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, 492 insertions, 0 deletions

diff --git a/arch/mips/include/asm/stackframe.h b/arch/mips/include/asm/stackframe.h
new file mode 100644
index 000000000..a8705aef4
--- /dev/null
+++ b/arch/mips/include/asm/stackframe.h
@@ -0,0 +1,492 @@
+/*
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (C) 1994, 95, 96, 99, 2001 Ralf Baechle
+ * Copyright (C) 1994, 1995, 1996 Paul M. Antoine.
+ * Copyright (C) 1999 Silicon Graphics, Inc.
+ * Copyright (C) 2007  Maciej W. Rozycki
+ */
+#ifndef _ASM_STACKFRAME_H
+#define _ASM_STACKFRAME_H
+
+#include <linux/threads.h>
+
+#include <asm/asm.h>
+#include <asm/asmmacro.h>
+#include <asm/mipsregs.h>
+#include <asm/asm-offsets.h>
+#include <asm/thread_info.h>
+
+/* Make the addition of cfi info a little easier. */
+	.macro cfi_rel_offset reg offset=0 docfi=0
+	.if \docfi
+	.cfi_rel_offset \reg, \offset
+	.endif
+	.endm
+
+	.macro cfi_st reg offset=0 docfi=0
+	LONG_S	\reg, \offset(sp)
+	cfi_rel_offset \reg, \offset, \docfi
+	.endm
+
+	.macro cfi_restore reg offset=0 docfi=0
+	.if \docfi
+	.cfi_restore \reg
+	.endif
+	.endm
+
+	.macro cfi_ld reg offset=0 docfi=0
+	LONG_L	\reg, \offset(sp)
+	cfi_restore \reg \offset \docfi
+	.endm
+
+#if defined(CONFIG_CPU_R3000)
+#define STATMASK 0x3f
+#else
+#define STATMASK 0x1f
+#endif
+
+		.macro	SAVE_AT docfi=0
+		.set	push
+		.set	noat
+		cfi_st	$1, PT_R1, \docfi
+		.set	pop
+		.endm
+
+		.macro	SAVE_TEMP docfi=0
+#ifdef CONFIG_CPU_HAS_SMARTMIPS
+		mflhxu	v1
+		LONG_S	v1, PT_LO(sp)
+		mflhxu	v1
+		LONG_S	v1, PT_HI(sp)
+		mflhxu	v1
+		LONG_S	v1, PT_ACX(sp)
+#elif !defined(CONFIG_CPU_MIPSR6)
+		mfhi	v1
+#endif
+#ifdef CONFIG_32BIT
+		cfi_st	$8, PT_R8, \docfi
+		cfi_st	$9, PT_R9, \docfi
+#endif
+		cfi_st	$10, PT_R10, \docfi
+		cfi_st	$11, PT_R11, \docfi
+		cfi_st	$12, PT_R12, \docfi
+#if !defined(CONFIG_CPU_HAS_SMARTMIPS) && !defined(CONFIG_CPU_MIPSR6)
+		LONG_S	v1, PT_HI(sp)
+		mflo	v1
+#endif
+		cfi_st	$13, PT_R13, \docfi
+		cfi_st	$14, PT_R14, \docfi
+		cfi_st	$15, PT_R15, \docfi
+		cfi_st	$24, PT_R24, \docfi
+#if !defined(CONFIG_CPU_HAS_SMARTMIPS) && !defined(CONFIG_CPU_MIPSR6)
+		LONG_S	v1, PT_LO(sp)
+#endif
+#ifdef CONFIG_CPU_CAVIUM_OCTEON
+		/*
+		 * The Octeon multiplier state is affected by general
+		 * multiply instructions. It must be saved before and
+		 * kernel code might corrupt it
+		 */
+		jal     octeon_mult_save
+#endif
+		.endm
+
+		.macro	SAVE_STATIC docfi=0
+		cfi_st	$16, PT_R16, \docfi
+		cfi_st	$17, PT_R17, \docfi
+		cfi_st	$18, PT_R18, \docfi
+		cfi_st	$19, PT_R19, \docfi
+		cfi_st	$20, PT_R20, \docfi
+		cfi_st	$21, PT_R21, \docfi
+		cfi_st	$22, PT_R22, \docfi
+		cfi_st	$23, PT_R23, \docfi
+		cfi_st	$30, PT_R30, \docfi
+		.endm
+
+/*
+ * get_saved_sp returns the SP for the current CPU by looking in the
+ * kernelsp array for it.  If tosp is set, it stores the current sp in
+ * k0 and loads the new value in sp.  If not, it clobbers k0 and
+ * stores the new value in k1, leaving sp unaffected.
+ */
+#ifdef CONFIG_SMP
+
+		/* SMP variation */
+		.macro	get_saved_sp docfi=0 tosp=0
+		ASM_CPUID_MFC0	k0, ASM_SMP_CPUID_REG
+#if defined(CONFIG_32BIT) || defined(KBUILD_64BIT_SYM32)
+		lui	k1, %hi(kernelsp)
+#else
+		lui	k1, %highest(kernelsp)
+		daddiu	k1, %higher(kernelsp)
+		dsll	k1, 16
+		daddiu	k1, %hi(kernelsp)
+		dsll	k1, 16
+#endif
+		LONG_SRL	k0, SMP_CPUID_PTRSHIFT
+		LONG_ADDU	k1, k0
+		.if \tosp
+		move	k0, sp
+		.if \docfi
+		.cfi_register sp, k0
+		.endif
+		LONG_L	sp, %lo(kernelsp)(k1)
+		.else
+		LONG_L	k1, %lo(kernelsp)(k1)
+		.endif
+		.endm
+
+		.macro	set_saved_sp stackp temp temp2
+		ASM_CPUID_MFC0	\temp, ASM_SMP_CPUID_REG
+		LONG_SRL	\temp, SMP_CPUID_PTRSHIFT
+		LONG_S	\stackp, kernelsp(\temp)
+		.endm
+#else /* !CONFIG_SMP */
+		/* Uniprocessor variation */
+		.macro	get_saved_sp docfi=0 tosp=0
+#ifdef CONFIG_CPU_JUMP_WORKAROUNDS
+		/*
+		 * Clear BTB (branch target buffer), forbid RAS (return address
+		 * stack) to workaround the Out-of-order Issue in Loongson2F
+		 * via its diagnostic register.
+		 */
+		move	k0, ra
+		jal	1f
+		 nop
+1:		jal	1f
+		 nop
+1:		jal	1f
+		 nop
+1:		jal	1f
+		 nop
+1:		move	ra, k0
+		li	k0, 3
+		mtc0	k0, $22
+#endif /* CONFIG_CPU_JUMP_WORKAROUNDS */
+#if defined(CONFIG_32BIT) || defined(KBUILD_64BIT_SYM32)
+		lui	k1, %hi(kernelsp)
+#else
+		lui	k1, %highest(kernelsp)
+		daddiu	k1, %higher(kernelsp)
+		dsll	k1, k1, 16
+		daddiu	k1, %hi(kernelsp)
+		dsll	k1, k1, 16
+#endif
+		.if \tosp
+		move	k0, sp
+		.if \docfi
+		.cfi_register sp, k0
+		.endif
+		LONG_L	sp, %lo(kernelsp)(k1)
+		.else
+		LONG_L	k1, %lo(kernelsp)(k1)
+		.endif
+		.endm
+
+		.macro	set_saved_sp stackp temp temp2
+		LONG_S	\stackp, kernelsp
+		.endm
+#endif
+
+		.macro	SAVE_SOME docfi=0
+		.set	push
+		.set	noat
+		.set	reorder
+		mfc0	k0, CP0_STATUS
+		sll	k0, 3		/* extract cu0 bit */
+		.set	noreorder
+		bltz	k0, 8f
+		 move	k0, sp
+		.if \docfi
+		.cfi_register sp, k0
+		.endif
+#ifdef CONFIG_EVA
+		/*
+		 * Flush interAptiv's Return Prediction Stack (RPS) by writing
+		 * EntryHi. Toggling Config7.RPS is slower and less portable.
+		 *
+		 * The RPS isn't automatically flushed when exceptions are
+		 * taken, which can result in kernel mode speculative accesses
+		 * to user addresses if the RPS mispredicts. That's harmless
+		 * when user and kernel share the same address space, but with
+		 * EVA the same user segments may be unmapped to kernel mode,
+		 * even containing sensitive MMIO regions or invalid memory.
+		 *
+		 * This can happen when the kernel sets the return address to
+		 * ret_from_* and jr's to the exception handler, which looks
+		 * more like a tail call than a function call. If nested calls
+		 * don't evict the last user address in the RPS, it will
+		 * mispredict the return and fetch from a user controlled
+		 * address into the icache.
+		 *
+		 * More recent EVA-capable cores with MAAR to restrict
+		 * speculative accesses aren't affected.
+		 */
+		MFC0	k0, CP0_ENTRYHI
+		MTC0	k0, CP0_ENTRYHI
+#endif
+		.set	reorder
+		/* Called from user mode, new stack. */
+		get_saved_sp docfi=\docfi tosp=1
+8:
+#ifdef CONFIG_CPU_DADDI_WORKAROUNDS
+		.set	at=k1
+#endif
+		PTR_SUBU sp, PT_SIZE
+#ifdef CONFIG_CPU_DADDI_WORKAROUNDS
+		.set	noat
+#endif
+		.if \docfi
+		.cfi_def_cfa sp,0
+		.endif
+		cfi_st	k0, PT_R29, \docfi
+		cfi_rel_offset  sp, PT_R29, \docfi
+		cfi_st	v1, PT_R3, \docfi
+		/*
+		 * You might think that you don't need to save $0,
+		 * but the FPU emulator and gdb remote debug stub
+		 * need it to operate correctly
+		 */
+		LONG_S	$0, PT_R0(sp)
+		mfc0	v1, CP0_STATUS
+		cfi_st	v0, PT_R2, \docfi
+		LONG_S	v1, PT_STATUS(sp)
+		cfi_st	$4, PT_R4, \docfi
+		mfc0	v1, CP0_CAUSE
+		cfi_st	$5, PT_R5, \docfi
+		LONG_S	v1, PT_CAUSE(sp)
+		cfi_st	$6, PT_R6, \docfi
+		cfi_st	ra, PT_R31, \docfi
+		MFC0	ra, CP0_EPC
+		cfi_st	$7, PT_R7, \docfi
+#ifdef CONFIG_64BIT
+		cfi_st	$8, PT_R8, \docfi
+		cfi_st	$9, PT_R9, \docfi
+#endif
+		LONG_S	ra, PT_EPC(sp)
+		.if \docfi
+		.cfi_rel_offset ra, PT_EPC
+		.endif
+		cfi_st	$25, PT_R25, \docfi
+		cfi_st	$28, PT_R28, \docfi
+
+		/* Set thread_info if we're coming from user mode */
+		mfc0	k0, CP0_STATUS
+		sll	k0, 3		/* extract cu0 bit */
+		bltz	k0, 9f
+
+		ori	$28, sp, _THREAD_MASK
+		xori	$28, _THREAD_MASK
+#ifdef CONFIG_CPU_CAVIUM_OCTEON
+		.set    mips64
+		pref    0, 0($28)       /* Prefetch the current pointer */
+#endif
+9:
+		.set	pop
+		.endm
+
+		.macro	SAVE_ALL docfi=0
+		SAVE_SOME \docfi
+		SAVE_AT \docfi
+		SAVE_TEMP \docfi
+		SAVE_STATIC \docfi
+		.endm
+
+		.macro	RESTORE_AT docfi=0
+		.set	push
+		.set	noat
+		cfi_ld	$1, PT_R1, \docfi
+		.set	pop
+		.endm
+
+		.macro	RESTORE_TEMP docfi=0
+#ifdef CONFIG_CPU_CAVIUM_OCTEON
+		/* Restore the Octeon multiplier state */
+		jal	octeon_mult_restore
+#endif
+#ifdef CONFIG_CPU_HAS_SMARTMIPS
+		LONG_L	$24, PT_ACX(sp)
+		mtlhx	$24
+		LONG_L	$24, PT_HI(sp)
+		mtlhx	$24
+		LONG_L	$24, PT_LO(sp)
+		mtlhx	$24
+#elif !defined(CONFIG_CPU_MIPSR6)
+		LONG_L	$24, PT_LO(sp)
+		mtlo	$24
+		LONG_L	$24, PT_HI(sp)
+		mthi	$24
+#endif
+#ifdef CONFIG_32BIT
+		cfi_ld	$8, PT_R8, \docfi
+		cfi_ld	$9, PT_R9, \docfi
+#endif
+		cfi_ld	$10, PT_R10, \docfi
+		cfi_ld	$11, PT_R11, \docfi
+		cfi_ld	$12, PT_R12, \docfi
+		cfi_ld	$13, PT_R13, \docfi
+		cfi_ld	$14, PT_R14, \docfi
+		cfi_ld	$15, PT_R15, \docfi
+		cfi_ld	$24, PT_R24, \docfi
+		.endm
+
+		.macro	RESTORE_STATIC docfi=0
+		cfi_ld	$16, PT_R16, \docfi
+		cfi_ld	$17, PT_R17, \docfi
+		cfi_ld	$18, PT_R18, \docfi
+		cfi_ld	$19, PT_R19, \docfi
+		cfi_ld	$20, PT_R20, \docfi
+		cfi_ld	$21, PT_R21, \docfi
+		cfi_ld	$22, PT_R22, \docfi
+		cfi_ld	$23, PT_R23, \docfi
+		cfi_ld	$30, PT_R30, \docfi
+		.endm
+
+		.macro	RESTORE_SP docfi=0
+		cfi_ld	sp, PT_R29, \docfi
+		.endm
+
+#if defined(CONFIG_CPU_R3000)
+
+		.macro	RESTORE_SOME docfi=0
+		.set	push
+		.set	reorder
+		.set	noat
+		mfc0	a0, CP0_STATUS
+		li	v1, ST0_CU1 | ST0_IM
+		ori	a0, STATMASK
+		xori	a0, STATMASK
+		mtc0	a0, CP0_STATUS
+		and	a0, v1
+		LONG_L	v0, PT_STATUS(sp)
+		nor	v1, $0, v1
+		and	v0, v1
+		or	v0, a0
+		mtc0	v0, CP0_STATUS
+		cfi_ld	$31, PT_R31, \docfi
+		cfi_ld	$28, PT_R28, \docfi
+		cfi_ld	$25, PT_R25, \docfi
+		cfi_ld	$7,  PT_R7, \docfi
+		cfi_ld	$6,  PT_R6, \docfi
+		cfi_ld	$5,  PT_R5, \docfi
+		cfi_ld	$4,  PT_R4, \docfi
+		cfi_ld	$3,  PT_R3, \docfi
+		cfi_ld	$2,  PT_R2, \docfi
+		.set	pop
+		.endm
+
+		.macro	RESTORE_SP_AND_RET docfi=0
+		.set	push
+		.set	noreorder
+		LONG_L	k0, PT_EPC(sp)
+		RESTORE_SP \docfi
+		jr	k0
+		 rfe
+		.set	pop
+		.endm
+
+#else
+		.macro	RESTORE_SOME docfi=0
+		.set	push
+		.set	reorder
+		.set	noat
+		mfc0	a0, CP0_STATUS
+		ori	a0, STATMASK
+		xori	a0, STATMASK
+		mtc0	a0, CP0_STATUS
+		li	v1, ST0_CU1 | ST0_FR | ST0_IM
+		and	a0, v1
+		LONG_L	v0, PT_STATUS(sp)
+		nor	v1, $0, v1
+		and	v0, v1
+		or	v0, a0
+		mtc0	v0, CP0_STATUS
+		LONG_L	v1, PT_EPC(sp)
+		MTC0	v1, CP0_EPC
+		cfi_ld	$31, PT_R31, \docfi
+		cfi_ld	$28, PT_R28, \docfi
+		cfi_ld	$25, PT_R25, \docfi
+#ifdef CONFIG_64BIT
+		cfi_ld	$8, PT_R8, \docfi
+		cfi_ld	$9, PT_R9, \docfi
+#endif
+		cfi_ld	$7,  PT_R7, \docfi
+		cfi_ld	$6,  PT_R6, \docfi
+		cfi_ld	$5,  PT_R5, \docfi
+		cfi_ld	$4,  PT_R4, \docfi
+		cfi_ld	$3,  PT_R3, \docfi
+		cfi_ld	$2,  PT_R2, \docfi
+		.set	pop
+		.endm
+
+		.macro	RESTORE_SP_AND_RET docfi=0
+		RESTORE_SP \docfi
+#if defined(CONFIG_CPU_MIPSR5) || defined(CONFIG_CPU_MIPSR6)
+		eretnc
+#else
+		.set	push
+		.set	arch=r4000
+		eret
+		.set	pop
+#endif
+		.endm
+
+#endif
+
+		.macro	RESTORE_ALL docfi=0
+		RESTORE_TEMP \docfi
+		RESTORE_STATIC \docfi
+		RESTORE_AT \docfi
+		RESTORE_SOME \docfi
+		RESTORE_SP \docfi
+		.endm
+
+/*
+ * Move to kernel mode and disable interrupts.
+ * Set cp0 enable bit as sign that we're running on the kernel stack
+ */
+		.macro	CLI
+		mfc0	t0, CP0_STATUS
+		li	t1, ST0_KERNEL_CUMASK | STATMASK
+		or	t0, t1
+		xori	t0, STATMASK
+		mtc0	t0, CP0_STATUS
+		irq_disable_hazard
+		.endm
+
+/*
+ * Move to kernel mode and enable interrupts.
+ * Set cp0 enable bit as sign that we're running on the kernel stack
+ */
+		.macro	STI
+		mfc0	t0, CP0_STATUS
+		li	t1, ST0_KERNEL_CUMASK | STATMASK
+		or	t0, t1
+		xori	t0, STATMASK & ~1
+		mtc0	t0, CP0_STATUS
+		irq_enable_hazard
+		.endm
+
+/*
+ * Just move to kernel mode and leave interrupts as they are.  Note
+ * for the R3000 this means copying the previous enable from IEp.
+ * Set cp0 enable bit as sign that we're running on the kernel stack
+ */
+		.macro	KMODE
+		mfc0	t0, CP0_STATUS
+		li	t1, ST0_KERNEL_CUMASK | (STATMASK & ~1)
+#if defined(CONFIG_CPU_R3000)
+		andi	t2, t0, ST0_IEP
+		srl	t2, 2
+		or	t0, t2
+#endif
+		or	t0, t1
+		xori	t0, STATMASK & ~1
+		mtc0	t0, CP0_STATUS
+		irq_disable_hazard
+		.endm
+
+#endif /* _ASM_STACKFRAME_H */