf_id), 0);
+	wr32(hw, VPINT_ALLOC_PCI(vf->vf_id), 0);
 
 	first = vf->first_vector_idx;
 	last = first + pf->num_vf_msix - 1;
@@ -519,6 +520,10 @@ static void ice_ena_vf_mappings(struct ice_vf *vf)
 	       VPINT_ALLOC_VALID_M);
 	wr32(hw, VPINT_ALLOC(vf->vf_id), reg);
 
+	reg = (((first << VPINT_ALLOC_PCI_FIRST_S) & VPINT_ALLOC_PCI_FIRST_M) |
+	       ((last << VPINT_ALLOC_PCI_LAST_S) & VPINT_ALLOC_PCI_LAST_M) |
+	       VPINT_ALLOC_PCI_VALID_M);
+	wr32(hw, VPINT_ALLOC_PCI(vf->vf_id), reg);
 	/* map the interrupts to its functions */
 	for (v = first; v <= last; v++) {
 		reg = (((abs_vf_id << GLINT_VECT2FUNC_VF_NUM_S) &
@@ -528,10 +533,11 @@ static void ice_ena_vf_mappings(struct ice_vf *vf)
 		wr32(hw, GLINT_VECT2FUNC(v), reg);
 	}
 
+	/* set regardless of mapping mode */
+	wr32(hw, VPLAN_TXQ_MAPENA(vf->vf_id), VPLAN_TXQ_MAPENA_TX_ENA_M);
+
 	/* VF Tx queues allocation */
 	if (vsi->tx_mapping_mode == ICE_VSI_MAP_CONTIG) {
-		wr32(hw, VPLAN_TXQ_MAPENA(vf->vf_id),
-		     VPLAN_TXQ_MAPENA_TX_ENA_M);
 		/* set the VF PF Tx queue range
 		 * VFNUMQ value should be set to (number of queues - 1). A value
 		 * of 0 means 1 queue and a value of 255 means 256 queues
@@ -546,10 +552,11 @@ static void ice_ena_vf_mappings(struct ice_vf *vf)
 			"Scattered mode for VF Tx queues is not yet implemented\n");
 	}
 
+	/* set regardless of mapping mode */
+	wr32(hw, VPLAN_RXQ_MAPENA(vf->vf_id), VPLAN_RXQ_MAPENA_RX_ENA_M);
+
 	/* VF Rx queues allocation */
 	if (vsi->rx_mapping_mode == ICE_VSI_MAP_CONTIG) {
-		wr32(hw, VPLAN_RXQ_MAPENA(vf->vf_id),
-		     VPLAN_RXQ_MAPENA_RX_ENA_M);
 		/* set the VF PF Rx queue range
 		 * VFNUMQ value should be set to (number of queues - 1). A value
 		 * of 0 means 1 queue and a value of 255 means 256 queues

drivers/net/ethernet/intel/ixgbe/ixgbe.h

@@ -30,7 +30,6 @@
 #include "ixgbe_ipsec.h"
 
 #include <net/xdp.h>
-#include <net/busy_poll.h>
 
 /* common prefix used by pr_<> macros */
 #undef pr_fmt

drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c

@@ -573,7 +573,7 @@ static int rvu_nix_aq_enq_inst(struct rvu *rvu, struct nix_aq_enq_req *req,
 				       sizeof(struct nix_cq_ctx_s));
 			else if (req->ctype == NIX_AQ_CTYPE_RSS)
 				memcpy(&rsp->rss, ctx,
-				       sizeof(struct nix_cq_ctx_s));
+				       sizeof(struct nix_rsse_s));
 			else if (req->ctype == NIX_AQ_CTYPE_MCE)
 				memcpy(&rsp->mce, ctx,
 				       sizeof(struct nix_rx_mce_s));
@@ -1294,7 +1294,7 @@ static int nix_update_mce_list(struct nix_mce_list *mce_list,
 		return 0;
 
 	/* Add a new one to the list, at the tail */
-	mce = kzalloc(sizeof(*mce), GFP_KERNEL);
+	mce = kzalloc(sizeof(*mce), GFP_ATOMIC);
 	if (!mce)
 		return -ENOMEM;
 	mce->idx = idx;

drivers/net/ethernet/mellanox/mlx4/en_netdev.c

@@ -39,7 +39,6 @@
 #include <linux/slab.h>
 #include <linux/hash.h>
 #include <net/ip.h>
-#include <net/busy_poll.h>
 #include <net/vxlan.h>
 #include <net/devlink.h>
 

drivers/net/ethernet/mellanox/mlx4/en_rx.c

@@ -31,7 +31,6 @@
  *
  */
 
-#include <net/busy_poll.h>
 #include <linux/bpf.h>
 #include <linux/bpf_trace.h>
 #include <linux/mlx4/cq.h>

drivers/net/ethernet/mellanox/mlx5/core/en_rx.c

@@ -34,7 +34,6 @@
 #include <linux/ip.h>
 #include <linux/ipv6.h>
 #include <linux/tcp.h>
-#include <net/busy_poll.h>
 #include <net/ip6_checksum.h>
 #include <net/page_pool.h>
 #include <net/inet_ecn.h>

drivers/net/ethernet/microchip/Kconfig

@@ -5,7 +5,6 @@
 config NET_VENDOR_MICROCHIP
 	bool "Microchip devices"
 	default y
-	depends on SPI
 	---help---
 	  If you have a network (Ethernet) card belonging to this class, say Y.
 

drivers/net/ethernet/myricom/myri10ge/myri10ge.c

@@ -70,7 +70,6 @@
 #include <net/tcp.h>
 #include <asm/byteorder.h>
 #include <asm/processor.h>
-#include <net/busy_poll.h>
 
 #include "myri10ge_mcp.h"
 #include "myri10ge_mcp_gen_header.h"

drivers/net/ethernet/realtek/r8169.c

@@ -4161,10 +4161,15 @@ static void rtl_wol_suspend_quirk(struct rtl8169_private *tp)
 
 static bool rtl_wol_pll_power_down(struct rtl8169_private *tp)
 {
-	if (!netif_running(tp->dev) || !__rtl8169_get_wol(tp))
+	struct phy_device *phydev;
+
+	if (!__rtl8169_get_wol(tp))
 		return false;
 
-	phy_speed_down(tp->dev->phydev, false);
+	/* phydev may not be attached to netdevice */
+	phydev = mdiobus_get_phy(tp->mii_bus, 0);
+
+	phy_speed_down(phydev, false);
 	rtl_wol_suspend_quirk(tp);
 
 	return true;

drivers/net/phy/phy-c45.c

@@ -329,7 +329,7 @@ struct phy_driver genphy_10g_driver = {
 	.name           = "Generic 10G PHY",
 	.soft_reset	= gen10g_no_soft_reset,
 	.config_init    = gen10g_config_init,
-	.features       = 0,
+	.features       = PHY_10GBIT_FEATURES,
 	.config_aneg    = gen10g_config_aneg,
 	.read_status    = gen10g_read_status,
 	.suspend        = gen10g_suspend,

include/net/ip_fib.h

@@ -226,6 +226,7 @@ struct fib_dump_filter {
 	u32			table_id;
 	/* filter_set is an optimization that an entry is set */
 	bool			filter_set;
+	bool			dump_all_families;
 	unsigned char		protocol;
 	unsigned char		rt_type;
 	unsigned int		flags;

net/bridge/br_multicast.c

@@ -1422,7 +1422,15 @@ static void br_multicast_query_received(struct net_bridge *br,
 		return;
 
 	br_multicast_update_query_timer(br, query, max_delay);
-	br_multicast_mark_router(br, port);
+
+	/* Based on RFC4541, section 2.1.1 IGMP Forwarding Rules,
+	 * the arrival port for IGMP Queries where the source address
+	 * is 0.0.0.0 should not be added to router port list.
+	 */
+	if ((saddr->proto == htons(ETH_P_IP) && saddr->u.ip4) ||
+	    (saddr->proto == htons(ETH_P_IPV6) &&
+	     !ipv6_addr_any(&saddr->u.ip6)))
+		br_multicast_mark_router(br, port);
 }
 
 static void br_ip4_multicast_query(struct net_bridge *br,

net/core/datagram.c

@@ -808,8 +808,9 @@ int skb_copy_and_csum_datagram_msg(struct sk_buff *skb,
 			return -EINVAL;
 		}
 
-		if (unlikely(skb->ip_summed == CHECKSUM_COMPLETE))
-			netdev_rx_csum_fault(skb->dev);
+		if (unlikely(skb->ip_summed == CHECKSUM_COMPLETE) &&
+		    !skb->csum_complete_sw)
+			netdev_rx_csum_fault(NULL);
 	}
 	return 0;
 fault:

net/core/neighbour.c

@@ -2364,7 +2364,7 @@ static bool neigh_master_filtered(struct net_device *dev, int master_idx)
 	if (!master_idx)
 		return false;
 
-	master = netdev_master_upper_dev_get(dev);
+	master = dev ? netdev_master_upper_dev_get(dev) : NULL;
 	if (!master || master->ifindex != master_idx)
 		return true;
 
@@ -2373,7 +2373,7 @@ static bool neigh_master_filtered(struct net_device *dev, int master_idx)
 
 static bool neigh_ifindex_filtered(struct net_device *dev, int filter_idx)
 {
-	if (filter_idx && dev->ifindex != filter_idx)
+	if (filter_idx && (!dev || dev->ifindex != filter_idx))
 		return true;
 
 	return false;

net/core/rtnetlink.c

@@ -3333,6 +3333,7 @@ static int rtnl_dump_all(struct sk_buff *skb, struct netlink_callback *cb)
 	int idx;
 	int s_idx = cb->family;
 	int type = cb->nlh->nlmsg_type - RTM_BASE;
+	int ret = 0;
 
 	if (s_idx == 0)
 		s_idx = 1;
@@ -3365,12 +3366,13 @@ static int rtnl_dump_all(struct sk_buff *skb, struct netlink_callback *cb)
 			cb->prev_seq = 0;
 			cb->seq = 0;
 		}
-		if (dumpit(skb, cb))
+		ret = dumpit(skb, cb);
+		if (ret < 0)
 			break;
 	}
 	cb->family = idx;
 
-	return skb->len;
+	return skb->len ? : ret;
 }
 
 struct sk_buff *rtmsg_ifinfo_build_skb(int type, struct net_device *dev,

net/ipv4/devinet.c

@@ -1704,6 +1704,7 @@ static int inet_valid_dump_ifaddr_req(const struct nlmsghdr *nlh,
 
 			net = rtnl_get_net_ns_capable(sk, fillargs->netnsid);
 			if (IS_ERR(net)) {
+				fillargs->netnsid = -1;
 				NL_SET_ERR_MSG(extack, "ipv4: Invalid target network namespace id");
 				return PTR_ERR(net);
 			}
@@ -1761,7 +1762,7 @@ static int inet_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb)
 	struct net_device *dev;
 	struct in_device *in_dev;
 	struct hlist_head *head;
-	int err;
+	int err = 0;
 
 	s_h = cb->args[0];
 	s_idx = idx = cb->args[1];
@@ -1771,12 +1772,15 @@ static int inet_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb)
 		err = inet_valid_dump_ifaddr_req(nlh, &fillargs, &tgt_net,
 						 skb->sk, cb);
 		if (err < 0)
-			return err;
+			goto put_tgt_net;
 
+		err = 0;
 		if (fillargs.ifindex) {
 			dev = __dev_get_by_index(tgt_net, fillargs.ifindex);
-			if (!dev)
-				return -ENODEV;
+			if (!dev) {
+				err = -ENODEV;
+				goto put_tgt_net;
+			}
 
 			in_dev = __in_dev_get_rtnl(dev);
 			if (in_dev) {
@@ -1821,7 +1825,7 @@ put_tgt_net:
 	if (fillargs.netnsid >= 0)
 		put_net(tgt_net);
 
-	return skb->len;
+	return err < 0 ? err : skb->len;
 }
 
 static void rtmsg_ifa(int event, struct in_ifaddr *ifa, struct nlmsghdr *nlh,

net/ipv4/fib_frontend.c

@@ -829,6 +829,7 @@ int ip_valid_fib_dump_req(struct net *net, const struct nlmsghdr *nlh,
 		return -EINVAL;
 	}
 
+	filter->dump_all_families = (rtm->rtm_family == AF_UNSPEC);
 	filter->flags    = rtm->rtm_flags;
 	filter->protocol = rtm->rtm_protocol;
 	filter->rt_type  = rtm->rtm_type;
@@ -899,6 +900,9 @@ static int inet_dump_fib(struct sk_buff *skb, struct netlink_callback *cb)
 	if (filter.table_id) {
 		tb = fib_get_table(net, filter.table_id);
 		if (!tb) {
+			if (filter.dump_all_families)
+				return skb->len;
+
 			NL_SET_ERR_MSG(cb->extack, "ipv4: FIB table does not exist");
 			return -ENOENT;
 		}

net/ipv4/ipmr.c

@@ -2542,6 +2542,9 @@ static int ipmr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb)
 
 		mrt = ipmr_get_table(sock_net(skb->sk), filter.table_id);
 		if (!mrt) {
+			if (filter.dump_all_families)
+				return skb->len;
+
 			NL_SET_ERR_MSG(cb->extack, "ipv4: MR table does not exist");
 			return -ENOENT;
 		}

net/ipv4/udp.c

@@ -609,8 +609,8 @@ void __udp4_lib_err(struct sk_buff *skb, u32 info, struct udp_table *udptable)
 	struct net *net = dev_net(skb->dev);
 
 	sk = __udp4_lib_lookup(net, iph->daddr, uh->dest,
-			       iph->saddr, uh->source, skb->dev->ifindex, 0,
-			       udptable, NULL);
+			       iph->saddr, uh->source, skb->dev->ifindex,
+			       inet_sdif(skb), udptable, NULL);
 	if (!sk) {
 		__ICMP_INC_STATS(net, ICMP_MIB_INERRORS);
 		return;	/* No socket for error */
@@ -2120,8 +2120,24 @@ static inline int udp4_csum_init(struct sk_buff *skb, struct udphdr *uh,
 	/* Note, we are only interested in != 0 or == 0, thus the
 	 * force to int.
 	 */
-	return (__force int)skb_checksum_init_zero_check(skb, proto, uh->check,
-							 inet_compute_pseudo);
+	err = (__force int)skb_checksum_init_zero_check(skb, proto, uh->check,
+							inet_compute_pseudo);
+	if (err)
+		return err;
+
+	if (skb->ip_summed == CHECKSUM_COMPLETE && !skb->csum_valid) {
+		/* If SW calculated the value, we know it's bad */
+		if (skb->csum_complete_sw)
+			return 1;
+
+		/* HW says the value is bad. Let's validate that.
+		 * skb->csum is no longer the full packet checksum,
+		 * so don't treat it as such.
+		 */
+		skb_checksum_complete_unset(skb);
+	}
+
+	return 0;
 }
 
 /* wrapper for udp_queue_rcv_skb tacking care of csum conversion and

net/ipv6/addrconf.c

@@ -5058,6 +5058,7 @@ static int inet6_valid_dump_ifaddr_req(const struct nlmsghdr *nlh,
 			fillargs->netnsid = nla_get_s32(tb[i]);
 			net = rtnl_get_net_ns_capable(sk, fillargs->netnsid);
 			if (IS_ERR(net)) {
+				fillargs->netnsid = -1;
 				NL_SET_ERR_MSG_MOD(extack, "Invalid target network namespace id");
 				return PTR_ERR(net);
 			}
@@ -5089,23 +5090,25 @@ static int inet6_dump_addr(struct sk_buff *skb, struct netlink_callback *cb,
 	struct net_device *dev;
 	struct inet6_dev *idev;
 	struct hlist_head *head;
+	int err = 0;
 
 	s_h = cb->args[0];
 	s_idx = idx = cb->args[1];
 	s_ip_idx = cb->args[2];
 
 	if (cb->strict_check) {
-		int err;
-
 		err = inet6_valid_dump_ifaddr_req(nlh, &fillargs, &tgt_net,
 						  skb->sk, cb);
 		if (err < 0)
-			return err;
+			goto put_tgt_net;
 
+		err = 0;
 		if (fillargs.ifindex) {
 			dev = __dev_get_by_index(tgt_net, fillargs.ifindex);
-			if (!dev)
-				return -ENODEV;
+			if (!dev) {
+				err = -ENODEV;
+				goto put_tgt_net;
+			}
 			idev = __in6_dev_get(dev);
 			if (idev) {
 				err = in6_dump_addrs(idev, skb, cb, s_ip_idx,
@@ -5144,7 +5147,7 @@ put_tgt_net:
 	if (fillargs.netnsid >= 0)
 		put_net(tgt_net);
 
-	return skb->len;
+	return err < 0 ? err : skb->len;
 }
 
 static int inet6_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb)

net/ipv6/ip6_checksum.c

@@ -88,8 +88,24 @@ int udp6_csum_init(struct sk_buff *skb, struct udphdr *uh, int proto)
 	 * Note, we are only interested in != 0 or == 0, thus the
 	 * force to int.
 	 */
-	return (__force int)skb_checksum_init_zero_check(skb, proto, uh->check,
-							 ip6_compute_pseudo);
+	err = (__force int)skb_checksum_init_zero_check(skb, proto, uh->check,
+							ip6_compute_pseudo);
+	if (err)
+		return err;
+
+	if (skb->ip_summed == CHECKSUM_COMPLETE && !skb->csum_valid) {
+		/* If SW calculated the value, we know it's bad */
+		if (skb->csum_complete_sw)
+			return 1;
+
+		/* HW says the value is bad. Let's validate that.
+		 * skb->csum is no longer the full packet checksum,
+		 * so don't treat is as such.
+		 */
+		skb_checksum_complete_unset(skb);
+	}
+
+	return 0;
 }
 EXPORT_SYMBOL(udp6_csum_init);
 

net/ipv6/ip6_fib.c

@@ -620,6 +620,9 @@ static int inet6_dump_fib(struct sk_buff *skb, struct netlink_callback *cb)
 	if (arg.filter.table_id) {
 		tb = fib6_get_table(net, arg.filter.table_id);
 		if (!tb) {
+			if (arg.filter.dump_all_families)
+				return skb->len;
+
 			NL_SET_ERR_MSG_MOD(cb->extack, "FIB table does not exist");
 			return -ENOENT;
 		}

net/ipv6/ip6mr.c

@@ -2473,6 +2473,9 @@ static int ip6mr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb)
 
 		mrt = ip6mr_get_table(sock_net(skb->sk), filter.table_id);
 		if (!mrt) {
+			if (filter.dump_all_families)
+				return skb->len;
+
 			NL_SET_ERR_MSG_MOD(cb->extack, "MR table does not exist");
 			return -ENOENT;
 		}

net/ipv6/ndisc.c

@@ -1732,10 +1732,9 @@ int ndisc_rcv(struct sk_buff *skb)
 		return 0;
 	}
 
-	memset(NEIGH_CB(skb), 0, sizeof(struct neighbour_cb));
-
 	switch (msg->icmph.icmp6_type) {
 	case NDISC_NEIGHBOUR_SOLICITATION:
+		memset(NEIGH_CB(skb), 0, sizeof(struct neighbour_cb));
 		ndisc_recv_ns(skb);
 		break;
 

net/ipv6/route.c

@@ -2745,6 +2745,8 @@ static int ip6_route_check_nh_onlink(struct net *net,
 	grt = ip6_nh_lookup_table(net, cfg, gw_addr, tbid, 0);
 	if (grt) {
 		if (!grt->dst.error &&
+		    /* ignore match if it is the default route */
+		    grt->from && !ipv6_addr_any(&grt->from->fib6_dst.addr) &&
 		    (grt->rt6i_flags & flags || dev != grt->dst.dev)) {
 			NL_SET_ERR_MSG(extack,
 				       "Nexthop has invalid gateway or device mismatch");

net/ipv6/udp.c

@@ -478,7 +478,7 @@ void __udp6_lib_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
 	struct net *net = dev_net(skb->dev);
 
 	sk = __udp6_lib_lookup(net, daddr, uh->dest, saddr, uh->source,
-			       inet6_iif(skb), 0, udptable, skb);
+			       inet6_iif(skb), inet6_sdif(skb), udptable, skb);
 	if (!sk) {
 		__ICMP6_INC_STATS(net, __in6_dev_get(skb->dev),
 				  ICMP6_MIB_INERRORS);

net/sched/sch_api.c

@@ -1320,7 +1320,6 @@ check_loop_fn(struct Qdisc *q, unsigned long cl, struct qdisc_walker *w)
 
 const struct nla_policy rtm_tca_policy[TCA_MAX + 1] = {
 	[TCA_KIND]		= { .type = NLA_STRING },
-	[TCA_OPTIONS]		= { .type = NLA_NESTED },
 	[TCA_RATE]		= { .type = NLA_BINARY,
 				    .len = sizeof(struct tc_estimator) },
 	[TCA_STAB]		= { .type = NLA_NESTED },

net/smc/smc_core.c

@@ -122,22 +122,17 @@ static void __smc_lgr_unregister_conn(struct smc_connection *conn)
 	sock_put(&smc->sk); /* sock_hold in smc_lgr_register_conn() */
 }
 
-/* Unregister connection and trigger lgr freeing if applicable
+/* Unregister connection from lgr
  */
 static void smc_lgr_unregister_conn(struct smc_connection *conn)
 {
 	struct smc_link_group *lgr = conn->lgr;
-	int reduced = 0;
 
 	write_lock_bh(&lgr->conns_lock);
 	if (conn->alert_token_local) {
-		reduced = 1;
 		__smc_lgr_unregister_conn(conn);
 	}
 	write_unlock_bh(&lgr->conns_lock);
-	if (!reduced || lgr->conns_num)
-		return;
-	smc_lgr_schedule_free_work(lgr);
 }
 
 /* Send delete link, either as client to request the initiation
@@ -291,7 +286,8 @@ out:
 	return rc;
 }
 
-static void smc_buf_unuse(struct smc_connection *conn)
+static void smc_buf_unuse(struct smc_connection *conn,
+			  struct smc_link_group *lgr)
 {
 	if (conn->sndbuf_desc)
 		conn->sndbuf_desc->used = 0;
@@ -301,8 +297,6 @@ static void smc_buf_unuse(struct smc_connection *conn)
 			conn->rmb_desc->used = 0;
 		} else {
 			/* buf registration failed, reuse not possible */
-			struct smc_link_group *lgr = conn->lgr;
-
 			write_lock_bh(&lgr->rmbs_lock);
 			list_del(&conn->rmb_desc->list);
 			write_unlock_bh(&lgr->rmbs_lock);
@@ -315,16 +309,21 @@ static void smc_buf_unuse(struct smc_connection *conn)
 /* remove a finished connection from its link group */
 void smc_conn_free(struct smc_connection *conn)
 {
-	if (!conn->lgr)
+	struct smc_link_group *lgr = conn->lgr;
+
+	if (!lgr)
 		return;
-	if (conn->lgr->is_smcd) {
+	if (lgr->is_smcd) {
 		smc_ism_unset_conn(conn);
 		tasklet_kill(&conn->rx_tsklet);
 	} else {
 		smc_cdc_tx_dismiss_slots(conn);
 	}
-	smc_lgr_unregister_conn(conn);
-	smc_buf_unuse(conn);
+	smc_lgr_unregister_conn(conn);		/* unsets conn->lgr */
+	smc_buf_unuse(conn, lgr);		/* allow buffer reuse */
+
+	if (!lgr->conns_num)
+		smc_lgr_schedule_free_work(lgr);
 }
 
 static void smc_link_clear(struct smc_link *lnk)

tools/testing/selftests/net/fib-onlink-tests.sh

@@ -167,8 +167,8 @@ setup()
 	# add vrf table
 	ip li add ${VRF} type vrf table ${VRF_TABLE}
 	ip li set ${VRF} up
-	ip ro add table ${VRF_TABLE} unreachable default
-	ip -6 ro add table ${VRF_TABLE} unreachable default
+	ip ro add table ${VRF_TABLE} unreachable default metric 8192
+	ip -6 ro add table ${VRF_TABLE} unreachable default metric 8192
 
 	# create test interfaces
 	ip li add ${NETIFS[p1]} type veth peer name ${NETIFS[p2]}
@@ -185,20 +185,20 @@ setup()
 	for n in 1 3 5 7; do
 		ip li set ${NETIFS[p${n}]} up
 		ip addr add ${V4ADDRS[p${n}]}/24 dev ${NETIFS[p${n}]}
-		ip addr add ${V6ADDRS[p${n}]}/64 dev ${NETIFS[p${n}]}
+		ip addr add ${V6ADDRS[p${n}]}/64 dev ${NETIFS[p${n}]} nodad
 	done
 
 	# move peer interfaces to namespace and add addresses
 	for n in 2 4 6 8; do
 		ip li set ${NETIFS[p${n}]} netns ${PEER_NS} up
 		ip -netns ${PEER_NS} addr add ${V4ADDRS[p${n}]}/24 dev ${NETIFS[p${n}]}
-		ip -netns ${PEER_NS} addr add ${V6ADDRS[p${n}]}/64 dev ${NETIFS[p${n}]}
+		ip -netns ${PEER_NS} addr add ${V6ADDRS[p${n}]}/64 dev ${NETIFS[p${n}]} nodad
 	done
 
-	set +e
+	ip -6 ro add default via ${V6ADDRS[p3]/::[0-9]/::64}
+	ip -6 ro add table ${VRF_TABLE} default via ${V6ADDRS[p7]/::[0-9]/::64}
 
-	# let DAD complete - assume default of 1 probe
-	sleep 1
+	set +e
 }
 
 cleanup()