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, 867 insertions, 0 deletions

diff --git a/kernel/jump_label.c b/kernel/jump_label.c
new file mode 100644
index 000000000..d9c822bbf
--- /dev/null
+++ b/kernel/jump_label.c
@@ -0,0 +1,867 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * jump label support
+ *
+ * Copyright (C) 2009 Jason Baron <jbaron@redhat.com>
+ * Copyright (C) 2011 Peter Zijlstra
+ *
+ */
+#include <linux/memory.h>
+#include <linux/uaccess.h>
+#include <linux/module.h>
+#include <linux/list.h>
+#include <linux/slab.h>
+#include <linux/sort.h>
+#include <linux/err.h>
+#include <linux/static_key.h>
+#include <linux/jump_label_ratelimit.h>
+#include <linux/bug.h>
+#include <linux/cpu.h>
+#include <asm/sections.h>
+
+/* mutex to protect coming/going of the jump_label table */
+static DEFINE_MUTEX(jump_label_mutex);
+
+void jump_label_lock(void)
+{
+	mutex_lock(&jump_label_mutex);
+}
+
+void jump_label_unlock(void)
+{
+	mutex_unlock(&jump_label_mutex);
+}
+
+static int jump_label_cmp(const void *a, const void *b)
+{
+	const struct jump_entry *jea = a;
+	const struct jump_entry *jeb = b;
+
+	/*
+	 * Entrires are sorted by key.
+	 */
+	if (jump_entry_key(jea) < jump_entry_key(jeb))
+		return -1;
+
+	if (jump_entry_key(jea) > jump_entry_key(jeb))
+		return 1;
+
+	/*
+	 * In the batching mode, entries should also be sorted by the code
+	 * inside the already sorted list of entries, enabling a bsearch in
+	 * the vector.
+	 */
+	if (jump_entry_code(jea) < jump_entry_code(jeb))
+		return -1;
+
+	if (jump_entry_code(jea) > jump_entry_code(jeb))
+		return 1;
+
+	return 0;
+}
+
+static void jump_label_swap(void *a, void *b, int size)
+{
+	long delta = (unsigned long)a - (unsigned long)b;
+	struct jump_entry *jea = a;
+	struct jump_entry *jeb = b;
+	struct jump_entry tmp = *jea;
+
+	jea->code	= jeb->code - delta;
+	jea->target	= jeb->target - delta;
+	jea->key	= jeb->key - delta;
+
+	jeb->code	= tmp.code + delta;
+	jeb->target	= tmp.target + delta;
+	jeb->key	= tmp.key + delta;
+}
+
+static void
+jump_label_sort_entries(struct jump_entry *start, struct jump_entry *stop)
+{
+	unsigned long size;
+	void *swapfn = NULL;
+
+	if (IS_ENABLED(CONFIG_HAVE_ARCH_JUMP_LABEL_RELATIVE))
+		swapfn = jump_label_swap;
+
+	size = (((unsigned long)stop - (unsigned long)start)
+					/ sizeof(struct jump_entry));
+	sort(start, size, sizeof(struct jump_entry), jump_label_cmp, swapfn);
+}
+
+static void jump_label_update(struct static_key *key);
+
+/*
+ * There are similar definitions for the !CONFIG_JUMP_LABEL case in jump_label.h.
+ * The use of 'atomic_read()' requires atomic.h and its problematic for some
+ * kernel headers such as kernel.h and others. Since static_key_count() is not
+ * used in the branch statements as it is for the !CONFIG_JUMP_LABEL case its ok
+ * to have it be a function here. Similarly, for 'static_key_enable()' and
+ * 'static_key_disable()', which require bug.h. This should allow jump_label.h
+ * to be included from most/all places for CONFIG_JUMP_LABEL.
+ */
+int static_key_count(struct static_key *key)
+{
+	/*
+	 * -1 means the first static_key_slow_inc() is in progress.
+	 *  static_key_enabled() must return true, so return 1 here.
+	 */
+	int n = atomic_read(&key->enabled);
+
+	return n >= 0 ? n : 1;
+}
+EXPORT_SYMBOL_GPL(static_key_count);
+
+/*
+ * static_key_fast_inc_not_disabled - adds a user for a static key
+ * @key: static key that must be already enabled
+ *
+ * The caller must make sure that the static key can't get disabled while
+ * in this function. It doesn't patch jump labels, only adds a user to
+ * an already enabled static key.
+ *
+ * Returns true if the increment was done. Unlike refcount_t the ref counter
+ * is not saturated, but will fail to increment on overflow.
+ */
+bool static_key_fast_inc_not_disabled(struct static_key *key)
+{
+	int v;
+
+	STATIC_KEY_CHECK_USE(key);
+	/*
+	 * Negative key->enabled has a special meaning: it sends
+	 * static_key_slow_inc() down the slow path, and it is non-zero
+	 * so it counts as "enabled" in jump_label_update().  Note that
+	 * atomic_inc_unless_negative() checks >= 0, so roll our own.
+	 */
+	v = atomic_read(&key->enabled);
+	do {
+		if (v <= 0 || (v + 1) < 0)
+			return false;
+	} while (!likely(atomic_try_cmpxchg(&key->enabled, &v, v + 1)));
+
+	return true;
+}
+EXPORT_SYMBOL_GPL(static_key_fast_inc_not_disabled);
+
+bool static_key_slow_inc_cpuslocked(struct static_key *key)
+{
+	lockdep_assert_cpus_held();
+
+	/*
+	 * Careful if we get concurrent static_key_slow_inc() calls;
+	 * later calls must wait for the first one to _finish_ the
+	 * jump_label_update() process.  At the same time, however,
+	 * the jump_label_update() call below wants to see
+	 * static_key_enabled(&key) for jumps to be updated properly.
+	 */
+	if (static_key_fast_inc_not_disabled(key))
+		return true;
+
+	jump_label_lock();
+	if (atomic_read(&key->enabled) == 0) {
+		atomic_set(&key->enabled, -1);
+		jump_label_update(key);
+		/*
+		 * Ensure that if the above cmpxchg loop observes our positive
+		 * value, it must also observe all the text changes.
+		 */
+		atomic_set_release(&key->enabled, 1);
+	} else {
+		if (WARN_ON_ONCE(!static_key_fast_inc_not_disabled(key))) {
+			jump_label_unlock();
+			return false;
+		}
+	}
+	jump_label_unlock();
+	return true;
+}
+
+bool static_key_slow_inc(struct static_key *key)
+{
+	bool ret;
+
+	cpus_read_lock();
+	ret = static_key_slow_inc_cpuslocked(key);
+	cpus_read_unlock();
+	return ret;
+}
+EXPORT_SYMBOL_GPL(static_key_slow_inc);
+
+void static_key_enable_cpuslocked(struct static_key *key)
+{
+	STATIC_KEY_CHECK_USE(key);
+	lockdep_assert_cpus_held();
+
+	if (atomic_read(&key->enabled) > 0) {
+		WARN_ON_ONCE(atomic_read(&key->enabled) != 1);
+		return;
+	}
+
+	jump_label_lock();
+	if (atomic_read(&key->enabled) == 0) {
+		atomic_set(&key->enabled, -1);
+		jump_label_update(key);
+		/*
+		 * See static_key_slow_inc().
+		 */
+		atomic_set_release(&key->enabled, 1);
+	}
+	jump_label_unlock();
+}
+EXPORT_SYMBOL_GPL(static_key_enable_cpuslocked);
+
+void static_key_enable(struct static_key *key)
+{
+	cpus_read_lock();
+	static_key_enable_cpuslocked(key);
+	cpus_read_unlock();
+}
+EXPORT_SYMBOL_GPL(static_key_enable);
+
+void static_key_disable_cpuslocked(struct static_key *key)
+{
+	STATIC_KEY_CHECK_USE(key);
+	lockdep_assert_cpus_held();
+
+	if (atomic_read(&key->enabled) != 1) {
+		WARN_ON_ONCE(atomic_read(&key->enabled) != 0);
+		return;
+	}
+
+	jump_label_lock();
+	if (atomic_cmpxchg(&key->enabled, 1, 0))
+		jump_label_update(key);
+	jump_label_unlock();
+}
+EXPORT_SYMBOL_GPL(static_key_disable_cpuslocked);
+
+void static_key_disable(struct static_key *key)
+{
+	cpus_read_lock();
+	static_key_disable_cpuslocked(key);
+	cpus_read_unlock();
+}
+EXPORT_SYMBOL_GPL(static_key_disable);
+
+static bool static_key_slow_try_dec(struct static_key *key)
+{
+	int val;
+
+	val = atomic_fetch_add_unless(&key->enabled, -1, 1);
+	if (val == 1)
+		return false;
+
+	/*
+	 * The negative count check is valid even when a negative
+	 * key->enabled is in use by static_key_slow_inc(); a
+	 * __static_key_slow_dec() before the first static_key_slow_inc()
+	 * returns is unbalanced, because all other static_key_slow_inc()
+	 * instances block while the update is in progress.
+	 */
+	WARN(val < 0, "jump label: negative count!\n");
+	return true;
+}
+
+static void __static_key_slow_dec_cpuslocked(struct static_key *key)
+{
+	lockdep_assert_cpus_held();
+
+	if (static_key_slow_try_dec(key))
+		return;
+
+	jump_label_lock();
+	if (atomic_dec_and_test(&key->enabled))
+		jump_label_update(key);
+	jump_label_unlock();
+}
+
+static void __static_key_slow_dec(struct static_key *key)
+{
+	cpus_read_lock();
+	__static_key_slow_dec_cpuslocked(key);
+	cpus_read_unlock();
+}
+
+void jump_label_update_timeout(struct work_struct *work)
+{
+	struct static_key_deferred *key =
+		container_of(work, struct static_key_deferred, work.work);
+	__static_key_slow_dec(&key->key);
+}
+EXPORT_SYMBOL_GPL(jump_label_update_timeout);
+
+void static_key_slow_dec(struct static_key *key)
+{
+	STATIC_KEY_CHECK_USE(key);
+	__static_key_slow_dec(key);
+}
+EXPORT_SYMBOL_GPL(static_key_slow_dec);
+
+void static_key_slow_dec_cpuslocked(struct static_key *key)
+{
+	STATIC_KEY_CHECK_USE(key);
+	__static_key_slow_dec_cpuslocked(key);
+}
+
+void __static_key_slow_dec_deferred(struct static_key *key,
+				    struct delayed_work *work,
+				    unsigned long timeout)
+{
+	STATIC_KEY_CHECK_USE(key);
+
+	if (static_key_slow_try_dec(key))
+		return;
+
+	schedule_delayed_work(work, timeout);
+}
+EXPORT_SYMBOL_GPL(__static_key_slow_dec_deferred);
+
+void __static_key_deferred_flush(void *key, struct delayed_work *work)
+{
+	STATIC_KEY_CHECK_USE(key);
+	flush_delayed_work(work);
+}
+EXPORT_SYMBOL_GPL(__static_key_deferred_flush);
+
+void jump_label_rate_limit(struct static_key_deferred *key,
+		unsigned long rl)
+{
+	STATIC_KEY_CHECK_USE(key);
+	key->timeout = rl;
+	INIT_DELAYED_WORK(&key->work, jump_label_update_timeout);
+}
+EXPORT_SYMBOL_GPL(jump_label_rate_limit);
+
+static int addr_conflict(struct jump_entry *entry, void *start, void *end)
+{
+	if (jump_entry_code(entry) <= (unsigned long)end &&
+	    jump_entry_code(entry) + jump_entry_size(entry) > (unsigned long)start)
+		return 1;
+
+	return 0;
+}
+
+static int __jump_label_text_reserved(struct jump_entry *iter_start,
+		struct jump_entry *iter_stop, void *start, void *end, bool init)
+{
+	struct jump_entry *iter;
+
+	iter = iter_start;
+	while (iter < iter_stop) {
+		if (init || !jump_entry_is_init(iter)) {
+			if (addr_conflict(iter, start, end))
+				return 1;
+		}
+		iter++;
+	}
+
+	return 0;
+}
+
+#ifndef arch_jump_label_transform_static
+static void arch_jump_label_transform_static(struct jump_entry *entry,
+					     enum jump_label_type type)
+{
+	/* nothing to do on most architectures */
+}
+#endif
+
+static inline struct jump_entry *static_key_entries(struct static_key *key)
+{
+	WARN_ON_ONCE(key->type & JUMP_TYPE_LINKED);
+	return (struct jump_entry *)(key->type & ~JUMP_TYPE_MASK);
+}
+
+static inline bool static_key_type(struct static_key *key)
+{
+	return key->type & JUMP_TYPE_TRUE;
+}
+
+static inline bool static_key_linked(struct static_key *key)
+{
+	return key->type & JUMP_TYPE_LINKED;
+}
+
+static inline void static_key_clear_linked(struct static_key *key)
+{
+	key->type &= ~JUMP_TYPE_LINKED;
+}
+
+static inline void static_key_set_linked(struct static_key *key)
+{
+	key->type |= JUMP_TYPE_LINKED;
+}
+
+/***
+ * A 'struct static_key' uses a union such that it either points directly
+ * to a table of 'struct jump_entry' or to a linked list of modules which in
+ * turn point to 'struct jump_entry' tables.
+ *
+ * The two lower bits of the pointer are used to keep track of which pointer
+ * type is in use and to store the initial branch direction, we use an access
+ * function which preserves these bits.
+ */
+static void static_key_set_entries(struct static_key *key,
+				   struct jump_entry *entries)
+{
+	unsigned long type;
+
+	WARN_ON_ONCE((unsigned long)entries & JUMP_TYPE_MASK);
+	type = key->type & JUMP_TYPE_MASK;
+	key->entries = entries;
+	key->type |= type;
+}
+
+static enum jump_label_type jump_label_type(struct jump_entry *entry)
+{
+	struct static_key *key = jump_entry_key(entry);
+	bool enabled = static_key_enabled(key);
+	bool branch = jump_entry_is_branch(entry);
+
+	/* See the comment in linux/jump_label.h */
+	return enabled ^ branch;
+}
+
+static bool jump_label_can_update(struct jump_entry *entry, bool init)
+{
+	/*
+	 * Cannot update code that was in an init text area.
+	 */
+	if (!init && jump_entry_is_init(entry))
+		return false;
+
+	if (!kernel_text_address(jump_entry_code(entry))) {
+		/*
+		 * This skips patching built-in __exit, which
+		 * is part of init_section_contains() but is
+		 * not part of kernel_text_address().
+		 *
+		 * Skipping built-in __exit is fine since it
+		 * will never be executed.
+		 */
+		WARN_ONCE(!jump_entry_is_init(entry),
+			  "can't patch jump_label at %pS",
+			  (void *)jump_entry_code(entry));
+		return false;
+	}
+
+	return true;
+}
+
+#ifndef HAVE_JUMP_LABEL_BATCH
+static void __jump_label_update(struct static_key *key,
+				struct jump_entry *entry,
+				struct jump_entry *stop,
+				bool init)
+{
+	for (; (entry < stop) && (jump_entry_key(entry) == key); entry++) {
+		if (jump_label_can_update(entry, init))
+			arch_jump_label_transform(entry, jump_label_type(entry));
+	}
+}
+#else
+static void __jump_label_update(struct static_key *key,
+				struct jump_entry *entry,
+				struct jump_entry *stop,
+				bool init)
+{
+	for (; (entry < stop) && (jump_entry_key(entry) == key); entry++) {
+
+		if (!jump_label_can_update(entry, init))
+			continue;
+
+		if (!arch_jump_label_transform_queue(entry, jump_label_type(entry))) {
+			/*
+			 * Queue is full: Apply the current queue and try again.
+			 */
+			arch_jump_label_transform_apply();
+			BUG_ON(!arch_jump_label_transform_queue(entry, jump_label_type(entry)));
+		}
+	}
+	arch_jump_label_transform_apply();
+}
+#endif
+
+void __init jump_label_init(void)
+{
+	struct jump_entry *iter_start = __start___jump_table;
+	struct jump_entry *iter_stop = __stop___jump_table;
+	struct static_key *key = NULL;
+	struct jump_entry *iter;
+
+	/*
+	 * Since we are initializing the static_key.enabled field with
+	 * with the 'raw' int values (to avoid pulling in atomic.h) in
+	 * jump_label.h, let's make sure that is safe. There are only two
+	 * cases to check since we initialize to 0 or 1.
+	 */
+	BUILD_BUG_ON((int)ATOMIC_INIT(0) != 0);
+	BUILD_BUG_ON((int)ATOMIC_INIT(1) != 1);
+
+	if (static_key_initialized)
+		return;
+
+	cpus_read_lock();
+	jump_label_lock();
+	jump_label_sort_entries(iter_start, iter_stop);
+
+	for (iter = iter_start; iter < iter_stop; iter++) {
+		struct static_key *iterk;
+		bool in_init;
+
+		/* rewrite NOPs */
+		if (jump_label_type(iter) == JUMP_LABEL_NOP)
+			arch_jump_label_transform_static(iter, JUMP_LABEL_NOP);
+
+		in_init = init_section_contains((void *)jump_entry_code(iter), 1);
+		jump_entry_set_init(iter, in_init);
+
+		iterk = jump_entry_key(iter);
+		if (iterk == key)
+			continue;
+
+		key = iterk;
+		static_key_set_entries(key, iter);
+	}
+	static_key_initialized = true;
+	jump_label_unlock();
+	cpus_read_unlock();
+}
+
+#ifdef CONFIG_MODULES
+
+enum jump_label_type jump_label_init_type(struct jump_entry *entry)
+{
+	struct static_key *key = jump_entry_key(entry);
+	bool type = static_key_type(key);
+	bool branch = jump_entry_is_branch(entry);
+
+	/* See the comment in linux/jump_label.h */
+	return type ^ branch;
+}
+
+struct static_key_mod {
+	struct static_key_mod *next;
+	struct jump_entry *entries;
+	struct module *mod;
+};
+
+static inline struct static_key_mod *static_key_mod(struct static_key *key)
+{
+	WARN_ON_ONCE(!static_key_linked(key));
+	return (struct static_key_mod *)(key->type & ~JUMP_TYPE_MASK);
+}
+
+/***
+ * key->type and key->next are the same via union.
+ * This sets key->next and preserves the type bits.
+ *
+ * See additional comments above static_key_set_entries().
+ */
+static void static_key_set_mod(struct static_key *key,
+			       struct static_key_mod *mod)
+{
+	unsigned long type;
+
+	WARN_ON_ONCE((unsigned long)mod & JUMP_TYPE_MASK);
+	type = key->type & JUMP_TYPE_MASK;
+	key->next = mod;
+	key->type |= type;
+}
+
+static int __jump_label_mod_text_reserved(void *start, void *end)
+{
+	struct module *mod;
+	int ret;
+
+	preempt_disable();
+	mod = __module_text_address((unsigned long)start);
+	WARN_ON_ONCE(__module_text_address((unsigned long)end) != mod);
+	if (!try_module_get(mod))
+		mod = NULL;
+	preempt_enable();
+
+	if (!mod)
+		return 0;
+
+	ret = __jump_label_text_reserved(mod->jump_entries,
+				mod->jump_entries + mod->num_jump_entries,
+				start, end, mod->state == MODULE_STATE_COMING);
+
+	module_put(mod);
+
+	return ret;
+}
+
+static void __jump_label_mod_update(struct static_key *key)
+{
+	struct static_key_mod *mod;
+
+	for (mod = static_key_mod(key); mod; mod = mod->next) {
+		struct jump_entry *stop;
+		struct module *m;
+
+		/*
+		 * NULL if the static_key is defined in a module
+		 * that does not use it
+		 */
+		if (!mod->entries)
+			continue;
+
+		m = mod->mod;
+		if (!m)
+			stop = __stop___jump_table;
+		else
+			stop = m->jump_entries + m->num_jump_entries;
+		__jump_label_update(key, mod->entries, stop,
+				    m && m->state == MODULE_STATE_COMING);
+	}
+}
+
+static int jump_label_add_module(struct module *mod)
+{
+	struct jump_entry *iter_start = mod->jump_entries;
+	struct jump_entry *iter_stop = iter_start + mod->num_jump_entries;
+	struct jump_entry *iter;
+	struct static_key *key = NULL;
+	struct static_key_mod *jlm, *jlm2;
+
+	/* if the module doesn't have jump label entries, just return */
+	if (iter_start == iter_stop)
+		return 0;
+
+	jump_label_sort_entries(iter_start, iter_stop);
+
+	for (iter = iter_start; iter < iter_stop; iter++) {
+		struct static_key *iterk;
+		bool in_init;
+
+		in_init = within_module_init(jump_entry_code(iter), mod);
+		jump_entry_set_init(iter, in_init);
+
+		iterk = jump_entry_key(iter);
+		if (iterk == key)
+			continue;
+
+		key = iterk;
+		if (within_module((unsigned long)key, mod)) {
+			static_key_set_entries(key, iter);
+			continue;
+		}
+		jlm = kzalloc(sizeof(struct static_key_mod), GFP_KERNEL);
+		if (!jlm)
+			return -ENOMEM;
+		if (!static_key_linked(key)) {
+			jlm2 = kzalloc(sizeof(struct static_key_mod),
+				       GFP_KERNEL);
+			if (!jlm2) {
+				kfree(jlm);
+				return -ENOMEM;
+			}
+			preempt_disable();
+			jlm2->mod = __module_address((unsigned long)key);
+			preempt_enable();
+			jlm2->entries = static_key_entries(key);
+			jlm2->next = NULL;
+			static_key_set_mod(key, jlm2);
+			static_key_set_linked(key);
+		}
+		jlm->mod = mod;
+		jlm->entries = iter;
+		jlm->next = static_key_mod(key);
+		static_key_set_mod(key, jlm);
+		static_key_set_linked(key);
+
+		/* Only update if we've changed from our initial state */
+		if (jump_label_type(iter) != jump_label_init_type(iter))
+			__jump_label_update(key, iter, iter_stop, true);
+	}
+
+	return 0;
+}
+
+static void jump_label_del_module(struct module *mod)
+{
+	struct jump_entry *iter_start = mod->jump_entries;
+	struct jump_entry *iter_stop = iter_start + mod->num_jump_entries;
+	struct jump_entry *iter;
+	struct static_key *key = NULL;
+	struct static_key_mod *jlm, **prev;
+
+	for (iter = iter_start; iter < iter_stop; iter++) {
+		if (jump_entry_key(iter) == key)
+			continue;
+
+		key = jump_entry_key(iter);
+
+		if (within_module((unsigned long)key, mod))
+			continue;
+
+		/* No memory during module load */
+		if (WARN_ON(!static_key_linked(key)))
+			continue;
+
+		prev = &key->next;
+		jlm = static_key_mod(key);
+
+		while (jlm && jlm->mod != mod) {
+			prev = &jlm->next;
+			jlm = jlm->next;
+		}
+
+		/* No memory during module load */
+		if (WARN_ON(!jlm))
+			continue;
+
+		if (prev == &key->next)
+			static_key_set_mod(key, jlm->next);
+		else
+			*prev = jlm->next;
+
+		kfree(jlm);
+
+		jlm = static_key_mod(key);
+		/* if only one etry is left, fold it back into the static_key */
+		if (jlm->next == NULL) {
+			static_key_set_entries(key, jlm->entries);
+			static_key_clear_linked(key);
+			kfree(jlm);
+		}
+	}
+}
+
+static int
+jump_label_module_notify(struct notifier_block *self, unsigned long val,
+			 void *data)
+{
+	struct module *mod = data;
+	int ret = 0;
+
+	cpus_read_lock();
+	jump_label_lock();
+
+	switch (val) {
+	case MODULE_STATE_COMING:
+		ret = jump_label_add_module(mod);
+		if (ret) {
+			WARN(1, "Failed to allocate memory: jump_label may not work properly.\n");
+			jump_label_del_module(mod);
+		}
+		break;
+	case MODULE_STATE_GOING:
+		jump_label_del_module(mod);
+		break;
+	}
+
+	jump_label_unlock();
+	cpus_read_unlock();
+
+	return notifier_from_errno(ret);
+}
+
+static struct notifier_block jump_label_module_nb = {
+	.notifier_call = jump_label_module_notify,
+	.priority = 1, /* higher than tracepoints */
+};
+
+static __init int jump_label_init_module(void)
+{
+	return register_module_notifier(&jump_label_module_nb);
+}
+early_initcall(jump_label_init_module);
+
+#endif /* CONFIG_MODULES */
+
+/***
+ * jump_label_text_reserved - check if addr range is reserved
+ * @start: start text addr
+ * @end: end text addr
+ *
+ * checks if the text addr located between @start and @end
+ * overlaps with any of the jump label patch addresses. Code
+ * that wants to modify kernel text should first verify that
+ * it does not overlap with any of the jump label addresses.
+ * Caller must hold jump_label_mutex.
+ *
+ * returns 1 if there is an overlap, 0 otherwise
+ */
+int jump_label_text_reserved(void *start, void *end)
+{
+	bool init = system_state < SYSTEM_RUNNING;
+	int ret = __jump_label_text_reserved(__start___jump_table,
+			__stop___jump_table, start, end, init);
+
+	if (ret)
+		return ret;
+
+#ifdef CONFIG_MODULES
+	ret = __jump_label_mod_text_reserved(start, end);
+#endif
+	return ret;
+}
+
+static void jump_label_update(struct static_key *key)
+{
+	struct jump_entry *stop = __stop___jump_table;
+	bool init = system_state < SYSTEM_RUNNING;
+	struct jump_entry *entry;
+#ifdef CONFIG_MODULES
+	struct module *mod;
+
+	if (static_key_linked(key)) {
+		__jump_label_mod_update(key);
+		return;
+	}
+
+	preempt_disable();
+	mod = __module_address((unsigned long)key);
+	if (mod) {
+		stop = mod->jump_entries + mod->num_jump_entries;
+		init = mod->state == MODULE_STATE_COMING;
+	}
+	preempt_enable();
+#endif
+	entry = static_key_entries(key);
+	/* if there are no users, entry can be NULL */
+	if (entry)
+		__jump_label_update(key, entry, stop, init);
+}
+
+#ifdef CONFIG_STATIC_KEYS_SELFTEST
+static DEFINE_STATIC_KEY_TRUE(sk_true);
+static DEFINE_STATIC_KEY_FALSE(sk_false);
+
+static __init int jump_label_test(void)
+{
+	int i;
+
+	for (i = 0; i < 2; i++) {
+		WARN_ON(static_key_enabled(&sk_true.key) != true);
+		WARN_ON(static_key_enabled(&sk_false.key) != false);
+
+		WARN_ON(!static_branch_likely(&sk_true));
+		WARN_ON(!static_branch_unlikely(&sk_true));
+		WARN_ON(static_branch_likely(&sk_false));
+		WARN_ON(static_branch_unlikely(&sk_false));
+
+		static_branch_disable(&sk_true);
+		static_branch_enable(&sk_false);
+
+		WARN_ON(static_key_enabled(&sk_true.key) == true);
+		WARN_ON(static_key_enabled(&sk_false.key) == false);
+
+		WARN_ON(static_branch_likely(&sk_true));
+		WARN_ON(static_branch_unlikely(&sk_true));
+		WARN_ON(!static_branch_likely(&sk_false));
+		WARN_ON(!static_branch_unlikely(&sk_false));
+
+		static_branch_enable(&sk_true);
+		static_branch_disable(&sk_false);
+	}
+
+	return 0;
+}
+early_initcall(jump_label_test);
+#endif /* STATIC_KEYS_SELFTEST */