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, 760 insertions, 0 deletions

diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
new file mode 100644
index 000000000..71d59b5ab
--- /dev/null
+++ b/arch/arm64/kernel/process.c
@@ -0,0 +1,760 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Based on arch/arm/kernel/process.c
+ *
+ * Original Copyright (C) 1995  Linus Torvalds
+ * Copyright (C) 1996-2000 Russell King - Converted to ARM.
+ * Copyright (C) 2012 ARM Ltd.
+ */
+#include <linux/compat.h>
+#include <linux/efi.h>
+#include <linux/elf.h>
+#include <linux/export.h>
+#include <linux/sched.h>
+#include <linux/sched/debug.h>
+#include <linux/sched/task.h>
+#include <linux/sched/task_stack.h>
+#include <linux/kernel.h>
+#include <linux/mman.h>
+#include <linux/mm.h>
+#include <linux/nospec.h>
+#include <linux/stddef.h>
+#include <linux/sysctl.h>
+#include <linux/unistd.h>
+#include <linux/user.h>
+#include <linux/delay.h>
+#include <linux/reboot.h>
+#include <linux/interrupt.h>
+#include <linux/init.h>
+#include <linux/cpu.h>
+#include <linux/elfcore.h>
+#include <linux/pm.h>
+#include <linux/tick.h>
+#include <linux/utsname.h>
+#include <linux/uaccess.h>
+#include <linux/random.h>
+#include <linux/hw_breakpoint.h>
+#include <linux/personality.h>
+#include <linux/notifier.h>
+#include <trace/events/power.h>
+#include <linux/percpu.h>
+#include <linux/thread_info.h>
+#include <linux/prctl.h>
+#include <linux/stacktrace.h>
+
+#include <asm/alternative.h>
+#include <asm/compat.h>
+#include <asm/cpufeature.h>
+#include <asm/cacheflush.h>
+#include <asm/exec.h>
+#include <asm/fpsimd.h>
+#include <asm/mmu_context.h>
+#include <asm/mte.h>
+#include <asm/processor.h>
+#include <asm/pointer_auth.h>
+#include <asm/stacktrace.h>
+#include <asm/switch_to.h>
+#include <asm/system_misc.h>
+
+#if defined(CONFIG_STACKPROTECTOR) && !defined(CONFIG_STACKPROTECTOR_PER_TASK)
+#include <linux/stackprotector.h>
+unsigned long __stack_chk_guard __ro_after_init;
+EXPORT_SYMBOL(__stack_chk_guard);
+#endif
+
+/*
+ * Function pointers to optional machine specific functions
+ */
+void (*pm_power_off)(void);
+EXPORT_SYMBOL_GPL(pm_power_off);
+
+#ifdef CONFIG_HOTPLUG_CPU
+void arch_cpu_idle_dead(void)
+{
+       cpu_die();
+}
+#endif
+
+/*
+ * Called by kexec, immediately prior to machine_kexec().
+ *
+ * This must completely disable all secondary CPUs; simply causing those CPUs
+ * to execute e.g. a RAM-based pin loop is not sufficient. This allows the
+ * kexec'd kernel to use any and all RAM as it sees fit, without having to
+ * avoid any code or data used by any SW CPU pin loop. The CPU hotplug
+ * functionality embodied in smpt_shutdown_nonboot_cpus() to achieve this.
+ */
+void machine_shutdown(void)
+{
+	smp_shutdown_nonboot_cpus(reboot_cpu);
+}
+
+/*
+ * Halting simply requires that the secondary CPUs stop performing any
+ * activity (executing tasks, handling interrupts). smp_send_stop()
+ * achieves this.
+ */
+void machine_halt(void)
+{
+	local_irq_disable();
+	smp_send_stop();
+	while (1);
+}
+
+/*
+ * Power-off simply requires that the secondary CPUs stop performing any
+ * activity (executing tasks, handling interrupts). smp_send_stop()
+ * achieves this. When the system power is turned off, it will take all CPUs
+ * with it.
+ */
+void machine_power_off(void)
+{
+	local_irq_disable();
+	smp_send_stop();
+	do_kernel_power_off();
+}
+
+/*
+ * Restart requires that the secondary CPUs stop performing any activity
+ * while the primary CPU resets the system. Systems with multiple CPUs must
+ * provide a HW restart implementation, to ensure that all CPUs reset at once.
+ * This is required so that any code running after reset on the primary CPU
+ * doesn't have to co-ordinate with other CPUs to ensure they aren't still
+ * executing pre-reset code, and using RAM that the primary CPU's code wishes
+ * to use. Implementing such co-ordination would be essentially impossible.
+ */
+void machine_restart(char *cmd)
+{
+	/* Disable interrupts first */
+	local_irq_disable();
+	smp_send_stop();
+
+	/*
+	 * UpdateCapsule() depends on the system being reset via
+	 * ResetSystem().
+	 */
+	if (efi_enabled(EFI_RUNTIME_SERVICES))
+		efi_reboot(reboot_mode, NULL);
+
+	/* Now call the architecture specific reboot code. */
+	do_kernel_restart(cmd);
+
+	/*
+	 * Whoops - the architecture was unable to reboot.
+	 */
+	printk("Reboot failed -- System halted\n");
+	while (1);
+}
+
+#define bstr(suffix, str) [PSR_BTYPE_ ## suffix >> PSR_BTYPE_SHIFT] = str
+static const char *const btypes[] = {
+	bstr(NONE, "--"),
+	bstr(  JC, "jc"),
+	bstr(   C, "-c"),
+	bstr(  J , "j-")
+};
+#undef bstr
+
+static void print_pstate(struct pt_regs *regs)
+{
+	u64 pstate = regs->pstate;
+
+	if (compat_user_mode(regs)) {
+		printk("pstate: %08llx (%c%c%c%c %c %s %s %c%c%c %cDIT %cSSBS)\n",
+			pstate,
+			pstate & PSR_AA32_N_BIT ? 'N' : 'n',
+			pstate & PSR_AA32_Z_BIT ? 'Z' : 'z',
+			pstate & PSR_AA32_C_BIT ? 'C' : 'c',
+			pstate & PSR_AA32_V_BIT ? 'V' : 'v',
+			pstate & PSR_AA32_Q_BIT ? 'Q' : 'q',
+			pstate & PSR_AA32_T_BIT ? "T32" : "A32",
+			pstate & PSR_AA32_E_BIT ? "BE" : "LE",
+			pstate & PSR_AA32_A_BIT ? 'A' : 'a',
+			pstate & PSR_AA32_I_BIT ? 'I' : 'i',
+			pstate & PSR_AA32_F_BIT ? 'F' : 'f',
+			pstate & PSR_AA32_DIT_BIT ? '+' : '-',
+			pstate & PSR_AA32_SSBS_BIT ? '+' : '-');
+	} else {
+		const char *btype_str = btypes[(pstate & PSR_BTYPE_MASK) >>
+					       PSR_BTYPE_SHIFT];
+
+		printk("pstate: %08llx (%c%c%c%c %c%c%c%c %cPAN %cUAO %cTCO %cDIT %cSSBS BTYPE=%s)\n",
+			pstate,
+			pstate & PSR_N_BIT ? 'N' : 'n',
+			pstate & PSR_Z_BIT ? 'Z' : 'z',
+			pstate & PSR_C_BIT ? 'C' : 'c',
+			pstate & PSR_V_BIT ? 'V' : 'v',
+			pstate & PSR_D_BIT ? 'D' : 'd',
+			pstate & PSR_A_BIT ? 'A' : 'a',
+			pstate & PSR_I_BIT ? 'I' : 'i',
+			pstate & PSR_F_BIT ? 'F' : 'f',
+			pstate & PSR_PAN_BIT ? '+' : '-',
+			pstate & PSR_UAO_BIT ? '+' : '-',
+			pstate & PSR_TCO_BIT ? '+' : '-',
+			pstate & PSR_DIT_BIT ? '+' : '-',
+			pstate & PSR_SSBS_BIT ? '+' : '-',
+			btype_str);
+	}
+}
+
+void __show_regs(struct pt_regs *regs)
+{
+	int i, top_reg;
+	u64 lr, sp;
+
+	if (compat_user_mode(regs)) {
+		lr = regs->compat_lr;
+		sp = regs->compat_sp;
+		top_reg = 12;
+	} else {
+		lr = regs->regs[30];
+		sp = regs->sp;
+		top_reg = 29;
+	}
+
+	show_regs_print_info(KERN_DEFAULT);
+	print_pstate(regs);
+
+	if (!user_mode(regs)) {
+		printk("pc : %pS\n", (void *)regs->pc);
+		printk("lr : %pS\n", (void *)ptrauth_strip_insn_pac(lr));
+	} else {
+		printk("pc : %016llx\n", regs->pc);
+		printk("lr : %016llx\n", lr);
+	}
+
+	printk("sp : %016llx\n", sp);
+
+	if (system_uses_irq_prio_masking())
+		printk("pmr_save: %08llx\n", regs->pmr_save);
+
+	i = top_reg;
+
+	while (i >= 0) {
+		printk("x%-2d: %016llx", i, regs->regs[i]);
+
+		while (i-- % 3)
+			pr_cont(" x%-2d: %016llx", i, regs->regs[i]);
+
+		pr_cont("\n");
+	}
+}
+
+void show_regs(struct pt_regs *regs)
+{
+	__show_regs(regs);
+	dump_backtrace(regs, NULL, KERN_DEFAULT);
+}
+
+static void tls_thread_flush(void)
+{
+	write_sysreg(0, tpidr_el0);
+	if (system_supports_tpidr2())
+		write_sysreg_s(0, SYS_TPIDR2_EL0);
+
+	if (is_compat_task()) {
+		current->thread.uw.tp_value = 0;
+
+		/*
+		 * We need to ensure ordering between the shadow state and the
+		 * hardware state, so that we don't corrupt the hardware state
+		 * with a stale shadow state during context switch.
+		 */
+		barrier();
+		write_sysreg(0, tpidrro_el0);
+	}
+}
+
+static void flush_tagged_addr_state(void)
+{
+	if (IS_ENABLED(CONFIG_ARM64_TAGGED_ADDR_ABI))
+		clear_thread_flag(TIF_TAGGED_ADDR);
+}
+
+void flush_thread(void)
+{
+	fpsimd_flush_thread();
+	tls_thread_flush();
+	flush_ptrace_hw_breakpoint(current);
+	flush_tagged_addr_state();
+}
+
+void arch_release_task_struct(struct task_struct *tsk)
+{
+	fpsimd_release_task(tsk);
+}
+
+int arch_dup_task_struct(struct task_struct *dst, struct task_struct *src)
+{
+	if (current->mm)
+		fpsimd_preserve_current_state();
+	*dst = *src;
+
+	/* We rely on the above assignment to initialize dst's thread_flags: */
+	BUILD_BUG_ON(!IS_ENABLED(CONFIG_THREAD_INFO_IN_TASK));
+
+	/*
+	 * Detach src's sve_state (if any) from dst so that it does not
+	 * get erroneously used or freed prematurely.  dst's copies
+	 * will be allocated on demand later on if dst uses SVE.
+	 * For consistency, also clear TIF_SVE here: this could be done
+	 * later in copy_process(), but to avoid tripping up future
+	 * maintainers it is best not to leave TIF flags and buffers in
+	 * an inconsistent state, even temporarily.
+	 */
+	dst->thread.sve_state = NULL;
+	clear_tsk_thread_flag(dst, TIF_SVE);
+
+	/*
+	 * In the unlikely event that we create a new thread with ZA
+	 * enabled we should retain the ZA and ZT state so duplicate
+	 * it here.  This may be shortly freed if we exec() or if
+	 * CLONE_SETTLS but it's simpler to do it here. To avoid
+	 * confusing the rest of the code ensure that we have a
+	 * sve_state allocated whenever sme_state is allocated.
+	 */
+	if (thread_za_enabled(&src->thread)) {
+		dst->thread.sve_state = kzalloc(sve_state_size(src),
+						GFP_KERNEL);
+		if (!dst->thread.sve_state)
+			return -ENOMEM;
+
+		dst->thread.sme_state = kmemdup(src->thread.sme_state,
+						sme_state_size(src),
+						GFP_KERNEL);
+		if (!dst->thread.sme_state) {
+			kfree(dst->thread.sve_state);
+			dst->thread.sve_state = NULL;
+			return -ENOMEM;
+		}
+	} else {
+		dst->thread.sme_state = NULL;
+		clear_tsk_thread_flag(dst, TIF_SME);
+	}
+
+	dst->thread.fp_type = FP_STATE_FPSIMD;
+
+	/* clear any pending asynchronous tag fault raised by the parent */
+	clear_tsk_thread_flag(dst, TIF_MTE_ASYNC_FAULT);
+
+	return 0;
+}
+
+asmlinkage void ret_from_fork(void) asm("ret_from_fork");
+
+int copy_thread(struct task_struct *p, const struct kernel_clone_args *args)
+{
+	unsigned long clone_flags = args->flags;
+	unsigned long stack_start = args->stack;
+	unsigned long tls = args->tls;
+	struct pt_regs *childregs = task_pt_regs(p);
+
+	memset(&p->thread.cpu_context, 0, sizeof(struct cpu_context));
+
+	/*
+	 * In case p was allocated the same task_struct pointer as some
+	 * other recently-exited task, make sure p is disassociated from
+	 * any cpu that may have run that now-exited task recently.
+	 * Otherwise we could erroneously skip reloading the FPSIMD
+	 * registers for p.
+	 */
+	fpsimd_flush_task_state(p);
+
+	ptrauth_thread_init_kernel(p);
+
+	if (likely(!args->fn)) {
+		*childregs = *current_pt_regs();
+		childregs->regs[0] = 0;
+
+		/*
+		 * Read the current TLS pointer from tpidr_el0 as it may be
+		 * out-of-sync with the saved value.
+		 */
+		*task_user_tls(p) = read_sysreg(tpidr_el0);
+		if (system_supports_tpidr2())
+			p->thread.tpidr2_el0 = read_sysreg_s(SYS_TPIDR2_EL0);
+
+		if (stack_start) {
+			if (is_compat_thread(task_thread_info(p)))
+				childregs->compat_sp = stack_start;
+			else
+				childregs->sp = stack_start;
+		}
+
+		/*
+		 * If a TLS pointer was passed to clone, use it for the new
+		 * thread.  We also reset TPIDR2 if it's in use.
+		 */
+		if (clone_flags & CLONE_SETTLS) {
+			p->thread.uw.tp_value = tls;
+			p->thread.tpidr2_el0 = 0;
+		}
+	} else {
+		/*
+		 * A kthread has no context to ERET to, so ensure any buggy
+		 * ERET is treated as an illegal exception return.
+		 *
+		 * When a user task is created from a kthread, childregs will
+		 * be initialized by start_thread() or start_compat_thread().
+		 */
+		memset(childregs, 0, sizeof(struct pt_regs));
+		childregs->pstate = PSR_MODE_EL1h | PSR_IL_BIT;
+
+		p->thread.cpu_context.x19 = (unsigned long)args->fn;
+		p->thread.cpu_context.x20 = (unsigned long)args->fn_arg;
+	}
+	p->thread.cpu_context.pc = (unsigned long)ret_from_fork;
+	p->thread.cpu_context.sp = (unsigned long)childregs;
+	/*
+	 * For the benefit of the unwinder, set up childregs->stackframe
+	 * as the final frame for the new task.
+	 */
+	p->thread.cpu_context.fp = (unsigned long)childregs->stackframe;
+
+	ptrace_hw_copy_thread(p);
+
+	return 0;
+}
+
+void tls_preserve_current_state(void)
+{
+	*task_user_tls(current) = read_sysreg(tpidr_el0);
+	if (system_supports_tpidr2() && !is_compat_task())
+		current->thread.tpidr2_el0 = read_sysreg_s(SYS_TPIDR2_EL0);
+}
+
+static void tls_thread_switch(struct task_struct *next)
+{
+	tls_preserve_current_state();
+
+	if (is_compat_thread(task_thread_info(next)))
+		write_sysreg(next->thread.uw.tp_value, tpidrro_el0);
+	else if (!arm64_kernel_unmapped_at_el0())
+		write_sysreg(0, tpidrro_el0);
+
+	write_sysreg(*task_user_tls(next), tpidr_el0);
+	if (system_supports_tpidr2())
+		write_sysreg_s(next->thread.tpidr2_el0, SYS_TPIDR2_EL0);
+}
+
+/*
+ * Force SSBS state on context-switch, since it may be lost after migrating
+ * from a CPU which treats the bit as RES0 in a heterogeneous system.
+ */
+static void ssbs_thread_switch(struct task_struct *next)
+{
+	/*
+	 * Nothing to do for kernel threads, but 'regs' may be junk
+	 * (e.g. idle task) so check the flags and bail early.
+	 */
+	if (unlikely(next->flags & PF_KTHREAD))
+		return;
+
+	/*
+	 * If all CPUs implement the SSBS extension, then we just need to
+	 * context-switch the PSTATE field.
+	 */
+	if (cpus_have_const_cap(ARM64_SSBS))
+		return;
+
+	spectre_v4_enable_task_mitigation(next);
+}
+
+/*
+ * We store our current task in sp_el0, which is clobbered by userspace. Keep a
+ * shadow copy so that we can restore this upon entry from userspace.
+ *
+ * This is *only* for exception entry from EL0, and is not valid until we
+ * __switch_to() a user task.
+ */
+DEFINE_PER_CPU(struct task_struct *, __entry_task);
+
+static void entry_task_switch(struct task_struct *next)
+{
+	__this_cpu_write(__entry_task, next);
+}
+
+/*
+ * ARM erratum 1418040 handling, affecting the 32bit view of CNTVCT.
+ * Ensure access is disabled when switching to a 32bit task, ensure
+ * access is enabled when switching to a 64bit task.
+ */
+static void erratum_1418040_thread_switch(struct task_struct *next)
+{
+	if (!IS_ENABLED(CONFIG_ARM64_ERRATUM_1418040) ||
+	    !this_cpu_has_cap(ARM64_WORKAROUND_1418040))
+		return;
+
+	if (is_compat_thread(task_thread_info(next)))
+		sysreg_clear_set(cntkctl_el1, ARCH_TIMER_USR_VCT_ACCESS_EN, 0);
+	else
+		sysreg_clear_set(cntkctl_el1, 0, ARCH_TIMER_USR_VCT_ACCESS_EN);
+}
+
+static void erratum_1418040_new_exec(void)
+{
+	preempt_disable();
+	erratum_1418040_thread_switch(current);
+	preempt_enable();
+}
+
+/*
+ * __switch_to() checks current->thread.sctlr_user as an optimisation. Therefore
+ * this function must be called with preemption disabled and the update to
+ * sctlr_user must be made in the same preemption disabled block so that
+ * __switch_to() does not see the variable update before the SCTLR_EL1 one.
+ */
+void update_sctlr_el1(u64 sctlr)
+{
+	/*
+	 * EnIA must not be cleared while in the kernel as this is necessary for
+	 * in-kernel PAC. It will be cleared on kernel exit if needed.
+	 */
+	sysreg_clear_set(sctlr_el1, SCTLR_USER_MASK & ~SCTLR_ELx_ENIA, sctlr);
+
+	/* ISB required for the kernel uaccess routines when setting TCF0. */
+	isb();
+}
+
+/*
+ * Thread switching.
+ */
+__notrace_funcgraph __sched
+struct task_struct *__switch_to(struct task_struct *prev,
+				struct task_struct *next)
+{
+	struct task_struct *last;
+
+	fpsimd_thread_switch(next);
+	tls_thread_switch(next);
+	hw_breakpoint_thread_switch(next);
+	contextidr_thread_switch(next);
+	entry_task_switch(next);
+	ssbs_thread_switch(next);
+	erratum_1418040_thread_switch(next);
+	ptrauth_thread_switch_user(next);
+
+	/*
+	 * Complete any pending TLB or cache maintenance on this CPU in case
+	 * the thread migrates to a different CPU.
+	 * This full barrier is also required by the membarrier system
+	 * call.
+	 */
+	dsb(ish);
+
+	/*
+	 * MTE thread switching must happen after the DSB above to ensure that
+	 * any asynchronous tag check faults have been logged in the TFSR*_EL1
+	 * registers.
+	 */
+	mte_thread_switch(next);
+	/* avoid expensive SCTLR_EL1 accesses if no change */
+	if (prev->thread.sctlr_user != next->thread.sctlr_user)
+		update_sctlr_el1(next->thread.sctlr_user);
+
+	/* the actual thread switch */
+	last = cpu_switch_to(prev, next);
+
+	return last;
+}
+
+struct wchan_info {
+	unsigned long	pc;
+	int		count;
+};
+
+static bool get_wchan_cb(void *arg, unsigned long pc)
+{
+	struct wchan_info *wchan_info = arg;
+
+	if (!in_sched_functions(pc)) {
+		wchan_info->pc = pc;
+		return false;
+	}
+	return wchan_info->count++ < 16;
+}
+
+unsigned long __get_wchan(struct task_struct *p)
+{
+	struct wchan_info wchan_info = {
+		.pc = 0,
+		.count = 0,
+	};
+
+	if (!try_get_task_stack(p))
+		return 0;
+
+	arch_stack_walk(get_wchan_cb, &wchan_info, p, NULL);
+
+	put_task_stack(p);
+
+	return wchan_info.pc;
+}
+
+unsigned long arch_align_stack(unsigned long sp)
+{
+	if (!(current->personality & ADDR_NO_RANDOMIZE) && randomize_va_space)
+		sp -= get_random_u32_below(PAGE_SIZE);
+	return sp & ~0xf;
+}
+
+#ifdef CONFIG_COMPAT
+int compat_elf_check_arch(const struct elf32_hdr *hdr)
+{
+	if (!system_supports_32bit_el0())
+		return false;
+
+	if ((hdr)->e_machine != EM_ARM)
+		return false;
+
+	if (!((hdr)->e_flags & EF_ARM_EABI_MASK))
+		return false;
+
+	/*
+	 * Prevent execve() of a 32-bit program from a deadline task
+	 * if the restricted affinity mask would be inadmissible on an
+	 * asymmetric system.
+	 */
+	return !static_branch_unlikely(&arm64_mismatched_32bit_el0) ||
+	       !dl_task_check_affinity(current, system_32bit_el0_cpumask());
+}
+#endif
+
+/*
+ * Called from setup_new_exec() after (COMPAT_)SET_PERSONALITY.
+ */
+void arch_setup_new_exec(void)
+{
+	unsigned long mmflags = 0;
+
+	if (is_compat_task()) {
+		mmflags = MMCF_AARCH32;
+
+		/*
+		 * Restrict the CPU affinity mask for a 32-bit task so that
+		 * it contains only 32-bit-capable CPUs.
+		 *
+		 * From the perspective of the task, this looks similar to
+		 * what would happen if the 64-bit-only CPUs were hot-unplugged
+		 * at the point of execve(), although we try a bit harder to
+		 * honour the cpuset hierarchy.
+		 */
+		if (static_branch_unlikely(&arm64_mismatched_32bit_el0))
+			force_compatible_cpus_allowed_ptr(current);
+	} else if (static_branch_unlikely(&arm64_mismatched_32bit_el0)) {
+		relax_compatible_cpus_allowed_ptr(current);
+	}
+
+	current->mm->context.flags = mmflags;
+	ptrauth_thread_init_user();
+	mte_thread_init_user();
+	erratum_1418040_new_exec();
+
+	if (task_spec_ssb_noexec(current)) {
+		arch_prctl_spec_ctrl_set(current, PR_SPEC_STORE_BYPASS,
+					 PR_SPEC_ENABLE);
+	}
+}
+
+#ifdef CONFIG_ARM64_TAGGED_ADDR_ABI
+/*
+ * Control the relaxed ABI allowing tagged user addresses into the kernel.
+ */
+static unsigned int tagged_addr_disabled;
+
+long set_tagged_addr_ctrl(struct task_struct *task, unsigned long arg)
+{
+	unsigned long valid_mask = PR_TAGGED_ADDR_ENABLE;
+	struct thread_info *ti = task_thread_info(task);
+
+	if (is_compat_thread(ti))
+		return -EINVAL;
+
+	if (system_supports_mte())
+		valid_mask |= PR_MTE_TCF_SYNC | PR_MTE_TCF_ASYNC \
+			| PR_MTE_TAG_MASK;
+
+	if (arg & ~valid_mask)
+		return -EINVAL;
+
+	/*
+	 * Do not allow the enabling of the tagged address ABI if globally
+	 * disabled via sysctl abi.tagged_addr_disabled.
+	 */
+	if (arg & PR_TAGGED_ADDR_ENABLE && tagged_addr_disabled)
+		return -EINVAL;
+
+	if (set_mte_ctrl(task, arg) != 0)
+		return -EINVAL;
+
+	update_ti_thread_flag(ti, TIF_TAGGED_ADDR, arg & PR_TAGGED_ADDR_ENABLE);
+
+	return 0;
+}
+
+long get_tagged_addr_ctrl(struct task_struct *task)
+{
+	long ret = 0;
+	struct thread_info *ti = task_thread_info(task);
+
+	if (is_compat_thread(ti))
+		return -EINVAL;
+
+	if (test_ti_thread_flag(ti, TIF_TAGGED_ADDR))
+		ret = PR_TAGGED_ADDR_ENABLE;
+
+	ret |= get_mte_ctrl(task);
+
+	return ret;
+}
+
+/*
+ * Global sysctl to disable the tagged user addresses support. This control
+ * only prevents the tagged address ABI enabling via prctl() and does not
+ * disable it for tasks that already opted in to the relaxed ABI.
+ */
+
+static struct ctl_table tagged_addr_sysctl_table[] = {
+	{
+		.procname	= "tagged_addr_disabled",
+		.mode		= 0644,
+		.data		= &tagged_addr_disabled,
+		.maxlen		= sizeof(int),
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= SYSCTL_ZERO,
+		.extra2		= SYSCTL_ONE,
+	},
+	{ }
+};
+
+static int __init tagged_addr_init(void)
+{
+	if (!register_sysctl("abi", tagged_addr_sysctl_table))
+		return -EINVAL;
+	return 0;
+}
+
+core_initcall(tagged_addr_init);
+#endif	/* CONFIG_ARM64_TAGGED_ADDR_ABI */
+
+#ifdef CONFIG_BINFMT_ELF
+int arch_elf_adjust_prot(int prot, const struct arch_elf_state *state,
+			 bool has_interp, bool is_interp)
+{
+	/*
+	 * For dynamically linked executables the interpreter is
+	 * responsible for setting PROT_BTI on everything except
+	 * itself.
+	 */
+	if (is_interp != has_interp)
+		return prot;
+
+	if (!(state->flags & ARM64_ELF_BTI))
+		return prot;
+
+	if (prot & PROT_EXEC)
+		prot |= PROT_BTI;
+
+	return prot;
+}
+#endif