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, 480 insertions, 0 deletions

diff --git a/drivers/firmware/efi/runtime-wrappers.c b/drivers/firmware/efi/runtime-wrappers.c
new file mode 100644
index 000000000..1fba4e09c
--- /dev/null
+++ b/drivers/firmware/efi/runtime-wrappers.c
@@ -0,0 +1,480 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * runtime-wrappers.c - Runtime Services function call wrappers
+ *
+ * Implementation summary:
+ * -----------------------
+ * 1. When user/kernel thread requests to execute efi_runtime_service(),
+ * enqueue work to efi_rts_wq.
+ * 2. Caller thread waits for completion until the work is finished
+ * because it's dependent on the return status and execution of
+ * efi_runtime_service().
+ * For instance, get_variable() and get_next_variable().
+ *
+ * Copyright (C) 2014 Linaro Ltd. <ard.biesheuvel@linaro.org>
+ *
+ * Split off from arch/x86/platform/efi/efi.c
+ *
+ * Copyright (C) 1999 VA Linux Systems
+ * Copyright (C) 1999 Walt Drummond <drummond@valinux.com>
+ * Copyright (C) 1999-2002 Hewlett-Packard Co.
+ * Copyright (C) 2005-2008 Intel Co.
+ * Copyright (C) 2013 SuSE Labs
+ */
+
+#define pr_fmt(fmt)	"efi: " fmt
+
+#include <linux/bug.h>
+#include <linux/efi.h>
+#include <linux/irqflags.h>
+#include <linux/mutex.h>
+#include <linux/semaphore.h>
+#include <linux/stringify.h>
+#include <linux/workqueue.h>
+#include <linux/completion.h>
+
+#include <asm/efi.h>
+
+/*
+ * Wrap around the new efi_call_virt_generic() macros so that the
+ * code doesn't get too cluttered:
+ */
+#define efi_call_virt(f, args...)   \
+	efi_call_virt_pointer(efi.runtime, f, args)
+#define __efi_call_virt(f, args...) \
+	__efi_call_virt_pointer(efi.runtime, f, args)
+
+struct efi_runtime_work efi_rts_work;
+
+/*
+ * efi_queue_work:	Queue efi_runtime_service() and wait until it's done
+ * @rts:		efi_runtime_service() function identifier
+ * @rts_arg<1-5>:	efi_runtime_service() function arguments
+ *
+ * Accesses to efi_runtime_services() are serialized by a binary
+ * semaphore (efi_runtime_lock) and caller waits until the work is
+ * finished, hence _only_ one work is queued at a time and the caller
+ * thread waits for completion.
+ */
+#define efi_queue_work(_rts, _arg1, _arg2, _arg3, _arg4, _arg5)		\
+({									\
+	efi_rts_work.status = EFI_ABORTED;				\
+									\
+	if (!efi_enabled(EFI_RUNTIME_SERVICES)) {			\
+		pr_warn_once("EFI Runtime Services are disabled!\n");	\
+		efi_rts_work.status = EFI_DEVICE_ERROR;			\
+		goto exit;						\
+	}								\
+									\
+	init_completion(&efi_rts_work.efi_rts_comp);			\
+	INIT_WORK(&efi_rts_work.work, efi_call_rts);			\
+	efi_rts_work.arg1 = _arg1;					\
+	efi_rts_work.arg2 = _arg2;					\
+	efi_rts_work.arg3 = _arg3;					\
+	efi_rts_work.arg4 = _arg4;					\
+	efi_rts_work.arg5 = _arg5;					\
+	efi_rts_work.efi_rts_id = _rts;					\
+									\
+	/*								\
+	 * queue_work() returns 0 if work was already on queue,         \
+	 * _ideally_ this should never happen.                          \
+	 */								\
+	if (queue_work(efi_rts_wq, &efi_rts_work.work))			\
+		wait_for_completion(&efi_rts_work.efi_rts_comp);	\
+	else								\
+		pr_err("Failed to queue work to efi_rts_wq.\n");	\
+									\
+	WARN_ON_ONCE(efi_rts_work.status == EFI_ABORTED);		\
+exit:									\
+	efi_rts_work.efi_rts_id = EFI_NONE;				\
+	efi_rts_work.status;						\
+})
+
+#ifndef arch_efi_save_flags
+#define arch_efi_save_flags(state_flags)	local_save_flags(state_flags)
+#define arch_efi_restore_flags(state_flags)	local_irq_restore(state_flags)
+#endif
+
+unsigned long efi_call_virt_save_flags(void)
+{
+	unsigned long flags;
+
+	arch_efi_save_flags(flags);
+	return flags;
+}
+
+void efi_call_virt_check_flags(unsigned long flags, const char *call)
+{
+	unsigned long cur_flags, mismatch;
+
+	cur_flags = efi_call_virt_save_flags();
+
+	mismatch = flags ^ cur_flags;
+	if (!WARN_ON_ONCE(mismatch & ARCH_EFI_IRQ_FLAGS_MASK))
+		return;
+
+	add_taint(TAINT_FIRMWARE_WORKAROUND, LOCKDEP_NOW_UNRELIABLE);
+	pr_err_ratelimited(FW_BUG "IRQ flags corrupted (0x%08lx=>0x%08lx) by EFI %s\n",
+			   flags, cur_flags, call);
+	arch_efi_restore_flags(flags);
+}
+
+/*
+ * According to section 7.1 of the UEFI spec, Runtime Services are not fully
+ * reentrant, and there are particular combinations of calls that need to be
+ * serialized. (source: UEFI Specification v2.4A)
+ *
+ * Table 31. Rules for Reentry Into Runtime Services
+ * +------------------------------------+-------------------------------+
+ * | If previous call is busy in	| Forbidden to call		|
+ * +------------------------------------+-------------------------------+
+ * | Any				| SetVirtualAddressMap()	|
+ * +------------------------------------+-------------------------------+
+ * | ConvertPointer()			| ConvertPointer()		|
+ * +------------------------------------+-------------------------------+
+ * | SetVariable()			| ResetSystem()			|
+ * | UpdateCapsule()			|				|
+ * | SetTime()				|				|
+ * | SetWakeupTime()			|				|
+ * | GetNextHighMonotonicCount()	|				|
+ * +------------------------------------+-------------------------------+
+ * | GetVariable()			| GetVariable()			|
+ * | GetNextVariableName()		| GetNextVariableName()		|
+ * | SetVariable()			| SetVariable()			|
+ * | QueryVariableInfo()		| QueryVariableInfo()		|
+ * | UpdateCapsule()			| UpdateCapsule()		|
+ * | QueryCapsuleCapabilities()		| QueryCapsuleCapabilities()	|
+ * | GetNextHighMonotonicCount()	| GetNextHighMonotonicCount()	|
+ * +------------------------------------+-------------------------------+
+ * | GetTime()				| GetTime()			|
+ * | SetTime()				| SetTime()			|
+ * | GetWakeupTime()			| GetWakeupTime()		|
+ * | SetWakeupTime()			| SetWakeupTime()		|
+ * +------------------------------------+-------------------------------+
+ *
+ * Due to the fact that the EFI pstore may write to the variable store in
+ * interrupt context, we need to use a lock for at least the groups that
+ * contain SetVariable() and QueryVariableInfo(). That leaves little else, as
+ * none of the remaining functions are actually ever called at runtime.
+ * So let's just use a single lock to serialize all Runtime Services calls.
+ */
+static DEFINE_SEMAPHORE(efi_runtime_lock);
+
+/*
+ * Expose the EFI runtime lock to the UV platform
+ */
+#ifdef CONFIG_X86_UV
+extern struct semaphore __efi_uv_runtime_lock __alias(efi_runtime_lock);
+#endif
+
+/*
+ * Calls the appropriate efi_runtime_service() with the appropriate
+ * arguments.
+ *
+ * Semantics followed by efi_call_rts() to understand efi_runtime_work:
+ * 1. If argument was a pointer, recast it from void pointer to original
+ * pointer type.
+ * 2. If argument was a value, recast it from void pointer to original
+ * pointer type and dereference it.
+ */
+static void efi_call_rts(struct work_struct *work)
+{
+	void *arg1, *arg2, *arg3, *arg4, *arg5;
+	efi_status_t status = EFI_NOT_FOUND;
+
+	arg1 = efi_rts_work.arg1;
+	arg2 = efi_rts_work.arg2;
+	arg3 = efi_rts_work.arg3;
+	arg4 = efi_rts_work.arg4;
+	arg5 = efi_rts_work.arg5;
+
+	switch (efi_rts_work.efi_rts_id) {
+	case EFI_GET_TIME:
+		status = efi_call_virt(get_time, (efi_time_t *)arg1,
+				       (efi_time_cap_t *)arg2);
+		break;
+	case EFI_SET_TIME:
+		status = efi_call_virt(set_time, (efi_time_t *)arg1);
+		break;
+	case EFI_GET_WAKEUP_TIME:
+		status = efi_call_virt(get_wakeup_time, (efi_bool_t *)arg1,
+				       (efi_bool_t *)arg2, (efi_time_t *)arg3);
+		break;
+	case EFI_SET_WAKEUP_TIME:
+		status = efi_call_virt(set_wakeup_time, *(efi_bool_t *)arg1,
+				       (efi_time_t *)arg2);
+		break;
+	case EFI_GET_VARIABLE:
+		status = efi_call_virt(get_variable, (efi_char16_t *)arg1,
+				       (efi_guid_t *)arg2, (u32 *)arg3,
+				       (unsigned long *)arg4, (void *)arg5);
+		break;
+	case EFI_GET_NEXT_VARIABLE:
+		status = efi_call_virt(get_next_variable, (unsigned long *)arg1,
+				       (efi_char16_t *)arg2,
+				       (efi_guid_t *)arg3);
+		break;
+	case EFI_SET_VARIABLE:
+		status = efi_call_virt(set_variable, (efi_char16_t *)arg1,
+				       (efi_guid_t *)arg2, *(u32 *)arg3,
+				       *(unsigned long *)arg4, (void *)arg5);
+		break;
+	case EFI_QUERY_VARIABLE_INFO:
+		status = efi_call_virt(query_variable_info, *(u32 *)arg1,
+				       (u64 *)arg2, (u64 *)arg3, (u64 *)arg4);
+		break;
+	case EFI_GET_NEXT_HIGH_MONO_COUNT:
+		status = efi_call_virt(get_next_high_mono_count, (u32 *)arg1);
+		break;
+	case EFI_UPDATE_CAPSULE:
+		status = efi_call_virt(update_capsule,
+				       (efi_capsule_header_t **)arg1,
+				       *(unsigned long *)arg2,
+				       *(unsigned long *)arg3);
+		break;
+	case EFI_QUERY_CAPSULE_CAPS:
+		status = efi_call_virt(query_capsule_caps,
+				       (efi_capsule_header_t **)arg1,
+				       *(unsigned long *)arg2, (u64 *)arg3,
+				       (int *)arg4);
+		break;
+	default:
+		/*
+		 * Ideally, we should never reach here because a caller of this
+		 * function should have put the right efi_runtime_service()
+		 * function identifier into efi_rts_work->efi_rts_id
+		 */
+		pr_err("Requested executing invalid EFI Runtime Service.\n");
+	}
+	efi_rts_work.status = status;
+	complete(&efi_rts_work.efi_rts_comp);
+}
+
+static efi_status_t virt_efi_get_time(efi_time_t *tm, efi_time_cap_t *tc)
+{
+	efi_status_t status;
+
+	if (down_interruptible(&efi_runtime_lock))
+		return EFI_ABORTED;
+	status = efi_queue_work(EFI_GET_TIME, tm, tc, NULL, NULL, NULL);
+	up(&efi_runtime_lock);
+	return status;
+}
+
+static efi_status_t virt_efi_set_time(efi_time_t *tm)
+{
+	efi_status_t status;
+
+	if (down_interruptible(&efi_runtime_lock))
+		return EFI_ABORTED;
+	status = efi_queue_work(EFI_SET_TIME, tm, NULL, NULL, NULL, NULL);
+	up(&efi_runtime_lock);
+	return status;
+}
+
+static efi_status_t virt_efi_get_wakeup_time(efi_bool_t *enabled,
+					     efi_bool_t *pending,
+					     efi_time_t *tm)
+{
+	efi_status_t status;
+
+	if (down_interruptible(&efi_runtime_lock))
+		return EFI_ABORTED;
+	status = efi_queue_work(EFI_GET_WAKEUP_TIME, enabled, pending, tm, NULL,
+				NULL);
+	up(&efi_runtime_lock);
+	return status;
+}
+
+static efi_status_t virt_efi_set_wakeup_time(efi_bool_t enabled, efi_time_t *tm)
+{
+	efi_status_t status;
+
+	if (down_interruptible(&efi_runtime_lock))
+		return EFI_ABORTED;
+	status = efi_queue_work(EFI_SET_WAKEUP_TIME, &enabled, tm, NULL, NULL,
+				NULL);
+	up(&efi_runtime_lock);
+	return status;
+}
+
+static efi_status_t virt_efi_get_variable(efi_char16_t *name,
+					  efi_guid_t *vendor,
+					  u32 *attr,
+					  unsigned long *data_size,
+					  void *data)
+{
+	efi_status_t status;
+
+	if (down_interruptible(&efi_runtime_lock))
+		return EFI_ABORTED;
+	status = efi_queue_work(EFI_GET_VARIABLE, name, vendor, attr, data_size,
+				data);
+	up(&efi_runtime_lock);
+	return status;
+}
+
+static efi_status_t virt_efi_get_next_variable(unsigned long *name_size,
+					       efi_char16_t *name,
+					       efi_guid_t *vendor)
+{
+	efi_status_t status;
+
+	if (down_interruptible(&efi_runtime_lock))
+		return EFI_ABORTED;
+	status = efi_queue_work(EFI_GET_NEXT_VARIABLE, name_size, name, vendor,
+				NULL, NULL);
+	up(&efi_runtime_lock);
+	return status;
+}
+
+static efi_status_t virt_efi_set_variable(efi_char16_t *name,
+					  efi_guid_t *vendor,
+					  u32 attr,
+					  unsigned long data_size,
+					  void *data)
+{
+	efi_status_t status;
+
+	if (down_interruptible(&efi_runtime_lock))
+		return EFI_ABORTED;
+	status = efi_queue_work(EFI_SET_VARIABLE, name, vendor, &attr, &data_size,
+				data);
+	up(&efi_runtime_lock);
+	return status;
+}
+
+static efi_status_t
+virt_efi_set_variable_nonblocking(efi_char16_t *name, efi_guid_t *vendor,
+				  u32 attr, unsigned long data_size,
+				  void *data)
+{
+	efi_status_t status;
+
+	if (down_trylock(&efi_runtime_lock))
+		return EFI_NOT_READY;
+
+	status = efi_call_virt(set_variable, name, vendor, attr, data_size,
+			       data);
+	up(&efi_runtime_lock);
+	return status;
+}
+
+
+static efi_status_t virt_efi_query_variable_info(u32 attr,
+						 u64 *storage_space,
+						 u64 *remaining_space,
+						 u64 *max_variable_size)
+{
+	efi_status_t status;
+
+	if (efi.runtime_version < EFI_2_00_SYSTEM_TABLE_REVISION)
+		return EFI_UNSUPPORTED;
+
+	if (down_interruptible(&efi_runtime_lock))
+		return EFI_ABORTED;
+	status = efi_queue_work(EFI_QUERY_VARIABLE_INFO, &attr, storage_space,
+				remaining_space, max_variable_size, NULL);
+	up(&efi_runtime_lock);
+	return status;
+}
+
+static efi_status_t
+virt_efi_query_variable_info_nonblocking(u32 attr,
+					 u64 *storage_space,
+					 u64 *remaining_space,
+					 u64 *max_variable_size)
+{
+	efi_status_t status;
+
+	if (efi.runtime_version < EFI_2_00_SYSTEM_TABLE_REVISION)
+		return EFI_UNSUPPORTED;
+
+	if (down_trylock(&efi_runtime_lock))
+		return EFI_NOT_READY;
+
+	status = efi_call_virt(query_variable_info, attr, storage_space,
+			       remaining_space, max_variable_size);
+	up(&efi_runtime_lock);
+	return status;
+}
+
+static efi_status_t virt_efi_get_next_high_mono_count(u32 *count)
+{
+	efi_status_t status;
+
+	if (down_interruptible(&efi_runtime_lock))
+		return EFI_ABORTED;
+	status = efi_queue_work(EFI_GET_NEXT_HIGH_MONO_COUNT, count, NULL, NULL,
+				NULL, NULL);
+	up(&efi_runtime_lock);
+	return status;
+}
+
+static void virt_efi_reset_system(int reset_type,
+				  efi_status_t status,
+				  unsigned long data_size,
+				  efi_char16_t *data)
+{
+	if (down_trylock(&efi_runtime_lock)) {
+		pr_warn("failed to invoke the reset_system() runtime service:\n"
+			"could not get exclusive access to the firmware\n");
+		return;
+	}
+	efi_rts_work.efi_rts_id = EFI_RESET_SYSTEM;
+	__efi_call_virt(reset_system, reset_type, status, data_size, data);
+	up(&efi_runtime_lock);
+}
+
+static efi_status_t virt_efi_update_capsule(efi_capsule_header_t **capsules,
+					    unsigned long count,
+					    unsigned long sg_list)
+{
+	efi_status_t status;
+
+	if (efi.runtime_version < EFI_2_00_SYSTEM_TABLE_REVISION)
+		return EFI_UNSUPPORTED;
+
+	if (down_interruptible(&efi_runtime_lock))
+		return EFI_ABORTED;
+	status = efi_queue_work(EFI_UPDATE_CAPSULE, capsules, &count, &sg_list,
+				NULL, NULL);
+	up(&efi_runtime_lock);
+	return status;
+}
+
+static efi_status_t virt_efi_query_capsule_caps(efi_capsule_header_t **capsules,
+						unsigned long count,
+						u64 *max_size,
+						int *reset_type)
+{
+	efi_status_t status;
+
+	if (efi.runtime_version < EFI_2_00_SYSTEM_TABLE_REVISION)
+		return EFI_UNSUPPORTED;
+
+	if (down_interruptible(&efi_runtime_lock))
+		return EFI_ABORTED;
+	status = efi_queue_work(EFI_QUERY_CAPSULE_CAPS, capsules, &count,
+				max_size, reset_type, NULL);
+	up(&efi_runtime_lock);
+	return status;
+}
+
+void efi_native_runtime_setup(void)
+{
+	efi.get_time = virt_efi_get_time;
+	efi.set_time = virt_efi_set_time;
+	efi.get_wakeup_time = virt_efi_get_wakeup_time;
+	efi.set_wakeup_time = virt_efi_set_wakeup_time;
+	efi.get_variable = virt_efi_get_variable;
+	efi.get_next_variable = virt_efi_get_next_variable;
+	efi.set_variable = virt_efi_set_variable;
+	efi.set_variable_nonblocking = virt_efi_set_variable_nonblocking;
+	efi.get_next_high_mono_count = virt_efi_get_next_high_mono_count;
+	efi.reset_system = virt_efi_reset_system;
+	efi.query_variable_info = virt_efi_query_variable_info;
+	efi.query_variable_info_nonblocking = virt_efi_query_variable_info_nonblocking;
+	efi.update_capsule = virt_efi_update_capsule;
+	efi.query_capsule_caps = virt_efi_query_capsule_caps;
+}