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, 1094 insertions, 0 deletions

diff --git a/drivers/firmware/arm_sdei.c b/drivers/firmware/arm_sdei.c
new file mode 100644
index 000000000..1e1a51510
--- /dev/null
+++ b/drivers/firmware/arm_sdei.c
@@ -0,0 +1,1094 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (C) 2017 Arm Ltd.
+#define pr_fmt(fmt) "sdei: " fmt
+
+#include <acpi/ghes.h>
+#include <linux/acpi.h>
+#include <linux/arm_sdei.h>
+#include <linux/arm-smccc.h>
+#include <linux/atomic.h>
+#include <linux/bitops.h>
+#include <linux/compiler.h>
+#include <linux/cpuhotplug.h>
+#include <linux/cpu.h>
+#include <linux/cpu_pm.h>
+#include <linux/errno.h>
+#include <linux/hardirq.h>
+#include <linux/kernel.h>
+#include <linux/kprobes.h>
+#include <linux/kvm_host.h>
+#include <linux/list.h>
+#include <linux/mutex.h>
+#include <linux/notifier.h>
+#include <linux/of.h>
+#include <linux/of_platform.h>
+#include <linux/percpu.h>
+#include <linux/platform_device.h>
+#include <linux/pm.h>
+#include <linux/ptrace.h>
+#include <linux/preempt.h>
+#include <linux/reboot.h>
+#include <linux/slab.h>
+#include <linux/smp.h>
+#include <linux/spinlock.h>
+
+/*
+ * The call to use to reach the firmware.
+ */
+static asmlinkage void (*sdei_firmware_call)(unsigned long function_id,
+		      unsigned long arg0, unsigned long arg1,
+		      unsigned long arg2, unsigned long arg3,
+		      unsigned long arg4, struct arm_smccc_res *res);
+
+/* entry point from firmware to arch asm code */
+static unsigned long sdei_entry_point;
+
+struct sdei_event {
+	/* These three are protected by the sdei_list_lock */
+	struct list_head	list;
+	bool			reregister;
+	bool			reenable;
+
+	u32			event_num;
+	u8			type;
+	u8			priority;
+
+	/* This pointer is handed to firmware as the event argument. */
+	union {
+		/* Shared events */
+		struct sdei_registered_event *registered;
+
+		/* CPU private events */
+		struct sdei_registered_event __percpu *private_registered;
+	};
+};
+
+/* Take the mutex for any API call or modification. Take the mutex first. */
+static DEFINE_MUTEX(sdei_events_lock);
+
+/* and then hold this when modifying the list */
+static DEFINE_SPINLOCK(sdei_list_lock);
+static LIST_HEAD(sdei_list);
+
+/* Private events are registered/enabled via IPI passing one of these */
+struct sdei_crosscall_args {
+	struct sdei_event *event;
+	atomic_t errors;
+	int first_error;
+};
+
+#define CROSSCALL_INIT(arg, event)		\
+	do {					\
+		arg.event = event;		\
+		arg.first_error = 0;		\
+		atomic_set(&arg.errors, 0);	\
+	} while (0)
+
+static inline int sdei_do_local_call(smp_call_func_t fn,
+				     struct sdei_event *event)
+{
+	struct sdei_crosscall_args arg;
+
+	CROSSCALL_INIT(arg, event);
+	fn(&arg);
+
+	return arg.first_error;
+}
+
+static inline int sdei_do_cross_call(smp_call_func_t fn,
+				     struct sdei_event *event)
+{
+	struct sdei_crosscall_args arg;
+
+	CROSSCALL_INIT(arg, event);
+	on_each_cpu(fn, &arg, true);
+
+	return arg.first_error;
+}
+
+static inline void
+sdei_cross_call_return(struct sdei_crosscall_args *arg, int err)
+{
+	if (err && (atomic_inc_return(&arg->errors) == 1))
+		arg->first_error = err;
+}
+
+static int sdei_to_linux_errno(unsigned long sdei_err)
+{
+	switch (sdei_err) {
+	case SDEI_NOT_SUPPORTED:
+		return -EOPNOTSUPP;
+	case SDEI_INVALID_PARAMETERS:
+		return -EINVAL;
+	case SDEI_DENIED:
+		return -EPERM;
+	case SDEI_PENDING:
+		return -EINPROGRESS;
+	case SDEI_OUT_OF_RESOURCE:
+		return -ENOMEM;
+	}
+
+	return 0;
+}
+
+static int invoke_sdei_fn(unsigned long function_id, unsigned long arg0,
+			  unsigned long arg1, unsigned long arg2,
+			  unsigned long arg3, unsigned long arg4,
+			  u64 *result)
+{
+	int err;
+	struct arm_smccc_res res;
+
+	if (sdei_firmware_call) {
+		sdei_firmware_call(function_id, arg0, arg1, arg2, arg3, arg4,
+				   &res);
+		err = sdei_to_linux_errno(res.a0);
+	} else {
+		/*
+		 * !sdei_firmware_call means we failed to probe or called
+		 * sdei_mark_interface_broken(). -EIO is not an error returned
+		 * by sdei_to_linux_errno() and is used to suppress messages
+		 * from this driver.
+		 */
+		err = -EIO;
+		res.a0 = SDEI_NOT_SUPPORTED;
+	}
+
+	if (result)
+		*result = res.a0;
+
+	return err;
+}
+NOKPROBE_SYMBOL(invoke_sdei_fn);
+
+static struct sdei_event *sdei_event_find(u32 event_num)
+{
+	struct sdei_event *e, *found = NULL;
+
+	lockdep_assert_held(&sdei_events_lock);
+
+	spin_lock(&sdei_list_lock);
+	list_for_each_entry(e, &sdei_list, list) {
+		if (e->event_num == event_num) {
+			found = e;
+			break;
+		}
+	}
+	spin_unlock(&sdei_list_lock);
+
+	return found;
+}
+
+int sdei_api_event_context(u32 query, u64 *result)
+{
+	return invoke_sdei_fn(SDEI_1_0_FN_SDEI_EVENT_CONTEXT, query, 0, 0, 0, 0,
+			      result);
+}
+NOKPROBE_SYMBOL(sdei_api_event_context);
+
+static int sdei_api_event_get_info(u32 event, u32 info, u64 *result)
+{
+	return invoke_sdei_fn(SDEI_1_0_FN_SDEI_EVENT_GET_INFO, event, info, 0,
+			      0, 0, result);
+}
+
+static struct sdei_event *sdei_event_create(u32 event_num,
+					    sdei_event_callback *cb,
+					    void *cb_arg)
+{
+	int err;
+	u64 result;
+	struct sdei_event *event;
+	struct sdei_registered_event *reg;
+
+	lockdep_assert_held(&sdei_events_lock);
+
+	event = kzalloc(sizeof(*event), GFP_KERNEL);
+	if (!event) {
+		err = -ENOMEM;
+		goto fail;
+	}
+
+	INIT_LIST_HEAD(&event->list);
+	event->event_num = event_num;
+
+	err = sdei_api_event_get_info(event_num, SDEI_EVENT_INFO_EV_PRIORITY,
+				      &result);
+	if (err)
+		goto fail;
+	event->priority = result;
+
+	err = sdei_api_event_get_info(event_num, SDEI_EVENT_INFO_EV_TYPE,
+				      &result);
+	if (err)
+		goto fail;
+	event->type = result;
+
+	if (event->type == SDEI_EVENT_TYPE_SHARED) {
+		reg = kzalloc(sizeof(*reg), GFP_KERNEL);
+		if (!reg) {
+			err = -ENOMEM;
+			goto fail;
+		}
+
+		reg->event_num = event->event_num;
+		reg->priority = event->priority;
+
+		reg->callback = cb;
+		reg->callback_arg = cb_arg;
+		event->registered = reg;
+	} else {
+		int cpu;
+		struct sdei_registered_event __percpu *regs;
+
+		regs = alloc_percpu(struct sdei_registered_event);
+		if (!regs) {
+			err = -ENOMEM;
+			goto fail;
+		}
+
+		for_each_possible_cpu(cpu) {
+			reg = per_cpu_ptr(regs, cpu);
+
+			reg->event_num = event->event_num;
+			reg->priority = event->priority;
+			reg->callback = cb;
+			reg->callback_arg = cb_arg;
+		}
+
+		event->private_registered = regs;
+	}
+
+	spin_lock(&sdei_list_lock);
+	list_add(&event->list, &sdei_list);
+	spin_unlock(&sdei_list_lock);
+
+	return event;
+
+fail:
+	kfree(event);
+	return ERR_PTR(err);
+}
+
+static void sdei_event_destroy_llocked(struct sdei_event *event)
+{
+	lockdep_assert_held(&sdei_events_lock);
+	lockdep_assert_held(&sdei_list_lock);
+
+	list_del(&event->list);
+
+	if (event->type == SDEI_EVENT_TYPE_SHARED)
+		kfree(event->registered);
+	else
+		free_percpu(event->private_registered);
+
+	kfree(event);
+}
+
+static void sdei_event_destroy(struct sdei_event *event)
+{
+	spin_lock(&sdei_list_lock);
+	sdei_event_destroy_llocked(event);
+	spin_unlock(&sdei_list_lock);
+}
+
+static int sdei_api_get_version(u64 *version)
+{
+	return invoke_sdei_fn(SDEI_1_0_FN_SDEI_VERSION, 0, 0, 0, 0, 0, version);
+}
+
+int sdei_mask_local_cpu(void)
+{
+	int err;
+
+	WARN_ON_ONCE(preemptible());
+
+	err = invoke_sdei_fn(SDEI_1_0_FN_SDEI_PE_MASK, 0, 0, 0, 0, 0, NULL);
+	if (err && err != -EIO) {
+		pr_warn_once("failed to mask CPU[%u]: %d\n",
+			      smp_processor_id(), err);
+		return err;
+	}
+
+	return 0;
+}
+
+static void _ipi_mask_cpu(void *ignored)
+{
+	sdei_mask_local_cpu();
+}
+
+int sdei_unmask_local_cpu(void)
+{
+	int err;
+
+	WARN_ON_ONCE(preemptible());
+
+	err = invoke_sdei_fn(SDEI_1_0_FN_SDEI_PE_UNMASK, 0, 0, 0, 0, 0, NULL);
+	if (err && err != -EIO) {
+		pr_warn_once("failed to unmask CPU[%u]: %d\n",
+			     smp_processor_id(), err);
+		return err;
+	}
+
+	return 0;
+}
+
+static void _ipi_unmask_cpu(void *ignored)
+{
+	sdei_unmask_local_cpu();
+}
+
+static void _ipi_private_reset(void *ignored)
+{
+	int err;
+
+	err = invoke_sdei_fn(SDEI_1_0_FN_SDEI_PRIVATE_RESET, 0, 0, 0, 0, 0,
+			     NULL);
+	if (err && err != -EIO)
+		pr_warn_once("failed to reset CPU[%u]: %d\n",
+			     smp_processor_id(), err);
+}
+
+static int sdei_api_shared_reset(void)
+{
+	return invoke_sdei_fn(SDEI_1_0_FN_SDEI_SHARED_RESET, 0, 0, 0, 0, 0,
+			      NULL);
+}
+
+static void sdei_mark_interface_broken(void)
+{
+	pr_err("disabling SDEI firmware interface\n");
+	on_each_cpu(&_ipi_mask_cpu, NULL, true);
+	sdei_firmware_call = NULL;
+}
+
+static int sdei_platform_reset(void)
+{
+	int err;
+
+	on_each_cpu(&_ipi_private_reset, NULL, true);
+	err = sdei_api_shared_reset();
+	if (err) {
+		pr_err("Failed to reset platform: %d\n", err);
+		sdei_mark_interface_broken();
+	}
+
+	return err;
+}
+
+static int sdei_api_event_enable(u32 event_num)
+{
+	return invoke_sdei_fn(SDEI_1_0_FN_SDEI_EVENT_ENABLE, event_num, 0, 0, 0,
+			      0, NULL);
+}
+
+/* Called directly by the hotplug callbacks */
+static void _local_event_enable(void *data)
+{
+	int err;
+	struct sdei_crosscall_args *arg = data;
+
+	WARN_ON_ONCE(preemptible());
+
+	err = sdei_api_event_enable(arg->event->event_num);
+
+	sdei_cross_call_return(arg, err);
+}
+
+int sdei_event_enable(u32 event_num)
+{
+	int err = -EINVAL;
+	struct sdei_event *event;
+
+	mutex_lock(&sdei_events_lock);
+	event = sdei_event_find(event_num);
+	if (!event) {
+		mutex_unlock(&sdei_events_lock);
+		return -ENOENT;
+	}
+
+
+	cpus_read_lock();
+	if (event->type == SDEI_EVENT_TYPE_SHARED)
+		err = sdei_api_event_enable(event->event_num);
+	else
+		err = sdei_do_cross_call(_local_event_enable, event);
+
+	if (!err) {
+		spin_lock(&sdei_list_lock);
+		event->reenable = true;
+		spin_unlock(&sdei_list_lock);
+	}
+	cpus_read_unlock();
+	mutex_unlock(&sdei_events_lock);
+
+	return err;
+}
+
+static int sdei_api_event_disable(u32 event_num)
+{
+	return invoke_sdei_fn(SDEI_1_0_FN_SDEI_EVENT_DISABLE, event_num, 0, 0,
+			      0, 0, NULL);
+}
+
+static void _ipi_event_disable(void *data)
+{
+	int err;
+	struct sdei_crosscall_args *arg = data;
+
+	err = sdei_api_event_disable(arg->event->event_num);
+
+	sdei_cross_call_return(arg, err);
+}
+
+int sdei_event_disable(u32 event_num)
+{
+	int err = -EINVAL;
+	struct sdei_event *event;
+
+	mutex_lock(&sdei_events_lock);
+	event = sdei_event_find(event_num);
+	if (!event) {
+		mutex_unlock(&sdei_events_lock);
+		return -ENOENT;
+	}
+
+	spin_lock(&sdei_list_lock);
+	event->reenable = false;
+	spin_unlock(&sdei_list_lock);
+
+	if (event->type == SDEI_EVENT_TYPE_SHARED)
+		err = sdei_api_event_disable(event->event_num);
+	else
+		err = sdei_do_cross_call(_ipi_event_disable, event);
+	mutex_unlock(&sdei_events_lock);
+
+	return err;
+}
+
+static int sdei_api_event_unregister(u32 event_num)
+{
+	return invoke_sdei_fn(SDEI_1_0_FN_SDEI_EVENT_UNREGISTER, event_num, 0,
+			      0, 0, 0, NULL);
+}
+
+/* Called directly by the hotplug callbacks */
+static void _local_event_unregister(void *data)
+{
+	int err;
+	struct sdei_crosscall_args *arg = data;
+
+	WARN_ON_ONCE(preemptible());
+
+	err = sdei_api_event_unregister(arg->event->event_num);
+
+	sdei_cross_call_return(arg, err);
+}
+
+int sdei_event_unregister(u32 event_num)
+{
+	int err;
+	struct sdei_event *event;
+
+	WARN_ON(in_nmi());
+
+	mutex_lock(&sdei_events_lock);
+	event = sdei_event_find(event_num);
+	if (!event) {
+		pr_warn("Event %u not registered\n", event_num);
+		err = -ENOENT;
+		goto unlock;
+	}
+
+	spin_lock(&sdei_list_lock);
+	event->reregister = false;
+	event->reenable = false;
+	spin_unlock(&sdei_list_lock);
+
+	if (event->type == SDEI_EVENT_TYPE_SHARED)
+		err = sdei_api_event_unregister(event->event_num);
+	else
+		err = sdei_do_cross_call(_local_event_unregister, event);
+
+	if (err)
+		goto unlock;
+
+	sdei_event_destroy(event);
+unlock:
+	mutex_unlock(&sdei_events_lock);
+
+	return err;
+}
+
+/*
+ * unregister events, but don't destroy them as they are re-registered by
+ * sdei_reregister_shared().
+ */
+static int sdei_unregister_shared(void)
+{
+	int err = 0;
+	struct sdei_event *event;
+
+	mutex_lock(&sdei_events_lock);
+	spin_lock(&sdei_list_lock);
+	list_for_each_entry(event, &sdei_list, list) {
+		if (event->type != SDEI_EVENT_TYPE_SHARED)
+			continue;
+
+		err = sdei_api_event_unregister(event->event_num);
+		if (err)
+			break;
+	}
+	spin_unlock(&sdei_list_lock);
+	mutex_unlock(&sdei_events_lock);
+
+	return err;
+}
+
+static int sdei_api_event_register(u32 event_num, unsigned long entry_point,
+				   void *arg, u64 flags, u64 affinity)
+{
+	return invoke_sdei_fn(SDEI_1_0_FN_SDEI_EVENT_REGISTER, event_num,
+			      (unsigned long)entry_point, (unsigned long)arg,
+			      flags, affinity, NULL);
+}
+
+/* Called directly by the hotplug callbacks */
+static void _local_event_register(void *data)
+{
+	int err;
+	struct sdei_registered_event *reg;
+	struct sdei_crosscall_args *arg = data;
+
+	WARN_ON(preemptible());
+
+	reg = per_cpu_ptr(arg->event->private_registered, smp_processor_id());
+	err = sdei_api_event_register(arg->event->event_num, sdei_entry_point,
+				      reg, 0, 0);
+
+	sdei_cross_call_return(arg, err);
+}
+
+int sdei_event_register(u32 event_num, sdei_event_callback *cb, void *arg)
+{
+	int err;
+	struct sdei_event *event;
+
+	WARN_ON(in_nmi());
+
+	mutex_lock(&sdei_events_lock);
+	if (sdei_event_find(event_num)) {
+		pr_warn("Event %u already registered\n", event_num);
+		err = -EBUSY;
+		goto unlock;
+	}
+
+	event = sdei_event_create(event_num, cb, arg);
+	if (IS_ERR(event)) {
+		err = PTR_ERR(event);
+		pr_warn("Failed to create event %u: %d\n", event_num, err);
+		goto unlock;
+	}
+
+	cpus_read_lock();
+	if (event->type == SDEI_EVENT_TYPE_SHARED) {
+		err = sdei_api_event_register(event->event_num,
+					      sdei_entry_point,
+					      event->registered,
+					      SDEI_EVENT_REGISTER_RM_ANY, 0);
+	} else {
+		err = sdei_do_cross_call(_local_event_register, event);
+		if (err)
+			sdei_do_cross_call(_local_event_unregister, event);
+	}
+
+	if (err) {
+		sdei_event_destroy(event);
+		pr_warn("Failed to register event %u: %d\n", event_num, err);
+		goto cpu_unlock;
+	}
+
+	spin_lock(&sdei_list_lock);
+	event->reregister = true;
+	spin_unlock(&sdei_list_lock);
+cpu_unlock:
+	cpus_read_unlock();
+unlock:
+	mutex_unlock(&sdei_events_lock);
+	return err;
+}
+
+static int sdei_reregister_shared(void)
+{
+	int err = 0;
+	struct sdei_event *event;
+
+	mutex_lock(&sdei_events_lock);
+	spin_lock(&sdei_list_lock);
+	list_for_each_entry(event, &sdei_list, list) {
+		if (event->type != SDEI_EVENT_TYPE_SHARED)
+			continue;
+
+		if (event->reregister) {
+			err = sdei_api_event_register(event->event_num,
+					sdei_entry_point, event->registered,
+					SDEI_EVENT_REGISTER_RM_ANY, 0);
+			if (err) {
+				pr_err("Failed to re-register event %u\n",
+				       event->event_num);
+				sdei_event_destroy_llocked(event);
+				break;
+			}
+		}
+
+		if (event->reenable) {
+			err = sdei_api_event_enable(event->event_num);
+			if (err) {
+				pr_err("Failed to re-enable event %u\n",
+				       event->event_num);
+				break;
+			}
+		}
+	}
+	spin_unlock(&sdei_list_lock);
+	mutex_unlock(&sdei_events_lock);
+
+	return err;
+}
+
+static int sdei_cpuhp_down(unsigned int cpu)
+{
+	struct sdei_event *event;
+	int err;
+
+	/* un-register private events */
+	spin_lock(&sdei_list_lock);
+	list_for_each_entry(event, &sdei_list, list) {
+		if (event->type == SDEI_EVENT_TYPE_SHARED)
+			continue;
+
+		err = sdei_do_local_call(_local_event_unregister, event);
+		if (err) {
+			pr_err("Failed to unregister event %u: %d\n",
+			       event->event_num, err);
+		}
+	}
+	spin_unlock(&sdei_list_lock);
+
+	return sdei_mask_local_cpu();
+}
+
+static int sdei_cpuhp_up(unsigned int cpu)
+{
+	struct sdei_event *event;
+	int err;
+
+	/* re-register/enable private events */
+	spin_lock(&sdei_list_lock);
+	list_for_each_entry(event, &sdei_list, list) {
+		if (event->type == SDEI_EVENT_TYPE_SHARED)
+			continue;
+
+		if (event->reregister) {
+			err = sdei_do_local_call(_local_event_register, event);
+			if (err) {
+				pr_err("Failed to re-register event %u: %d\n",
+				       event->event_num, err);
+			}
+		}
+
+		if (event->reenable) {
+			err = sdei_do_local_call(_local_event_enable, event);
+			if (err) {
+				pr_err("Failed to re-enable event %u: %d\n",
+				       event->event_num, err);
+			}
+		}
+	}
+	spin_unlock(&sdei_list_lock);
+
+	return sdei_unmask_local_cpu();
+}
+
+/* When entering idle, mask/unmask events for this cpu */
+static int sdei_pm_notifier(struct notifier_block *nb, unsigned long action,
+			    void *data)
+{
+	int rv;
+
+	switch (action) {
+	case CPU_PM_ENTER:
+		rv = sdei_mask_local_cpu();
+		break;
+	case CPU_PM_EXIT:
+	case CPU_PM_ENTER_FAILED:
+		rv = sdei_unmask_local_cpu();
+		break;
+	default:
+		return NOTIFY_DONE;
+	}
+
+	if (rv)
+		return notifier_from_errno(rv);
+
+	return NOTIFY_OK;
+}
+
+static struct notifier_block sdei_pm_nb = {
+	.notifier_call = sdei_pm_notifier,
+};
+
+static int sdei_device_suspend(struct device *dev)
+{
+	on_each_cpu(_ipi_mask_cpu, NULL, true);
+
+	return 0;
+}
+
+static int sdei_device_resume(struct device *dev)
+{
+	on_each_cpu(_ipi_unmask_cpu, NULL, true);
+
+	return 0;
+}
+
+/*
+ * We need all events to be reregistered when we resume from hibernate.
+ *
+ * The sequence is freeze->thaw. Reboot. freeze->restore. We unregister
+ * events during freeze, then re-register and re-enable them during thaw
+ * and restore.
+ */
+static int sdei_device_freeze(struct device *dev)
+{
+	int err;
+
+	/* unregister private events */
+	cpuhp_remove_state(CPUHP_AP_ARM_SDEI_STARTING);
+
+	err = sdei_unregister_shared();
+	if (err)
+		return err;
+
+	return 0;
+}
+
+static int sdei_device_thaw(struct device *dev)
+{
+	int err;
+
+	/* re-register shared events */
+	err = sdei_reregister_shared();
+	if (err) {
+		pr_warn("Failed to re-register shared events...\n");
+		sdei_mark_interface_broken();
+		return err;
+	}
+
+	err = cpuhp_setup_state(CPUHP_AP_ARM_SDEI_STARTING, "SDEI",
+				&sdei_cpuhp_up, &sdei_cpuhp_down);
+	if (err)
+		pr_warn("Failed to re-register CPU hotplug notifier...\n");
+
+	return err;
+}
+
+static int sdei_device_restore(struct device *dev)
+{
+	int err;
+
+	err = sdei_platform_reset();
+	if (err)
+		return err;
+
+	return sdei_device_thaw(dev);
+}
+
+static const struct dev_pm_ops sdei_pm_ops = {
+	.suspend = sdei_device_suspend,
+	.resume = sdei_device_resume,
+	.freeze = sdei_device_freeze,
+	.thaw = sdei_device_thaw,
+	.restore = sdei_device_restore,
+};
+
+/*
+ * Mask all CPUs and unregister all events on panic, reboot or kexec.
+ */
+static int sdei_reboot_notifier(struct notifier_block *nb, unsigned long action,
+				void *data)
+{
+	/*
+	 * We are going to reset the interface, after this there is no point
+	 * doing work when we take CPUs offline.
+	 */
+	cpuhp_remove_state(CPUHP_AP_ARM_SDEI_STARTING);
+
+	sdei_platform_reset();
+
+	return NOTIFY_OK;
+}
+
+static struct notifier_block sdei_reboot_nb = {
+	.notifier_call = sdei_reboot_notifier,
+};
+
+static void sdei_smccc_smc(unsigned long function_id,
+			   unsigned long arg0, unsigned long arg1,
+			   unsigned long arg2, unsigned long arg3,
+			   unsigned long arg4, struct arm_smccc_res *res)
+{
+	arm_smccc_smc(function_id, arg0, arg1, arg2, arg3, arg4, 0, 0, res);
+}
+NOKPROBE_SYMBOL(sdei_smccc_smc);
+
+static void sdei_smccc_hvc(unsigned long function_id,
+			   unsigned long arg0, unsigned long arg1,
+			   unsigned long arg2, unsigned long arg3,
+			   unsigned long arg4, struct arm_smccc_res *res)
+{
+	arm_smccc_hvc(function_id, arg0, arg1, arg2, arg3, arg4, 0, 0, res);
+}
+NOKPROBE_SYMBOL(sdei_smccc_hvc);
+
+int sdei_register_ghes(struct ghes *ghes, sdei_event_callback *normal_cb,
+		       sdei_event_callback *critical_cb)
+{
+	int err;
+	u64 result;
+	u32 event_num;
+	sdei_event_callback *cb;
+
+	if (!IS_ENABLED(CONFIG_ACPI_APEI_GHES))
+		return -EOPNOTSUPP;
+
+	event_num = ghes->generic->notify.vector;
+	if (event_num == 0) {
+		/*
+		 * Event 0 is reserved by the specification for
+		 * SDEI_EVENT_SIGNAL.
+		 */
+		return -EINVAL;
+	}
+
+	err = sdei_api_event_get_info(event_num, SDEI_EVENT_INFO_EV_PRIORITY,
+				      &result);
+	if (err)
+		return err;
+
+	if (result == SDEI_EVENT_PRIORITY_CRITICAL)
+		cb = critical_cb;
+	else
+		cb = normal_cb;
+
+	err = sdei_event_register(event_num, cb, ghes);
+	if (!err)
+		err = sdei_event_enable(event_num);
+
+	return err;
+}
+
+int sdei_unregister_ghes(struct ghes *ghes)
+{
+	int i;
+	int err;
+	u32 event_num = ghes->generic->notify.vector;
+
+	might_sleep();
+
+	if (!IS_ENABLED(CONFIG_ACPI_APEI_GHES))
+		return -EOPNOTSUPP;
+
+	/*
+	 * The event may be running on another CPU. Disable it
+	 * to stop new events, then try to unregister a few times.
+	 */
+	err = sdei_event_disable(event_num);
+	if (err)
+		return err;
+
+	for (i = 0; i < 3; i++) {
+		err = sdei_event_unregister(event_num);
+		if (err != -EINPROGRESS)
+			break;
+
+		schedule();
+	}
+
+	return err;
+}
+
+static int sdei_get_conduit(struct platform_device *pdev)
+{
+	const char *method;
+	struct device_node *np = pdev->dev.of_node;
+
+	sdei_firmware_call = NULL;
+	if (np) {
+		if (of_property_read_string(np, "method", &method)) {
+			pr_warn("missing \"method\" property\n");
+			return SMCCC_CONDUIT_NONE;
+		}
+
+		if (!strcmp("hvc", method)) {
+			sdei_firmware_call = &sdei_smccc_hvc;
+			return SMCCC_CONDUIT_HVC;
+		} else if (!strcmp("smc", method)) {
+			sdei_firmware_call = &sdei_smccc_smc;
+			return SMCCC_CONDUIT_SMC;
+		}
+
+		pr_warn("invalid \"method\" property: %s\n", method);
+	} else if (!acpi_disabled) {
+		if (acpi_psci_use_hvc()) {
+			sdei_firmware_call = &sdei_smccc_hvc;
+			return SMCCC_CONDUIT_HVC;
+		} else {
+			sdei_firmware_call = &sdei_smccc_smc;
+			return SMCCC_CONDUIT_SMC;
+		}
+	}
+
+	return SMCCC_CONDUIT_NONE;
+}
+
+static int sdei_probe(struct platform_device *pdev)
+{
+	int err;
+	u64 ver = 0;
+	int conduit;
+
+	conduit = sdei_get_conduit(pdev);
+	if (!sdei_firmware_call)
+		return 0;
+
+	err = sdei_api_get_version(&ver);
+	if (err) {
+		pr_err("Failed to get SDEI version: %d\n", err);
+		sdei_mark_interface_broken();
+		return err;
+	}
+
+	pr_info("SDEIv%d.%d (0x%x) detected in firmware.\n",
+		(int)SDEI_VERSION_MAJOR(ver), (int)SDEI_VERSION_MINOR(ver),
+		(int)SDEI_VERSION_VENDOR(ver));
+
+	if (SDEI_VERSION_MAJOR(ver) != 1) {
+		pr_warn("Conflicting SDEI version detected.\n");
+		sdei_mark_interface_broken();
+		return -EINVAL;
+	}
+
+	err = sdei_platform_reset();
+	if (err)
+		return err;
+
+	sdei_entry_point = sdei_arch_get_entry_point(conduit);
+	if (!sdei_entry_point) {
+		/* Not supported due to hardware or boot configuration */
+		sdei_mark_interface_broken();
+		return 0;
+	}
+
+	err = cpu_pm_register_notifier(&sdei_pm_nb);
+	if (err) {
+		pr_warn("Failed to register CPU PM notifier...\n");
+		goto error;
+	}
+
+	err = register_reboot_notifier(&sdei_reboot_nb);
+	if (err) {
+		pr_warn("Failed to register reboot notifier...\n");
+		goto remove_cpupm;
+	}
+
+	err = cpuhp_setup_state(CPUHP_AP_ARM_SDEI_STARTING, "SDEI",
+				&sdei_cpuhp_up, &sdei_cpuhp_down);
+	if (err) {
+		pr_warn("Failed to register CPU hotplug notifier...\n");
+		goto remove_reboot;
+	}
+
+	return 0;
+
+remove_reboot:
+	unregister_reboot_notifier(&sdei_reboot_nb);
+
+remove_cpupm:
+	cpu_pm_unregister_notifier(&sdei_pm_nb);
+
+error:
+	sdei_mark_interface_broken();
+	return err;
+}
+
+static const struct of_device_id sdei_of_match[] = {
+	{ .compatible = "arm,sdei-1.0" },
+	{}
+};
+
+static struct platform_driver sdei_driver = {
+	.driver		= {
+		.name			= "sdei",
+		.pm			= &sdei_pm_ops,
+		.of_match_table		= sdei_of_match,
+	},
+	.probe		= sdei_probe,
+};
+
+static bool __init sdei_present_acpi(void)
+{
+	acpi_status status;
+	struct acpi_table_header *sdei_table_header;
+
+	if (acpi_disabled)
+		return false;
+
+	status = acpi_get_table(ACPI_SIG_SDEI, 0, &sdei_table_header);
+	if (ACPI_FAILURE(status) && status != AE_NOT_FOUND) {
+		const char *msg = acpi_format_exception(status);
+
+		pr_info("Failed to get ACPI:SDEI table, %s\n", msg);
+	}
+	if (ACPI_FAILURE(status))
+		return false;
+
+	acpi_put_table(sdei_table_header);
+
+	return true;
+}
+
+void __init sdei_init(void)
+{
+	struct platform_device *pdev;
+	int ret;
+
+	ret = platform_driver_register(&sdei_driver);
+	if (ret || !sdei_present_acpi())
+		return;
+
+	pdev = platform_device_register_simple(sdei_driver.driver.name,
+					       0, NULL, 0);
+	if (IS_ERR(pdev)) {
+		ret = PTR_ERR(pdev);
+		platform_driver_unregister(&sdei_driver);
+		pr_info("Failed to register ACPI:SDEI platform device %d\n",
+			ret);
+	}
+}
+
+int sdei_event_handler(struct pt_regs *regs,
+		       struct sdei_registered_event *arg)
+{
+	int err;
+	u32 event_num = arg->event_num;
+
+	err = arg->callback(event_num, regs, arg->callback_arg);
+	if (err)
+		pr_err_ratelimited("event %u on CPU %u failed with error: %d\n",
+				   event_num, smp_processor_id(), err);
+
+	return err;
+}
+NOKPROBE_SYMBOL(sdei_event_handler);