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, 289 insertions, 0 deletions

diff --git a/kernel/livepatch/patch.c b/kernel/livepatch/patch.c
new file mode 100644
index 000000000..4152c7150
--- /dev/null
+++ b/kernel/livepatch/patch.c
@@ -0,0 +1,289 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * patch.c - livepatch patching functions
+ *
+ * Copyright (C) 2014 Seth Jennings <sjenning@redhat.com>
+ * Copyright (C) 2014 SUSE
+ * Copyright (C) 2015 Josh Poimboeuf <jpoimboe@redhat.com>
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/livepatch.h>
+#include <linux/list.h>
+#include <linux/ftrace.h>
+#include <linux/rculist.h>
+#include <linux/slab.h>
+#include <linux/bug.h>
+#include <linux/printk.h>
+#include "core.h"
+#include "patch.h"
+#include "transition.h"
+
+static LIST_HEAD(klp_ops);
+
+struct klp_ops *klp_find_ops(void *old_func)
+{
+	struct klp_ops *ops;
+	struct klp_func *func;
+
+	list_for_each_entry(ops, &klp_ops, node) {
+		func = list_first_entry(&ops->func_stack, struct klp_func,
+					stack_node);
+		if (func->old_func == old_func)
+			return ops;
+	}
+
+	return NULL;
+}
+
+static void notrace klp_ftrace_handler(unsigned long ip,
+				       unsigned long parent_ip,
+				       struct ftrace_ops *fops,
+				       struct ftrace_regs *fregs)
+{
+	struct klp_ops *ops;
+	struct klp_func *func;
+	int patch_state;
+	int bit;
+
+	ops = container_of(fops, struct klp_ops, fops);
+
+	/*
+	 * The ftrace_test_recursion_trylock() will disable preemption,
+	 * which is required for the variant of synchronize_rcu() that is
+	 * used to allow patching functions where RCU is not watching.
+	 * See klp_synchronize_transition() for more details.
+	 */
+	bit = ftrace_test_recursion_trylock(ip, parent_ip);
+	if (WARN_ON_ONCE(bit < 0))
+		return;
+
+	func = list_first_or_null_rcu(&ops->func_stack, struct klp_func,
+				      stack_node);
+
+	/*
+	 * func should never be NULL because preemption should be disabled here
+	 * and unregister_ftrace_function() does the equivalent of a
+	 * synchronize_rcu() before the func_stack removal.
+	 */
+	if (WARN_ON_ONCE(!func))
+		goto unlock;
+
+	/*
+	 * In the enable path, enforce the order of the ops->func_stack and
+	 * func->transition reads.  The corresponding write barrier is in
+	 * __klp_enable_patch().
+	 *
+	 * (Note that this barrier technically isn't needed in the disable
+	 * path.  In the rare case where klp_update_patch_state() runs before
+	 * this handler, its TIF_PATCH_PENDING read and this func->transition
+	 * read need to be ordered.  But klp_update_patch_state() already
+	 * enforces that.)
+	 */
+	smp_rmb();
+
+	if (unlikely(func->transition)) {
+
+		/*
+		 * Enforce the order of the func->transition and
+		 * current->patch_state reads.  Otherwise we could read an
+		 * out-of-date task state and pick the wrong function.  The
+		 * corresponding write barrier is in klp_init_transition().
+		 */
+		smp_rmb();
+
+		patch_state = current->patch_state;
+
+		WARN_ON_ONCE(patch_state == KLP_UNDEFINED);
+
+		if (patch_state == KLP_UNPATCHED) {
+			/*
+			 * Use the previously patched version of the function.
+			 * If no previous patches exist, continue with the
+			 * original function.
+			 */
+			func = list_entry_rcu(func->stack_node.next,
+					      struct klp_func, stack_node);
+
+			if (&func->stack_node == &ops->func_stack)
+				goto unlock;
+		}
+	}
+
+	/*
+	 * NOPs are used to replace existing patches with original code.
+	 * Do nothing! Setting pc would cause an infinite loop.
+	 */
+	if (func->nop)
+		goto unlock;
+
+	ftrace_regs_set_instruction_pointer(fregs, (unsigned long)func->new_func);
+
+unlock:
+	ftrace_test_recursion_unlock(bit);
+}
+
+static void klp_unpatch_func(struct klp_func *func)
+{
+	struct klp_ops *ops;
+
+	if (WARN_ON(!func->patched))
+		return;
+	if (WARN_ON(!func->old_func))
+		return;
+
+	ops = klp_find_ops(func->old_func);
+	if (WARN_ON(!ops))
+		return;
+
+	if (list_is_singular(&ops->func_stack)) {
+		unsigned long ftrace_loc;
+
+		ftrace_loc = ftrace_location((unsigned long)func->old_func);
+		if (WARN_ON(!ftrace_loc))
+			return;
+
+		WARN_ON(unregister_ftrace_function(&ops->fops));
+		WARN_ON(ftrace_set_filter_ip(&ops->fops, ftrace_loc, 1, 0));
+
+		list_del_rcu(&func->stack_node);
+		list_del(&ops->node);
+		kfree(ops);
+	} else {
+		list_del_rcu(&func->stack_node);
+	}
+
+	func->patched = false;
+}
+
+static int klp_patch_func(struct klp_func *func)
+{
+	struct klp_ops *ops;
+	int ret;
+
+	if (WARN_ON(!func->old_func))
+		return -EINVAL;
+
+	if (WARN_ON(func->patched))
+		return -EINVAL;
+
+	ops = klp_find_ops(func->old_func);
+	if (!ops) {
+		unsigned long ftrace_loc;
+
+		ftrace_loc = ftrace_location((unsigned long)func->old_func);
+		if (!ftrace_loc) {
+			pr_err("failed to find location for function '%s'\n",
+				func->old_name);
+			return -EINVAL;
+		}
+
+		ops = kzalloc(sizeof(*ops), GFP_KERNEL);
+		if (!ops)
+			return -ENOMEM;
+
+		ops->fops.func = klp_ftrace_handler;
+		ops->fops.flags = FTRACE_OPS_FL_DYNAMIC |
+#ifndef CONFIG_HAVE_DYNAMIC_FTRACE_WITH_ARGS
+				  FTRACE_OPS_FL_SAVE_REGS |
+#endif
+				  FTRACE_OPS_FL_IPMODIFY |
+				  FTRACE_OPS_FL_PERMANENT;
+
+		list_add(&ops->node, &klp_ops);
+
+		INIT_LIST_HEAD(&ops->func_stack);
+		list_add_rcu(&func->stack_node, &ops->func_stack);
+
+		ret = ftrace_set_filter_ip(&ops->fops, ftrace_loc, 0, 0);
+		if (ret) {
+			pr_err("failed to set ftrace filter for function '%s' (%d)\n",
+			       func->old_name, ret);
+			goto err;
+		}
+
+		ret = register_ftrace_function(&ops->fops);
+		if (ret) {
+			pr_err("failed to register ftrace handler for function '%s' (%d)\n",
+			       func->old_name, ret);
+			ftrace_set_filter_ip(&ops->fops, ftrace_loc, 1, 0);
+			goto err;
+		}
+
+
+	} else {
+		list_add_rcu(&func->stack_node, &ops->func_stack);
+	}
+
+	func->patched = true;
+
+	return 0;
+
+err:
+	list_del_rcu(&func->stack_node);
+	list_del(&ops->node);
+	kfree(ops);
+	return ret;
+}
+
+static void __klp_unpatch_object(struct klp_object *obj, bool nops_only)
+{
+	struct klp_func *func;
+
+	klp_for_each_func(obj, func) {
+		if (nops_only && !func->nop)
+			continue;
+
+		if (func->patched)
+			klp_unpatch_func(func);
+	}
+
+	if (obj->dynamic || !nops_only)
+		obj->patched = false;
+}
+
+
+void klp_unpatch_object(struct klp_object *obj)
+{
+	__klp_unpatch_object(obj, false);
+}
+
+int klp_patch_object(struct klp_object *obj)
+{
+	struct klp_func *func;
+	int ret;
+
+	if (WARN_ON(obj->patched))
+		return -EINVAL;
+
+	klp_for_each_func(obj, func) {
+		ret = klp_patch_func(func);
+		if (ret) {
+			klp_unpatch_object(obj);
+			return ret;
+		}
+	}
+	obj->patched = true;
+
+	return 0;
+}
+
+static void __klp_unpatch_objects(struct klp_patch *patch, bool nops_only)
+{
+	struct klp_object *obj;
+
+	klp_for_each_object(patch, obj)
+		if (obj->patched)
+			__klp_unpatch_object(obj, nops_only);
+}
+
+void klp_unpatch_objects(struct klp_patch *patch)
+{
+	__klp_unpatch_objects(patch, false);
+}
+
+void klp_unpatch_objects_dynamic(struct klp_patch *patch)
+{
+	__klp_unpatch_objects(patch, true);
+}