Merge tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-nextgrafted

Pull networking updates from Jakub Kicinski:
 "Core:

   - Add dedicated kmem_cache for typical/small skb->head, avoid having
     to access struct page at kfree time, and improve memory use.

   - Introduce sysctl to set default RPS configuration for new netdevs.

   - Define Netlink protocol specification format which can be used to
     describe messages used by each family and auto-generate parsers.
     Add tools for generating kernel data structures and uAPI headers.

   - Expose all net/core sysctls inside netns.

   - Remove 4s sleep in netpoll if carrier is instantly detected on
     boot.

   - Add configurable limit of MDB entries per port, and port-vlan.

   - Continue populating drop reasons throughout the stack.

   - Retire a handful of legacy Qdiscs and classifiers.

  Protocols:

   - Support IPv4 big TCP (TSO frames larger than 64kB).

   - Add IP_LOCAL_PORT_RANGE socket option, to control local port range
     on socket by socket basis.

   - Track and report in procfs number of MPTCP sockets used.

   - Support mixing IPv4 and IPv6 flows in the in-kernel MPTCP path
     manager.

   - IPv6: don't check net.ipv6.route.max_size and rely on garbage
     collection to free memory (similarly to IPv4).

   - Support Penultimate Segment Pop (PSP) flavor in SRv6 (RFC8986).

   - ICMP: add per-rate limit counters.

   - Add support for user scanning requests in ieee802154.

   - Remove static WEP support.

   - Support minimal Wi-Fi 7 Extremely High Throughput (EHT) rate
     reporting.

   - WiFi 7 EHT channel puncturing support (client & AP).

  BPF:

   - Add a rbtree data structure following the "next-gen data structure"
     precedent set by recently added linked list, that is, by using
     kfunc + kptr instead of adding a new BPF map type.

   - Expose XDP hints via kfuncs with initial support for RX hash and
     timestamp metadata.

   - Add BPF_F_NO_TUNNEL_KEY extension to bpf_skb_set_tunnel_key to
     better support decap on GRE tunnel devices not operating in collect
     metadata.

   - Improve x86 JIT's codegen for PROBE_MEM runtime error checks.

   - Remove the need for trace_printk_lock for bpf_trace_printk and
     bpf_trace_vprintk helpers.

   - Extend libbpf's bpf_tracing.h support for tracing arguments of
     kprobes/uprobes and syscall as a special case.

   - Significantly reduce the search time for module symbols by
     livepatch and BPF.

   - Enable cpumasks to be used as kptrs, which is useful for tracing
     programs tracking which tasks end up running on which CPUs in
     different time intervals.

   - Add support for BPF trampoline on s390x and riscv64.

   - Add capability to export the XDP features supported by the NIC.

   - Add __bpf_kfunc tag for marking kernel functions as kfuncs.

   - Add cgroup.memory=nobpf kernel parameter option to disable BPF
     memory accounting for container environments.

  Netfilter:

   - Remove the CLUSTERIP target. It has been marked as obsolete for
     years, and we still have WARN splats wrt races of the out-of-band
     /proc interface installed by this target.

   - Add 'destroy' commands to nf_tables. They are identical to the
     existing 'delete' commands, but do not return an error if the
     referenced object (set, chain, rule...) did not exist.

  Driver API:

   - Improve cpumask_local_spread() locality to help NICs set the right
     IRQ affinity on AMD platforms.

   - Separate C22 and C45 MDIO bus transactions more clearly.

   - Introduce new DCB table to control DSCP rewrite on egress.

   - Support configuration of Physical Layer Collision Avoidance (PLCA)
     Reconciliation Sublayer (RS) (802.3cg-2019). Modern version of
     shared medium Ethernet.

   - Support for MAC Merge layer (IEEE 802.3-2018 clause 99). Allowing
     preemption of low priority frames by high priority frames.

   - Add support for controlling MACSec offload using netlink SET.

   - Rework devlink instance refcounts to allow registration and
     de-registration under the instance lock. Split the code into
     multiple files, drop some of the unnecessarily granular locks and
     factor out common parts of netlink operation handling.

   - Add TX frame aggregation parameters (for USB drivers).

   - Add a new attr TCA_EXT_WARN_MSG to report TC (offload) warning
     messages with notifications for debug.

   - Allow offloading of UDP NEW connections via act_ct.

   - Add support for per action HW stats in TC.

   - Support hardware miss to TC action (continue processing in SW from
     a specific point in the action chain).

   - Warn if old Wireless Extension user space interface is used with
     modern cfg80211/mac80211 drivers. Do not support Wireless
     Extensions for Wi-Fi 7 devices at all. Everyone should switch to
     using nl80211 interface instead.

   - Improve the CAN bit timing configuration. Use extack to return
     error messages directly to user space, update the SJW handling,
     including the definition of a new default value that will benefit
     CAN-FD controllers, by increasing their oscillator tolerance.

  New hardware / drivers:

   - Ethernet:
      - nVidia BlueField-3 support (control traffic driver)
      - Ethernet support for imx93 SoCs
      - Motorcomm yt8531 gigabit Ethernet PHY
      - onsemi NCN26000 10BASE-T1S PHY (with support for PLCA)
      - Microchip LAN8841 PHY (incl. cable diagnostics and PTP)
      - Amlogic gxl MDIO mux

   - WiFi:
      - RealTek RTL8188EU (rtl8xxxu)
      - Qualcomm Wi-Fi 7 devices (ath12k)

   - CAN:
      - Renesas R-Car V4H

  Drivers:

   - Bluetooth:
      - Set Per Platform Antenna Gain (PPAG) for Intel controllers.

   - Ethernet NICs:
      - Intel (1G, igc):
         - support TSN / Qbv / packet scheduling features of i226 model
      - Intel (100G, ice):
         - use GNSS subsystem instead of TTY
         - multi-buffer XDP support
         - extend support for GPIO pins to E823 devices
      - nVidia/Mellanox:
         - update the shared buffer configuration on PFC commands
         - implement PTP adjphase function for HW offset control
         - TC support for Geneve and GRE with VF tunnel offload
         - more efficient crypto key management method
         - multi-port eswitch support
      - Netronome/Corigine:
         - add DCB IEEE support
         - support IPsec offloading for NFP3800
      - Freescale/NXP (enetc):
         - support XDP_REDIRECT for XDP non-linear buffers
         - improve reconfig, avoid link flap and waiting for idle
         - support MAC Merge layer
      - Other NICs:
         - sfc/ef100: add basic devlink support for ef100
         - ionic: rx_push mode operation (writing descriptors via MMIO)
         - bnxt: use the auxiliary bus abstraction for RDMA
         - r8169: disable ASPM and reset bus in case of tx timeout
         - cpsw: support QSGMII mode for J721e CPSW9G
         - cpts: support pulse-per-second output
         - ngbe: add an mdio bus driver
         - usbnet: optimize usbnet_bh() by avoiding unnecessary queuing
         - r8152: handle devices with FW with NCM support
         - amd-xgbe: support 10Mbps, 2.5GbE speeds and rx-adaptation
         - virtio-net: support multi buffer XDP
         - virtio/vsock: replace virtio_vsock_pkt with sk_buff
         - tsnep: XDP support

   - Ethernet high-speed switches:
      - nVidia/Mellanox (mlxsw):
         - add support for latency TLV (in FW control messages)
      - Microchip (sparx5):
         - separate explicit and implicit traffic forwarding rules, make
           the implicit rules always active
         - add support for egress DSCP rewrite
         - IS0 VCAP support (Ingress Classification)
         - IS2 VCAP filters (protos, L3 addrs, L4 ports, flags, ToS
           etc.)
         - ES2 VCAP support (Egress Access Control)
         - support for Per-Stream Filtering and Policing (802.1Q,
           8.6.5.1)

   - Ethernet embedded switches:
      - Marvell (mv88e6xxx):
         - add MAB (port auth) offload support
         - enable PTP receive for mv88e6390
      - NXP (ocelot):
         - support MAC Merge layer
         - support for the the vsc7512 internal copper phys
      - Microchip:
         - lan9303: convert to PHYLINK
         - lan966x: support TC flower filter statistics
         - lan937x: PTP support for KSZ9563/KSZ8563 and LAN937x
         - lan937x: support Credit Based Shaper configuration
         - ksz9477: support Energy Efficient Ethernet
      - other:
         - qca8k: convert to regmap read/write API, use bulk operations
         - rswitch: Improve TX timestamp accuracy

   - Intel WiFi (iwlwifi):
      - EHT (Wi-Fi 7) rate reporting
      - STEP equalizer support: transfer some STEP (connection to radio
        on platforms with integrated wifi) related parameters from the
        BIOS to the firmware.

   - Qualcomm 802.11ax WiFi (ath11k):
      - IPQ5018 support
      - Fine Timing Measurement (FTM) responder role support
      - channel 177 support

   - MediaTek WiFi (mt76):
      - per-PHY LED support
      - mt7996: EHT (Wi-Fi 7) support
      - Wireless Ethernet Dispatch (WED) reset support
      - switch to using page pool allocator

   - RealTek WiFi (rtw89):
      - support new version of Bluetooth co-existance

   - Mobile:
      - rmnet: support TX aggregation"

* tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1872 commits)
  page_pool: add a comment explaining the fragment counter usage
  net: ethtool: fix __ethtool_dev_mm_supported() implementation
  ethtool: pse-pd: Fix double word in comments
  xsk: add linux/vmalloc.h to xsk.c
  sefltests: netdevsim: wait for devlink instance after netns removal
  selftest: fib_tests: Always cleanup before exit
  net/mlx5e: Align IPsec ASO result memory to be as required by hardware
  net/mlx5e: TC, Set CT miss to the specific ct action instance
  net/mlx5e: Rename CHAIN_TO_REG to MAPPED_OBJ_TO_REG
  net/mlx5: Refactor tc miss handling to a single function
  net/mlx5: Kconfig: Make tc offload depend on tc skb extension
  net/sched: flower: Support hardware miss to tc action
  net/sched: flower: Move filter handle initialization earlier
  net/sched: cls_api: Support hardware miss to tc action
  net/sched: Rename user cookie and act cookie
  sfc: fix builds without CONFIG_RTC_LIB
  sfc: clean up some inconsistent indentings
  net/mlx4_en: Introduce flexible array to silence overflow warning
  net: lan966x: Fix possible deadlock inside PTP
  net/ulp: Remove redundant ->clone() test in inet_clone_ulp().
  ...

1 files changed, 351 insertions, 0 deletions

diff --git a/drivers/of/resolver.c b/drivers/of/resolver.c
new file mode 100644
index 000000000..b278ab433
--- /dev/null
+++ b/drivers/of/resolver.c
@@ -0,0 +1,351 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Functions for dealing with DT resolution
+ *
+ * Copyright (C) 2012 Pantelis Antoniou <panto@antoniou-consulting.com>
+ * Copyright (C) 2012 Texas Instruments Inc.
+ */
+
+#define pr_fmt(fmt)	"OF: resolver: " fmt
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_device.h>
+#include <linux/string.h>
+#include <linux/ctype.h>
+#include <linux/errno.h>
+#include <linux/slab.h>
+
+#include "of_private.h"
+
+static phandle live_tree_max_phandle(void)
+{
+	struct device_node *node;
+	phandle phandle;
+	unsigned long flags;
+
+	raw_spin_lock_irqsave(&devtree_lock, flags);
+	phandle = 0;
+	for_each_of_allnodes(node) {
+		if (node->phandle != OF_PHANDLE_ILLEGAL &&
+				node->phandle > phandle)
+			phandle = node->phandle;
+	}
+	raw_spin_unlock_irqrestore(&devtree_lock, flags);
+
+	return phandle;
+}
+
+static void adjust_overlay_phandles(struct device_node *overlay,
+		int phandle_delta)
+{
+	struct device_node *child;
+	struct property *prop;
+	phandle phandle;
+
+	/* adjust node's phandle in node */
+	if (overlay->phandle != 0 && overlay->phandle != OF_PHANDLE_ILLEGAL)
+		overlay->phandle += phandle_delta;
+
+	/* copy adjusted phandle into *phandle properties */
+	for_each_property_of_node(overlay, prop) {
+
+		if (of_prop_cmp(prop->name, "phandle") &&
+		    of_prop_cmp(prop->name, "linux,phandle"))
+			continue;
+
+		if (prop->length < 4)
+			continue;
+
+		phandle = be32_to_cpup(prop->value);
+		if (phandle == OF_PHANDLE_ILLEGAL)
+			continue;
+
+		*(__be32 *)prop->value = cpu_to_be32(overlay->phandle);
+	}
+
+	for_each_child_of_node(overlay, child)
+		adjust_overlay_phandles(child, phandle_delta);
+}
+
+static int update_usages_of_a_phandle_reference(struct device_node *overlay,
+		struct property *prop_fixup, phandle phandle)
+{
+	struct device_node *refnode;
+	struct property *prop;
+	char *value, *cur, *end, *node_path, *prop_name, *s;
+	int offset, len;
+	int err = 0;
+
+	value = kmemdup(prop_fixup->value, prop_fixup->length, GFP_KERNEL);
+	if (!value)
+		return -ENOMEM;
+
+	/* prop_fixup contains a list of tuples of path:property_name:offset */
+	end = value + prop_fixup->length;
+	for (cur = value; cur < end; cur += len + 1) {
+		len = strlen(cur);
+
+		node_path = cur;
+		s = strchr(cur, ':');
+		if (!s) {
+			err = -EINVAL;
+			goto err_fail;
+		}
+		*s++ = '\0';
+
+		prop_name = s;
+		s = strchr(s, ':');
+		if (!s) {
+			err = -EINVAL;
+			goto err_fail;
+		}
+		*s++ = '\0';
+
+		err = kstrtoint(s, 10, &offset);
+		if (err)
+			goto err_fail;
+
+		refnode = __of_find_node_by_full_path(of_node_get(overlay), node_path);
+		if (!refnode)
+			continue;
+
+		for_each_property_of_node(refnode, prop) {
+			if (!of_prop_cmp(prop->name, prop_name))
+				break;
+		}
+		of_node_put(refnode);
+
+		if (!prop) {
+			err = -ENOENT;
+			goto err_fail;
+		}
+
+		if (offset < 0 || offset + sizeof(__be32) > prop->length) {
+			err = -EINVAL;
+			goto err_fail;
+		}
+
+		*(__be32 *)(prop->value + offset) = cpu_to_be32(phandle);
+	}
+
+err_fail:
+	kfree(value);
+	return err;
+}
+
+/* compare nodes taking into account that 'name' strips out the @ part */
+static int node_name_cmp(const struct device_node *dn1,
+		const struct device_node *dn2)
+{
+	const char *n1 = kbasename(dn1->full_name);
+	const char *n2 = kbasename(dn2->full_name);
+
+	return of_node_cmp(n1, n2);
+}
+
+/*
+ * Adjust the local phandle references by the given phandle delta.
+ *
+ * Subtree @local_fixups, which is overlay node __local_fixups__,
+ * mirrors the fragment node structure at the root of the overlay.
+ *
+ * For each property in the fragments that contains a phandle reference,
+ * @local_fixups has a property of the same name that contains a list
+ * of offsets of the phandle reference(s) within the respective property
+ * value(s).  The values at these offsets will be fixed up.
+ */
+static int adjust_local_phandle_references(struct device_node *local_fixups,
+		struct device_node *overlay, int phandle_delta)
+{
+	struct device_node *child, *overlay_child;
+	struct property *prop_fix, *prop;
+	int err, i, count;
+	unsigned int off;
+
+	if (!local_fixups)
+		return 0;
+
+	for_each_property_of_node(local_fixups, prop_fix) {
+
+		/* skip properties added automatically */
+		if (!of_prop_cmp(prop_fix->name, "name") ||
+		    !of_prop_cmp(prop_fix->name, "phandle") ||
+		    !of_prop_cmp(prop_fix->name, "linux,phandle"))
+			continue;
+
+		if ((prop_fix->length % 4) != 0 || prop_fix->length == 0)
+			return -EINVAL;
+		count = prop_fix->length / sizeof(__be32);
+
+		for_each_property_of_node(overlay, prop) {
+			if (!of_prop_cmp(prop->name, prop_fix->name))
+				break;
+		}
+
+		if (!prop)
+			return -EINVAL;
+
+		for (i = 0; i < count; i++) {
+			off = be32_to_cpu(((__be32 *)prop_fix->value)[i]);
+			if ((off + 4) > prop->length)
+				return -EINVAL;
+
+			be32_add_cpu(prop->value + off, phandle_delta);
+		}
+	}
+
+	/*
+	 * These nested loops recurse down two subtrees in parallel, where the
+	 * node names in the two subtrees match.
+	 *
+	 * The roots of the subtrees are the overlay's __local_fixups__ node
+	 * and the overlay's root node.
+	 */
+	for_each_child_of_node(local_fixups, child) {
+
+		for_each_child_of_node(overlay, overlay_child)
+			if (!node_name_cmp(child, overlay_child)) {
+				of_node_put(overlay_child);
+				break;
+			}
+
+		if (!overlay_child) {
+			of_node_put(child);
+			return -EINVAL;
+		}
+
+		err = adjust_local_phandle_references(child, overlay_child,
+				phandle_delta);
+		if (err) {
+			of_node_put(child);
+			return err;
+		}
+	}
+
+	return 0;
+}
+
+/**
+ * of_resolve_phandles - Relocate and resolve overlay against live tree
+ *
+ * @overlay:	Pointer to devicetree overlay to relocate and resolve
+ *
+ * Modify (relocate) values of local phandles in @overlay to a range that
+ * does not conflict with the live expanded devicetree.  Update references
+ * to the local phandles in @overlay.  Update (resolve) phandle references
+ * in @overlay that refer to the live expanded devicetree.
+ *
+ * Phandle values in the live tree are in the range of
+ * 1 .. live_tree_max_phandle().  The range of phandle values in the overlay
+ * also begin with at 1.  Adjust the phandle values in the overlay to begin
+ * at live_tree_max_phandle() + 1.  Update references to the phandles to
+ * the adjusted phandle values.
+ *
+ * The name of each property in the "__fixups__" node in the overlay matches
+ * the name of a symbol (a label) in the live tree.  The values of each
+ * property in the "__fixups__" node is a list of the property values in the
+ * overlay that need to be updated to contain the phandle reference
+ * corresponding to that symbol in the live tree.  Update the references in
+ * the overlay with the phandle values in the live tree.
+ *
+ * @overlay must be detached.
+ *
+ * Resolving and applying @overlay to the live expanded devicetree must be
+ * protected by a mechanism to ensure that multiple overlays are processed
+ * in a single threaded manner so that multiple overlays will not relocate
+ * phandles to overlapping ranges.  The mechanism to enforce this is not
+ * yet implemented.
+ *
+ * Return: %0 on success or a negative error value on error.
+ */
+int of_resolve_phandles(struct device_node *overlay)
+{
+	struct device_node *child, *local_fixups, *refnode;
+	struct device_node *tree_symbols, *overlay_fixups;
+	struct property *prop;
+	const char *refpath;
+	phandle phandle, phandle_delta;
+	int err;
+
+	tree_symbols = NULL;
+
+	if (!overlay) {
+		pr_err("null overlay\n");
+		err = -EINVAL;
+		goto out;
+	}
+
+	if (!of_node_check_flag(overlay, OF_DETACHED)) {
+		pr_err("overlay not detached\n");
+		err = -EINVAL;
+		goto out;
+	}
+
+	phandle_delta = live_tree_max_phandle() + 1;
+	adjust_overlay_phandles(overlay, phandle_delta);
+
+	for_each_child_of_node(overlay, local_fixups)
+		if (of_node_name_eq(local_fixups, "__local_fixups__"))
+			break;
+
+	err = adjust_local_phandle_references(local_fixups, overlay, phandle_delta);
+	if (err)
+		goto out;
+
+	overlay_fixups = NULL;
+
+	for_each_child_of_node(overlay, child) {
+		if (of_node_name_eq(child, "__fixups__"))
+			overlay_fixups = child;
+	}
+
+	if (!overlay_fixups) {
+		err = 0;
+		goto out;
+	}
+
+	tree_symbols = of_find_node_by_path("/__symbols__");
+	if (!tree_symbols) {
+		pr_err("no symbols in root of device tree.\n");
+		err = -EINVAL;
+		goto out;
+	}
+
+	for_each_property_of_node(overlay_fixups, prop) {
+
+		/* skip properties added automatically */
+		if (!of_prop_cmp(prop->name, "name"))
+			continue;
+
+		err = of_property_read_string(tree_symbols,
+				prop->name, &refpath);
+		if (err) {
+			pr_err("node label '%s' not found in live devicetree symbols table\n",
+			       prop->name);
+			goto out;
+		}
+
+		refnode = of_find_node_by_path(refpath);
+		if (!refnode) {
+			err = -ENOENT;
+			goto out;
+		}
+
+		phandle = refnode->phandle;
+		of_node_put(refnode);
+
+		err = update_usages_of_a_phandle_reference(overlay, prop, phandle);
+		if (err)
+			break;
+	}
+
+out:
+	if (err)
+		pr_err("overlay phandle fixup failed: %d\n", err);
+	of_node_put(tree_symbols);
+
+	return err;
+}
+EXPORT_SYMBOL_GPL(of_resolve_phandles);