Merge tag 'net-6.9-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net

Pull networking fixes from Jakub Kicinski:
 "Including fixes from CAN, netfilter, wireguard and IPsec.

  I'd like to highlight [ lowlight? - Linus ] Florian W stepping down as
  a netfilter maintainer due to constant stream of bug reports. Not sure
  what we can do but IIUC this is not the first such case.

  Current release - regressions:

   - rxrpc: fix use of page_frag_alloc_align(), it changed semantics and
     we added a new caller in a different subtree

   - xfrm: allow UDP encapsulation only in offload modes

  Current release - new code bugs:

   - tcp: fix refcnt handling in __inet_hash_connect()

   - Revert "net: Re-use and set mono_delivery_time bit for userspace
     tstamp packets", conflicted with some expectations in BPF uAPI

  Previous releases - regressions:

   - ipv4: raw: fix sending packets from raw sockets via IPsec tunnels

   - devlink: fix devlink's parallel command processing

   - veth: do not manipulate GRO when using XDP

   - esp: fix bad handling of pages from page_pool

  Previous releases - always broken:

   - report RCU QS for busy network kthreads (with Paul McK's blessing)

   - tcp/rds: fix use-after-free on netns with kernel TCP reqsk

   - virt: vmxnet3: fix missing reserved tailroom with XDP

  Misc:

   - couple of build fixes for Documentation"

* tag 'net-6.9-rc1' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (59 commits)
  selftests: forwarding: Fix ping failure due to short timeout
  MAINTAINERS: step down as netfilter maintainer
  netfilter: nf_tables: Fix a memory leak in nf_tables_updchain
  net: dsa: mt7530: fix handling of all link-local frames
  net: dsa: mt7530: fix link-local frames that ingress vlan filtering ports
  bpf: report RCU QS in cpumap kthread
  net: report RCU QS on threaded NAPI repolling
  rcu: add a helper to report consolidated flavor QS
  ionic: update documentation for XDP support
  lib/bitmap: Fix bitmap_scatter() and bitmap_gather() kernel doc
  netfilter: nf_tables: do not compare internal table flags on updates
  netfilter: nft_set_pipapo: release elements in clone only from destroy path
  octeontx2-af: Use separate handlers for interrupts
  octeontx2-pf: Send UP messages to VF only when VF is up.
  octeontx2-pf: Use default max_active works instead of one
  octeontx2-pf: Wait till detach_resources msg is complete
  octeontx2: Detect the mbox up or down message via register
  devlink: fix port new reply cmd type
  tcp: Clear req->syncookie in reqsk_alloc().
  net/bnx2x: Prevent access to a freed page in page_pool
  ...

Author: torvalds

Documentation/networking/device_drivers/ethernet/pensando/ionic.rst

@@ -99,6 +99,12 @@ Minimal SR-IOV support is currently offered and can be enabled by setting
 the sysfs 'sriov_numvfs' value, if supported by your particular firmware
 configuration.
 
+XDP
+---
+
+Support for XDP includes the basics, plus Jumbo frames, Redirect and
+ndo_xmit.  There is no current support for zero-copy sockets or HW offload.
+
 Statistics
 ==========
 
@@ -138,6 +144,12 @@ Driver port specific::
      rx_csum_none: 0
      rx_csum_complete: 3
      rx_csum_error: 0
+     xdp_drop: 0
+     xdp_aborted: 0
+     xdp_pass: 0
+     xdp_tx: 0
+     xdp_redirect: 0
+     xdp_frames: 0
 
 Driver queue specific::
 
@@ -149,18 +161,28 @@ Driver queue specific::
      tx_0_frags: 0
      tx_0_tso: 0
      tx_0_tso_bytes: 0
+     tx_0_hwstamp_valid: 0
+     tx_0_hwstamp_invalid: 0
      tx_0_csum_none: 3
      tx_0_csum: 0
      tx_0_vlan_inserted: 0
+     tx_0_xdp_frames: 0
      rx_0_pkts: 2
      rx_0_bytes: 120
      rx_0_dma_map_err: 0
      rx_0_alloc_err: 0
      rx_0_csum_none: 0
      rx_0_csum_complete: 0
      rx_0_csum_error: 0
+     rx_0_hwstamp_valid: 0
+     rx_0_hwstamp_invalid: 0
      rx_0_dropped: 0
      rx_0_vlan_stripped: 0
+     rx_0_xdp_drop: 0
+     rx_0_xdp_aborted: 0
+     rx_0_xdp_pass: 0
+     rx_0_xdp_tx: 0
+     rx_0_xdp_redirect: 0
 
 Firmware port specific::
 

Documentation/networking/multi-pf-netdev.rst

@@ -87,35 +87,35 @@ all using the same instance under "priv->mdev".
 
 Observability
 =============
-The relation between PF, irq, napi, and queue can be observed via netlink spec:
-
-$ ./tools/net/ynl/cli.py --spec Documentation/netlink/specs/netdev.yaml --dump queue-get --json='{"ifindex": 13}'
-[{'id': 0, 'ifindex': 13, 'napi-id': 539, 'type': 'rx'},
- {'id': 1, 'ifindex': 13, 'napi-id': 540, 'type': 'rx'},
- {'id': 2, 'ifindex': 13, 'napi-id': 541, 'type': 'rx'},
- {'id': 3, 'ifindex': 13, 'napi-id': 542, 'type': 'rx'},
- {'id': 4, 'ifindex': 13, 'napi-id': 543, 'type': 'rx'},
- {'id': 0, 'ifindex': 13, 'napi-id': 539, 'type': 'tx'},
- {'id': 1, 'ifindex': 13, 'napi-id': 540, 'type': 'tx'},
- {'id': 2, 'ifindex': 13, 'napi-id': 541, 'type': 'tx'},
- {'id': 3, 'ifindex': 13, 'napi-id': 542, 'type': 'tx'},
- {'id': 4, 'ifindex': 13, 'napi-id': 543, 'type': 'tx'}]
-
-$ ./tools/net/ynl/cli.py --spec Documentation/netlink/specs/netdev.yaml --dump napi-get --json='{"ifindex": 13}'
-[{'id': 543, 'ifindex': 13, 'irq': 42},
- {'id': 542, 'ifindex': 13, 'irq': 41},
- {'id': 541, 'ifindex': 13, 'irq': 40},
- {'id': 540, 'ifindex': 13, 'irq': 39},
- {'id': 539, 'ifindex': 13, 'irq': 36}]
-
-Here you can clearly observe our channels distribution policy:
-
-$ ls /proc/irq/{36,39,40,41,42}/mlx5* -d -1
-/proc/irq/36/mlx5_comp1@pci:0000:08:00.0
-/proc/irq/39/mlx5_comp1@pci:0000:09:00.0
-/proc/irq/40/mlx5_comp2@pci:0000:08:00.0
-/proc/irq/41/mlx5_comp2@pci:0000:09:00.0
-/proc/irq/42/mlx5_comp3@pci:0000:08:00.0
+The relation between PF, irq, napi, and queue can be observed via netlink spec::
+
+  $ ./tools/net/ynl/cli.py --spec Documentation/netlink/specs/netdev.yaml --dump queue-get --json='{"ifindex": 13}'
+  [{'id': 0, 'ifindex': 13, 'napi-id': 539, 'type': 'rx'},
+   {'id': 1, 'ifindex': 13, 'napi-id': 540, 'type': 'rx'},
+   {'id': 2, 'ifindex': 13, 'napi-id': 541, 'type': 'rx'},
+   {'id': 3, 'ifindex': 13, 'napi-id': 542, 'type': 'rx'},
+   {'id': 4, 'ifindex': 13, 'napi-id': 543, 'type': 'rx'},
+   {'id': 0, 'ifindex': 13, 'napi-id': 539, 'type': 'tx'},
+   {'id': 1, 'ifindex': 13, 'napi-id': 540, 'type': 'tx'},
+   {'id': 2, 'ifindex': 13, 'napi-id': 541, 'type': 'tx'},
+   {'id': 3, 'ifindex': 13, 'napi-id': 542, 'type': 'tx'},
+   {'id': 4, 'ifindex': 13, 'napi-id': 543, 'type': 'tx'}]
+
+  $ ./tools/net/ynl/cli.py --spec Documentation/netlink/specs/netdev.yaml --dump napi-get --json='{"ifindex": 13}'
+  [{'id': 543, 'ifindex': 13, 'irq': 42},
+   {'id': 542, 'ifindex': 13, 'irq': 41},
+   {'id': 541, 'ifindex': 13, 'irq': 40},
+   {'id': 540, 'ifindex': 13, 'irq': 39},
+   {'id': 539, 'ifindex': 13, 'irq': 36}]
+
+Here you can clearly observe our channels distribution policy::
+
+  $ ls /proc/irq/{36,39,40,41,42}/mlx5* -d -1
+  /proc/irq/36/mlx5_comp1@pci:0000:08:00.0
+  /proc/irq/39/mlx5_comp1@pci:0000:09:00.0
+  /proc/irq/40/mlx5_comp2@pci:0000:08:00.0
+  /proc/irq/41/mlx5_comp2@pci:0000:09:00.0
+  /proc/irq/42/mlx5_comp3@pci:0000:08:00.0
 
 Steering
 ========

Documentation/networking/net_cachelines/net_device.rst

@@ -13,7 +13,7 @@ struct_dev_ifalias*                 ifalias
 unsigned_long                       mem_end                                                         
 unsigned_long                       mem_start                                                       
 unsigned_long                       base_addr                                                       
-unsigned_long                       state                                                           
+unsigned_long                       state                   read_mostly         read_mostly         netif_running(dev)
 struct_list_head                    dev_list                                                        
 struct_list_head                    napi_list                                                       
 struct_list_head                    unreg_list                                                      

MAINTAINERS

@@ -15237,7 +15237,6 @@ F:	drivers/net/ethernet/neterion/
 NETFILTER
 M:	Pablo Neira Ayuso <[email protected]>
 M:	Jozsef Kadlecsik <[email protected]>
-M:	Florian Westphal <[email protected]>
 L:	[email protected]
 L:	[email protected]
 S:	Maintained

drivers/net/can/kvaser_pciefd.c

@@ -370,8 +370,8 @@ static const struct kvaser_pciefd_irq_mask kvaser_pciefd_sf2_irq_mask = {
 
 static const struct kvaser_pciefd_irq_mask kvaser_pciefd_xilinx_irq_mask = {
 	.kcan_rx0 = BIT(4),
-	.kcan_tx = { BIT(16), BIT(17), BIT(18), BIT(19) },
-	.all = GENMASK(19, 16) | BIT(4),
+	.kcan_tx = { BIT(16), BIT(17), BIT(18), BIT(19), BIT(20), BIT(21), BIT(22), BIT(23) },
+	.all = GENMASK(23, 16) | BIT(4),
 };
 
 static const struct kvaser_pciefd_dev_ops kvaser_pciefd_altera_dev_ops = {

drivers/net/dsa/mt7530.c

@@ -950,20 +950,56 @@ static void mt7530_setup_port5(struct dsa_switch *ds, phy_interface_t interface)
 	mutex_unlock(&priv->reg_mutex);
 }
 
+/* On page 205, section "8.6.3 Frame filtering" of the active standard, IEEE Std
+ * 802.1Q™-2022, it is stated that frames with 01:80:C2:00:00:00-0F as MAC DA
+ * must only be propagated to C-VLAN and MAC Bridge components. That means
+ * VLAN-aware and VLAN-unaware bridges. On the switch designs with CPU ports,
+ * these frames are supposed to be processed by the CPU (software). So we make
+ * the switch only forward them to the CPU port. And if received from a CPU
+ * port, forward to a single port. The software is responsible of making the
+ * switch conform to the latter by setting a single port as destination port on
+ * the special tag.
+ *
+ * This switch intellectual property cannot conform to this part of the standard
+ * fully. Whilst the REV_UN frame tag covers the remaining :04-0D and :0F MAC
+ * DAs, it also includes :22-FF which the scope of propagation is not supposed
+ * to be restricted for these MAC DAs.
+ */
 static void
 mt753x_trap_frames(struct mt7530_priv *priv)
 {
-	/* Trap BPDUs to the CPU port(s) */
-	mt7530_rmw(priv, MT753X_BPC, MT753X_BPDU_PORT_FW_MASK,
+	/* Trap 802.1X PAE frames and BPDUs to the CPU port(s) and egress them
+	 * VLAN-untagged.
+	 */
+	mt7530_rmw(priv, MT753X_BPC, MT753X_PAE_EG_TAG_MASK |
+		   MT753X_PAE_PORT_FW_MASK | MT753X_BPDU_EG_TAG_MASK |
+		   MT753X_BPDU_PORT_FW_MASK,
+		   MT753X_PAE_EG_TAG(MT7530_VLAN_EG_UNTAGGED) |
+		   MT753X_PAE_PORT_FW(MT753X_BPDU_CPU_ONLY) |
+		   MT753X_BPDU_EG_TAG(MT7530_VLAN_EG_UNTAGGED) |
 		   MT753X_BPDU_CPU_ONLY);
 
-	/* Trap 802.1X PAE frames to the CPU port(s) */
-	mt7530_rmw(priv, MT753X_BPC, MT753X_PAE_PORT_FW_MASK,
-		   MT753X_PAE_PORT_FW(MT753X_BPDU_CPU_ONLY));
+	/* Trap frames with :01 and :02 MAC DAs to the CPU port(s) and egress
+	 * them VLAN-untagged.
+	 */
+	mt7530_rmw(priv, MT753X_RGAC1, MT753X_R02_EG_TAG_MASK |
+		   MT753X_R02_PORT_FW_MASK | MT753X_R01_EG_TAG_MASK |
+		   MT753X_R01_PORT_FW_MASK,
+		   MT753X_R02_EG_TAG(MT7530_VLAN_EG_UNTAGGED) |
+		   MT753X_R02_PORT_FW(MT753X_BPDU_CPU_ONLY) |
+		   MT753X_R01_EG_TAG(MT7530_VLAN_EG_UNTAGGED) |
+		   MT753X_BPDU_CPU_ONLY);
 
-	/* Trap LLDP frames with :0E MAC DA to the CPU port(s) */
-	mt7530_rmw(priv, MT753X_RGAC2, MT753X_R0E_PORT_FW_MASK,
-		   MT753X_R0E_PORT_FW(MT753X_BPDU_CPU_ONLY));
+	/* Trap frames with :03 and :0E MAC DAs to the CPU port(s) and egress
+	 * them VLAN-untagged.
+	 */
+	mt7530_rmw(priv, MT753X_RGAC2, MT753X_R0E_EG_TAG_MASK |
+		   MT753X_R0E_PORT_FW_MASK | MT753X_R03_EG_TAG_MASK |
+		   MT753X_R03_PORT_FW_MASK,
+		   MT753X_R0E_EG_TAG(MT7530_VLAN_EG_UNTAGGED) |
+		   MT753X_R0E_PORT_FW(MT753X_BPDU_CPU_ONLY) |
+		   MT753X_R03_EG_TAG(MT7530_VLAN_EG_UNTAGGED) |
+		   MT753X_BPDU_CPU_ONLY);
 }
 
 static void
@@ -2192,22 +2228,16 @@ mt7530_setup(struct dsa_switch *ds)
 		}
 	}
 
-	/* Disable LEDs before reset to prevent the MT7530 sampling a
-	 * potentially incorrect HT_XTAL_FSEL value.
-	 */
-	mt7530_write(priv, MT7530_LED_EN, 0);
-	usleep_range(1000, 1100);
-
 	/* Reset whole chip through gpio pin or memory-mapped registers for
 	 * different type of hardware
 	 */
 	if (priv->mcm) {
 		reset_control_assert(priv->rstc);
-		usleep_range(1000, 1100);
+		usleep_range(5000, 5100);
 		reset_control_deassert(priv->rstc);
 	} else {
 		gpiod_set_value_cansleep(priv->reset, 0);
-		usleep_range(1000, 1100);
+		usleep_range(5000, 5100);
 		gpiod_set_value_cansleep(priv->reset, 1);
 	}
 
@@ -2420,11 +2450,11 @@ mt7531_setup(struct dsa_switch *ds)
 	 */
 	if (priv->mcm) {
 		reset_control_assert(priv->rstc);
-		usleep_range(1000, 1100);
+		usleep_range(5000, 5100);
 		reset_control_deassert(priv->rstc);
 	} else {
 		gpiod_set_value_cansleep(priv->reset, 0);
-		usleep_range(1000, 1100);
+		usleep_range(5000, 5100);
 		gpiod_set_value_cansleep(priv->reset, 1);
 	}
 

drivers/net/dsa/mt7530.h

@@ -65,14 +65,33 @@ enum mt753x_id {
 
 /* Registers for BPDU and PAE frame control*/
 #define MT753X_BPC			0x24
-#define  MT753X_BPDU_PORT_FW_MASK	GENMASK(2, 0)
+#define  MT753X_PAE_EG_TAG_MASK		GENMASK(24, 22)
+#define  MT753X_PAE_EG_TAG(x)		FIELD_PREP(MT753X_PAE_EG_TAG_MASK, x)
 #define  MT753X_PAE_PORT_FW_MASK	GENMASK(18, 16)
 #define  MT753X_PAE_PORT_FW(x)		FIELD_PREP(MT753X_PAE_PORT_FW_MASK, x)
+#define  MT753X_BPDU_EG_TAG_MASK	GENMASK(8, 6)
+#define  MT753X_BPDU_EG_TAG(x)		FIELD_PREP(MT753X_BPDU_EG_TAG_MASK, x)
+#define  MT753X_BPDU_PORT_FW_MASK	GENMASK(2, 0)
+
+/* Register for :01 and :02 MAC DA frame control */
+#define MT753X_RGAC1			0x28
+#define  MT753X_R02_EG_TAG_MASK		GENMASK(24, 22)
+#define  MT753X_R02_EG_TAG(x)		FIELD_PREP(MT753X_R02_EG_TAG_MASK, x)
+#define  MT753X_R02_PORT_FW_MASK	GENMASK(18, 16)
+#define  MT753X_R02_PORT_FW(x)		FIELD_PREP(MT753X_R02_PORT_FW_MASK, x)
+#define  MT753X_R01_EG_TAG_MASK		GENMASK(8, 6)
+#define  MT753X_R01_EG_TAG(x)		FIELD_PREP(MT753X_R01_EG_TAG_MASK, x)
+#define  MT753X_R01_PORT_FW_MASK	GENMASK(2, 0)
 
 /* Register for :03 and :0E MAC DA frame control */
 #define MT753X_RGAC2			0x2c
+#define  MT753X_R0E_EG_TAG_MASK		GENMASK(24, 22)
+#define  MT753X_R0E_EG_TAG(x)		FIELD_PREP(MT753X_R0E_EG_TAG_MASK, x)
 #define  MT753X_R0E_PORT_FW_MASK	GENMASK(18, 16)
 #define  MT753X_R0E_PORT_FW(x)		FIELD_PREP(MT753X_R0E_PORT_FW_MASK, x)
+#define  MT753X_R03_EG_TAG_MASK		GENMASK(8, 6)
+#define  MT753X_R03_EG_TAG(x)		FIELD_PREP(MT753X_R03_EG_TAG_MASK, x)
+#define  MT753X_R03_PORT_FW_MASK	GENMASK(2, 0)
 
 enum mt753x_bpdu_port_fw {
 	MT753X_BPDU_FOLLOW_MFC,
@@ -253,6 +272,7 @@ enum mt7530_port_mode {
 enum mt7530_vlan_port_eg_tag {
 	MT7530_VLAN_EG_DISABLED = 0,
 	MT7530_VLAN_EG_CONSISTENT = 1,
+	MT7530_VLAN_EG_UNTAGGED = 4,
 };
 
 enum mt7530_vlan_port_attr {

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

@@ -1002,9 +1002,6 @@ static inline void bnx2x_set_fw_mac_addr(__le16 *fw_hi, __le16 *fw_mid,
 static inline void bnx2x_free_rx_mem_pool(struct bnx2x *bp,
 					  struct bnx2x_alloc_pool *pool)
 {
-	if (!pool->page)
-		return;
-
 	put_page(pool->page);
 
 	pool->page = NULL;
@@ -1015,6 +1012,9 @@ static inline void bnx2x_free_rx_sge_range(struct bnx2x *bp,
 {
 	int i;
 
+	if (!fp->page_pool.page)
+		return;
+
 	if (fp->mode == TPA_MODE_DISABLED)
 		return;
 

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

@@ -1338,7 +1338,7 @@ static irqreturn_t cgx_fwi_event_handler(int irq, void *data)
 
 		/* Release thread waiting for completion  */
 		lmac->cmd_pend = false;
-		wake_up_interruptible(&lmac->wq_cmd_cmplt);
+		wake_up(&lmac->wq_cmd_cmplt);
 		break;
 	case CGX_EVT_ASYNC:
 		if (cgx_event_is_linkevent(event))

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

@@ -214,11 +214,12 @@ int otx2_mbox_busy_poll_for_rsp(struct otx2_mbox *mbox, int devid)
 }
 EXPORT_SYMBOL(otx2_mbox_busy_poll_for_rsp);
 
-void otx2_mbox_msg_send(struct otx2_mbox *mbox, int devid)
+static void otx2_mbox_msg_send_data(struct otx2_mbox *mbox, int devid, u64 data)
 {
 	struct otx2_mbox_dev *mdev = &mbox->dev[devid];
 	struct mbox_hdr *tx_hdr, *rx_hdr;
 	void *hw_mbase = mdev->hwbase;
+	u64 intr_val;
 
 	tx_hdr = hw_mbase + mbox->tx_start;
 	rx_hdr = hw_mbase + mbox->rx_start;
@@ -254,14 +255,52 @@ void otx2_mbox_msg_send(struct otx2_mbox *mbox, int devid)
 
 	spin_unlock(&mdev->mbox_lock);
 
+	/* Check if interrupt pending */
+	intr_val = readq((void __iomem *)mbox->reg_base +
+		     (mbox->trigger | (devid << mbox->tr_shift)));
+
+	intr_val |= data;
 	/* The interrupt should be fired after num_msgs is written
 	 * to the shared memory
 	 */
-	writeq(1, (void __iomem *)mbox->reg_base +
+	writeq(intr_val, (void __iomem *)mbox->reg_base +
 	       (mbox->trigger | (devid << mbox->tr_shift)));
 }
+
+void otx2_mbox_msg_send(struct otx2_mbox *mbox, int devid)
+{
+	otx2_mbox_msg_send_data(mbox, devid, MBOX_DOWN_MSG);
+}
 EXPORT_SYMBOL(otx2_mbox_msg_send);
 
+void otx2_mbox_msg_send_up(struct otx2_mbox *mbox, int devid)
+{
+	otx2_mbox_msg_send_data(mbox, devid, MBOX_UP_MSG);
+}
+EXPORT_SYMBOL(otx2_mbox_msg_send_up);
+
+bool otx2_mbox_wait_for_zero(struct otx2_mbox *mbox, int devid)
+{
+	u64 data;
+
+	data = readq((void __iomem *)mbox->reg_base +
+		     (mbox->trigger | (devid << mbox->tr_shift)));
+
+	/* If data is non-zero wait for ~1ms and return to caller
+	 * whether data has changed to zero or not after the wait.
+	 */
+	if (!data)
+		return true;
+
+	usleep_range(950, 1000);
+
+	data = readq((void __iomem *)mbox->reg_base +
+		     (mbox->trigger | (devid << mbox->tr_shift)));
+
+	return data == 0;
+}
+EXPORT_SYMBOL(otx2_mbox_wait_for_zero);
+
 struct mbox_msghdr *otx2_mbox_alloc_msg_rsp(struct otx2_mbox *mbox, int devid,
 					    int size, int size_rsp)
 {