Merge tag 'net-6.10-rc2' of git://git.kernel.org/pub/scm/linux/kernel…

…/git/netdev/net

Pull networking fixes from Paolo Abeni:
 "Including fixes from bpf and netfilter.

  Current release - regressions:

   - gro: initialize network_offset in network layer

   - tcp: reduce accepted window in NEW_SYN_RECV state

  Current release - new code bugs:

   - eth: mlx5e: do not use ptp structure for tx ts stats when not
     initialized

   - eth: ice: check for unregistering correct number of devlink params

  Previous releases - regressions:

   - bpf: Allow delete from sockmap/sockhash only if update is allowed

   - sched: taprio: extend minimum interval restriction to entire cycle
     too

   - netfilter: ipset: add list flush to cancel_gc

   - ipv4: fix address dump when IPv4 is disabled on an interface

   - sock_map: avoid race between sock_map_close and sk_psock_put

   - eth: mlx5: use mlx5_ipsec_rx_status_destroy to correctly delete
     status rules

  Previous releases - always broken:

   - core: fix __dst_negative_advice() race

   - bpf:
       - fix multi-uprobe PID filtering logic
       - fix pkt_type override upon netkit pass verdict

   - netfilter: tproxy: bail out if IP has been disabled on the device

   - af_unix: annotate data-race around unix_sk(sk)->addr

   - eth: mlx5e: fix UDP GSO for encapsulated packets

   - eth: idpf: don't enable NAPI and interrupts prior to allocating Rx
     buffers

   - eth: i40e: fully suspend and resume IO operations in EEH case

   - eth: octeontx2-pf: free send queue buffers incase of leaf to inner

   - eth: ipvlan: dont Use skb->sk in ipvlan_process_v{4,6}_outbound"

* tag 'net-6.10-rc2' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net: (69 commits)
  netdev: add qstat for csum complete
  ipvlan: Dont Use skb->sk in ipvlan_process_v{4,6}_outbound
  net: ena: Fix redundant device NUMA node override
  ice: check for unregistering correct number of devlink params
  ice: fix 200G PHY types to link speed mapping
  i40e: Fully suspend and resume IO operations in EEH case
  i40e: factoring out i40e_suspend/i40e_resume
  e1000e: move force SMBUS near the end of enable_ulp function
  net: dsa: microchip: fix RGMII error in KSZ DSA driver
  ipv4: correctly iterate over the target netns in inet_dump_ifaddr()
  net: fix __dst_negative_advice() race
  nfc/nci: Add the inconsistency check between the input data length and count
  MAINTAINERS: dwmac: starfive: update Maintainer
  net/sched: taprio: extend minimum interval restriction to entire cycle too
  net/sched: taprio: make q->picos_per_byte available to fill_sched_entry()
  netfilter: nft_fib: allow from forward/input without iif selector
  netfilter: tproxy: bail out if IP has been disabled on the device
  netfilter: nft_payload: skbuff vlan metadata mangle support
  net: ti: icssg-prueth: Fix start counter for ft1 filter
  sock_map: avoid race between sock_map_close and sk_psock_put
  ...

Documentation/devicetree/bindings/net/pse-pd/microchip,pd692x0.yaml

@@ -24,6 +24,7 @@ properties:
 
   managers:
     type: object
+    additionalProperties: false
     description:
       List of the PD69208T4/PD69204T4/PD69208M PSE managers. Each manager
       have 4 or 8 physical ports according to the chip version. No need to
@@ -47,8 +48,9 @@ properties:
       - "#size-cells"
 
     patternProperties:
-      "^manager@0[0-9a-b]$":
+      "^manager@[0-9a-b]$":
         type: object
+        additionalProperties: false
         description:
           PD69208T4/PD69204T4/PD69208M PSE manager exposing 4 or 8 physical
           ports.
@@ -69,9 +71,14 @@ properties:
         patternProperties:
           '^port@[0-7]$':
             type: object
+            additionalProperties: false
+
+            properties:
+              reg:
+                maxItems: 1
+
             required:
               - reg
-            additionalProperties: false
 
         required:
           - reg

Documentation/devicetree/bindings/net/pse-pd/ti,tps23881.yaml

@@ -29,13 +29,31 @@ properties:
       of the ports conversion matrix that establishes relationship between
       the logical ports and the physical channels.
     type: object
+    additionalProperties: false
+
+    properties:
+      "#address-cells":
+        const: 1
+
+      "#size-cells":
+        const: 0
 
     patternProperties:
       '^channel@[0-7]$':
         type: object
+        additionalProperties: false
+
+        properties:
+          reg:
+            maxItems: 1
+
         required:
           - reg
 
+    required:
+      - "#address-cells"
+      - "#size-cells"
+
 unevaluatedProperties: false
 
 required:

Documentation/netlink/specs/netdev.yaml

@@ -349,6 +349,10 @@ attribute-sets:
           Number of packets dropped due to transient lack of resources, such as
           buffer space, host descriptors etc.
         type: uint
+      -
+        name: rx-csum-complete
+        doc: Number of packets that were marked as CHECKSUM_COMPLETE.
+        type: uint
       -
         name: rx-csum-unnecessary
         doc: Number of packets that were marked as CHECKSUM_UNNECESSARY.

Documentation/process/maintainer-netdev.rst

@@ -227,7 +227,7 @@ preferably including links to previous postings, for example::
   The amount of mooing will depend on packet rate so should match
   the diurnal cycle quite well.
 
-  Signed-of-by: Joe Defarmer <[email protected]>
+  Signed-off-by: Joe Defarmer <[email protected]>
   ---
   v3:
     - add a note about time-of-day mooing fluctuation to the commit message

MAINTAINERS

@@ -3854,6 +3854,7 @@ BPF JIT for ARM64
 M:	Daniel Borkmann <[email protected]>
 M:	Alexei Starovoitov <[email protected]>
 M:	Puranjay Mohan <[email protected]>
+R:	Xu Kuohai <[email protected]>
 L:	[email protected]
 S:	Supported
 F:	arch/arm64/net/
@@ -21316,7 +21317,7 @@ F:	arch/riscv/boot/dts/starfive/
 
 STARFIVE DWMAC GLUE LAYER
 M:	Emil Renner Berthing <[email protected]>
-M:	Samin Guo <samin.guo@starfivetech.com>
+M:	Minda Chen <minda.chen@starfivetech.com>
 S:	Maintained
 F:	Documentation/devicetree/bindings/net/starfive,jh7110-dwmac.yaml
 F:	drivers/net/ethernet/stmicro/stmmac/dwmac-starfive.c

arch/arc/net/bpf_jit.h

@@ -39,7 +39,7 @@
 
 /************** Functions that the back-end must provide **************/
 /* Extension for 32-bit operations. */
-inline u8 zext(u8 *buf, u8 rd);
+u8 zext(u8 *buf, u8 rd);
 /***** Moves *****/
 u8 mov_r32(u8 *buf, u8 rd, u8 rs, u8 sign_ext);
 u8 mov_r32_i32(u8 *buf, u8 reg, s32 imm);

arch/arc/net/bpf_jit_arcv2.c

@@ -62,7 +62,7 @@ enum {
  *   If/when we decide to add ARCv2 instructions that do use register pairs,
  *   the mapping, hopefully, doesn't need to be revisited.
  */
-const u8 bpf2arc[][2] = {
+static const u8 bpf2arc[][2] = {
 	/* Return value from in-kernel function, and exit value from eBPF */
 	[BPF_REG_0] = {ARC_R_8, ARC_R_9},
 	/* Arguments from eBPF program to in-kernel function */
@@ -1302,7 +1302,7 @@ static u8 arc_b(u8 *buf, s32 offset)
 
 /************* Packers (Deal with BPF_REGs) **************/
 
-inline u8 zext(u8 *buf, u8 rd)
+u8 zext(u8 *buf, u8 rd)
 {
 	if (rd != BPF_REG_FP)
 		return arc_movi_r(buf, REG_HI(rd), 0);
@@ -2235,6 +2235,7 @@ u8 gen_swap(u8 *buf, u8 rd, u8 size, u8 endian, bool force, bool do_zext)
 			break;
 		default:
 			/* The caller must have handled this. */
+			break;
 		}
 	} else {
 		/*
@@ -2253,6 +2254,7 @@ u8 gen_swap(u8 *buf, u8 rd, u8 size, u8 endian, bool force, bool do_zext)
 			break;
 		default:
 			/* The caller must have handled this. */
+			break;
 		}
 	}
 
@@ -2517,7 +2519,7 @@ u8 arc_epilogue(u8 *buf, u32 usage, u16 frame_size)
 #define JCC64_NR_OF_JMPS 3	/* Number of jumps in jcc64 template. */
 #define JCC64_INSNS_TO_END 3	/* Number of insn. inclusive the 2nd jmp to end. */
 #define JCC64_SKIP_JMP 1	/* Index of the "skip" jump to "end". */
-const struct {
+static const struct {
 	/*
 	 * "jit_off" is common between all "jmp[]" and is coupled with
 	 * "cond" of each "jmp[]" instance. e.g.:
@@ -2883,7 +2885,7 @@ u8 gen_jmp_64(u8 *buf, u8 rd, u8 rs, u8 cond, u32 curr_off, u32 targ_off)
  * The "ARC_CC_SET" becomes "CC_unequal" because of the "tst"
  * instruction that precedes the conditional branch.
  */
-const u8 arcv2_32_jmps[ARC_CC_LAST] = {
+static const u8 arcv2_32_jmps[ARC_CC_LAST] = {
 	[ARC_CC_UGT] = CC_great_u,
 	[ARC_CC_UGE] = CC_great_eq_u,
 	[ARC_CC_ULT] = CC_less_u,

arch/arc/net/bpf_jit_core.c

@@ -159,15 +159,15 @@ static void jit_dump(const struct jit_context *ctx)
 /* Initialise the context so there's no garbage. */
 static int jit_ctx_init(struct jit_context *ctx, struct bpf_prog *prog)
 {
-	memset(ctx, 0, sizeof(ctx));
+	memset(ctx, 0, sizeof(*ctx));
 
 	ctx->orig_prog = prog;
 
 	/* If constant blinding was requested but failed, scram. */
 	ctx->prog = bpf_jit_blind_constants(prog);
 	if (IS_ERR(ctx->prog))
 		return PTR_ERR(ctx->prog);
-	ctx->blinded = (ctx->prog == ctx->orig_prog ? false : true);
+	ctx->blinded = (ctx->prog != ctx->orig_prog);
 
 	/* If the verifier doesn't zero-extend, then we have to do it. */
 	ctx->do_zext = !ctx->prog->aux->verifier_zext;
@@ -1182,12 +1182,12 @@ static int jit_prepare(struct jit_context *ctx)
 }
 
 /*
- * All the "handle_*()" functions have been called before by the
- * "jit_prepare()". If there was an error, we would know by now.
- * Therefore, no extra error checking at this point, other than
- * a sanity check at the end that expects the calculated length
- * (jit.len) to be equal to the length of generated instructions
- * (jit.index).
+ * jit_compile() is the real compilation phase. jit_prepare() is
+ * invoked before jit_compile() as a dry-run to make sure everything
+ * will go OK and allocate the necessary memory.
+ *
+ * In the end, jit_compile() checks if it has produced the same number
+ * of instructions as jit_prepare() would.
  */
 static int jit_compile(struct jit_context *ctx)
 {
@@ -1407,9 +1407,9 @@ static struct bpf_prog *do_extra_pass(struct bpf_prog *prog)
 
 /*
  * This function may be invoked twice for the same stream of BPF
- * instructions. The "extra pass" happens, when there are "call"s
- * involved that their addresses are not known during the first
- * invocation.
+ * instructions. The "extra pass" happens, when there are
+ * (re)locations involved that their addresses are not known
+ * during the first run.
  */
 struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
 {

drivers/net/dsa/microchip/ksz_common.c

@@ -3142,7 +3142,7 @@ phy_interface_t ksz_get_xmii(struct ksz_device *dev, int port, bool gbit)
 		else
 			interface = PHY_INTERFACE_MODE_MII;
 	} else if (val == bitval[P_RMII_SEL]) {
-		interface = PHY_INTERFACE_MODE_RGMII;
+		interface = PHY_INTERFACE_MODE_RMII;
 	} else {
 		interface = PHY_INTERFACE_MODE_RGMII;
 		if (data8 & P_RGMII_ID_EG_ENABLE)

drivers/net/ethernet/amazon/ena/ena_com.c

@@ -312,7 +312,6 @@ static int ena_com_init_io_sq(struct ena_com_dev *ena_dev,
 			      struct ena_com_io_sq *io_sq)
 {
 	size_t size;
-	int dev_node = 0;
 
 	memset(&io_sq->desc_addr, 0x0, sizeof(io_sq->desc_addr));
 
@@ -325,12 +324,9 @@ static int ena_com_init_io_sq(struct ena_com_dev *ena_dev,
 	size = io_sq->desc_entry_size * io_sq->q_depth;
 
 	if (io_sq->mem_queue_type == ENA_ADMIN_PLACEMENT_POLICY_HOST) {
-		dev_node = dev_to_node(ena_dev->dmadev);
-		set_dev_node(ena_dev->dmadev, ctx->numa_node);
 		io_sq->desc_addr.virt_addr =
 			dma_alloc_coherent(ena_dev->dmadev, size, &io_sq->desc_addr.phys_addr,
 					   GFP_KERNEL);
-		set_dev_node(ena_dev->dmadev, dev_node);
 		if (!io_sq->desc_addr.virt_addr) {
 			io_sq->desc_addr.virt_addr =
 				dma_alloc_coherent(ena_dev->dmadev, size,
@@ -354,10 +350,7 @@ static int ena_com_init_io_sq(struct ena_com_dev *ena_dev,
 		size = (size_t)io_sq->bounce_buf_ctrl.buffer_size *
 			io_sq->bounce_buf_ctrl.buffers_num;
 
-		dev_node = dev_to_node(ena_dev->dmadev);
-		set_dev_node(ena_dev->dmadev, ctx->numa_node);
 		io_sq->bounce_buf_ctrl.base_buffer = devm_kzalloc(ena_dev->dmadev, size, GFP_KERNEL);
-		set_dev_node(ena_dev->dmadev, dev_node);
 		if (!io_sq->bounce_buf_ctrl.base_buffer)
 			io_sq->bounce_buf_ctrl.base_buffer =
 				devm_kzalloc(ena_dev->dmadev, size, GFP_KERNEL);
@@ -397,7 +390,6 @@ static int ena_com_init_io_cq(struct ena_com_dev *ena_dev,
 			      struct ena_com_io_cq *io_cq)
 {
 	size_t size;
-	int prev_node = 0;
 
 	memset(&io_cq->cdesc_addr, 0x0, sizeof(io_cq->cdesc_addr));
 
@@ -409,11 +401,8 @@ static int ena_com_init_io_cq(struct ena_com_dev *ena_dev,
 
 	size = io_cq->cdesc_entry_size_in_bytes * io_cq->q_depth;
 
-	prev_node = dev_to_node(ena_dev->dmadev);
-	set_dev_node(ena_dev->dmadev, ctx->numa_node);
 	io_cq->cdesc_addr.virt_addr =
 		dma_alloc_coherent(ena_dev->dmadev, size, &io_cq->cdesc_addr.phys_addr, GFP_KERNEL);
-	set_dev_node(ena_dev->dmadev, prev_node);
 	if (!io_cq->cdesc_addr.virt_addr) {
 		io_cq->cdesc_addr.virt_addr =
 			dma_alloc_coherent(ena_dev->dmadev, size, &io_cq->cdesc_addr.phys_addr,

drivers/net/ethernet/cisco/enic/enic_main.c

@@ -1117,18 +1117,30 @@ static int enic_set_vf_port(struct net_device *netdev, int vf,
 	pp->request = nla_get_u8(port[IFLA_PORT_REQUEST]);
 
 	if (port[IFLA_PORT_PROFILE]) {
+		if (nla_len(port[IFLA_PORT_PROFILE]) != PORT_PROFILE_MAX) {
+			memcpy(pp, &prev_pp, sizeof(*pp));
+			return -EINVAL;
+		}
 		pp->set |= ENIC_SET_NAME;
 		memcpy(pp->name, nla_data(port[IFLA_PORT_PROFILE]),
 			PORT_PROFILE_MAX);
 	}
 
 	if (port[IFLA_PORT_INSTANCE_UUID]) {
+		if (nla_len(port[IFLA_PORT_INSTANCE_UUID]) != PORT_UUID_MAX) {
+			memcpy(pp, &prev_pp, sizeof(*pp));
+			return -EINVAL;
+		}
 		pp->set |= ENIC_SET_INSTANCE;
 		memcpy(pp->instance_uuid,
 			nla_data(port[IFLA_PORT_INSTANCE_UUID]), PORT_UUID_MAX);
 	}
 
 	if (port[IFLA_PORT_HOST_UUID]) {
+		if (nla_len(port[IFLA_PORT_HOST_UUID]) != PORT_UUID_MAX) {
+			memcpy(pp, &prev_pp, sizeof(*pp));
+			return -EINVAL;
+		}
 		pp->set |= ENIC_SET_HOST;
 		memcpy(pp->host_uuid,
 			nla_data(port[IFLA_PORT_HOST_UUID]), PORT_UUID_MAX);

drivers/net/ethernet/freescale/fec_main.c

@@ -4130,6 +4130,14 @@ static int fec_enet_init(struct net_device *ndev)
 	return ret;
 }
 
+static void fec_enet_deinit(struct net_device *ndev)
+{
+	struct fec_enet_private *fep = netdev_priv(ndev);
+
+	netif_napi_del(&fep->napi);
+	fec_enet_free_queue(ndev);
+}
+
 #ifdef CONFIG_OF
 static int fec_reset_phy(struct platform_device *pdev)
 {
@@ -4524,6 +4532,7 @@ fec_probe(struct platform_device *pdev)
 	fec_enet_mii_remove(fep);
 failed_mii_init:
 failed_irq:
+	fec_enet_deinit(ndev);
 failed_init:
 	fec_ptp_stop(pdev);
 failed_reset:
@@ -4587,6 +4596,7 @@ fec_drv_remove(struct platform_device *pdev)
 	pm_runtime_put_noidle(&pdev->dev);
 	pm_runtime_disable(&pdev->dev);
 
+	fec_enet_deinit(ndev);
 	free_netdev(ndev);
 }
 

drivers/net/ethernet/intel/e1000e/ich8lan.c

@@ -1225,6 +1225,28 @@ s32 e1000_enable_ulp_lpt_lp(struct e1000_hw *hw, bool to_sx)
 	}
 
 release:
+	/* Switching PHY interface always returns MDI error
+	 * so disable retry mechanism to avoid wasting time
+	 */
+	e1000e_disable_phy_retry(hw);
+
+	/* Force SMBus mode in PHY */
+	ret_val = e1000_read_phy_reg_hv_locked(hw, CV_SMB_CTRL, &phy_reg);
+	if (ret_val) {
+		e1000e_enable_phy_retry(hw);
+		hw->phy.ops.release(hw);
+		goto out;
+	}
+	phy_reg |= CV_SMB_CTRL_FORCE_SMBUS;
+	e1000_write_phy_reg_hv_locked(hw, CV_SMB_CTRL, phy_reg);
+
+	e1000e_enable_phy_retry(hw);
+
+	/* Force SMBus mode in MAC */
+	mac_reg = er32(CTRL_EXT);
+	mac_reg |= E1000_CTRL_EXT_FORCE_SMBUS;
+	ew32(CTRL_EXT, mac_reg);
+
 	hw->phy.ops.release(hw);
 out:
 	if (ret_val)

drivers/net/ethernet/intel/e1000e/netdev.c

@@ -6623,7 +6623,6 @@ static int __e1000_shutdown(struct pci_dev *pdev, bool runtime)
 	struct e1000_hw *hw = &adapter->hw;
 	u32 ctrl, ctrl_ext, rctl, status, wufc;
 	int retval = 0;
-	u16 smb_ctrl;
 
 	/* Runtime suspend should only enable wakeup for link changes */
 	if (runtime)
@@ -6697,23 +6696,6 @@ static int __e1000_shutdown(struct pci_dev *pdev, bool runtime)
 			if (retval)
 				return retval;
 		}
-
-		/* Force SMBUS to allow WOL */
-		/* Switching PHY interface always returns MDI error
-		 * so disable retry mechanism to avoid wasting time
-		 */
-		e1000e_disable_phy_retry(hw);
-
-		e1e_rphy(hw, CV_SMB_CTRL, &smb_ctrl);
-		smb_ctrl |= CV_SMB_CTRL_FORCE_SMBUS;
-		e1e_wphy(hw, CV_SMB_CTRL, smb_ctrl);
-
-		e1000e_enable_phy_retry(hw);
-
-		/* Force SMBus mode in MAC */
-		ctrl_ext = er32(CTRL_EXT);
-		ctrl_ext |= E1000_CTRL_EXT_FORCE_SMBUS;
-		ew32(CTRL_EXT, ctrl_ext);
 	}
 
 	/* Ensure that the appropriate bits are set in LPI_CTRL