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().
  ...

4 files changed, 473 insertions, 0 deletions

diff --git a/arch/x86/entry/vsyscall/Makefile b/arch/x86/entry/vsyscall/Makefile
new file mode 100644
index 000000000..93c1b3e94
--- /dev/null
+++ b/arch/x86/entry/vsyscall/Makefile
@@ -0,0 +1,6 @@
+# SPDX-License-Identifier: GPL-2.0-only
+#
+# Makefile for the x86 low level vsyscall code
+#
+obj-$(CONFIG_X86_VSYSCALL_EMULATION)	+= vsyscall_64.o vsyscall_emu_64.o
+
diff --git a/arch/x86/entry/vsyscall/vsyscall_64.c b/arch/x86/entry/vsyscall/vsyscall_64.c
new file mode 100644
index 000000000..4af81df13
--- /dev/null
+++ b/arch/x86/entry/vsyscall/vsyscall_64.c
@@ -0,0 +1,398 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2012-2014 Andy Lutomirski <luto@amacapital.net>
+ *
+ * Based on the original implementation which is:
+ *  Copyright (C) 2001 Andrea Arcangeli <andrea@suse.de> SuSE
+ *  Copyright 2003 Andi Kleen, SuSE Labs.
+ *
+ *  Parts of the original code have been moved to arch/x86/vdso/vma.c
+ *
+ * This file implements vsyscall emulation.  vsyscalls are a legacy ABI:
+ * Userspace can request certain kernel services by calling fixed
+ * addresses.  This concept is problematic:
+ *
+ * - It interferes with ASLR.
+ * - It's awkward to write code that lives in kernel addresses but is
+ *   callable by userspace at fixed addresses.
+ * - The whole concept is impossible for 32-bit compat userspace.
+ * - UML cannot easily virtualize a vsyscall.
+ *
+ * As of mid-2014, I believe that there is no new userspace code that
+ * will use a vsyscall if the vDSO is present.  I hope that there will
+ * soon be no new userspace code that will ever use a vsyscall.
+ *
+ * The code in this file emulates vsyscalls when notified of a page
+ * fault to a vsyscall address.
+ */
+
+#include <linux/kernel.h>
+#include <linux/timer.h>
+#include <linux/sched/signal.h>
+#include <linux/mm_types.h>
+#include <linux/syscalls.h>
+#include <linux/ratelimit.h>
+
+#include <asm/vsyscall.h>
+#include <asm/unistd.h>
+#include <asm/fixmap.h>
+#include <asm/traps.h>
+#include <asm/paravirt.h>
+
+#define CREATE_TRACE_POINTS
+#include "vsyscall_trace.h"
+
+static enum { EMULATE, XONLY, NONE } vsyscall_mode __ro_after_init =
+#ifdef CONFIG_LEGACY_VSYSCALL_NONE
+	NONE;
+#elif defined(CONFIG_LEGACY_VSYSCALL_XONLY)
+	XONLY;
+#else
+	#error VSYSCALL config is broken
+#endif
+
+static int __init vsyscall_setup(char *str)
+{
+	if (str) {
+		if (!strcmp("emulate", str))
+			vsyscall_mode = EMULATE;
+		else if (!strcmp("xonly", str))
+			vsyscall_mode = XONLY;
+		else if (!strcmp("none", str))
+			vsyscall_mode = NONE;
+		else
+			return -EINVAL;
+
+		return 0;
+	}
+
+	return -EINVAL;
+}
+early_param("vsyscall", vsyscall_setup);
+
+static void warn_bad_vsyscall(const char *level, struct pt_regs *regs,
+			      const char *message)
+{
+	if (!show_unhandled_signals)
+		return;
+
+	printk_ratelimited("%s%s[%d] %s ip:%lx cs:%lx sp:%lx ax:%lx si:%lx di:%lx\n",
+			   level, current->comm, task_pid_nr(current),
+			   message, regs->ip, regs->cs,
+			   regs->sp, regs->ax, regs->si, regs->di);
+}
+
+static int addr_to_vsyscall_nr(unsigned long addr)
+{
+	int nr;
+
+	if ((addr & ~0xC00UL) != VSYSCALL_ADDR)
+		return -EINVAL;
+
+	nr = (addr & 0xC00UL) >> 10;
+	if (nr >= 3)
+		return -EINVAL;
+
+	return nr;
+}
+
+static bool write_ok_or_segv(unsigned long ptr, size_t size)
+{
+	/*
+	 * XXX: if access_ok, get_user, and put_user handled
+	 * sig_on_uaccess_err, this could go away.
+	 */
+
+	if (!access_ok((void __user *)ptr, size)) {
+		struct thread_struct *thread = &current->thread;
+
+		thread->error_code	= X86_PF_USER | X86_PF_WRITE;
+		thread->cr2		= ptr;
+		thread->trap_nr		= X86_TRAP_PF;
+
+		force_sig_fault(SIGSEGV, SEGV_MAPERR, (void __user *)ptr);
+		return false;
+	} else {
+		return true;
+	}
+}
+
+bool emulate_vsyscall(unsigned long error_code,
+		      struct pt_regs *regs, unsigned long address)
+{
+	struct task_struct *tsk;
+	unsigned long caller;
+	int vsyscall_nr, syscall_nr, tmp;
+	int prev_sig_on_uaccess_err;
+	long ret;
+	unsigned long orig_dx;
+
+	/* Write faults or kernel-privilege faults never get fixed up. */
+	if ((error_code & (X86_PF_WRITE | X86_PF_USER)) != X86_PF_USER)
+		return false;
+
+	if (!(error_code & X86_PF_INSTR)) {
+		/* Failed vsyscall read */
+		if (vsyscall_mode == EMULATE)
+			return false;
+
+		/*
+		 * User code tried and failed to read the vsyscall page.
+		 */
+		warn_bad_vsyscall(KERN_INFO, regs, "vsyscall read attempt denied -- look up the vsyscall kernel parameter if you need a workaround");
+		return false;
+	}
+
+	/*
+	 * No point in checking CS -- the only way to get here is a user mode
+	 * trap to a high address, which means that we're in 64-bit user code.
+	 */
+
+	WARN_ON_ONCE(address != regs->ip);
+
+	if (vsyscall_mode == NONE) {
+		warn_bad_vsyscall(KERN_INFO, regs,
+				  "vsyscall attempted with vsyscall=none");
+		return false;
+	}
+
+	vsyscall_nr = addr_to_vsyscall_nr(address);
+
+	trace_emulate_vsyscall(vsyscall_nr);
+
+	if (vsyscall_nr < 0) {
+		warn_bad_vsyscall(KERN_WARNING, regs,
+				  "misaligned vsyscall (exploit attempt or buggy program) -- look up the vsyscall kernel parameter if you need a workaround");
+		goto sigsegv;
+	}
+
+	if (get_user(caller, (unsigned long __user *)regs->sp) != 0) {
+		warn_bad_vsyscall(KERN_WARNING, regs,
+				  "vsyscall with bad stack (exploit attempt?)");
+		goto sigsegv;
+	}
+
+	tsk = current;
+
+	/*
+	 * Check for access_ok violations and find the syscall nr.
+	 *
+	 * NULL is a valid user pointer (in the access_ok sense) on 32-bit and
+	 * 64-bit, so we don't need to special-case it here.  For all the
+	 * vsyscalls, NULL means "don't write anything" not "write it at
+	 * address 0".
+	 */
+	switch (vsyscall_nr) {
+	case 0:
+		if (!write_ok_or_segv(regs->di, sizeof(struct __kernel_old_timeval)) ||
+		    !write_ok_or_segv(regs->si, sizeof(struct timezone))) {
+			ret = -EFAULT;
+			goto check_fault;
+		}
+
+		syscall_nr = __NR_gettimeofday;
+		break;
+
+	case 1:
+		if (!write_ok_or_segv(regs->di, sizeof(__kernel_old_time_t))) {
+			ret = -EFAULT;
+			goto check_fault;
+		}
+
+		syscall_nr = __NR_time;
+		break;
+
+	case 2:
+		if (!write_ok_or_segv(regs->di, sizeof(unsigned)) ||
+		    !write_ok_or_segv(regs->si, sizeof(unsigned))) {
+			ret = -EFAULT;
+			goto check_fault;
+		}
+
+		syscall_nr = __NR_getcpu;
+		break;
+	}
+
+	/*
+	 * Handle seccomp.  regs->ip must be the original value.
+	 * See seccomp_send_sigsys and Documentation/userspace-api/seccomp_filter.rst.
+	 *
+	 * We could optimize the seccomp disabled case, but performance
+	 * here doesn't matter.
+	 */
+	regs->orig_ax = syscall_nr;
+	regs->ax = -ENOSYS;
+	tmp = secure_computing();
+	if ((!tmp && regs->orig_ax != syscall_nr) || regs->ip != address) {
+		warn_bad_vsyscall(KERN_DEBUG, regs,
+				  "seccomp tried to change syscall nr or ip");
+		force_exit_sig(SIGSYS);
+		return true;
+	}
+	regs->orig_ax = -1;
+	if (tmp)
+		goto do_ret;  /* skip requested */
+
+	/*
+	 * With a real vsyscall, page faults cause SIGSEGV.  We want to
+	 * preserve that behavior to make writing exploits harder.
+	 */
+	prev_sig_on_uaccess_err = current->thread.sig_on_uaccess_err;
+	current->thread.sig_on_uaccess_err = 1;
+
+	ret = -EFAULT;
+	switch (vsyscall_nr) {
+	case 0:
+		/* this decodes regs->di and regs->si on its own */
+		ret = __x64_sys_gettimeofday(regs);
+		break;
+
+	case 1:
+		/* this decodes regs->di on its own */
+		ret = __x64_sys_time(regs);
+		break;
+
+	case 2:
+		/* while we could clobber regs->dx, we didn't in the past... */
+		orig_dx = regs->dx;
+		regs->dx = 0;
+		/* this decodes regs->di, regs->si and regs->dx on its own */
+		ret = __x64_sys_getcpu(regs);
+		regs->dx = orig_dx;
+		break;
+	}
+
+	current->thread.sig_on_uaccess_err = prev_sig_on_uaccess_err;
+
+check_fault:
+	if (ret == -EFAULT) {
+		/* Bad news -- userspace fed a bad pointer to a vsyscall. */
+		warn_bad_vsyscall(KERN_INFO, regs,
+				  "vsyscall fault (exploit attempt?)");
+
+		/*
+		 * If we failed to generate a signal for any reason,
+		 * generate one here.  (This should be impossible.)
+		 */
+		if (WARN_ON_ONCE(!sigismember(&tsk->pending.signal, SIGBUS) &&
+				 !sigismember(&tsk->pending.signal, SIGSEGV)))
+			goto sigsegv;
+
+		return true;  /* Don't emulate the ret. */
+	}
+
+	regs->ax = ret;
+
+do_ret:
+	/* Emulate a ret instruction. */
+	regs->ip = caller;
+	regs->sp += 8;
+	return true;
+
+sigsegv:
+	force_sig(SIGSEGV);
+	return true;
+}
+
+/*
+ * A pseudo VMA to allow ptrace access for the vsyscall page.  This only
+ * covers the 64bit vsyscall page now. 32bit has a real VMA now and does
+ * not need special handling anymore:
+ */
+static const char *gate_vma_name(struct vm_area_struct *vma)
+{
+	return "[vsyscall]";
+}
+static const struct vm_operations_struct gate_vma_ops = {
+	.name = gate_vma_name,
+};
+static struct vm_area_struct gate_vma __ro_after_init = {
+	.vm_start	= VSYSCALL_ADDR,
+	.vm_end		= VSYSCALL_ADDR + PAGE_SIZE,
+	.vm_page_prot	= PAGE_READONLY_EXEC,
+	.vm_flags	= VM_READ | VM_EXEC,
+	.vm_ops		= &gate_vma_ops,
+};
+
+struct vm_area_struct *get_gate_vma(struct mm_struct *mm)
+{
+#ifdef CONFIG_COMPAT
+	if (!mm || !(mm->context.flags & MM_CONTEXT_HAS_VSYSCALL))
+		return NULL;
+#endif
+	if (vsyscall_mode == NONE)
+		return NULL;
+	return &gate_vma;
+}
+
+int in_gate_area(struct mm_struct *mm, unsigned long addr)
+{
+	struct vm_area_struct *vma = get_gate_vma(mm);
+
+	if (!vma)
+		return 0;
+
+	return (addr >= vma->vm_start) && (addr < vma->vm_end);
+}
+
+/*
+ * Use this when you have no reliable mm, typically from interrupt
+ * context. It is less reliable than using a task's mm and may give
+ * false positives.
+ */
+int in_gate_area_no_mm(unsigned long addr)
+{
+	return vsyscall_mode != NONE && (addr & PAGE_MASK) == VSYSCALL_ADDR;
+}
+
+/*
+ * The VSYSCALL page is the only user-accessible page in the kernel address
+ * range.  Normally, the kernel page tables can have _PAGE_USER clear, but
+ * the tables covering VSYSCALL_ADDR need _PAGE_USER set if vsyscalls
+ * are enabled.
+ *
+ * Some day we may create a "minimal" vsyscall mode in which we emulate
+ * vsyscalls but leave the page not present.  If so, we skip calling
+ * this.
+ */
+void __init set_vsyscall_pgtable_user_bits(pgd_t *root)
+{
+	pgd_t *pgd;
+	p4d_t *p4d;
+	pud_t *pud;
+	pmd_t *pmd;
+
+	pgd = pgd_offset_pgd(root, VSYSCALL_ADDR);
+	set_pgd(pgd, __pgd(pgd_val(*pgd) | _PAGE_USER));
+	p4d = p4d_offset(pgd, VSYSCALL_ADDR);
+#if CONFIG_PGTABLE_LEVELS >= 5
+	set_p4d(p4d, __p4d(p4d_val(*p4d) | _PAGE_USER));
+#endif
+	pud = pud_offset(p4d, VSYSCALL_ADDR);
+	set_pud(pud, __pud(pud_val(*pud) | _PAGE_USER));
+	pmd = pmd_offset(pud, VSYSCALL_ADDR);
+	set_pmd(pmd, __pmd(pmd_val(*pmd) | _PAGE_USER));
+}
+
+void __init map_vsyscall(void)
+{
+	extern char __vsyscall_page;
+	unsigned long physaddr_vsyscall = __pa_symbol(&__vsyscall_page);
+
+	/*
+	 * For full emulation, the page needs to exist for real.  In
+	 * execute-only mode, there is no PTE at all backing the vsyscall
+	 * page.
+	 */
+	if (vsyscall_mode == EMULATE) {
+		__set_fixmap(VSYSCALL_PAGE, physaddr_vsyscall,
+			     PAGE_KERNEL_VVAR);
+		set_vsyscall_pgtable_user_bits(swapper_pg_dir);
+	}
+
+	if (vsyscall_mode == XONLY)
+		gate_vma.vm_flags = VM_EXEC;
+
+	BUILD_BUG_ON((unsigned long)__fix_to_virt(VSYSCALL_PAGE) !=
+		     (unsigned long)VSYSCALL_ADDR);
+}
diff --git a/arch/x86/entry/vsyscall/vsyscall_emu_64.S b/arch/x86/entry/vsyscall/vsyscall_emu_64.S
new file mode 100644
index 000000000..ef2dd1827
--- /dev/null
+++ b/arch/x86/entry/vsyscall/vsyscall_emu_64.S
@@ -0,0 +1,39 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * vsyscall_emu_64.S: Vsyscall emulation page
+ *
+ * Copyright (c) 2011 Andy Lutomirski
+ */
+
+#include <linux/linkage.h>
+
+#include <asm/irq_vectors.h>
+#include <asm/page_types.h>
+#include <asm/unistd_64.h>
+
+__PAGE_ALIGNED_DATA
+	.globl __vsyscall_page
+	.balign PAGE_SIZE, 0xcc
+	.type __vsyscall_page, @object
+__vsyscall_page:
+
+	mov $__NR_gettimeofday, %rax
+	syscall
+	ret
+	int3
+
+	.balign 1024, 0xcc
+	mov $__NR_time, %rax
+	syscall
+	ret
+	int3
+
+	.balign 1024, 0xcc
+	mov $__NR_getcpu, %rax
+	syscall
+	ret
+	int3
+
+	.balign 4096, 0xcc
+
+	.size __vsyscall_page, 4096
diff --git a/arch/x86/entry/vsyscall/vsyscall_trace.h b/arch/x86/entry/vsyscall/vsyscall_trace.h
new file mode 100644
index 000000000..3c3f9765a
--- /dev/null
+++ b/arch/x86/entry/vsyscall/vsyscall_trace.h
@@ -0,0 +1,30 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#undef TRACE_SYSTEM
+#define TRACE_SYSTEM vsyscall
+
+#if !defined(__VSYSCALL_TRACE_H) || defined(TRACE_HEADER_MULTI_READ)
+#define __VSYSCALL_TRACE_H
+
+#include <linux/tracepoint.h>
+
+TRACE_EVENT(emulate_vsyscall,
+
+	    TP_PROTO(int nr),
+
+	    TP_ARGS(nr),
+
+	    TP_STRUCT__entry(__field(int, nr)),
+
+	    TP_fast_assign(
+			   __entry->nr = nr;
+			   ),
+
+	    TP_printk("nr = %d", __entry->nr)
+);
+
+#endif
+
+#undef TRACE_INCLUDE_PATH
+#define TRACE_INCLUDE_PATH ../../arch/x86/entry/vsyscall/
+#define TRACE_INCLUDE_FILE vsyscall_trace
+#include <trace/define_trace.h>