Merge tag 'net-6.12-rc6' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull networking fixes from Paolo Abeni:
 "Including fixes from WiFi, bluetooth and netfilter.

  No known new regressions outstanding.

  Current release - regressions:

   - wifi: mt76: do not increase mcu skb refcount if retry is not
     supported

  Current release - new code bugs:

   - wifi:
      - rtw88: fix the RX aggregation in USB 3 mode
      - mac80211: fix memory corruption bug in struct ieee80211_chanctx

  Previous releases - regressions:

   - sched:
      - stop qdisc_tree_reduce_backlog on TC_H_ROOT
      - sch_api: fix xa_insert() error path in tcf_block_get_ext()

   - wifi:
      - revert "wifi: iwlwifi: remove retry loops in start"
      - cfg80211: clear wdev->cqm_config pointer on free

   - netfilter: fix potential crash in nf_send_reset6()

   - ip_tunnel: fix suspicious RCU usage warning in ip_tunnel_find()

   - bluetooth: fix null-ptr-deref in hci_read_supported_codecs

   - eth: mlxsw: add missing verification before pushing Tx header

   - eth: hns3: fixed hclge_fetch_pf_reg accesses bar space out of
     bounds issue

  Previous releases - always broken:

   - wifi: mac80211: do not pass a stopped vif to the driver in
     .get_txpower

   - netfilter: sanitize offset and length before calling skb_checksum()

   - core:
      - fix crash when config small gso_max_size/gso_ipv4_max_size
      - skip offload for NETIF_F_IPV6_CSUM if ipv6 header contains extension

   - mptcp: protect sched with rcu_read_lock

   - eth: ice: fix crash on probe for DPLL enabled E810 LOM

   - eth: macsec: fix use-after-free while sending the offloading packet

   - eth: stmmac: fix unbalanced DMA map/unmap for non-paged SKB data

   - eth: hns3: fix kernel crash when 1588 is sent on HIP08 devices

   - eth: mtk_wed: fix path of MT7988 WO firmware"

* tag 'net-6.12-rc6' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (70 commits)
  net: hns3: fix kernel crash when 1588 is sent on HIP08 devices
  net: hns3: fixed hclge_fetch_pf_reg accesses bar space out of bounds issue
  net: hns3: initialize reset_timer before hclgevf_misc_irq_init()
  net: hns3: don't auto enable misc vector
  net: hns3: Resolved the issue that the debugfs query result is inconsistent.
  net: hns3: fix missing features due to dev->features configuration too early
  net: hns3: fixed reset failure issues caused by the incorrect reset type
  net: hns3: add sync command to sync io-pgtable
  net: hns3: default enable tx bounce buffer when smmu enabled
  netfilter: nft_payload: sanitize offset and length before calling skb_checksum()
  net: ethernet: mtk_wed: fix path of MT7988 WO firmware
  selftests: forwarding: Add IPv6 GRE remote change tests
  mlxsw: spectrum_ipip: Fix memory leak when changing remote IPv6 address
  mlxsw: pci: Sync Rx buffers for device
  mlxsw: pci: Sync Rx buffers for CPU
  mlxsw: spectrum_ptp: Add missing verification before pushing Tx header
  net: skip offload for NETIF_F_IPV6_CSUM if ipv6 header contains extension
  Bluetooth: hci: fix null-ptr-deref in hci_read_supported_codecs
  netfilter: nf_reject_ipv6: fix potential crash in nf_send_reset6()
  netfilter: Fix use-after-free in get_info()
  ...

Author: torvalds

Documentation/networking/packet_mmap.rst

@@ -16,7 +16,7 @@ ii) transmit network traffic, or any other that needs raw
 
 Howto can be found at:
 
-    https://sites.google.com/site/packetmmap/
+    https://web.archive.org/web/20220404160947/https://sites.google.com/site/packetmmap/
 
 Please send your comments to
     - Ulisses Alonso Camaró <[email protected]>
@@ -166,7 +166,8 @@ As capture, each frame contains two parts::
     /* bind socket to eth0 */
     bind(this->socket, (struct sockaddr *)&my_addr, sizeof(struct sockaddr_ll));
 
- A complete tutorial is available at: https://sites.google.com/site/packetmmap/
+ A complete tutorial is available at:
+ https://web.archive.org/web/20220404160947/https://sites.google.com/site/packetmmap/
 
 By default, the user should put data at::
 

drivers/net/ethernet/hisilicon/hns3/hns3_debugfs.c

@@ -1293,8 +1293,10 @@ static ssize_t hns3_dbg_read(struct file *filp, char __user *buffer,
 
 		/* save the buffer addr until the last read operation */
 		*save_buf = read_buf;
+	}
 
-		/* get data ready for the first time to read */
+	/* get data ready for the first time to read */
+	if (!*ppos) {
 		ret = hns3_dbg_read_cmd(dbg_data, hns3_dbg_cmd[index].cmd,
 					read_buf, hns3_dbg_cmd[index].buf_len);
 		if (ret)

drivers/net/ethernet/hisilicon/hns3/hns3_enet.c

@@ -11,6 +11,7 @@
 #include <linux/irq.h>
 #include <linux/ip.h>
 #include <linux/ipv6.h>
+#include <linux/iommu.h>
 #include <linux/module.h>
 #include <linux/pci.h>
 #include <linux/skbuff.h>
@@ -380,6 +381,24 @@ static const struct hns3_rx_ptype hns3_rx_ptype_tbl[] = {
 #define HNS3_INVALID_PTYPE \
 		ARRAY_SIZE(hns3_rx_ptype_tbl)
 
+static void hns3_dma_map_sync(struct device *dev, unsigned long iova)
+{
+	struct iommu_domain *domain = iommu_get_domain_for_dev(dev);
+	struct iommu_iotlb_gather iotlb_gather;
+	size_t granule;
+
+	if (!domain || !iommu_is_dma_domain(domain))
+		return;
+
+	granule = 1 << __ffs(domain->pgsize_bitmap);
+	iova = ALIGN_DOWN(iova, granule);
+	iotlb_gather.start = iova;
+	iotlb_gather.end = iova + granule - 1;
+	iotlb_gather.pgsize = granule;
+
+	iommu_iotlb_sync(domain, &iotlb_gather);
+}
+
 static irqreturn_t hns3_irq_handle(int irq, void *vector)
 {
 	struct hns3_enet_tqp_vector *tqp_vector = vector;
@@ -1032,6 +1051,8 @@ static bool hns3_can_use_tx_sgl(struct hns3_enet_ring *ring,
 static void hns3_init_tx_spare_buffer(struct hns3_enet_ring *ring)
 {
 	u32 alloc_size = ring->tqp->handle->kinfo.tx_spare_buf_size;
+	struct net_device *netdev = ring_to_netdev(ring);
+	struct hns3_nic_priv *priv = netdev_priv(netdev);
 	struct hns3_tx_spare *tx_spare;
 	struct page *page;
 	dma_addr_t dma;
@@ -1073,6 +1094,7 @@ static void hns3_init_tx_spare_buffer(struct hns3_enet_ring *ring)
 	tx_spare->buf = page_address(page);
 	tx_spare->len = PAGE_SIZE << order;
 	ring->tx_spare = tx_spare;
+	ring->tx_copybreak = priv->tx_copybreak;
 	return;
 
 dma_mapping_error:
@@ -1724,7 +1746,9 @@ static int hns3_map_and_fill_desc(struct hns3_enet_ring *ring, void *priv,
 				  unsigned int type)
 {
 	struct hns3_desc_cb *desc_cb = &ring->desc_cb[ring->next_to_use];
+	struct hnae3_handle *handle = ring->tqp->handle;
 	struct device *dev = ring_to_dev(ring);
+	struct hnae3_ae_dev *ae_dev;
 	unsigned int size;
 	dma_addr_t dma;
 
@@ -1756,6 +1780,13 @@ static int hns3_map_and_fill_desc(struct hns3_enet_ring *ring, void *priv,
 		return -ENOMEM;
 	}
 
+	/* Add a SYNC command to sync io-pgtale to avoid errors in pgtable
+	 * prefetch
+	 */
+	ae_dev = hns3_get_ae_dev(handle);
+	if (ae_dev->dev_version >= HNAE3_DEVICE_VERSION_V3)
+		hns3_dma_map_sync(dev, dma);
+
 	desc_cb->priv = priv;
 	desc_cb->length = size;
 	desc_cb->dma = dma;
@@ -2452,7 +2483,6 @@ static int hns3_nic_set_features(struct net_device *netdev,
 			return ret;
 	}
 
-	netdev->features = features;
 	return 0;
 }
 
@@ -4868,6 +4898,30 @@ static void hns3_nic_dealloc_vector_data(struct hns3_nic_priv *priv)
 	devm_kfree(&pdev->dev, priv->tqp_vector);
 }
 
+static void hns3_update_tx_spare_buf_config(struct hns3_nic_priv *priv)
+{
+#define HNS3_MIN_SPARE_BUF_SIZE (2 * 1024 * 1024)
+#define HNS3_MAX_PACKET_SIZE (64 * 1024)
+
+	struct iommu_domain *domain = iommu_get_domain_for_dev(priv->dev);
+	struct hnae3_ae_dev *ae_dev = hns3_get_ae_dev(priv->ae_handle);
+	struct hnae3_handle *handle = priv->ae_handle;
+
+	if (ae_dev->dev_version < HNAE3_DEVICE_VERSION_V3)
+		return;
+
+	if (!(domain && iommu_is_dma_domain(domain)))
+		return;
+
+	priv->min_tx_copybreak = HNS3_MAX_PACKET_SIZE;
+	priv->min_tx_spare_buf_size = HNS3_MIN_SPARE_BUF_SIZE;
+
+	if (priv->tx_copybreak < priv->min_tx_copybreak)
+		priv->tx_copybreak = priv->min_tx_copybreak;
+	if (handle->kinfo.tx_spare_buf_size < priv->min_tx_spare_buf_size)
+		handle->kinfo.tx_spare_buf_size = priv->min_tx_spare_buf_size;
+}
+
 static void hns3_ring_get_cfg(struct hnae3_queue *q, struct hns3_nic_priv *priv,
 			      unsigned int ring_type)
 {
@@ -5101,6 +5155,7 @@ int hns3_init_all_ring(struct hns3_nic_priv *priv)
 	int i, j;
 	int ret;
 
+	hns3_update_tx_spare_buf_config(priv);
 	for (i = 0; i < ring_num; i++) {
 		ret = hns3_alloc_ring_memory(&priv->ring[i]);
 		if (ret) {
@@ -5305,6 +5360,8 @@ static int hns3_client_init(struct hnae3_handle *handle)
 	priv->ae_handle = handle;
 	priv->tx_timeout_count = 0;
 	priv->max_non_tso_bd_num = ae_dev->dev_specs.max_non_tso_bd_num;
+	priv->min_tx_copybreak = 0;
+	priv->min_tx_spare_buf_size = 0;
 	set_bit(HNS3_NIC_STATE_DOWN, &priv->state);
 
 	handle->msg_enable = netif_msg_init(debug, DEFAULT_MSG_LEVEL);

drivers/net/ethernet/hisilicon/hns3/hns3_enet.h

@@ -596,6 +596,8 @@ struct hns3_nic_priv {
 	struct hns3_enet_coalesce rx_coal;
 	u32 tx_copybreak;
 	u32 rx_copybreak;
+	u32 min_tx_copybreak;
+	u32 min_tx_spare_buf_size;
 };
 
 union l3_hdr_info {

drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c

@@ -1933,6 +1933,31 @@ static int hns3_set_tx_spare_buf_size(struct net_device *netdev,
 	return ret;
 }
 
+static int hns3_check_tx_copybreak(struct net_device *netdev, u32 copybreak)
+{
+	struct hns3_nic_priv *priv = netdev_priv(netdev);
+
+	if (copybreak < priv->min_tx_copybreak) {
+		netdev_err(netdev, "tx copybreak %u should be no less than %u!\n",
+			   copybreak, priv->min_tx_copybreak);
+		return -EINVAL;
+	}
+	return 0;
+}
+
+static int hns3_check_tx_spare_buf_size(struct net_device *netdev, u32 buf_size)
+{
+	struct hns3_nic_priv *priv = netdev_priv(netdev);
+
+	if (buf_size < priv->min_tx_spare_buf_size) {
+		netdev_err(netdev,
+			   "tx spare buf size %u should be no less than %u!\n",
+			   buf_size, priv->min_tx_spare_buf_size);
+		return -EINVAL;
+	}
+	return 0;
+}
+
 static int hns3_set_tunable(struct net_device *netdev,
 			    const struct ethtool_tunable *tuna,
 			    const void *data)
@@ -1949,6 +1974,10 @@ static int hns3_set_tunable(struct net_device *netdev,
 
 	switch (tuna->id) {
 	case ETHTOOL_TX_COPYBREAK:
+		ret = hns3_check_tx_copybreak(netdev, *(u32 *)data);
+		if (ret)
+			return ret;
+
 		priv->tx_copybreak = *(u32 *)data;
 
 		for (i = 0; i < h->kinfo.num_tqps; i++)
@@ -1963,6 +1992,10 @@ static int hns3_set_tunable(struct net_device *netdev,
 
 		break;
 	case ETHTOOL_TX_COPYBREAK_BUF_SIZE:
+		ret = hns3_check_tx_spare_buf_size(netdev, *(u32 *)data);
+		if (ret)
+			return ret;
+
 		old_tx_spare_buf_size = h->kinfo.tx_spare_buf_size;
 		new_tx_spare_buf_size = *(u32 *)data;
 		netdev_info(netdev, "request to set tx spare buf size from %u to %u\n",

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

@@ -6,6 +6,7 @@
 #include <linux/etherdevice.h>
 #include <linux/init.h>
 #include <linux/interrupt.h>
+#include <linux/irq.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/netdevice.h>
@@ -3584,6 +3585,17 @@ static int hclge_set_vf_link_state(struct hnae3_handle *handle, int vf,
 	return ret;
 }
 
+static void hclge_set_reset_pending(struct hclge_dev *hdev,
+				    enum hnae3_reset_type reset_type)
+{
+	/* When an incorrect reset type is executed, the get_reset_level
+	 * function generates the HNAE3_NONE_RESET flag. As a result, this
+	 * type do not need to pending.
+	 */
+	if (reset_type != HNAE3_NONE_RESET)
+		set_bit(reset_type, &hdev->reset_pending);
+}
+
 static u32 hclge_check_event_cause(struct hclge_dev *hdev, u32 *clearval)
 {
 	u32 cmdq_src_reg, msix_src_reg, hw_err_src_reg;
@@ -3604,7 +3616,7 @@ static u32 hclge_check_event_cause(struct hclge_dev *hdev, u32 *clearval)
 	 */
 	if (BIT(HCLGE_VECTOR0_IMPRESET_INT_B) & msix_src_reg) {
 		dev_info(&hdev->pdev->dev, "IMP reset interrupt\n");
-		set_bit(HNAE3_IMP_RESET, &hdev->reset_pending);
+		hclge_set_reset_pending(hdev, HNAE3_IMP_RESET);
 		set_bit(HCLGE_COMM_STATE_CMD_DISABLE, &hdev->hw.hw.comm_state);
 		*clearval = BIT(HCLGE_VECTOR0_IMPRESET_INT_B);
 		hdev->rst_stats.imp_rst_cnt++;
@@ -3614,7 +3626,7 @@ static u32 hclge_check_event_cause(struct hclge_dev *hdev, u32 *clearval)
 	if (BIT(HCLGE_VECTOR0_GLOBALRESET_INT_B) & msix_src_reg) {
 		dev_info(&hdev->pdev->dev, "global reset interrupt\n");
 		set_bit(HCLGE_COMM_STATE_CMD_DISABLE, &hdev->hw.hw.comm_state);
-		set_bit(HNAE3_GLOBAL_RESET, &hdev->reset_pending);
+		hclge_set_reset_pending(hdev, HNAE3_GLOBAL_RESET);
 		*clearval = BIT(HCLGE_VECTOR0_GLOBALRESET_INT_B);
 		hdev->rst_stats.global_rst_cnt++;
 		return HCLGE_VECTOR0_EVENT_RST;
@@ -3769,7 +3781,7 @@ static int hclge_misc_irq_init(struct hclge_dev *hdev)
 	snprintf(hdev->misc_vector.name, HNAE3_INT_NAME_LEN, "%s-misc-%s",
 		 HCLGE_NAME, pci_name(hdev->pdev));
 	ret = request_irq(hdev->misc_vector.vector_irq, hclge_misc_irq_handle,
-			  0, hdev->misc_vector.name, hdev);
+			  IRQ_NOAUTOEN, hdev->misc_vector.name, hdev);
 	if (ret) {
 		hclge_free_vector(hdev, 0);
 		dev_err(&hdev->pdev->dev, "request misc irq(%d) fail\n",
@@ -4062,7 +4074,7 @@ static void hclge_do_reset(struct hclge_dev *hdev)
 	case HNAE3_FUNC_RESET:
 		dev_info(&pdev->dev, "PF reset requested\n");
 		/* schedule again to check later */
-		set_bit(HNAE3_FUNC_RESET, &hdev->reset_pending);
+		hclge_set_reset_pending(hdev, HNAE3_FUNC_RESET);
 		hclge_reset_task_schedule(hdev);
 		break;
 	default:
@@ -4096,6 +4108,8 @@ static enum hnae3_reset_type hclge_get_reset_level(struct hnae3_ae_dev *ae_dev,
 		clear_bit(HNAE3_FLR_RESET, addr);
 	}
 
+	clear_bit(HNAE3_NONE_RESET, addr);
+
 	if (hdev->reset_type != HNAE3_NONE_RESET &&
 	    rst_level < hdev->reset_type)
 		return HNAE3_NONE_RESET;
@@ -4237,7 +4251,7 @@ static bool hclge_reset_err_handle(struct hclge_dev *hdev)
 		return false;
 	} else if (hdev->rst_stats.reset_fail_cnt < MAX_RESET_FAIL_CNT) {
 		hdev->rst_stats.reset_fail_cnt++;
-		set_bit(hdev->reset_type, &hdev->reset_pending);
+		hclge_set_reset_pending(hdev, hdev->reset_type);
 		dev_info(&hdev->pdev->dev,
 			 "re-schedule reset task(%u)\n",
 			 hdev->rst_stats.reset_fail_cnt);
@@ -4480,8 +4494,20 @@ static void hclge_reset_event(struct pci_dev *pdev, struct hnae3_handle *handle)
 static void hclge_set_def_reset_request(struct hnae3_ae_dev *ae_dev,
 					enum hnae3_reset_type rst_type)
 {
+#define HCLGE_SUPPORT_RESET_TYPE \
+	(BIT(HNAE3_FLR_RESET) | BIT(HNAE3_FUNC_RESET) | \
+	BIT(HNAE3_GLOBAL_RESET) | BIT(HNAE3_IMP_RESET))
+
 	struct hclge_dev *hdev = ae_dev->priv;
 
+	if (!(BIT(rst_type) & HCLGE_SUPPORT_RESET_TYPE)) {
+		/* To prevent reset triggered by hclge_reset_event */
+		set_bit(HNAE3_NONE_RESET, &hdev->default_reset_request);
+		dev_warn(&hdev->pdev->dev, "unsupported reset type %d\n",
+			 rst_type);
+		return;
+	}
+
 	set_bit(rst_type, &hdev->default_reset_request);
 }
 
@@ -11891,9 +11917,6 @@ static int hclge_init_ae_dev(struct hnae3_ae_dev *ae_dev)
 
 	hclge_init_rxd_adv_layout(hdev);
 
-	/* Enable MISC vector(vector0) */
-	hclge_enable_vector(&hdev->misc_vector, true);
-
 	ret = hclge_init_wol(hdev);
 	if (ret)
 		dev_warn(&pdev->dev,
@@ -11906,6 +11929,10 @@ static int hclge_init_ae_dev(struct hnae3_ae_dev *ae_dev)
 	hclge_state_init(hdev);
 	hdev->last_reset_time = jiffies;
 
+	/* Enable MISC vector(vector0) */
+	enable_irq(hdev->misc_vector.vector_irq);
+	hclge_enable_vector(&hdev->misc_vector, true);
+
 	dev_info(&hdev->pdev->dev, "%s driver initialization finished.\n",
 		 HCLGE_DRIVER_NAME);
 
@@ -12311,7 +12338,7 @@ static void hclge_uninit_ae_dev(struct hnae3_ae_dev *ae_dev)
 
 	/* Disable MISC vector(vector0) */
 	hclge_enable_vector(&hdev->misc_vector, false);
-	synchronize_irq(hdev->misc_vector.vector_irq);
+	disable_irq(hdev->misc_vector.vector_irq);
 
 	/* Disable all hw interrupts */
 	hclge_config_mac_tnl_int(hdev, false);

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

@@ -58,6 +58,9 @@ bool hclge_ptp_set_tx_info(struct hnae3_handle *handle, struct sk_buff *skb)
 	struct hclge_dev *hdev = vport->back;
 	struct hclge_ptp *ptp = hdev->ptp;
 
+	if (!ptp)
+		return false;
+
 	if (!test_bit(HCLGE_PTP_FLAG_TX_EN, &ptp->flags) ||
 	    test_and_set_bit(HCLGE_STATE_PTP_TX_HANDLING, &hdev->state)) {
 		ptp->tx_skipped++;

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

@@ -510,9 +510,9 @@ static int hclge_get_dfx_reg(struct hclge_dev *hdev, void *data)
 static int hclge_fetch_pf_reg(struct hclge_dev *hdev, void *data,
 			      struct hnae3_knic_private_info *kinfo)
 {
-#define HCLGE_RING_REG_OFFSET		0x200
 #define HCLGE_RING_INT_REG_OFFSET	0x4
 
+	struct hnae3_queue *tqp;
 	int i, j, reg_num;
 	int data_num_sum;
 	u32 *reg = data;
@@ -533,10 +533,11 @@ static int hclge_fetch_pf_reg(struct hclge_dev *hdev, void *data,
 	reg_num = ARRAY_SIZE(ring_reg_addr_list);
 	for (j = 0; j < kinfo->num_tqps; j++) {
 		reg += hclge_reg_get_tlv(HCLGE_REG_TAG_RING, reg_num, reg);
+		tqp = kinfo->tqp[j];
 		for (i = 0; i < reg_num; i++)
-			*reg++ = hclge_read_dev(&hdev->hw,
-						ring_reg_addr_list[i] +
-						HCLGE_RING_REG_OFFSET * j);
+			*reg++ = readl_relaxed(tqp->io_base -
+					       HCLGE_TQP_REG_OFFSET +
+					       ring_reg_addr_list[i]);
 	}
 	data_num_sum += (reg_num + HCLGE_REG_TLV_SPACE) * kinfo->num_tqps;