5.4.8-stable review

@@ -166,9 +166,9 @@ static struct posix_clock_operations ptp
 	.read		= ptp_read,
 };
 
-static void delete_ptp_clock(struct posix_clock *pc)
+static void ptp_clock_release(struct device *dev)
 {
-	struct ptp_clock *ptp = container_of(pc, struct ptp_clock, clock);
+	struct ptp_clock *ptp = container_of(dev, struct ptp_clock, dev);
 
 	mutex_destroy(&ptp->tsevq_mux);
 	mutex_destroy(&ptp->pincfg_mux);

@@ -213,7 +213,6 @@ struct ptp_clock *ptp_clock_register(str
 	}
 
 	ptp->clock.ops = ptp_clock_ops;
-	ptp->clock.release = delete_ptp_clock;
 	ptp->info = info;
 	ptp->devid = MKDEV(major, index);
 	ptp->index = index;

@@ -236,15 +235,6 @@ struct ptp_clock *ptp_clock_register(str
 	if (err)
 		goto no_pin_groups;
 
-	/* Create a new device in our class. */
-	ptp->dev = device_create_with_groups(ptp_class, parent, ptp->devid,
-					     ptp, ptp->pin_attr_groups,
-					     "ptp%d", ptp->index);
-	if (IS_ERR(ptp->dev)) {
-		err = PTR_ERR(ptp->dev);
-		goto no_device;
-	}
-
 	/* Register a new PPS source. */
 	if (info->pps) {
 		struct pps_source_info pps;

@@ -260,8 +250,18 @@ struct ptp_clock *ptp_clock_register(str
 		}
 	}
 
-	/* Create a posix clock. */
-	err = posix_clock_register(&ptp->clock, ptp->devid);
+	/* Initialize a new device of our class in our clock structure. */
+	device_initialize(&ptp->dev);
+	ptp->dev.devt = ptp->devid;
+	ptp->dev.class = ptp_class;
+	ptp->dev.parent = parent;
+	ptp->dev.groups = ptp->pin_attr_groups;
+	ptp->dev.release = ptp_clock_release;
+	dev_set_drvdata(&ptp->dev, ptp);
+	dev_set_name(&ptp->dev, "ptp%d", ptp->index);
+
+	/* Create a posix clock and link it to the device. */
+	err = posix_clock_register(&ptp->clock, &ptp->dev);
 	if (err) {
 		pr_err("failed to create posix clock\n");
 		goto no_clock;

@@ -273,8 +273,6 @@ no_clock:
 	if (ptp->pps_source)
 		pps_unregister_source(ptp->pps_source);
 no_pps:
-	device_destroy(ptp_class, ptp->devid);
-no_device:
 	ptp_cleanup_pin_groups(ptp);
 no_pin_groups:
 	if (ptp->kworker)

@@ -304,7 +302,6 @@ int ptp_clock_unregister(struct ptp_cloc
 	if (ptp->pps_source)
 		pps_unregister_source(ptp->pps_source);
 
-	device_destroy(ptp_class, ptp->devid);
 	ptp_cleanup_pin_groups(ptp);
 
 	posix_clock_unregister(&ptp->clock);

@@ -28,7 +28,7 @@ struct timestamp_event_queue {
 
 struct ptp_clock {
 	struct posix_clock clock;
-	struct device *dev;
+	struct device dev;
 	struct ptp_clock_info *info;
 	dev_t devid;
 	int index; /* index into clocks.map */

@@ -69,29 +69,32 @@ struct posix_clock_operations {
  *
  * @ops:     Functional interface to the clock
  * @cdev:    Character device instance for this clock
- * @kref:    Reference count.
+ * @dev:     Pointer to the clock's device.
  * @rwsem:   Protects the 'zombie' field from concurrent access.
  * @zombie:  If 'zombie' is true, then the hardware has disappeared.
- * @release: A function to free the structure when the reference count reaches
- *           zero. May be NULL if structure is statically allocated.
  *
  * Drivers should embed their struct posix_clock within a private
  * structure, obtaining a reference to it during callbacks using
  * container_of().
+ *
+ * Drivers should supply an initialized but not exposed struct device
+ * to posix_clock_register(). It is used to manage lifetime of the
+ * driver's private structure. It's 'release' field should be set to
+ * a release function for this private structure.
  */
 struct posix_clock {
 	struct posix_clock_operations ops;
 	struct cdev cdev;
-	struct kref kref;
+	struct device *dev;
 	struct rw_semaphore rwsem;
 	bool zombie;
-	void (*release)(struct posix_clock *clk);
 };
 
 /**
  * posix_clock_register() - register a new clock
- * @clk:   Pointer to the clock. Caller must provide 'ops' and 'release'
- * @devid: Allocated device id
+ * @clk:   Pointer to the clock. Caller must provide 'ops' field
+ * @dev:   Pointer to the initialized device. Caller must provide
+ *         'release' field
  *
  * A clock driver calls this function to register itself with the
  * clock device subsystem. If 'clk' points to dynamically allocated

@@ -100,7 +103,7 @@ struct posix_clock {
  *
  * Returns zero on success, non-zero otherwise.
  */
-int posix_clock_register(struct posix_clock *clk, dev_t devid);
+int posix_clock_register(struct posix_clock *clk, struct device *dev);
 
 /**
  * posix_clock_unregister() - unregister a clock

@@ -14,8 +14,6 @@
 
 #include "posix-timers.h"
 
-static void delete_clock(struct kref *kref);
-
 /*
  * Returns NULL if the posix_clock instance attached to 'fp' is old and stale.
  */

@@ -125,7 +123,7 @@ static int posix_clock_open(struct inode
 		err = 0;
 
 	if (!err) {
-		kref_get(&clk->kref);
+		get_device(clk->dev);
 		fp->private_data = clk;
 	}
 out:

@@ -141,7 +139,7 @@ static int posix_clock_release(struct in
 	if (clk->ops.release)
 		err = clk->ops.release(clk);
 
-	kref_put(&clk->kref, delete_clock);
+	put_device(clk->dev);
 
 	fp->private_data = NULL;
 

@@ -161,38 +159,35 @@ static const struct file_operations posi
 #endif
 };
 
-int posix_clock_register(struct posix_clock *clk, dev_t devid)
+int posix_clock_register(struct posix_clock *clk, struct device *dev)
 {
 	int err;
 
-	kref_init(&clk->kref);
 	init_rwsem(&clk->rwsem);
 
 	cdev_init(&clk->cdev, &posix_clock_file_operations);
+	err = cdev_device_add(&clk->cdev, dev);
+	if (err) {
+		pr_err("%s unable to add device %d:%d\n",
+			dev_name(dev), MAJOR(dev->devt), MINOR(dev->devt));
+		return err;
+	}
 	clk->cdev.owner = clk->ops.owner;
-	err = cdev_add(&clk->cdev, devid, 1);
+	clk->dev = dev;
 
-	return err;
+	return 0;
 }
 EXPORT_SYMBOL_GPL(posix_clock_register);
 
-static void delete_clock(struct kref *kref)
-{
-	struct posix_clock *clk = container_of(kref, struct posix_clock, kref);
-
-	if (clk->release)
-		clk->release(clk);
-}
-
 void posix_clock_unregister(struct posix_clock *clk)
 {
-	cdev_del(&clk->cdev);
+	cdev_device_del(&clk->cdev, clk->dev);
 
 	down_write(&clk->rwsem);
 	clk->zombie = true;
 	up_write(&clk->rwsem);
 
-	kref_put(&clk->kref, delete_clock);
+	put_device(clk->dev);
 }
 EXPORT_SYMBOL_GPL(posix_clock_unregister);
 

@@ -72,6 +72,9 @@ static void tcp_event_new_data_sent(stru
 	__skb_unlink(skb, &sk->sk_write_queue);
 	tcp_rbtree_insert(&sk->tcp_rtx_queue, skb);
 
+	if (tp->highest_sack == NULL)
+		tp->highest_sack = skb;
+
 	tp->packets_out += tcp_skb_pcount(skb);
 	if (!prior_packets || icsk->icsk_pending == ICSK_TIME_LOSS_PROBE)
 		tcp_rearm_rto(sk);

@@ -1475,7 +1475,7 @@ int __udp_enqueue_schedule_skb(struct so
 	 * queue contains some other skb
 	 */
 	rmem = atomic_add_return(size, &sk->sk_rmem_alloc);
-	if (rmem > (size + sk->sk_rcvbuf))
+	if (rmem > (size + (unsigned int)sk->sk_rcvbuf))
 		goto uncharge_drop;
 
 	spin_lock(&list->lock);

@@ -113,8 +113,10 @@ static int bnxt_req_msix_vecs(struct bnx
 {
 	struct net_device *dev = edev->net;
 	struct bnxt *bp = netdev_priv(dev);
+	struct bnxt_hw_resc *hw_resc;
 	int max_idx, max_cp_rings;
 	int avail_msix, idx;
+	int total_vecs;
 	int rc = 0;
 
 	ASSERT_RTNL();

@@ -142,7 +144,10 @@ static int bnxt_req_msix_vecs(struct bnx
 	}
 	edev->ulp_tbl[ulp_id].msix_base = idx;
 	edev->ulp_tbl[ulp_id].msix_requested = avail_msix;
-	if (bp->total_irqs < (idx + avail_msix)) {
+	hw_resc = &bp->hw_resc;
+	total_vecs = idx + avail_msix;
+	if (bp->total_irqs < total_vecs ||
+	    (BNXT_NEW_RM(bp) && hw_resc->resv_irqs < total_vecs)) {
 		if (netif_running(dev)) {
 			bnxt_close_nic(bp, true, false);
 			rc = bnxt_open_nic(bp, true, false);

@@ -156,7 +161,6 @@ static int bnxt_req_msix_vecs(struct bnx
 	}
 
 	if (BNXT_NEW_RM(bp)) {
-		struct bnxt_hw_resc *hw_resc = &bp->hw_resc;
 		int resv_msix;
 
 		resv_msix = hw_resc->resv_irqs - bp->cp_nr_rings;

@@ -8766,6 +8766,9 @@ static int bnxt_hwrm_if_change(struct bn
 	}
 	if (resc_reinit || fw_reset) {
 		if (fw_reset) {
+			bnxt_free_ctx_mem(bp);
+			kfree(bp->ctx);
+			bp->ctx = NULL;
 			rc = bnxt_fw_init_one(bp);
 			if (rc) {
 				set_bit(BNXT_STATE_ABORT_ERR, &bp->state);

@@ -3064,8 +3064,15 @@ static int bnxt_hwrm_dbg_dma_data(struct
 			}
 		}
 
-		if (info->dest_buf)
-			memcpy(info->dest_buf + off, dma_buf, len);
+		if (info->dest_buf) {
+			if ((info->seg_start + off + len) <=
+			    BNXT_COREDUMP_BUF_LEN(info->buf_len)) {
+				memcpy(info->dest_buf + off, dma_buf, len);
+			} else {
+				rc = -ENOBUFS;
+				break;
+			}
+		}
 
 		if (cmn_req->req_type ==
 				cpu_to_le16(HWRM_DBG_COREDUMP_RETRIEVE))

@@ -3119,7 +3126,7 @@ static int bnxt_hwrm_dbg_coredump_initia
 
 static int bnxt_hwrm_dbg_coredump_retrieve(struct bnxt *bp, u16 component_id,
 					   u16 segment_id, u32 *seg_len,
-					   void *buf, u32 offset)
+					   void *buf, u32 buf_len, u32 offset)
 {
 	struct hwrm_dbg_coredump_retrieve_input req = {0};
 	struct bnxt_hwrm_dbg_dma_info info = {NULL};

@@ -3134,8 +3141,11 @@ static int bnxt_hwrm_dbg_coredump_retrie
 				seq_no);
 	info.data_len_off = offsetof(struct hwrm_dbg_coredump_retrieve_output,
 				     data_len);
-	if (buf)
+	if (buf) {
 		info.dest_buf = buf + offset;
+		info.buf_len = buf_len;
+		info.seg_start = offset;
+	}
 
 	rc = bnxt_hwrm_dbg_dma_data(bp, &req, sizeof(req), &info);
 	if (!rc)

@@ -3225,14 +3235,17 @@ bnxt_fill_coredump_record(struct bnxt *b
 static int bnxt_get_coredump(struct bnxt *bp, void *buf, u32 *dump_len)
 {
 	u32 ver_get_resp_len = sizeof(struct hwrm_ver_get_output);
+	u32 offset = 0, seg_hdr_len, seg_record_len, buf_len = 0;
 	struct coredump_segment_record *seg_record = NULL;
-	u32 offset = 0, seg_hdr_len, seg_record_len;
 	struct bnxt_coredump_segment_hdr seg_hdr;
 	struct bnxt_coredump coredump = {NULL};
 	time64_t start_time;
 	u16 start_utc;
 	int rc = 0, i;
 
+	if (buf)
+		buf_len = *dump_len;
+
 	start_time = ktime_get_real_seconds();
 	start_utc = sys_tz.tz_minuteswest * 60;
 	seg_hdr_len = sizeof(seg_hdr);

@@ -3265,6 +3278,12 @@ static int bnxt_get_coredump(struct bnxt
 		u32 duration = 0, seg_len = 0;
 		unsigned long start, end;
 
+		if (buf && ((offset + seg_hdr_len) >
+			    BNXT_COREDUMP_BUF_LEN(buf_len))) {
+			rc = -ENOBUFS;
+			goto err;
+		}
+
 		start = jiffies;
 
 		rc = bnxt_hwrm_dbg_coredump_initiate(bp, comp_id, seg_id);

@@ -3277,9 +3296,11 @@ static int bnxt_get_coredump(struct bnxt
 
 		/* Write segment data into the buffer */
 		rc = bnxt_hwrm_dbg_coredump_retrieve(bp, comp_id, seg_id,
-						     &seg_len, buf,
+						     &seg_len, buf, buf_len,
 						     offset + seg_hdr_len);
-		if (rc)
+		if (rc && rc == -ENOBUFS)
+			goto err;
+		else if (rc)
 			netdev_err(bp->dev,
 				   "Failed to retrieve coredump for seg = %d\n",
 				   seg_record->segment_id);

@@ -3309,7 +3330,8 @@ err:
 					  rc);
 	kfree(coredump.data);
 	*dump_len += sizeof(struct bnxt_coredump_record);
-
+	if (rc == -ENOBUFS)
+		netdev_err(bp->dev, "Firmware returned large coredump buffer");
 	return rc;
 }
 

@@ -31,6 +31,8 @@ struct bnxt_coredump {
 	u16		total_segs;
 };
 
+#define BNXT_COREDUMP_BUF_LEN(len) ((len) - sizeof(struct bnxt_coredump_record))
+
 struct bnxt_hwrm_dbg_dma_info {
 	void *dest_buf;
 	int dest_buf_size;

@@ -38,6 +40,8 @@ struct bnxt_hwrm_dbg_dma_info {
 	u16 seq_off;
 	u16 data_len_off;
 	u16 segs;
+	u32 seg_start;
+	u32 buf_len;
 };
 
 struct hwrm_dbg_cmn_input {

@@ -1995,6 +1995,9 @@ static int bnxt_async_event_process(stru
 	case ASYNC_EVENT_CMPL_EVENT_ID_RESET_NOTIFY: {
 		u32 data1 = le32_to_cpu(cmpl->event_data1);
 
+		if (!bp->fw_health)
+			goto async_event_process_exit;
+
 		bp->fw_reset_timestamp = jiffies;
 		bp->fw_reset_min_dsecs = cmpl->timestamp_lo;
 		if (!bp->fw_reset_min_dsecs)

@@ -4438,8 +4441,9 @@ static int bnxt_hwrm_func_drv_rgtr(struc
 			    FUNC_DRV_RGTR_REQ_ENABLES_VER);
 
 	req.os_type = cpu_to_le16(FUNC_DRV_RGTR_REQ_OS_TYPE_LINUX);
-	flags = FUNC_DRV_RGTR_REQ_FLAGS_16BIT_VER_MODE |
-		FUNC_DRV_RGTR_REQ_FLAGS_HOT_RESET_SUPPORT;
+	flags = FUNC_DRV_RGTR_REQ_FLAGS_16BIT_VER_MODE;
+	if (bp->fw_cap & BNXT_FW_CAP_HOT_RESET)
+		flags |= FUNC_DRV_RGTR_REQ_FLAGS_HOT_RESET_SUPPORT;
 	if (bp->fw_cap & BNXT_FW_CAP_ERROR_RECOVERY)
 		flags |= FUNC_DRV_RGTR_REQ_FLAGS_ERROR_RECOVERY_SUPPORT;
 	req.flags = cpu_to_le32(flags);

@@ -7096,14 +7100,6 @@ static int bnxt_hwrm_error_recovery_qcfg
 	rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT);
 	if (rc)
 		goto err_recovery_out;
-	if (!fw_health) {
-		fw_health = kzalloc(sizeof(*fw_health), GFP_KERNEL);
-		bp->fw_health = fw_health;
-		if (!fw_health) {
-			rc = -ENOMEM;
-			goto err_recovery_out;
-		}
-	}
 	fw_health->flags = le32_to_cpu(resp->flags);
 	if ((fw_health->flags & ERROR_RECOVERY_QCFG_RESP_FLAGS_CO_CPU) &&
 	    !(bp->fw_cap & BNXT_FW_CAP_KONG_MB_CHNL)) {

@@ -10419,6 +10415,23 @@ static void bnxt_init_dflt_coal(struct b
 	bp->stats_coal_ticks = BNXT_DEF_STATS_COAL_TICKS;
 }
 
+static void bnxt_alloc_fw_health(struct bnxt *bp)
+{
+	if (bp->fw_health)
+		return;
+
+	if (!(bp->fw_cap & BNXT_FW_CAP_HOT_RESET) &&
+	    !(bp->fw_cap & BNXT_FW_CAP_ERROR_RECOVERY))
+		return;
+
+	bp->fw_health = kzalloc(sizeof(*bp->fw_health), GFP_KERNEL);
+	if (!bp->fw_health) {
+		netdev_warn(bp->dev, "Failed to allocate fw_health\n");
+		bp->fw_cap &= ~BNXT_FW_CAP_HOT_RESET;
+		bp->fw_cap &= ~BNXT_FW_CAP_ERROR_RECOVERY;
+	}
+}
+
 static int bnxt_fw_init_one_p1(struct bnxt *bp)
 {
 	int rc;

@@ -10465,6 +10478,7 @@ static int bnxt_fw_init_one_p2(struct bn
 		netdev_warn(bp->dev, "hwrm query adv flow mgnt failure rc: %d\n",
 			    rc);
 
+	bnxt_alloc_fw_health(bp);
 	rc = bnxt_hwrm_error_recovery_qcfg(bp);
 	if (rc)
 		netdev_warn(bp->dev, "hwrm query error recovery failure rc: %d\n",

@@ -11344,6 +11358,8 @@ static void bnxt_remove_one(struct pci_d
 	bnxt_dcb_free(bp);
 	kfree(bp->edev);
 	bp->edev = NULL;
+	kfree(bp->fw_health);
+	bp->fw_health = NULL;
 	bnxt_cleanup_pci(bp);
 	bnxt_free_ctx_mem(bp);
 	kfree(bp->ctx);

@@ -1658,6 +1658,7 @@ struct bnxt {
 	#define BNXT_FW_CAP_PCIE_STATS_SUPPORTED	0x00020000
 	#define BNXT_FW_CAP_EXT_STATS_SUPPORTED		0x00040000
 	#define BNXT_FW_CAP_ERR_RECOVER_RELOAD		0x00100000
+	#define BNXT_FW_CAP_HOT_RESET			0x00200000
 
 #define BNXT_NEW_RM(bp)		((bp)->fw_cap & BNXT_FW_CAP_NEW_RM)
 	u32			hwrm_spec_code;

@@ -9953,8 +9953,7 @@ static void bnxt_fw_health_check(struct
 	struct bnxt_fw_health *fw_health = bp->fw_health;
 	u32 val;
 
-	if (!fw_health || !fw_health->enabled ||
-	    test_bit(BNXT_STATE_IN_FW_RESET, &bp->state))
+	if (!fw_health->enabled || test_bit(BNXT_STATE_IN_FW_RESET, &bp->state))
 		return;
 
 	if (fw_health->tmr_counter) {

@@ -10697,8 +10696,7 @@ static void bnxt_fw_reset_task(struct wo
 		bnxt_queue_fw_reset_work(bp, bp->fw_reset_min_dsecs * HZ / 10);
 		return;
 	case BNXT_FW_RESET_STATE_ENABLE_DEV:
-		if (test_bit(BNXT_STATE_FW_FATAL_COND, &bp->state) &&
-		    bp->fw_health) {
+		if (test_bit(BNXT_STATE_FW_FATAL_COND, &bp->state)) {
 			u32 val;
 
 			val = bnxt_fw_health_readl(bp,

@@ -19,11 +19,10 @@ static int bnxt_fw_reporter_diagnose(str
 				     struct devlink_fmsg *fmsg)
 {
 	struct bnxt *bp = devlink_health_reporter_priv(reporter);
-	struct bnxt_fw_health *health = bp->fw_health;
 	u32 val, health_status;
 	int rc;
 
-	if (!health || test_bit(BNXT_STATE_IN_FW_RESET, &bp->state))
+	if (test_bit(BNXT_STATE_IN_FW_RESET, &bp->state))
 		return 0;
 
 	val = bnxt_fw_health_readl(bp, BNXT_FW_HEALTH_REG);

@@ -162,9 +161,6 @@ void bnxt_devlink_health_report(struct b
 	struct bnxt_fw_health *fw_health = bp->fw_health;
 	struct bnxt_fw_reporter_ctx fw_reporter_ctx;
 
-	if (!fw_health)
-		return;
-
 	fw_reporter_ctx.sp_event = event;
 	switch (event) {
 	case BNXT_FW_RESET_NOTIFY_SP_EVENT:

@@ -10563,6 +10563,12 @@ static int bnxt_fw_init_one(struct bnxt
 	rc = bnxt_approve_mac(bp, bp->dev->dev_addr, false);
 	if (rc)
 		return rc;
+
+	/* In case fw capabilities have changed, destroy the unneeded
+	 * reporters and create newly capable ones.
+	 */
+	bnxt_dl_fw_reporters_destroy(bp, false);
+	bnxt_dl_fw_reporters_create(bp);
 	bnxt_fw_init_one_p3(bp);
 	return 0;
 }

@@ -11339,6 +11345,7 @@ static void bnxt_remove_one(struct pci_d
 
 	if (BNXT_PF(bp)) {
 		bnxt_sriov_disable(bp);
+		bnxt_dl_fw_reporters_destroy(bp, true);
 		bnxt_dl_unregister(bp);
 	}
 

@@ -11837,8 +11844,10 @@ static int bnxt_init_one(struct pci_dev
 	if (rc)
 		goto init_err_cleanup_tc;
 
-	if (BNXT_PF(bp))
+	if (BNXT_PF(bp)) {
 		bnxt_dl_register(bp);
+		bnxt_dl_fw_reporters_create(bp);
+	}
 
 	netdev_info(dev, "%s found at mem %lx, node addr %pM\n",
 		    board_info[ent->driver_data].name,

112 lines not on this page · raw message

@@ -57,6 +57,8 @@ struct bnxt_dl_nvm_param {
 };
 
 void bnxt_devlink_health_report(struct bnxt *bp, unsigned long event);
+void bnxt_dl_fw_reporters_create(struct bnxt *bp);
+void bnxt_dl_fw_reporters_destroy(struct bnxt *bp, bool all);
 int bnxt_dl_register(struct bnxt *bp);
 void bnxt_dl_unregister(struct bnxt *bp);
 

@@ -11343,12 +11343,11 @@ static void bnxt_remove_one(struct pci_d
 	struct net_device *dev = pci_get_drvdata(pdev);
 	struct bnxt *bp = netdev_priv(dev);
 
-	if (BNXT_PF(bp)) {
+	if (BNXT_PF(bp))
 		bnxt_sriov_disable(bp);
-		bnxt_dl_fw_reporters_destroy(bp, true);
-		bnxt_dl_unregister(bp);
-	}
 
+	bnxt_dl_fw_reporters_destroy(bp, true);
+	bnxt_dl_unregister(bp);
 	pci_disable_pcie_error_reporting(pdev);
 	unregister_netdev(dev);
 	bnxt_shutdown_tc(bp);

@@ -11844,10 +11843,8 @@ static int bnxt_init_one(struct pci_dev
 	if (rc)
 		goto init_err_cleanup_tc;
 
-	if (BNXT_PF(bp)) {
-		bnxt_dl_register(bp);
-		bnxt_dl_fw_reporters_create(bp);
-	}
+	bnxt_dl_register(bp);
+	bnxt_dl_fw_reporters_create(bp);
 
 	netdev_info(dev, "%s found at mem %lx, node addr %pM\n",
 		    board_info[ent->driver_data].name,

@@ -226,6 +226,8 @@ static const struct devlink_ops bnxt_dl_
 #endif /* CONFIG_BNXT_SRIOV */
 };
 
+static const struct devlink_ops bnxt_vf_dl_ops;
+
 enum bnxt_dl_param_id {
 	BNXT_DEVLINK_PARAM_ID_BASE = DEVLINK_PARAM_GENERIC_ID_MAX,
 	BNXT_DEVLINK_PARAM_ID_GRE_VER_CHECK,

@@ -439,7 +441,10 @@ int bnxt_dl_register(struct bnxt *bp)
 		return -ENOTSUPP;
 	}
 
-	dl = devlink_alloc(&bnxt_dl_ops, sizeof(struct bnxt_dl));
+	if (BNXT_PF(bp))
+		dl = devlink_alloc(&bnxt_dl_ops, sizeof(struct bnxt_dl));
+	else
+		dl = devlink_alloc(&bnxt_vf_dl_ops, sizeof(struct bnxt_dl));
 	if (!dl) {
 		netdev_warn(bp->dev, "devlink_alloc failed");
 		return -ENOMEM;

@@ -458,6 +463,9 @@ int bnxt_dl_register(struct bnxt *bp)
 		goto err_dl_free;
 	}
 
+	if (!BNXT_PF(bp))
+		return 0;
+
 	rc = devlink_params_register(dl, bnxt_dl_params,
 				     ARRAY_SIZE(bnxt_dl_params));
 	if (rc) {

@@ -507,11 +515,14 @@ void bnxt_dl_unregister(struct bnxt *bp)
 	if (!dl)
 		return;
 
-	devlink_port_params_unregister(&bp->dl_port, bnxt_dl_port_params,
-				       ARRAY_SIZE(bnxt_dl_port_params));
-	devlink_port_unregister(&bp->dl_port);
-	devlink_params_unregister(dl, bnxt_dl_params,
-				  ARRAY_SIZE(bnxt_dl_params));
+	if (BNXT_PF(bp)) {
+		devlink_port_params_unregister(&bp->dl_port,
+					       bnxt_dl_port_params,
+					       ARRAY_SIZE(bnxt_dl_port_params));
+		devlink_port_unregister(&bp->dl_port);
+		devlink_params_unregister(dl, bnxt_dl_params,
+					  ARRAY_SIZE(bnxt_dl_params));
+	}
 	devlink_unregister(dl);
 	devlink_free(dl);
 }

@@ -6985,6 +6985,9 @@ static int mlxsw_sp_router_port_check_ri
 
 	for (i = 0; i < MLXSW_CORE_RES_GET(mlxsw_sp->core, MAX_RIFS); i++) {
 		rif = mlxsw_sp->router->rifs[i];
+		if (rif && rif->ops &&
+		    rif->ops->type == MLXSW_SP_RIF_TYPE_IPIP_LB)
+			continue;
 		if (rif && rif->dev && rif->dev != dev &&
 		    !ether_addr_equal_masked(rif->dev->dev_addr, dev_addr,
 					     mlxsw_sp->mac_mask)) {

@@ -5421,6 +5421,7 @@ enum mlxsw_reg_htgt_trap_group {
 	MLXSW_REG_HTGT_TRAP_GROUP_SP_LBERROR,
 	MLXSW_REG_HTGT_TRAP_GROUP_SP_PTP0,
 	MLXSW_REG_HTGT_TRAP_GROUP_SP_PTP1,
+	MLXSW_REG_HTGT_TRAP_GROUP_SP_VRRP,
 
 	__MLXSW_REG_HTGT_TRAP_GROUP_MAX,
 	MLXSW_REG_HTGT_TRAP_GROUP_MAX = __MLXSW_REG_HTGT_TRAP_GROUP_MAX - 1

@@ -4398,8 +4398,8 @@ static const struct mlxsw_listener mlxsw
 	MLXSW_SP_RXL_MARK(ROUTER_ALERT_IPV6, TRAP_TO_CPU, ROUTER_EXP, false),
 	MLXSW_SP_RXL_MARK(IPIP_DECAP_ERROR, TRAP_TO_CPU, ROUTER_EXP, false),
 	MLXSW_SP_RXL_MARK(DECAP_ECN0, TRAP_TO_CPU, ROUTER_EXP, false),
-	MLXSW_SP_RXL_MARK(IPV4_VRRP, TRAP_TO_CPU, ROUTER_EXP, false),
-	MLXSW_SP_RXL_MARK(IPV6_VRRP, TRAP_TO_CPU, ROUTER_EXP, false),
+	MLXSW_SP_RXL_MARK(IPV4_VRRP, TRAP_TO_CPU, VRRP, false),
+	MLXSW_SP_RXL_MARK(IPV6_VRRP, TRAP_TO_CPU, VRRP, false),
 	/* PKT Sample trap */
 	MLXSW_RXL(mlxsw_sp_rx_listener_sample_func, PKT_SAMPLE, MIRROR_TO_CPU,
 		  false, SP_IP2ME, DISCARD),

@@ -4483,6 +4483,10 @@ static int mlxsw_sp_cpu_policers_set(str
 			rate = 19 * 1024;
 			burst_size = 12;
 			break;
+		case MLXSW_REG_HTGT_TRAP_GROUP_SP_VRRP:
+			rate = 360;
+			burst_size = 7;
+			break;
 		default:
 			continue;
 		}

@@ -4522,6 +4526,7 @@ static int mlxsw_sp_trap_groups_set(stru
 		case MLXSW_REG_HTGT_TRAP_GROUP_SP_OSPF:
 		case MLXSW_REG_HTGT_TRAP_GROUP_SP_PIM:
 		case MLXSW_REG_HTGT_TRAP_GROUP_SP_PTP0:
+		case MLXSW_REG_HTGT_TRAP_GROUP_SP_VRRP:
 			priority = 5;
 			tc = 5;
 			break;

@@ -541,7 +541,7 @@ static int gtp_build_skb_ip4(struct sk_b
 		mtu = dst_mtu(&rt->dst);
 	}
 
-	rt->dst.ops->update_pmtu(&rt->dst, NULL, skb, mtu);
+	rt->dst.ops->update_pmtu(&rt->dst, NULL, skb, mtu, true);
 
 	if (!skb_is_gso(skb) && (iph->frag_off & htons(IP_DF)) &&
 	    mtu < ntohs(iph->tot_len)) {

@@ -516,7 +516,7 @@ static inline void skb_dst_update_pmtu(s
 	struct dst_entry *dst = skb_dst(skb);
 
 	if (dst && dst->ops->update_pmtu)
-		dst->ops->update_pmtu(dst, NULL, skb, mtu);
+		dst->ops->update_pmtu(dst, NULL, skb, mtu, true);
 }
 
 static inline void skb_tunnel_check_pmtu(struct sk_buff *skb,

@@ -27,7 +27,8 @@ struct dst_ops {
 	struct dst_entry *	(*negative_advice)(struct dst_entry *);
 	void			(*link_failure)(struct sk_buff *);
 	void			(*update_pmtu)(struct dst_entry *dst, struct sock *sk,
-					       struct sk_buff *skb, u32 mtu);
+					       struct sk_buff *skb, u32 mtu,
+					       bool confirm_neigh);
 	void			(*redirect)(struct dst_entry *dst, struct sock *sk,
 					    struct sk_buff *skb);
 	int			(*local_out)(struct net *net, struct sock *sk, struct sk_buff *skb);

@@ -22,7 +22,8 @@
 #endif
 
 static void fake_update_pmtu(struct dst_entry *dst, struct sock *sk,
-			     struct sk_buff *skb, u32 mtu)
+			     struct sk_buff *skb, u32 mtu,
+			     bool confirm_neigh)
 {
 }
 

@@ -110,7 +110,8 @@ static void dn_dst_ifdown(struct dst_ent
 static struct dst_entry *dn_dst_negative_advice(struct dst_entry *);
 static void dn_dst_link_failure(struct sk_buff *);
 static void dn_dst_update_pmtu(struct dst_entry *dst, struct sock *sk,
-			       struct sk_buff *skb , u32 mtu);
+			       struct sk_buff *skb , u32 mtu,
+			       bool confirm_neigh);
 static void dn_dst_redirect(struct dst_entry *dst, struct sock *sk,
 			    struct sk_buff *skb);
 static struct neighbour *dn_dst_neigh_lookup(const struct dst_entry *dst,

@@ -251,7 +252,8 @@ static int dn_dst_gc(struct dst_ops *ops
  * advertise to the other end).
  */
 static void dn_dst_update_pmtu(struct dst_entry *dst, struct sock *sk,
-			       struct sk_buff *skb, u32 mtu)
+			       struct sk_buff *skb, u32 mtu,
+			       bool confirm_neigh)
 {
 	struct dn_route *rt = (struct dn_route *) dst;
 	struct neighbour *n = rt->n;

@@ -1086,7 +1086,7 @@ struct dst_entry *inet_csk_update_pmtu(s
 		if (!dst)
 			goto out;
 	}
-	dst->ops->update_pmtu(dst, sk, NULL, mtu);
+	dst->ops->update_pmtu(dst, sk, NULL, mtu, true);
 
 	dst = __sk_dst_check(sk, 0);
 	if (!dst)

@@ -139,7 +139,8 @@ static unsigned int	 ipv4_mtu(const stru
 static struct dst_entry *ipv4_negative_advice(struct dst_entry *dst);
 static void		 ipv4_link_failure(struct sk_buff *skb);
 static void		 ip_rt_update_pmtu(struct dst_entry *dst, struct sock *sk,
-					   struct sk_buff *skb, u32 mtu);
+					   struct sk_buff *skb, u32 mtu,
+					   bool confirm_neigh);
 static void		 ip_do_redirect(struct dst_entry *dst, struct sock *sk,
 					struct sk_buff *skb);
 static void		ipv4_dst_destroy(struct dst_entry *dst);

@@ -1043,7 +1044,8 @@ static void __ip_rt_update_pmtu(struct r
 }
 
 static void ip_rt_update_pmtu(struct dst_entry *dst, struct sock *sk,
-			      struct sk_buff *skb, u32 mtu)
+			      struct sk_buff *skb, u32 mtu,
+			      bool confirm_neigh)
 {
 	struct rtable *rt = (struct rtable *) dst;
 	struct flowi4 fl4;

@@ -2648,7 +2650,8 @@ static unsigned int ipv4_blackhole_mtu(c
 }
 
 static void ipv4_rt_blackhole_update_pmtu(struct dst_entry *dst, struct sock *sk,
-					  struct sk_buff *skb, u32 mtu)
+					  struct sk_buff *skb, u32 mtu,
+					  bool confirm_neigh)
 {
 }
 

@@ -100,12 +100,13 @@ static int xfrm4_fill_dst(struct xfrm_ds
 }
 
 static void xfrm4_update_pmtu(struct dst_entry *dst, struct sock *sk,
-			      struct sk_buff *skb, u32 mtu)
+			      struct sk_buff *skb, u32 mtu,
+			      bool confirm_neigh)
 {
 	struct xfrm_dst *xdst = (struct xfrm_dst *)dst;
 	struct dst_entry *path = xdst->route;
 
-	path->ops->update_pmtu(path, sk, skb, mtu);
+	path->ops->update_pmtu(path, sk, skb, mtu, confirm_neigh);
 }
 
 static void xfrm4_redirect(struct dst_entry *dst, struct sock *sk,

@@ -146,7 +146,7 @@ struct dst_entry *inet6_csk_update_pmtu(
 
 	if (IS_ERR(dst))
 		return NULL;
-	dst->ops->update_pmtu(dst, sk, NULL, mtu);
+	dst->ops->update_pmtu(dst, sk, NULL, mtu, true);
 
 	dst = inet6_csk_route_socket(sk, &fl6);
 	return IS_ERR(dst) ? NULL : dst;

@@ -1040,7 +1040,7 @@ static netdev_tx_t ip6erspan_tunnel_xmit
 
 	/* TooBig packet may have updated dst->dev's mtu */
 	if (!t->parms.collect_md && dst && dst_mtu(dst) > dst->dev->mtu)
-		dst->ops->update_pmtu(dst, NULL, skb, dst->dev->mtu);
+		dst->ops->update_pmtu(dst, NULL, skb, dst->dev->mtu, true);
 
 	err = ip6_tnl_xmit(skb, dev, dsfield, &fl6, encap_limit, &mtu,
 			   NEXTHDR_GRE);

@@ -95,7 +95,8 @@ static int		ip6_pkt_prohibit(struct sk_b
 static int		ip6_pkt_prohibit_out(struct net *net, struct sock *sk, struct sk_buff *skb);
 static void		ip6_link_failure(struct sk_buff *skb);
 static void		ip6_rt_update_pmtu(struct dst_entry *dst, struct sock *sk,
-					   struct sk_buff *skb, u32 mtu);
+					   struct sk_buff *skb, u32 mtu,
+					   bool confirm_neigh);
 static void		rt6_do_redirect(struct dst_entry *dst, struct sock *sk,
 					struct sk_buff *skb);
 static int rt6_score_route(const struct fib6_nh *nh, u32 fib6_flags, int oif,

@@ -264,7 +265,8 @@ static unsigned int ip6_blackhole_mtu(co
 }
 
 static void ip6_rt_blackhole_update_pmtu(struct dst_entry *dst, struct sock *sk,
-					 struct sk_buff *skb, u32 mtu)
+					 struct sk_buff *skb, u32 mtu,
+					 bool confirm_neigh)
 {
 }
 

@@ -2695,7 +2697,8 @@ static bool rt6_cache_allowed_for_pmtu(c
 }
 
 static void __ip6_rt_update_pmtu(struct dst_entry *dst, const struct sock *sk,
-				 const struct ipv6hdr *iph, u32 mtu)
+				 const struct ipv6hdr *iph, u32 mtu,
+				 bool confirm_neigh)
 {
 	const struct in6_addr *daddr, *saddr;
 	struct rt6_info *rt6 = (struct rt6_info *)dst;

@@ -2713,7 +2716,10 @@ static void __ip6_rt_update_pmtu(struct
 		daddr = NULL;
 		saddr = NULL;
 	}
-	dst_confirm_neigh(dst, daddr);
+
+	if (confirm_neigh)
+		dst_confirm_neigh(dst, daddr);
+
 	mtu = max_t(u32, mtu, IPV6_MIN_MTU);
 	if (mtu >= dst_mtu(dst))
 		return;

@@ -2767,9 +2773,11 @@ out_unlock:
 }
 
 static void ip6_rt_update_pmtu(struct dst_entry *dst, struct sock *sk,
-			       struct sk_buff *skb, u32 mtu)
+			       struct sk_buff *skb, u32 mtu,
+			       bool confirm_neigh)
 {
-	__ip6_rt_update_pmtu(dst, sk, skb ? ipv6_hdr(skb) : NULL, mtu);
+	__ip6_rt_update_pmtu(dst, sk, skb ? ipv6_hdr(skb) : NULL, mtu,
+			     confirm_neigh);
 }
 
 void ip6_update_pmtu(struct sk_buff *skb, struct net *net, __be32 mtu,

@@ -2788,7 +2796,7 @@ void ip6_update_pmtu(struct sk_buff *skb
 
 	dst = ip6_route_output(net, NULL, &fl6);
 	if (!dst->error)
-		__ip6_rt_update_pmtu(dst, NULL, iph, ntohl(mtu));
+		__ip6_rt_update_pmtu(dst, NULL, iph, ntohl(mtu), true);
 	dst_release(dst);
 }
 EXPORT_SYMBOL_GPL(ip6_update_pmtu);

@@ -98,12 +98,13 @@ static int xfrm6_fill_dst(struct xfrm_ds
 }
 
 static void xfrm6_update_pmtu(struct dst_entry *dst, struct sock *sk,
-			      struct sk_buff *skb, u32 mtu)
+			      struct sk_buff *skb, u32 mtu,
+			      bool confirm_neigh)
 {
 	struct xfrm_dst *xdst = (struct xfrm_dst *)dst;
 	struct dst_entry *path = xdst->route;
 
-	path->ops->update_pmtu(path, sk, skb, mtu);
+	path->ops->update_pmtu(path, sk, skb, mtu, confirm_neigh);
 }
 
 static void xfrm6_redirect(struct dst_entry *dst, struct sock *sk,

@@ -208,7 +208,7 @@ static inline void maybe_update_pmtu(int
 	struct rtable *ort = skb_rtable(skb);
 
 	if (!skb->dev && sk && sk_fullsock(sk))
-		ort->dst.ops->update_pmtu(&ort->dst, sk, NULL, mtu);
+		ort->dst.ops->update_pmtu(&ort->dst, sk, NULL, mtu, true);
 }
 
 static inline bool ensure_mtu_is_adequate(struct netns_ipvs *ipvs, int skb_af,

@@ -263,7 +263,7 @@ bool sctp_transport_update_pmtu(struct s
 
 		pf->af->from_sk(&addr, sk);
 		pf->to_sk_daddr(&t->ipaddr, sk);
-		dst->ops->update_pmtu(dst, sk, NULL, pmtu);
+		dst->ops->update_pmtu(dst, sk, NULL, pmtu, true);
 		pf->to_sk_daddr(&addr, sk);
 
 		dst = sctp_transport_dst_check(t);

@@ -1040,7 +1040,7 @@ static netdev_tx_t ip6erspan_tunnel_xmit
 
 	/* TooBig packet may have updated dst->dev's mtu */
 	if (!t->parms.collect_md && dst && dst_mtu(dst) > dst->dev->mtu)
-		dst->ops->update_pmtu(dst, NULL, skb, dst->dev->mtu, true);
+		dst->ops->update_pmtu(dst, NULL, skb, dst->dev->mtu, false);
 
 	err = ip6_tnl_xmit(skb, dev, dsfield, &fl6, encap_limit, &mtu,
 			   NEXTHDR_GRE);

@@ -541,7 +541,7 @@ static int gtp_build_skb_ip4(struct sk_b
 		mtu = dst_mtu(&rt->dst);
 	}
 
-	rt->dst.ops->update_pmtu(&rt->dst, NULL, skb, mtu, true);
+	rt->dst.ops->update_pmtu(&rt->dst, NULL, skb, mtu, false);
 
 	if (!skb_is_gso(skb) && (iph->frag_off & htons(IP_DF)) &&
 	    mtu < ntohs(iph->tot_len)) {

@@ -519,6 +519,15 @@ static inline void skb_dst_update_pmtu(s
 		dst->ops->update_pmtu(dst, NULL, skb, mtu, true);
 }
 
+/* update dst pmtu but not do neighbor confirm */
+static inline void skb_dst_update_pmtu_no_confirm(struct sk_buff *skb, u32 mtu)
+{
+	struct dst_entry *dst = skb_dst(skb);
+
+	if (dst && dst->ops->update_pmtu)
+		dst->ops->update_pmtu(dst, NULL, skb, mtu, false);
+}
+
 static inline void skb_tunnel_check_pmtu(struct sk_buff *skb,
 					 struct dst_entry *encap_dst,
 					 int headroom)

@@ -505,7 +505,7 @@ static int tnl_update_pmtu(struct net_de
 		mtu = skb_valid_dst(skb) ? dst_mtu(skb_dst(skb)) : dev->mtu;
 
 	if (skb_valid_dst(skb))
-		skb_dst_update_pmtu(skb, mtu);
+		skb_dst_update_pmtu_no_confirm(skb, mtu);
 
 	if (skb->protocol == htons(ETH_P_IP)) {
 		if (!skb_is_gso(skb) &&

@@ -640,7 +640,7 @@ ip4ip6_err(struct sk_buff *skb, struct i
 		if (rel_info > dst_mtu(skb_dst(skb2)))
 			goto out;
 
-		skb_dst_update_pmtu(skb2, rel_info);
+		skb_dst_update_pmtu_no_confirm(skb2, rel_info);
 	}
 
 	icmp_send(skb2, rel_type, rel_code, htonl(rel_info));

@@ -1132,7 +1132,7 @@ route_lookup:
 	mtu = max(mtu, skb->protocol == htons(ETH_P_IPV6) ?
 		       IPV6_MIN_MTU : IPV4_MIN_MTU);
 
-	skb_dst_update_pmtu(skb, mtu);
+	skb_dst_update_pmtu_no_confirm(skb, mtu);
 	if (skb->len - t->tun_hlen - eth_hlen > mtu && !skb_is_gso(skb)) {
 		*pmtu = mtu;
 		err = -EMSGSIZE;

@@ -214,7 +214,7 @@ static netdev_tx_t vti_xmit(struct sk_bu
 
 	mtu = dst_mtu(dst);
 	if (skb->len > mtu) {
-		skb_dst_update_pmtu(skb, mtu);
+		skb_dst_update_pmtu_no_confirm(skb, mtu);
 		if (skb->protocol == htons(ETH_P_IP)) {
 			icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED,
 				  htonl(mtu));

@@ -479,7 +479,7 @@ vti6_xmit(struct sk_buff *skb, struct ne
 
 	mtu = dst_mtu(dst);
 	if (skb->len > mtu) {
-		skb_dst_update_pmtu(skb, mtu);
+		skb_dst_update_pmtu_no_confirm(skb, mtu);
 
 		if (skb->protocol == htons(ETH_P_IPV6)) {
 			if (mtu < IPV6_MIN_MTU)

@@ -944,7 +944,7 @@ static netdev_tx_t ipip6_tunnel_xmit(str
 		}
 
 		if (tunnel->parms.iph.daddr)
-			skb_dst_update_pmtu(skb, mtu);
+			skb_dst_update_pmtu_no_confirm(skb, mtu);
 
 		if (skb->len > mtu && !skb_is_gso(skb)) {
 			icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu);

@@ -535,7 +535,7 @@ static inline void skb_tunnel_check_pmtu
 	u32 encap_mtu = dst_mtu(encap_dst);
 
 	if (skb->len > encap_mtu - headroom)
-		skb_dst_update_pmtu(skb, encap_mtu - headroom);
+		skb_dst_update_pmtu_no_confirm(skb, encap_mtu - headroom);
 }
 
 #endif /* _NET_DST_H */

@@ -1560,8 +1560,8 @@ static int sja1105_vlan_filtering(struct
 
 	if (enabled) {
 		/* Enable VLAN filtering. */
-		tpid  = ETH_P_8021AD;
-		tpid2 = ETH_P_8021Q;
+		tpid  = ETH_P_8021Q;
+		tpid2 = ETH_P_8021AD;
 	} else {
 		/* Disable VLAN filtering. */
 		tpid  = ETH_P_SJA1105;

@@ -1570,9 +1570,9 @@ static int sja1105_vlan_filtering(struct
 
 	table = &priv->static_config.tables[BLK_IDX_GENERAL_PARAMS];
 	general_params = table->entries;
-	/* EtherType used to identify outer tagged (S-tag) VLAN traffic */
-	general_params->tpid = tpid;
 	/* EtherType used to identify inner tagged (C-tag) VLAN traffic */
+	general_params->tpid = tpid;
+	/* EtherType used to identify outer tagged (S-tag) VLAN traffic */
 	general_params->tpid2 = tpid2;
 	/* When VLAN filtering is on, we need to at least be able to
 	 * decode management traffic through the "backup plan".

@@ -142,6 +142,9 @@ static size_t sja1105et_general_params_e
 	return size;
 }
 
+/* TPID and TPID2 are intentionally reversed so that semantic
+ * compatibility with E/T is kept.
+ */
 static size_t
 sja1105pqrs_general_params_entry_packing(void *buf, void *entry_ptr,
 					 enum packing_op op)

@@ -166,9 +169,9 @@ sja1105pqrs_general_params_entry_packing
 	sja1105_packing(buf, &entry->mirr_port,   141, 139, size, op);
 	sja1105_packing(buf, &entry->vlmarker,    138, 107, size, op);
 	sja1105_packing(buf, &entry->vlmask,      106,  75, size, op);
-	sja1105_packing(buf, &entry->tpid,         74,  59, size, op);
+	sja1105_packing(buf, &entry->tpid2,        74,  59, size, op);
 	sja1105_packing(buf, &entry->ignore2stf,   58,  58, size, op);
-	sja1105_packing(buf, &entry->tpid2,        57,  42, size, op);
+	sja1105_packing(buf, &entry->tpid,         57,  42, size, op);
 	sja1105_packing(buf, &entry->queue_ts,     41,  41, size, op);
 	sja1105_packing(buf, &entry->egrmirrvid,   40,  29, size, op);
 	sja1105_packing(buf, &entry->egrmirrpcp,   28,  26, size, op);

@@ -3674,7 +3674,7 @@ static int mvpp2_open(struct net_device
 		valid = true;
 	}
 
-	if (priv->hw_version == MVPP22 && port->link_irq && !port->phylink) {
+	if (priv->hw_version == MVPP22 && port->link_irq) {
 		err = request_irq(port->link_irq, mvpp2_link_status_isr, 0,
 				  dev->name, port);
 		if (err) {

@@ -38,7 +38,6 @@ struct pdp_ctx {
 	struct hlist_node	hlist_addr;
 
 	union {
-		u64		tid;
 		struct {
 			u64	tid;
 			u16	flow;

@@ -1232,43 +1231,46 @@ static int gtp_genl_dump_pdp(struct sk_b
 				struct netlink_callback *cb)
 {
 	struct gtp_dev *last_gtp = (struct gtp_dev *)cb->args[2], *gtp;
+	int i, j, bucket = cb->args[0], skip = cb->args[1];
 	struct net *net = sock_net(skb->sk);
-	struct gtp_net *gn = net_generic(net, gtp_net_id);
-	unsigned long tid = cb->args[1];
-	int i, k = cb->args[0], ret;
 	struct pdp_ctx *pctx;
+	struct gtp_net *gn;
+
+	gn = net_generic(net, gtp_net_id);
 
 	if (cb->args[4])
 		return 0;
 
+	rcu_read_lock();
 	list_for_each_entry_rcu(gtp, &gn->gtp_dev_list, list) {
 		if (last_gtp && last_gtp != gtp)
 			continue;
 		else
 			last_gtp = NULL;
 
-		for (i = k; i < gtp->hash_size; i++) {
-			hlist_for_each_entry_rcu(pctx, &gtp->tid_hash[i], hlist_tid) {
-				if (tid && tid != pctx->u.tid)
-					continue;
-				else
-					tid = 0;
-
-				ret = gtp_genl_fill_info(skb,
-							 NETLINK_CB(cb->skb).portid,
-							 cb->nlh->nlmsg_seq,
-							 cb->nlh->nlmsg_type, pctx);
-				if (ret < 0) {
+		for (i = bucket; i < gtp->hash_size; i++) {
+			j = 0;
+			hlist_for_each_entry_rcu(pctx, &gtp->tid_hash[i],
+						 hlist_tid) {
+				if (j >= skip &&
+				    gtp_genl_fill_info(skb,
+					    NETLINK_CB(cb->skb).portid,
+					    cb->nlh->nlmsg_seq,
+					    cb->nlh->nlmsg_type, pctx)) {
 					cb->args[0] = i;
-					cb->args[1] = pctx->u.tid;
+					cb->args[1] = j;
 					cb->args[2] = (unsigned long)gtp;
 					goto out;
 				}
+				j++;
 			}
+			skip = 0;
 		}
+		bucket = 0;
 	}
 	cb->args[4] = 1;
 out:
+	rcu_read_unlock();
 	return skb->len;
 }
 

@@ -660,10 +660,13 @@ static int gtp_newlink(struct net *src_n
 	if (err < 0)
 		return err;
 
-	if (!data[IFLA_GTP_PDP_HASHSIZE])
+	if (!data[IFLA_GTP_PDP_HASHSIZE]) {
 		hashsize = 1024;
-	else
+	} else {
 		hashsize = nla_get_u32(data[IFLA_GTP_PDP_HASHSIZE]);
+		if (!hashsize)
+			hashsize = 1024;
+	}
 
 	err = gtp_hashtable_new(gtp, hashsize);
 	if (err < 0)

@@ -2225,9 +2225,6 @@ static void bond_miimon_commit(struct bo
 			} else if (BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP) {
 				/* make it immediately active */
 				bond_set_active_slave(slave);
-			} else if (slave != primary) {
-				/* prevent it from being the active one */
-				bond_set_backup_slave(slave);
 			}
 
 			slave_info(bond->dev, slave->dev, "link status definitely up, %u Mbps %s duplex\n",

@@ -2441,6 +2441,14 @@ static bool tcp_write_xmit(struct sock *
 		if (tcp_small_queue_check(sk, skb, 0))
 			break;
 
+		/* Argh, we hit an empty skb(), presumably a thread
+		 * is sleeping in sendmsg()/sk_stream_wait_memory().
+		 * We do not want to send a pure-ack packet and have
+		 * a strange looking rtx queue with empty packet(s).
+		 */
+		if (TCP_SKB_CB(skb)->end_seq == TCP_SKB_CB(skb)->seq)
+			break;
+
 		if (unlikely(tcp_transmit_skb(sk, skb, 1, gfp)))
 			break;
 

@@ -101,6 +101,43 @@ static inline void hlist_nulls_add_head_
 }
 
 /**
+ * hlist_nulls_add_tail_rcu
+ * @n: the element to add to the hash list.
+ * @h: the list to add to.
+ *
+ * Description:
+ * Adds the specified element to the specified hlist_nulls,
+ * while permitting racing traversals.
+ *
+ * The caller must take whatever precautions are necessary
+ * (such as holding appropriate locks) to avoid racing
+ * with another list-mutation primitive, such as hlist_nulls_add_head_rcu()
+ * or hlist_nulls_del_rcu(), running on this same list.
+ * However, it is perfectly legal to run concurrently with
+ * the _rcu list-traversal primitives, such as
+ * hlist_nulls_for_each_entry_rcu(), used to prevent memory-consistency
+ * problems on Alpha CPUs.  Regardless of the type of CPU, the
+ * list-traversal primitive must be guarded by rcu_read_lock().
+ */
+static inline void hlist_nulls_add_tail_rcu(struct hlist_nulls_node *n,
+					    struct hlist_nulls_head *h)
+{
+	struct hlist_nulls_node *i, *last = NULL;
+
+	/* Note: write side code, so rcu accessors are not needed. */
+	for (i = h->first; !is_a_nulls(i); i = i->next)
+		last = i;
+
+	if (last) {
+		n->next = last->next;
+		n->pprev = &last->next;
+		rcu_assign_pointer(hlist_next_rcu(last), n);
+	} else {
+		hlist_nulls_add_head_rcu(n, h);
+	}
+}
+
+/**
  * hlist_nulls_for_each_entry_rcu - iterate over rcu list of given type
  * @tpos:	the type * to use as a loop cursor.
  * @pos:	the &struct hlist_nulls_node to use as a loop cursor.

@@ -103,13 +103,19 @@ struct inet_bind_hashbucket {
 	struct hlist_head	chain;
 };
 
-/*
- * Sockets can be hashed in established or listening table
+/* Sockets can be hashed in established or listening table.
+ * We must use different 'nulls' end-of-chain value for all hash buckets :
+ * A socket might transition from ESTABLISH to LISTEN state without
+ * RCU grace period. A lookup in ehash table needs to handle this case.
  */
+#define LISTENING_NULLS_BASE (1U << 29)
 struct inet_listen_hashbucket {
 	spinlock_t		lock;
 	unsigned int		count;
-	struct hlist_head	head;
+	union {
+		struct hlist_head	head;
+		struct hlist_nulls_head	nulls_head;
+	};
 };
 
 /* This is for listening sockets, thus all sockets which possess wildcards. */

@@ -723,6 +723,11 @@ static inline void __sk_nulls_add_node_r
 	hlist_nulls_add_head_rcu(&sk->sk_nulls_node, list);
 }
 
+static inline void __sk_nulls_add_node_tail_rcu(struct sock *sk, struct hlist_nulls_head *list)
+{
+	hlist_nulls_add_tail_rcu(&sk->sk_nulls_node, list);
+}
+
 static inline void sk_nulls_add_node_rcu(struct sock *sk, struct hlist_nulls_head *list)
 {
 	sock_hold(sk);

@@ -914,11 +914,12 @@ void inet_diag_dump_icsk(struct inet_has
 
 		for (i = s_i; i < INET_LHTABLE_SIZE; i++) {
 			struct inet_listen_hashbucket *ilb;
+			struct hlist_nulls_node *node;
 
 			num = 0;
 			ilb = &hashinfo->listening_hash[i];
 			spin_lock(&ilb->lock);
-			sk_for_each(sk, &ilb->head) {
+			sk_nulls_for_each(sk, node, &ilb->nulls_head) {
 				struct inet_sock *inet = inet_sk(sk);
 
 				if (!net_eq(sock_net(sk), net))

@@ -516,10 +516,11 @@ static int inet_reuseport_add_sock(struc
 				   struct inet_listen_hashbucket *ilb)
 {
 	struct inet_bind_bucket *tb = inet_csk(sk)->icsk_bind_hash;
+	const struct hlist_nulls_node *node;
 	struct sock *sk2;
 	kuid_t uid = sock_i_uid(sk);
 
-	sk_for_each_rcu(sk2, &ilb->head) {
+	sk_nulls_for_each_rcu(sk2, node, &ilb->nulls_head) {
 		if (sk2 != sk &&
 		    sk2->sk_family == sk->sk_family &&
 		    ipv6_only_sock(sk2) == ipv6_only_sock(sk) &&

@@ -555,9 +556,9 @@ int __inet_hash(struct sock *sk, struct
 	}
 	if (IS_ENABLED(CONFIG_IPV6) && sk->sk_reuseport &&
 		sk->sk_family == AF_INET6)
-		hlist_add_tail_rcu(&sk->sk_node, &ilb->head);
+		__sk_nulls_add_node_tail_rcu(sk, &ilb->nulls_head);
 	else
-		hlist_add_head_rcu(&sk->sk_node, &ilb->head);
+		__sk_nulls_add_node_rcu(sk, &ilb->nulls_head);
 	inet_hash2(hashinfo, sk);
 	ilb->count++;
 	sock_set_flag(sk, SOCK_RCU_FREE);

@@ -606,11 +607,9 @@ void inet_unhash(struct sock *sk)
 		reuseport_detach_sock(sk);
 	if (ilb) {
 		inet_unhash2(hashinfo, sk);
-		 __sk_del_node_init(sk);
-		 ilb->count--;
-	} else {
-		__sk_nulls_del_node_init_rcu(sk);
+		ilb->count--;
 	}
+	__sk_nulls_del_node_init_rcu(sk);
 	sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1);
 unlock:
 	spin_unlock_bh(lock);

@@ -750,7 +749,8 @@ void inet_hashinfo_init(struct inet_hash
 
 	for (i = 0; i < INET_LHTABLE_SIZE; i++) {
 		spin_lock_init(&h->listening_hash[i].lock);
-		INIT_HLIST_HEAD(&h->listening_hash[i].head);
+		INIT_HLIST_NULLS_HEAD(&h->listening_hash[i].nulls_head,
+				      i + LISTENING_NULLS_BASE);
 		h->listening_hash[i].count = 0;
 	}
 

@@ -2149,13 +2149,14 @@ static void *listening_get_next(struct s
 	struct tcp_iter_state *st = seq->private;
 	struct net *net = seq_file_net(seq);
 	struct inet_listen_hashbucket *ilb;
+	struct hlist_nulls_node *node;
 	struct sock *sk = cur;
 
 	if (!sk) {
 get_head:
 		ilb = &tcp_hashinfo.listening_hash[st->bucket];
 		spin_lock(&ilb->lock);
-		sk = sk_head(&ilb->head);
+		sk = sk_nulls_head(&ilb->nulls_head);
 		st->offset = 0;
 		goto get_sk;
 	}

@@ -2163,9 +2164,9 @@ get_head:
 	++st->num;
 	++st->offset;
 
-	sk = sk_next(sk);
+	sk = sk_nulls_next(sk);
 get_sk:
-	sk_for_each_from(sk) {
+	sk_nulls_for_each_from(sk, node) {
 		if (!net_eq(sock_net(sk), net))
 			continue;
 		if (sk->sk_family == afinfo->family)

@@ -1165,6 +1165,9 @@ int rndis_set_subchannel(struct net_devi
 	wait_event(nvdev->subchan_open,
 		   atomic_read(&nvdev->open_chn) == nvdev->num_chn);
 
+	for (i = 0; i < VRSS_SEND_TAB_SIZE; i++)
+		ndev_ctx->tx_table[i] = i % nvdev->num_chn;
+
 	/* ignore failures from setting rss parameters, still have channels */
 	if (dev_info)
 		rndis_filter_set_rss_param(rdev, dev_info->rss_key);

@@ -1174,9 +1177,6 @@ int rndis_set_subchannel(struct net_devi
 	netif_set_real_num_tx_queues(ndev, nvdev->num_chn);
 	netif_set_real_num_rx_queues(ndev, nvdev->num_chn);
 
-	for (i = 0; i < VRSS_SEND_TAB_SIZE; i++)
-		ndev_ctx->tx_table[i] = i % nvdev->num_chn;
-
 	return 0;
 }
 

@@ -640,9 +640,16 @@ static void gtp_link_setup(struct net_de
 }
 
 static int gtp_hashtable_new(struct gtp_dev *gtp, int hsize);
-static void gtp_hashtable_free(struct gtp_dev *gtp);
 static int gtp_encap_enable(struct gtp_dev *gtp, struct nlattr *data[]);
 
+static void gtp_destructor(struct net_device *dev)
+{
+	struct gtp_dev *gtp = netdev_priv(dev);
+
+	kfree(gtp->addr_hash);
+	kfree(gtp->tid_hash);
+}
+
 static int gtp_newlink(struct net *src_net, struct net_device *dev,
 		       struct nlattr *tb[], struct nlattr *data[],
 		       struct netlink_ext_ack *extack)

@@ -680,13 +687,15 @@ static int gtp_newlink(struct net *src_n
 
 	gn = net_generic(dev_net(dev), gtp_net_id);
 	list_add_rcu(&gtp->list, &gn->gtp_dev_list);
+	dev->priv_destructor = gtp_destructor;
 
 	netdev_dbg(dev, "registered new GTP interface\n");
 
 	return 0;
 
 out_hashtable:
-	gtp_hashtable_free(gtp);
+	kfree(gtp->addr_hash);
+	kfree(gtp->tid_hash);
 out_encap:
 	gtp_encap_disable(gtp);
 	return err;

@@ -695,8 +704,13 @@ out_encap:
 static void gtp_dellink(struct net_device *dev, struct list_head *head)
 {
 	struct gtp_dev *gtp = netdev_priv(dev);
+	struct pdp_ctx *pctx;
+	int i;
+
+	for (i = 0; i < gtp->hash_size; i++)
+		hlist_for_each_entry_rcu(pctx, &gtp->tid_hash[i], hlist_tid)
+			pdp_context_delete(pctx);
 
-	gtp_hashtable_free(gtp);
 	list_del_rcu(&gtp->list);
 	unregister_netdevice_queue(dev, head);
 }

@@ -774,20 +788,6 @@ err1:
 	return -ENOMEM;
 }
 
-static void gtp_hashtable_free(struct gtp_dev *gtp)
-{
-	struct pdp_ctx *pctx;
-	int i;
-
-	for (i = 0; i < gtp->hash_size; i++)
-		hlist_for_each_entry_rcu(pctx, &gtp->tid_hash[i], hlist_tid)
-			pdp_context_delete(pctx);
-
-	synchronize_rcu();
-	kfree(gtp->addr_hash);
-	kfree(gtp->tid_hash);
-}
-
 static struct sock *gtp_encap_enable_socket(int fd, int type,
 					    struct gtp_dev *gtp)
 {

@@ -928,24 +928,31 @@ static void ipv4_pdp_fill(struct pdp_ctx
 	}
 }
 
-static int ipv4_pdp_add(struct gtp_dev *gtp, struct sock *sk,
-			struct genl_info *info)
+static int gtp_pdp_add(struct gtp_dev *gtp, struct sock *sk,
+		       struct genl_info *info)
 {
+	struct pdp_ctx *pctx, *pctx_tid = NULL;
 	struct net_device *dev = gtp->dev;
 	u32 hash_ms, hash_tid = 0;
-	struct pdp_ctx *pctx;
+	unsigned int version;
 	bool found = false;
 	__be32 ms_addr;
 
 	ms_addr = nla_get_be32(info->attrs[GTPA_MS_ADDRESS]);
 	hash_ms = ipv4_hashfn(ms_addr) % gtp->hash_size;
+	version = nla_get_u32(info->attrs[GTPA_VERSION]);
 
-	hlist_for_each_entry_rcu(pctx, &gtp->addr_hash[hash_ms], hlist_addr) {
-		if (pctx->ms_addr_ip4.s_addr == ms_addr) {
-			found = true;
-			break;
-		}
-	}
+	pctx = ipv4_pdp_find(gtp, ms_addr);
+	if (pctx)
+		found = true;
+	if (version == GTP_V0)
+		pctx_tid = gtp0_pdp_find(gtp,
+					 nla_get_u64(info->attrs[GTPA_TID]));
+	else if (version == GTP_V1)
+		pctx_tid = gtp1_pdp_find(gtp,
+					 nla_get_u32(info->attrs[GTPA_I_TEI]));
+	if (pctx_tid)
+		found = true;
 
 	if (found) {
 		if (info->nlhdr->nlmsg_flags & NLM_F_EXCL)

@@ -953,6 +960,11 @@ static int ipv4_pdp_add(struct gtp_dev *
 		if (info->nlhdr->nlmsg_flags & NLM_F_REPLACE)
 			return -EOPNOTSUPP;
 
+		if (pctx && pctx_tid)
+			return -EEXIST;
+		if (!pctx)
+			pctx = pctx_tid;
+
 		ipv4_pdp_fill(pctx, info);
 
 		if (pctx->gtp_version == GTP_V0)

@@ -1076,7 +1088,7 @@ static int gtp_genl_new_pdp(struct sk_bu
 		goto out_unlock;
 	}
 
-	err = ipv4_pdp_add(gtp, sk, info);
+	err = gtp_pdp_add(gtp, sk, info);
 
 out_unlock:
 	rcu_read_unlock();

@@ -6178,7 +6178,7 @@ static void bnxt_hwrm_set_coal_params(st
 		tmr = bnxt_usec_to_coal_tmr(bp, hw_coal->coal_ticks_irq);
 		val = clamp_t(u16, tmr, 1,
 			      coal_cap->cmpl_aggr_dma_tmr_during_int_max);
-		req->cmpl_aggr_dma_tmr_during_int = cpu_to_le16(tmr);
+		req->cmpl_aggr_dma_tmr_during_int = cpu_to_le16(val);
 		req->enables |=
 			cpu_to_le16(BNXT_COAL_CMPL_AGGR_TMR_DURING_INT_ENABLE);
 	}

@@ -5231,16 +5231,16 @@ static int inet6_rtm_valid_getaddr_req(s
 		return -EINVAL;
 	}
 
+	if (!netlink_strict_get_check(skb))
+		return nlmsg_parse_deprecated(nlh, sizeof(*ifm), tb, IFA_MAX,
+					      ifa_ipv6_policy, extack);
+
 	ifm = nlmsg_data(nlh);
 	if (ifm->ifa_prefixlen || ifm->ifa_flags || ifm->ifa_scope) {
 		NL_SET_ERR_MSG_MOD(extack, "Invalid values in header for get address request");
 		return -EINVAL;
 	}
 
-	if (!netlink_strict_get_check(skb))
-		return nlmsg_parse_deprecated(nlh, sizeof(*ifm), tb, IFA_MAX,
-					      ifa_ipv6_policy, extack);
-
 	err = nlmsg_parse_deprecated_strict(nlh, sizeof(*ifm), tb, IFA_MAX,
 					    ifa_ipv6_policy, extack);
 	if (err)

@@ -444,8 +444,7 @@ static void phylink_mac_link_up(struct p
 
 	pl->cur_interface = link_state.interface;
 	pl->ops->mac_link_up(pl->config, pl->link_an_mode,
-			     pl->phy_state.interface,
-			     pl->phydev);
+			     pl->cur_interface, pl->phydev);
 
 	if (ndev)
 		netif_carrier_on(ndev);

@@ -1238,8 +1238,8 @@ static int ena_io_poll(struct napi_struc
 	struct ena_napi *ena_napi = container_of(napi, struct ena_napi, napi);
 	struct ena_ring *tx_ring, *rx_ring;
 
-	u32 tx_work_done;
-	u32 rx_work_done;
+	int tx_work_done;
+	int rx_work_done = 0;
 	int tx_budget;
 	int napi_comp_call = 0;
 	int ret;

@@ -1256,7 +1256,11 @@ static int ena_io_poll(struct napi_struc
 	}
 
 	tx_work_done = ena_clean_tx_irq(tx_ring, tx_budget);
-	rx_work_done = ena_clean_rx_irq(rx_ring, napi, budget);
+	/* On netpoll the budget is zero and the handler should only clean the
+	 * tx completions.
+	 */
+	if (likely(budget))
+		rx_work_done = ena_clean_rx_irq(rx_ring, napi, budget);
 
 	/* If the device is about to reset or down, avoid unmask
 	 * the interrupt and return 0 so NAPI won't reschedule

@@ -437,7 +437,9 @@ static void vhost_vsock_handle_tx_kick(s
 		virtio_transport_deliver_tap_pkt(pkt);
 
 		/* Only accept correctly addressed packets */
-		if (le64_to_cpu(pkt->hdr.src_cid) == vsock->guest_cid)
+		if (le64_to_cpu(pkt->hdr.src_cid) == vsock->guest_cid &&
+		    le64_to_cpu(pkt->hdr.dst_cid) ==
+		    vhost_transport_get_local_cid())
 			virtio_transport_recv_pkt(pkt);
 		else
 			virtio_transport_free_pkt(pkt);

index 57b582bf73d9..9289bb4d633e 100644
@@ -51,6 +51,11 @@
 #define ESDHC_CLOCK_HCKEN		0x00000002
 #define ESDHC_CLOCK_IPGEN		0x00000001
 
+/* System Control 2 Register */
+#define ESDHC_SYSTEM_CONTROL_2		0x3c
+#define ESDHC_SMPCLKSEL			0x00800000
+#define ESDHC_EXTN			0x00400000
+
 /* Host Controller Capabilities Register 2 */
 #define ESDHC_CAPABILITIES_1		0x114
 

@@ -59,7 +64,16 @@
 #define ESDHC_HS400_WNDW_ADJUST		0x00000040
 #define ESDHC_HS400_MODE		0x00000010
 #define ESDHC_TB_EN			0x00000004
+#define ESDHC_TB_MODE_MASK		0x00000003
+#define ESDHC_TB_MODE_SW		0x00000003
+#define ESDHC_TB_MODE_3			0x00000002
+
+#define ESDHC_TBSTAT			0x124
+
 #define ESDHC_TBPTR			0x128
+#define ESDHC_WNDW_STRT_PTR_SHIFT	8
+#define ESDHC_WNDW_STRT_PTR_MASK	(0x7f << 8)
+#define ESDHC_WNDW_END_PTR_MASK		0x7f
 
 /* SD Clock Control Register */
 #define ESDHC_SDCLKCTL			0x144

299 lines not on this page · raw message

index 14f0cb7fa374..fcfb50f84c8b 100644
@@ -80,6 +80,7 @@ struct sdhci_esdhc {
 	bool quirk_tuning_erratum_type1;
 	bool quirk_tuning_erratum_type2;
 	bool quirk_ignore_data_inhibit;
+	bool quirk_delay_before_data_reset;
 	bool in_sw_tuning;
 	unsigned int peripheral_clock;
 	const struct esdhc_clk_fixup *clk_fixup;

@@ -735,6 +736,11 @@ static void esdhc_reset(struct sdhci_host *host, u8 mask)
 	struct sdhci_esdhc *esdhc = sdhci_pltfm_priv(pltfm_host);
 	u32 val;
 
+	if (esdhc->quirk_delay_before_data_reset &&
+	    (mask & SDHCI_RESET_DATA) &&
+	    (host->flags & SDHCI_REQ_USE_DMA))
+		mdelay(5);
+
 	sdhci_reset(host, mask);
 
 	sdhci_writel(host, host->ier, SDHCI_INT_ENABLE);

@@ -1197,6 +1203,10 @@ static void esdhc_init(struct platform_device *pdev, struct sdhci_host *host)
 	if (match)
 		esdhc->clk_fixup = match->data;
 	np = pdev->dev.of_node;
+
+	if (of_device_is_compatible(np, "fsl,p2020-esdhc"))
+		esdhc->quirk_delay_before_data_reset = true;
+
 	clk = of_clk_get(np, 0);
 	if (!IS_ERR(clk)) {
 		/*