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, 422 insertions, 0 deletions

diff --git a/arch/powerpc/platforms/52xx/lite5200_sleep.S b/arch/powerpc/platforms/52xx/lite5200_sleep.S
new file mode 100644
index 000000000..0b12647e7
--- /dev/null
+++ b/arch/powerpc/platforms/52xx/lite5200_sleep.S
@@ -0,0 +1,422 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#include <linux/linkage.h>
+
+#include <asm/reg.h>
+#include <asm/ppc_asm.h>
+#include <asm/processor.h>
+#include <asm/cache.h>
+
+
+#define SDRAM_CTRL	0x104
+#define SC_MODE_EN	(1<<31)
+#define SC_CKE		(1<<30)
+#define SC_REF_EN	(1<<28)
+#define SC_SOFT_PRE	(1<<1)
+
+#define GPIOW_GPIOE	0xc00
+#define GPIOW_DDR	0xc08
+#define GPIOW_DVO	0xc0c
+
+#define CDM_CE		0x214
+#define CDM_SDRAM	(1<<3)
+
+
+/* helpers... beware: r10 and r4 are overwritten */
+#define SAVE_SPRN(reg, addr)		\
+	mfspr	r10, SPRN_##reg;	\
+	stw	r10, ((addr)*4)(r4);
+
+#define LOAD_SPRN(reg, addr)		\
+	lwz	r10, ((addr)*4)(r4);	\
+	mtspr	SPRN_##reg, r10;	\
+	sync;				\
+	isync;
+
+
+	.data
+registers:
+	.space 0x5c*4
+	.text
+
+/* ---------------------------------------------------------------------- */
+/* low-power mode with help of M68HLC908QT1 */
+
+	.globl lite5200_low_power
+lite5200_low_power:
+
+	mr	r7, r3	/* save SRAM va */
+	mr	r8, r4	/* save MBAR va */
+
+	/* setup wakeup address for u-boot at physical location 0x0 */
+	lis	r3, CONFIG_KERNEL_START@h
+	lis	r4, lite5200_wakeup@h
+	ori	r4, r4, lite5200_wakeup@l
+	sub	r4, r4, r3
+	stw	r4, 0(r3)
+
+
+	/*
+	 * save stuff BDI overwrites
+	 * 0xf0 (0xe0->0x100 gets overwritten when BDI connected;
+	 *   even when CONFIG_BDI_SWITCH is disabled and MMU XLAT commented; heisenbug?))
+	 * WARNING: self-refresh doesn't seem to work when BDI2000 is connected,
+	 *   possibly because BDI sets SDRAM registers before wakeup code does
+	 */
+	lis	r4, registers@h
+	ori	r4, r4, registers@l
+	lwz	r10, 0xf0(r3)
+	stw	r10, (0x1d*4)(r4)
+
+	/* save registers to r4 [destroys r10] */
+	SAVE_SPRN(LR, 0x1c)
+	bl	save_regs
+
+	/* flush caches [destroys r3, r4] */
+	bl	flush_data_cache
+
+
+	/* copy code to sram */
+	mr	r4, r7
+	li	r3, (sram_code_end - sram_code)/4
+	mtctr	r3
+	lis	r3, sram_code@h
+	ori	r3, r3, sram_code@l
+1:
+	lwz	r5, 0(r3)
+	stw	r5, 0(r4)
+	addi	r3, r3, 4
+	addi	r4, r4, 4
+	bdnz	1b
+
+	/* get tb_ticks_per_usec */
+	lis	r3, tb_ticks_per_usec@h
+	lwz	r11, tb_ticks_per_usec@l(r3)
+
+	/* disable I and D caches */
+	mfspr	r3, SPRN_HID0
+	ori	r3, r3, HID0_ICE | HID0_DCE
+	xori	r3, r3, HID0_ICE | HID0_DCE
+	sync; isync;
+	mtspr	SPRN_HID0, r3
+	sync; isync;
+
+	/* jump to sram */
+	mtlr	r7
+	blrl
+	/* doesn't return */
+
+
+sram_code:
+	/* self refresh */
+	lwz	r4, SDRAM_CTRL(r8)
+
+	/* send NOP (precharge) */
+	oris	r4, r4, SC_MODE_EN@h	/* mode_en */
+	stw	r4, SDRAM_CTRL(r8)
+	sync
+
+	ori	r4, r4, SC_SOFT_PRE	/* soft_pre */
+	stw	r4, SDRAM_CTRL(r8)
+	sync
+	xori	r4, r4, SC_SOFT_PRE
+
+	xoris	r4, r4, SC_MODE_EN@h	/* !mode_en */
+	stw	r4, SDRAM_CTRL(r8)
+	sync
+
+	/* delay (for NOP to finish) */
+	li	r12, 1
+	bl	udelay
+
+	/*
+	 * mode_en must not be set when enabling self-refresh
+	 * send AR with CKE low (self-refresh)
+	 */
+	oris	r4, r4, (SC_REF_EN | SC_CKE)@h
+	xoris	r4, r4, (SC_CKE)@h	/* ref_en !cke */
+	stw	r4, SDRAM_CTRL(r8)
+	sync
+
+	/* delay (after !CKE there should be two cycles) */
+	li	r12, 1
+	bl	udelay
+
+	/* disable clock */
+	lwz	r4, CDM_CE(r8)
+	ori	r4, r4, CDM_SDRAM
+	xori	r4, r4, CDM_SDRAM
+	stw	r4, CDM_CE(r8)
+	sync
+
+	/* delay a bit */
+	li	r12, 1
+	bl	udelay
+
+
+	/* turn off with QT chip */
+	li	r4, 0x02
+	stb	r4, GPIOW_GPIOE(r8)	/* enable gpio_wkup1 */
+	sync
+
+	stb	r4, GPIOW_DVO(r8)	/* "output" high */
+	sync
+	stb	r4, GPIOW_DDR(r8)	/* output */
+	sync
+	stb	r4, GPIOW_DVO(r8)	/* output high */
+	sync
+
+	/* 10uS delay */
+	li	r12, 10
+	bl	udelay
+
+	/* turn off */
+	li	r4, 0
+	stb	r4, GPIOW_DVO(r8)	/* output low */
+	sync
+
+	/* wait until we're offline */
+  1:
+	b	1b
+
+
+	/* local udelay in sram is needed */
+SYM_FUNC_START_LOCAL(udelay)
+	/* r11 - tb_ticks_per_usec, r12 - usecs, overwrites r13 */
+	mullw	r12, r12, r11
+	mftb	r13	/* start */
+	add	r12, r13, r12 /* end */
+    1:
+	mftb	r13	/* current */
+	cmp	cr0, r13, r12
+	blt	1b
+	blr
+SYM_FUNC_END(udelay)
+
+sram_code_end:
+
+
+
+/* uboot jumps here on resume */
+lite5200_wakeup:
+	bl	restore_regs
+
+
+	/* HIDs, MSR */
+	LOAD_SPRN(HID1, 0x19)
+	LOAD_SPRN(HID2, 0x1a)
+
+
+	/* address translation is tricky (see turn_on_mmu) */
+	mfmsr	r10
+	ori	r10, r10, MSR_DR | MSR_IR
+
+
+	mtspr	SPRN_SRR1, r10
+	lis	r10, mmu_on@h
+	ori	r10, r10, mmu_on@l
+	mtspr	SPRN_SRR0, r10
+	sync
+	rfi
+mmu_on:
+	/* kernel offset (r4 is still set from restore_registers) */
+	addis	r4, r4, CONFIG_KERNEL_START@h
+
+
+	/* restore MSR */
+	lwz	r10, (4*0x1b)(r4)
+	mtmsr	r10
+	sync; isync;
+
+	/* invalidate caches */
+	mfspr	r10, SPRN_HID0
+	ori	r5, r10, HID0_ICFI | HID0_DCI
+	mtspr	SPRN_HID0, r5	/* invalidate caches */
+	sync; isync;
+	mtspr	SPRN_HID0, r10
+	sync; isync;
+
+	/* enable caches */
+	lwz	r10, (4*0x18)(r4)
+	mtspr	SPRN_HID0, r10	/* restore (enable caches, DPM) */
+	/* ^ this has to be after address translation set in MSR */
+	sync
+	isync
+
+
+	/* restore 0xf0 (BDI2000) */
+	lis	r3, CONFIG_KERNEL_START@h
+	lwz	r10, (0x1d*4)(r4)
+	stw	r10, 0xf0(r3)
+
+	LOAD_SPRN(LR, 0x1c)
+
+
+	blr
+_ASM_NOKPROBE_SYMBOL(lite5200_wakeup)
+
+
+/* ---------------------------------------------------------------------- */
+/* boring code: helpers */
+
+/* save registers */
+#define SAVE_BAT(n, addr)		\
+	SAVE_SPRN(DBAT##n##L, addr);	\
+	SAVE_SPRN(DBAT##n##U, addr+1);	\
+	SAVE_SPRN(IBAT##n##L, addr+2);	\
+	SAVE_SPRN(IBAT##n##U, addr+3);
+
+#define SAVE_SR(n, addr)		\
+	mfsr	r10, n;			\
+	stw	r10, ((addr)*4)(r4);
+
+#define SAVE_4SR(n, addr)	\
+	SAVE_SR(n, addr);	\
+	SAVE_SR(n+1, addr+1);	\
+	SAVE_SR(n+2, addr+2);	\
+	SAVE_SR(n+3, addr+3);
+
+SYM_FUNC_START_LOCAL(save_regs)
+	stw	r0, 0(r4)
+	stw	r1, 0x4(r4)
+	stw	r2, 0x8(r4)
+	stmw	r11, 0xc(r4) /* 0xc -> 0x5f, (0x18*4-1) */
+
+	SAVE_SPRN(HID0, 0x18)
+	SAVE_SPRN(HID1, 0x19)
+	SAVE_SPRN(HID2, 0x1a)
+	mfmsr	r10
+	stw	r10, (4*0x1b)(r4)
+	/*SAVE_SPRN(LR, 0x1c) have to save it before the call */
+	/* 0x1d reserved by 0xf0 */
+	SAVE_SPRN(RPA,   0x1e)
+	SAVE_SPRN(SDR1,  0x1f)
+
+	/* save MMU regs */
+	SAVE_BAT(0, 0x20)
+	SAVE_BAT(1, 0x24)
+	SAVE_BAT(2, 0x28)
+	SAVE_BAT(3, 0x2c)
+	SAVE_BAT(4, 0x30)
+	SAVE_BAT(5, 0x34)
+	SAVE_BAT(6, 0x38)
+	SAVE_BAT(7, 0x3c)
+
+	SAVE_4SR(0, 0x40)
+	SAVE_4SR(4, 0x44)
+	SAVE_4SR(8, 0x48)
+	SAVE_4SR(12, 0x4c)
+
+	SAVE_SPRN(SPRG0, 0x50)
+	SAVE_SPRN(SPRG1, 0x51)
+	SAVE_SPRN(SPRG2, 0x52)
+	SAVE_SPRN(SPRG3, 0x53)
+	SAVE_SPRN(SPRG4, 0x54)
+	SAVE_SPRN(SPRG5, 0x55)
+	SAVE_SPRN(SPRG6, 0x56)
+	SAVE_SPRN(SPRG7, 0x57)
+
+	SAVE_SPRN(IABR,  0x58)
+	SAVE_SPRN(DABR,  0x59)
+	SAVE_SPRN(TBRL,  0x5a)
+	SAVE_SPRN(TBRU,  0x5b)
+
+	blr
+SYM_FUNC_END(save_regs)
+
+
+/* restore registers */
+#define LOAD_BAT(n, addr)		\
+	LOAD_SPRN(DBAT##n##L, addr);	\
+	LOAD_SPRN(DBAT##n##U, addr+1);	\
+	LOAD_SPRN(IBAT##n##L, addr+2);	\
+	LOAD_SPRN(IBAT##n##U, addr+3);
+
+#define LOAD_SR(n, addr)		\
+	lwz	r10, ((addr)*4)(r4);	\
+	mtsr	n, r10;
+
+#define LOAD_4SR(n, addr)	\
+	LOAD_SR(n, addr);	\
+	LOAD_SR(n+1, addr+1);	\
+	LOAD_SR(n+2, addr+2);	\
+	LOAD_SR(n+3, addr+3);
+
+SYM_FUNC_START_LOCAL(restore_regs)
+	lis	r4, registers@h
+	ori	r4, r4, registers@l
+
+	/* MMU is not up yet */
+	subis	r4, r4, CONFIG_KERNEL_START@h
+
+	lwz	r0, 0(r4)
+	lwz	r1, 0x4(r4)
+	lwz	r2, 0x8(r4)
+	lmw	r11, 0xc(r4)
+
+	/*
+	 * these are a bit tricky
+	 *
+	 * 0x18 - HID0
+	 * 0x19 - HID1
+	 * 0x1a - HID2
+	 * 0x1b - MSR
+	 * 0x1c - LR
+	 * 0x1d - reserved by 0xf0 (BDI2000)
+	 */
+	LOAD_SPRN(RPA,   0x1e);
+	LOAD_SPRN(SDR1,  0x1f);
+
+	/* restore MMU regs */
+	LOAD_BAT(0, 0x20)
+	LOAD_BAT(1, 0x24)
+	LOAD_BAT(2, 0x28)
+	LOAD_BAT(3, 0x2c)
+	LOAD_BAT(4, 0x30)
+	LOAD_BAT(5, 0x34)
+	LOAD_BAT(6, 0x38)
+	LOAD_BAT(7, 0x3c)
+
+	LOAD_4SR(0, 0x40)
+	LOAD_4SR(4, 0x44)
+	LOAD_4SR(8, 0x48)
+	LOAD_4SR(12, 0x4c)
+
+	/* rest of regs */
+	LOAD_SPRN(SPRG0, 0x50);
+	LOAD_SPRN(SPRG1, 0x51);
+	LOAD_SPRN(SPRG2, 0x52);
+	LOAD_SPRN(SPRG3, 0x53);
+	LOAD_SPRN(SPRG4, 0x54);
+	LOAD_SPRN(SPRG5, 0x55);
+	LOAD_SPRN(SPRG6, 0x56);
+	LOAD_SPRN(SPRG7, 0x57);
+
+	LOAD_SPRN(IABR,  0x58);
+	LOAD_SPRN(DABR,  0x59);
+	LOAD_SPRN(TBWL,  0x5a);	/* these two have separate R/W regs */
+	LOAD_SPRN(TBWU,  0x5b);
+
+	blr
+_ASM_NOKPROBE_SYMBOL(restore_regs)
+SYM_FUNC_END(restore_regs)
+
+
+
+/* cache flushing code. copied from arch/ppc/boot/util.S */
+#define NUM_CACHE_LINES (128*8)
+
+/*
+ * Flush data cache
+ * Do this by just reading lots of stuff into the cache.
+ */
+SYM_FUNC_START_LOCAL(flush_data_cache)
+	lis	r3,CONFIG_KERNEL_START@h
+	ori	r3,r3,CONFIG_KERNEL_START@l
+	li	r4,NUM_CACHE_LINES
+	mtctr	r4
+1:
+	lwz	r4,0(r3)
+	addi	r3,r3,L1_CACHE_BYTES	/* Next line, please */
+	bdnz	1b
+	blr
+SYM_FUNC_END(flush_data_cache)