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, 1010 insertions, 0 deletions

diff --git a/arch/powerpc/kernel/head_64.S b/arch/powerpc/kernel/head_64.S
new file mode 100644
index 000000000..7558ba4eb
--- /dev/null
+++ b/arch/powerpc/kernel/head_64.S
@@ -0,0 +1,1010 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ *  PowerPC version
+ *    Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
+ *
+ *  Rewritten by Cort Dougan (cort@cs.nmt.edu) for PReP
+ *    Copyright (C) 1996 Cort Dougan <cort@cs.nmt.edu>
+ *  Adapted for Power Macintosh by Paul Mackerras.
+ *  Low-level exception handlers and MMU support
+ *  rewritten by Paul Mackerras.
+ *    Copyright (C) 1996 Paul Mackerras.
+ *
+ *  Adapted for 64bit PowerPC by Dave Engebretsen, Peter Bergner, and
+ *    Mike Corrigan {engebret|bergner|mikejc}@us.ibm.com
+ *
+ *  This file contains the entry point for the 64-bit kernel along
+ *  with some early initialization code common to all 64-bit powerpc
+ *  variants.
+ */
+
+#include <linux/linkage.h>
+#include <linux/threads.h>
+#include <linux/init.h>
+#include <asm/reg.h>
+#include <asm/page.h>
+#include <asm/mmu.h>
+#include <asm/ppc_asm.h>
+#include <asm/head-64.h>
+#include <asm/asm-offsets.h>
+#include <asm/bug.h>
+#include <asm/cputable.h>
+#include <asm/setup.h>
+#include <asm/hvcall.h>
+#include <asm/thread_info.h>
+#include <asm/firmware.h>
+#include <asm/page_64.h>
+#include <asm/irqflags.h>
+#include <asm/kvm_book3s_asm.h>
+#include <asm/ptrace.h>
+#include <asm/hw_irq.h>
+#include <asm/cputhreads.h>
+#include <asm/ppc-opcode.h>
+#include <asm/export.h>
+#include <asm/feature-fixups.h>
+#ifdef CONFIG_PPC_BOOK3S
+#include <asm/exception-64s.h>
+#else
+#include <asm/exception-64e.h>
+#endif
+
+/* The physical memory is laid out such that the secondary processor
+ * spin code sits at 0x0000...0x00ff. On server, the vectors follow
+ * using the layout described in exceptions-64s.S
+ */
+
+/*
+ * Entering into this code we make the following assumptions:
+ *
+ *  For pSeries or server processors:
+ *   1. The MMU is off & open firmware is running in real mode.
+ *   2. The primary CPU enters at __start.
+ *   3. If the RTAS supports "query-cpu-stopped-state", then secondary
+ *      CPUs will enter as directed by "start-cpu" RTAS call, which is
+ *      generic_secondary_smp_init, with PIR in r3.
+ *   4. Else the secondary CPUs will enter at secondary_hold (0x60) as
+ *      directed by the "start-cpu" RTS call, with PIR in r3.
+ * -or- For OPAL entry:
+ *   1. The MMU is off, processor in HV mode.
+ *   2. The primary CPU enters at 0 with device-tree in r3, OPAL base
+ *      in r8, and entry in r9 for debugging purposes.
+ *   3. Secondary CPUs enter as directed by OPAL_START_CPU call, which
+ *      is at generic_secondary_smp_init, with PIR in r3.
+ *
+ *  For Book3E processors:
+ *   1. The MMU is on running in AS0 in a state defined in ePAPR
+ *   2. The kernel is entered at __start
+ */
+
+OPEN_FIXED_SECTION(first_256B, 0x0, 0x100)
+USE_FIXED_SECTION(first_256B)
+	/*
+	 * Offsets are relative from the start of fixed section, and
+	 * first_256B starts at 0. Offsets are a bit easier to use here
+	 * than the fixed section entry macros.
+	 */
+	. = 0x0
+_GLOBAL(__start)
+	/* NOP this out unconditionally */
+BEGIN_FTR_SECTION
+	FIXUP_ENDIAN
+	b	__start_initialization_multiplatform
+END_FTR_SECTION(0, 1)
+
+	/* Catch branch to 0 in real mode */
+	trap
+
+	/* Secondary processors spin on this value until it becomes non-zero.
+	 * When non-zero, it contains the real address of the function the cpu
+	 * should jump to.
+	 */
+	.balign 8
+	.globl  __secondary_hold_spinloop
+__secondary_hold_spinloop:
+	.8byte	0x0
+
+	/* Secondary processors write this value with their cpu # */
+	/* after they enter the spin loop immediately below.	  */
+	.globl	__secondary_hold_acknowledge
+__secondary_hold_acknowledge:
+	.8byte	0x0
+
+#ifdef CONFIG_RELOCATABLE
+	/* This flag is set to 1 by a loader if the kernel should run
+	 * at the loaded address instead of the linked address.  This
+	 * is used by kexec-tools to keep the kdump kernel in the
+	 * crash_kernel region.  The loader is responsible for
+	 * observing the alignment requirement.
+	 */
+
+#ifdef CONFIG_RELOCATABLE_TEST
+#define RUN_AT_LOAD_DEFAULT 1		/* Test relocation, do not copy to 0 */
+#else
+#define RUN_AT_LOAD_DEFAULT 0x72756e30  /* "run0" -- relocate to 0 by default */
+#endif
+
+	/* Do not move this variable as kexec-tools knows about it. */
+	. = 0x5c
+	.globl	__run_at_load
+__run_at_load:
+DEFINE_FIXED_SYMBOL(__run_at_load, first_256B)
+	.long	RUN_AT_LOAD_DEFAULT
+#endif
+
+	. = 0x60
+/*
+ * The following code is used to hold secondary processors
+ * in a spin loop after they have entered the kernel, but
+ * before the bulk of the kernel has been relocated.  This code
+ * is relocated to physical address 0x60 before prom_init is run.
+ * All of it must fit below the first exception vector at 0x100.
+ * Use .globl here not _GLOBAL because we want __secondary_hold
+ * to be the actual text address, not a descriptor.
+ */
+	.globl	__secondary_hold
+__secondary_hold:
+	FIXUP_ENDIAN
+#ifndef CONFIG_PPC_BOOK3E_64
+	mfmsr	r24
+	ori	r24,r24,MSR_RI
+	mtmsrd	r24			/* RI on */
+#endif
+	/* Grab our physical cpu number */
+	mr	r24,r3
+	/* stash r4 for book3e */
+	mr	r25,r4
+
+	/* Tell the master cpu we're here */
+	/* Relocation is off & we are located at an address less */
+	/* than 0x100, so only need to grab low order offset.    */
+	std	r24,(ABS_ADDR(__secondary_hold_acknowledge, first_256B))(0)
+	sync
+
+	li	r26,0
+#ifdef CONFIG_PPC_BOOK3E_64
+	tovirt(r26,r26)
+#endif
+	/* All secondary cpus wait here until told to start. */
+100:	ld	r12,(ABS_ADDR(__secondary_hold_spinloop, first_256B))(r26)
+	cmpdi	0,r12,0
+	beq	100b
+
+#if defined(CONFIG_SMP) || defined(CONFIG_KEXEC_CORE)
+#ifdef CONFIG_PPC_BOOK3E_64
+	tovirt(r12,r12)
+#endif
+	mtctr	r12
+	mr	r3,r24
+	/*
+	 * it may be the case that other platforms have r4 right to
+	 * begin with, this gives us some safety in case it is not
+	 */
+#ifdef CONFIG_PPC_BOOK3E_64
+	mr	r4,r25
+#else
+	li	r4,0
+#endif
+	/* Make sure that patched code is visible */
+	isync
+	bctr
+#else
+0:	trap
+	EMIT_BUG_ENTRY 0b, __FILE__, __LINE__, 0
+#endif
+CLOSE_FIXED_SECTION(first_256B)
+
+/*
+ * On server, we include the exception vectors code here as it
+ * relies on absolute addressing which is only possible within
+ * this compilation unit
+ */
+#ifdef CONFIG_PPC_BOOK3S
+#include "exceptions-64s.S"
+#else
+OPEN_TEXT_SECTION(0x100)
+#endif
+
+USE_TEXT_SECTION()
+
+#include "interrupt_64.S"
+
+#ifdef CONFIG_PPC_BOOK3E_64
+/*
+ * The booting_thread_hwid holds the thread id we want to boot in cpu
+ * hotplug case. It is set by cpu hotplug code, and is invalid by default.
+ * The thread id is the same as the initial value of SPRN_PIR[THREAD_ID]
+ * bit field.
+ */
+	.globl	booting_thread_hwid
+booting_thread_hwid:
+	.long  INVALID_THREAD_HWID
+	.align 3
+/*
+ * start a thread in the same core
+ * input parameters:
+ * r3 = the thread physical id
+ * r4 = the entry point where thread starts
+ */
+_GLOBAL(book3e_start_thread)
+	LOAD_REG_IMMEDIATE(r5, MSR_KERNEL)
+	cmpwi	r3, 0
+	beq	10f
+	cmpwi	r3, 1
+	beq	11f
+	/* If the thread id is invalid, just exit. */
+	b	13f
+10:
+	MTTMR(TMRN_IMSR0, 5)
+	MTTMR(TMRN_INIA0, 4)
+	b	12f
+11:
+	MTTMR(TMRN_IMSR1, 5)
+	MTTMR(TMRN_INIA1, 4)
+12:
+	isync
+	li	r6, 1
+	sld	r6, r6, r3
+	mtspr	SPRN_TENS, r6
+13:
+	blr
+
+/*
+ * stop a thread in the same core
+ * input parameter:
+ * r3 = the thread physical id
+ */
+_GLOBAL(book3e_stop_thread)
+	cmpwi	r3, 0
+	beq	10f
+	cmpwi	r3, 1
+	beq	10f
+	/* If the thread id is invalid, just exit. */
+	b	13f
+10:
+	li	r4, 1
+	sld	r4, r4, r3
+	mtspr	SPRN_TENC, r4
+13:
+	blr
+
+_GLOBAL(fsl_secondary_thread_init)
+	mfspr	r4,SPRN_BUCSR
+
+	/* Enable branch prediction */
+	lis     r3,BUCSR_INIT@h
+	ori     r3,r3,BUCSR_INIT@l
+	mtspr   SPRN_BUCSR,r3
+	isync
+
+	/*
+	 * Fix PIR to match the linear numbering in the device tree.
+	 *
+	 * On e6500, the reset value of PIR uses the low three bits for
+	 * the thread within a core, and the upper bits for the core
+	 * number.  There are two threads per core, so shift everything
+	 * but the low bit right by two bits so that the cpu numbering is
+	 * continuous.
+	 *
+	 * If the old value of BUCSR is non-zero, this thread has run
+	 * before.  Thus, we assume we are coming from kexec or a similar
+	 * scenario, and PIR is already set to the correct value.  This
+	 * is a bit of a hack, but there are limited opportunities for
+	 * getting information into the thread and the alternatives
+	 * seemed like they'd be overkill.  We can't tell just by looking
+	 * at the old PIR value which state it's in, since the same value
+	 * could be valid for one thread out of reset and for a different
+	 * thread in Linux.
+	 */
+
+	mfspr	r3, SPRN_PIR
+	cmpwi	r4,0
+	bne	1f
+	rlwimi	r3, r3, 30, 2, 30
+	mtspr	SPRN_PIR, r3
+1:
+	mr	r24,r3
+
+	/* turn on 64-bit mode */
+	bl	enable_64b_mode
+
+	/* get a valid TOC pointer, wherever we're mapped at */
+	bl	relative_toc
+	tovirt(r2,r2)
+
+	/* Book3E initialization */
+	mr	r3,r24
+	bl	book3e_secondary_thread_init
+	b	generic_secondary_common_init
+
+#endif /* CONFIG_PPC_BOOK3E_64 */
+
+/*
+ * On pSeries and most other platforms, secondary processors spin
+ * in the following code.
+ * At entry, r3 = this processor's number (physical cpu id)
+ *
+ * On Book3E, r4 = 1 to indicate that the initial TLB entry for
+ * this core already exists (setup via some other mechanism such
+ * as SCOM before entry).
+ */
+_GLOBAL(generic_secondary_smp_init)
+	FIXUP_ENDIAN
+	mr	r24,r3
+	mr	r25,r4
+
+	/* turn on 64-bit mode */
+	bl	enable_64b_mode
+
+	/* get a valid TOC pointer, wherever we're mapped at */
+	bl	relative_toc
+	tovirt(r2,r2)
+
+#ifdef CONFIG_PPC_BOOK3E_64
+	/* Book3E initialization */
+	mr	r3,r24
+	mr	r4,r25
+	bl	book3e_secondary_core_init
+
+/*
+ * After common core init has finished, check if the current thread is the
+ * one we wanted to boot. If not, start the specified thread and stop the
+ * current thread.
+ */
+	LOAD_REG_ADDR(r4, booting_thread_hwid)
+	lwz     r3, 0(r4)
+	li	r5, INVALID_THREAD_HWID
+	cmpw	r3, r5
+	beq	20f
+
+	/*
+	 * The value of booting_thread_hwid has been stored in r3,
+	 * so make it invalid.
+	 */
+	stw	r5, 0(r4)
+
+	/*
+	 * Get the current thread id and check if it is the one we wanted.
+	 * If not, start the one specified in booting_thread_hwid and stop
+	 * the current thread.
+	 */
+	mfspr	r8, SPRN_TIR
+	cmpw	r3, r8
+	beq	20f
+
+	/* start the specified thread */
+	LOAD_REG_ADDR(r5, fsl_secondary_thread_init)
+	ld	r4, 0(r5)
+	bl	book3e_start_thread
+
+	/* stop the current thread */
+	mr	r3, r8
+	bl	book3e_stop_thread
+10:
+	b	10b
+20:
+#endif
+
+generic_secondary_common_init:
+	/* Set up a paca value for this processor. Since we have the
+	 * physical cpu id in r24, we need to search the pacas to find
+	 * which logical id maps to our physical one.
+	 */
+#ifndef CONFIG_SMP
+	b	kexec_wait		/* wait for next kernel if !SMP	 */
+#else
+	LOAD_REG_ADDR(r8, paca_ptrs)	/* Load paca_ptrs pointe	 */
+	ld	r8,0(r8)		/* Get base vaddr of array	 */
+#if (NR_CPUS == 1) || defined(CONFIG_FORCE_NR_CPUS)
+	LOAD_REG_IMMEDIATE(r7, NR_CPUS)
+#else
+	LOAD_REG_ADDR(r7, nr_cpu_ids)	/* Load nr_cpu_ids address       */
+	lwz	r7,0(r7)		/* also the max paca allocated 	 */
+#endif
+	li	r5,0			/* logical cpu id                */
+1:
+	sldi	r9,r5,3			/* get paca_ptrs[] index from cpu id */
+	ldx	r13,r9,r8		/* r13 = paca_ptrs[cpu id]       */
+	lhz	r6,PACAHWCPUID(r13)	/* Load HW procid from paca      */
+	cmpw	r6,r24			/* Compare to our id             */
+	beq	2f
+	addi	r5,r5,1
+	cmpw	r5,r7			/* Check if more pacas exist     */
+	blt	1b
+
+	mr	r3,r24			/* not found, copy phys to r3	 */
+	b	kexec_wait		/* next kernel might do better	 */
+
+2:	SET_PACA(r13)
+#ifdef CONFIG_PPC_BOOK3E_64
+	addi	r12,r13,PACA_EXTLB	/* and TLB exc frame in another  */
+	mtspr	SPRN_SPRG_TLB_EXFRAME,r12
+#endif
+
+	/* From now on, r24 is expected to be logical cpuid */
+	mr	r24,r5
+
+	/* Create a temp kernel stack for use before relocation is on.	*/
+	ld	r1,PACAEMERGSP(r13)
+	subi	r1,r1,STACK_FRAME_MIN_SIZE
+
+	/* See if we need to call a cpu state restore handler */
+	LOAD_REG_ADDR(r23, cur_cpu_spec)
+	ld	r23,0(r23)
+	ld	r12,CPU_SPEC_RESTORE(r23)
+	cmpdi	0,r12,0
+	beq	3f
+#ifdef CONFIG_PPC64_ELF_ABI_V1
+	ld	r12,0(r12)
+#endif
+	mtctr	r12
+	bctrl
+
+3:	LOAD_REG_ADDR(r3, spinning_secondaries) /* Decrement spinning_secondaries */
+	lwarx	r4,0,r3
+	subi	r4,r4,1
+	stwcx.	r4,0,r3
+	bne	3b
+	isync
+
+4:	HMT_LOW
+	lbz	r23,PACAPROCSTART(r13)	/* Test if this processor should */
+					/* start.			 */
+	cmpwi	0,r23,0
+	beq	4b			/* Loop until told to go	 */
+
+	sync				/* order paca.run and cur_cpu_spec */
+	isync				/* In case code patching happened */
+
+	b	__secondary_start
+#endif /* SMP */
+
+/*
+ * Turn the MMU off.
+ * Assumes we're mapped EA == RA if the MMU is on.
+ */
+#ifdef CONFIG_PPC_BOOK3S
+SYM_FUNC_START_LOCAL(__mmu_off)
+	mfmsr	r3
+	andi.	r0,r3,MSR_IR|MSR_DR
+	beqlr
+	mflr	r4
+	andc	r3,r3,r0
+	mtspr	SPRN_SRR0,r4
+	mtspr	SPRN_SRR1,r3
+	sync
+	rfid
+	b	.	/* prevent speculative execution */
+SYM_FUNC_END(__mmu_off)
+#endif
+
+
+/*
+ * Here is our main kernel entry point. We support currently 2 kind of entries
+ * depending on the value of r5.
+ *
+ *   r5 != NULL -> OF entry, we go to prom_init, "legacy" parameter content
+ *                 in r3...r7
+ *   
+ *   r5 == NULL -> kexec style entry. r3 is a physical pointer to the
+ *                 DT block, r4 is a physical pointer to the kernel itself
+ *
+ */
+__start_initialization_multiplatform:
+	/* Make sure we are running in 64 bits mode */
+	bl	enable_64b_mode
+
+	/* Zero r13 (paca) so early program check / mce don't use it */
+	li	r13,0
+
+	/* Get TOC pointer (current runtime address) */
+	bl	relative_toc
+
+	/* find out where we are now */
+	bcl	20,31,$+4
+0:	mflr	r26			/* r26 = runtime addr here */
+	addis	r26,r26,(_stext - 0b)@ha
+	addi	r26,r26,(_stext - 0b)@l	/* current runtime base addr */
+
+	/*
+	 * Are we booted from a PROM Of-type client-interface ?
+	 */
+	cmpldi	cr0,r5,0
+	beq	1f
+	b	__boot_from_prom		/* yes -> prom */
+1:
+	/* Save parameters */
+	mr	r31,r3
+	mr	r30,r4
+#ifdef CONFIG_PPC_EARLY_DEBUG_OPAL
+	/* Save OPAL entry */
+	mr	r28,r8
+	mr	r29,r9
+#endif
+
+#ifdef CONFIG_PPC_BOOK3E_64
+	bl	start_initialization_book3e
+	b	__after_prom_start
+#else
+	/* Setup some critical 970 SPRs before switching MMU off */
+	mfspr	r0,SPRN_PVR
+	srwi	r0,r0,16
+	cmpwi	r0,0x39		/* 970 */
+	beq	1f
+	cmpwi	r0,0x3c		/* 970FX */
+	beq	1f
+	cmpwi	r0,0x44		/* 970MP */
+	beq	1f
+	cmpwi	r0,0x45		/* 970GX */
+	bne	2f
+1:	bl	__cpu_preinit_ppc970
+2:
+
+	/* Switch off MMU if not already off */
+	bl	__mmu_off
+	b	__after_prom_start
+#endif /* CONFIG_PPC_BOOK3E_64 */
+
+__REF
+__boot_from_prom:
+#ifdef CONFIG_PPC_OF_BOOT_TRAMPOLINE
+	/* Save parameters */
+	mr	r31,r3
+	mr	r30,r4
+	mr	r29,r5
+	mr	r28,r6
+	mr	r27,r7
+
+	/*
+	 * Align the stack to 16-byte boundary
+	 * Depending on the size and layout of the ELF sections in the initial
+	 * boot binary, the stack pointer may be unaligned on PowerMac
+	 */
+	rldicr	r1,r1,0,59
+
+#ifdef CONFIG_RELOCATABLE
+	/* Relocate code for where we are now */
+	mr	r3,r26
+	bl	relocate
+#endif
+
+	/* Restore parameters */
+	mr	r3,r31
+	mr	r4,r30
+	mr	r5,r29
+	mr	r6,r28
+	mr	r7,r27
+
+	/* Do all of the interaction with OF client interface */
+	mr	r8,r26
+	bl	prom_init
+#endif /* #CONFIG_PPC_OF_BOOT_TRAMPOLINE */
+
+	/* We never return. We also hit that trap if trying to boot
+	 * from OF while CONFIG_PPC_OF_BOOT_TRAMPOLINE isn't selected */
+	trap
+	.previous
+
+__after_prom_start:
+#ifdef CONFIG_RELOCATABLE
+	/* process relocations for the final address of the kernel */
+	lis	r25,PAGE_OFFSET@highest	/* compute virtual base of kernel */
+	sldi	r25,r25,32
+#if defined(CONFIG_PPC_BOOK3E_64)
+	tovirt(r26,r26)		/* on booke, we already run at PAGE_OFFSET */
+#endif
+	lwz	r7,(FIXED_SYMBOL_ABS_ADDR(__run_at_load))(r26)
+#if defined(CONFIG_PPC_BOOK3E_64)
+	tophys(r26,r26)
+#endif
+	cmplwi	cr0,r7,1	/* flagged to stay where we are ? */
+	bne	1f
+	add	r25,r25,r26
+1:	mr	r3,r25
+	bl	relocate
+#if defined(CONFIG_PPC_BOOK3E_64)
+	/* IVPR needs to be set after relocation. */
+	bl	init_core_book3e
+#endif
+#endif
+
+/*
+ * We need to run with _stext at physical address PHYSICAL_START.
+ * This will leave some code in the first 256B of
+ * real memory, which are reserved for software use.
+ *
+ * Note: This process overwrites the OF exception vectors.
+ */
+	li	r3,0			/* target addr */
+#ifdef CONFIG_PPC_BOOK3E_64
+	tovirt(r3,r3)		/* on booke, we already run at PAGE_OFFSET */
+#endif
+	mr.	r4,r26			/* In some cases the loader may  */
+#if defined(CONFIG_PPC_BOOK3E_64)
+	tovirt(r4,r4)
+#endif
+	beq	9f			/* have already put us at zero */
+	li	r6,0x100		/* Start offset, the first 0x100 */
+					/* bytes were copied earlier.	 */
+
+#ifdef CONFIG_RELOCATABLE
+/*
+ * Check if the kernel has to be running as relocatable kernel based on the
+ * variable __run_at_load, if it is set the kernel is treated as relocatable
+ * kernel, otherwise it will be moved to PHYSICAL_START
+ */
+#if defined(CONFIG_PPC_BOOK3E_64)
+	tovirt(r26,r26)		/* on booke, we already run at PAGE_OFFSET */
+#endif
+	lwz	r7,(FIXED_SYMBOL_ABS_ADDR(__run_at_load))(r26)
+	cmplwi	cr0,r7,1
+	bne	3f
+
+#ifdef CONFIG_PPC_BOOK3E_64
+	LOAD_REG_ADDR(r5, __end_interrupts)
+	LOAD_REG_ADDR(r11, _stext)
+	sub	r5,r5,r11
+#else
+	/* just copy interrupts */
+	LOAD_REG_IMMEDIATE_SYM(r5, r11, FIXED_SYMBOL_ABS_ADDR(__end_interrupts))
+#endif
+	b	5f
+3:
+#endif
+	/* # bytes of memory to copy */
+	lis	r5,(ABS_ADDR(copy_to_here, text))@ha
+	addi	r5,r5,(ABS_ADDR(copy_to_here, text))@l
+
+	bl	copy_and_flush		/* copy the first n bytes	 */
+					/* this includes the code being	 */
+					/* executed here.		 */
+	/* Jump to the copy of this code that we just made */
+	addis	r8,r3,(ABS_ADDR(4f, text))@ha
+	addi	r12,r8,(ABS_ADDR(4f, text))@l
+	mtctr	r12
+	bctr
+
+.balign 8
+p_end: .8byte _end - copy_to_here
+
+4:
+	/*
+	 * Now copy the rest of the kernel up to _end, add
+	 * _end - copy_to_here to the copy limit and run again.
+	 */
+	addis   r8,r26,(ABS_ADDR(p_end, text))@ha
+	ld      r8,(ABS_ADDR(p_end, text))@l(r8)
+	add	r5,r5,r8
+5:	bl	copy_and_flush		/* copy the rest */
+
+9:	b	start_here_multiplatform
+
+/*
+ * Copy routine used to copy the kernel to start at physical address 0
+ * and flush and invalidate the caches as needed.
+ * r3 = dest addr, r4 = source addr, r5 = copy limit, r6 = start offset
+ * on exit, r3, r4, r5 are unchanged, r6 is updated to be >= r5.
+ *
+ * Note: this routine *only* clobbers r0, r6 and lr
+ */
+_GLOBAL(copy_and_flush)
+	addi	r5,r5,-8
+	addi	r6,r6,-8
+4:	li	r0,8			/* Use the smallest common	*/
+					/* denominator cache line	*/
+					/* size.  This results in	*/
+					/* extra cache line flushes	*/
+					/* but operation is correct.	*/
+					/* Can't get cache line size	*/
+					/* from NACA as it is being	*/
+					/* moved too.			*/
+
+	mtctr	r0			/* put # words/line in ctr	*/
+3:	addi	r6,r6,8			/* copy a cache line		*/
+	ldx	r0,r6,r4
+	stdx	r0,r6,r3
+	bdnz	3b
+	dcbst	r6,r3			/* write it to memory		*/
+	sync
+	icbi	r6,r3			/* flush the icache line	*/
+	cmpld	0,r6,r5
+	blt	4b
+	sync
+	addi	r5,r5,8
+	addi	r6,r6,8
+	isync
+	blr
+
+_ASM_NOKPROBE_SYMBOL(copy_and_flush); /* Called in real mode */
+
+.align 8
+copy_to_here:
+
+#ifdef CONFIG_SMP
+#ifdef CONFIG_PPC_PMAC
+/*
+ * On PowerMac, secondary processors starts from the reset vector, which
+ * is temporarily turned into a call to one of the functions below.
+ */
+	.section ".text";
+	.align 2 ;
+
+	.globl	__secondary_start_pmac_0
+__secondary_start_pmac_0:
+	/* NB the entries for cpus 0, 1, 2 must each occupy 8 bytes. */
+	li	r24,0
+	b	1f
+	li	r24,1
+	b	1f
+	li	r24,2
+	b	1f
+	li	r24,3
+1:
+	
+_GLOBAL(pmac_secondary_start)
+	/* turn on 64-bit mode */
+	bl	enable_64b_mode
+
+	li	r0,0
+	mfspr	r3,SPRN_HID4
+	rldimi	r3,r0,40,23	/* clear bit 23 (rm_ci) */
+	sync
+	mtspr	SPRN_HID4,r3
+	isync
+	sync
+	slbia
+
+	/* get TOC pointer (real address) */
+	bl	relative_toc
+	tovirt(r2,r2)
+
+	/* Copy some CPU settings from CPU 0 */
+	bl	__restore_cpu_ppc970
+
+	/* pSeries do that early though I don't think we really need it */
+	mfmsr	r3
+	ori	r3,r3,MSR_RI
+	mtmsrd	r3			/* RI on */
+
+	/* Set up a paca value for this processor. */
+	LOAD_REG_ADDR(r4,paca_ptrs)	/* Load paca pointer		*/
+	ld	r4,0(r4)		/* Get base vaddr of paca_ptrs array */
+	sldi	r5,r24,3		/* get paca_ptrs[] index from cpu id */
+	ldx	r13,r5,r4		/* r13 = paca_ptrs[cpu id]       */
+	SET_PACA(r13)			/* Save vaddr of paca in an SPRG*/
+
+	/* Mark interrupts soft and hard disabled (they might be enabled
+	 * in the PACA when doing hotplug)
+	 */
+	li	r0,IRQS_DISABLED
+	stb	r0,PACAIRQSOFTMASK(r13)
+	li	r0,PACA_IRQ_HARD_DIS
+	stb	r0,PACAIRQHAPPENED(r13)
+
+	/* Create a temp kernel stack for use before relocation is on.	*/
+	ld	r1,PACAEMERGSP(r13)
+	subi	r1,r1,STACK_FRAME_MIN_SIZE
+
+	b	__secondary_start
+
+#endif /* CONFIG_PPC_PMAC */
+
+/*
+ * This function is called after the master CPU has released the
+ * secondary processors.  The execution environment is relocation off.
+ * The paca for this processor has the following fields initialized at
+ * this point:
+ *   1. Processor number
+ *   2. Segment table pointer (virtual address)
+ * On entry the following are set:
+ *   r1	       = stack pointer (real addr of temp stack)
+ *   r24       = cpu# (in Linux terms)
+ *   r13       = paca virtual address
+ *   SPRG_PACA = paca virtual address
+ */
+	.section ".text";
+	.align 2 ;
+
+	.globl	__secondary_start
+__secondary_start:
+	/* Set thread priority to MEDIUM */
+	HMT_MEDIUM
+
+	/*
+	 * Do early setup for this CPU, in particular initialising the MMU so we
+	 * can turn it on below. This is a call to C, which is OK, we're still
+	 * running on the emergency stack.
+	 */
+	bl	early_setup_secondary
+
+	/*
+	 * The primary has initialized our kernel stack for us in the paca, grab
+	 * it and put it in r1. We must *not* use it until we turn on the MMU
+	 * below, because it may not be inside the RMO.
+	 */
+	ld	r1, PACAKSAVE(r13)
+
+	/* Clear backchain so we get nice backtraces */
+	li	r7,0
+	mtlr	r7
+
+	/* Mark interrupts soft and hard disabled (they might be enabled
+	 * in the PACA when doing hotplug)
+	 */
+	li	r7,IRQS_DISABLED
+	stb	r7,PACAIRQSOFTMASK(r13)
+	li	r0,PACA_IRQ_HARD_DIS
+	stb	r0,PACAIRQHAPPENED(r13)
+
+	/* enable MMU and jump to start_secondary */
+	LOAD_REG_ADDR(r3, start_secondary_prolog)
+	LOAD_REG_IMMEDIATE(r4, MSR_KERNEL)
+
+	mtspr	SPRN_SRR0,r3
+	mtspr	SPRN_SRR1,r4
+	RFI_TO_KERNEL
+	b	.	/* prevent speculative execution */
+
+/* 
+ * Running with relocation on at this point.  All we want to do is
+ * zero the stack back-chain pointer and get the TOC virtual address
+ * before going into C code.
+ */
+start_secondary_prolog:
+	LOAD_PACA_TOC()
+	li	r3,0
+	std	r3,0(r1)		/* Zero the stack frame pointer	*/
+	bl	start_secondary
+	b	.
+/*
+ * Reset stack pointer and call start_secondary
+ * to continue with online operation when woken up
+ * from cede in cpu offline.
+ */
+_GLOBAL(start_secondary_resume)
+	ld	r1,PACAKSAVE(r13)	/* Reload kernel stack pointer */
+	li	r3,0
+	std	r3,0(r1)		/* Zero the stack frame pointer	*/
+	bl	start_secondary
+	b	.
+#endif
+
+/*
+ * This subroutine clobbers r11 and r12
+ */
+SYM_FUNC_START_LOCAL(enable_64b_mode)
+	mfmsr	r11			/* grab the current MSR */
+#ifdef CONFIG_PPC_BOOK3E_64
+	oris	r11,r11,0x8000		/* CM bit set, we'll set ICM later */
+	mtmsr	r11
+#else /* CONFIG_PPC_BOOK3E_64 */
+	LOAD_REG_IMMEDIATE(r12, MSR_64BIT)
+	or	r11,r11,r12
+	mtmsrd	r11
+	isync
+#endif
+	blr
+SYM_FUNC_END(enable_64b_mode)
+
+/*
+ * This puts the TOC pointer into r2, offset by 0x8000 (as expected
+ * by the toolchain).  It computes the correct value for wherever we
+ * are running at the moment, using position-independent code.
+ *
+ * Note: The compiler constructs pointers using offsets from the
+ * TOC in -mcmodel=medium mode. After we relocate to 0 but before
+ * the MMU is on we need our TOC to be a virtual address otherwise
+ * these pointers will be real addresses which may get stored and
+ * accessed later with the MMU on. We use tovirt() at the call
+ * sites to handle this.
+ */
+_GLOBAL(relative_toc)
+	mflr	r0
+	bcl	20,31,$+4
+0:	mflr	r11
+	ld	r2,(p_toc - 0b)(r11)
+	add	r2,r2,r11
+	mtlr	r0
+	blr
+
+.balign 8
+p_toc:	.8byte	.TOC. - 0b
+
+/*
+ * This is where the main kernel code starts.
+ */
+__REF
+start_here_multiplatform:
+	/* set up the TOC */
+	bl      relative_toc
+	tovirt(r2,r2)
+
+	/* Clear out the BSS. It may have been done in prom_init,
+	 * already but that's irrelevant since prom_init will soon
+	 * be detached from the kernel completely. Besides, we need
+	 * to clear it now for kexec-style entry.
+	 */
+	LOAD_REG_ADDR(r11,__bss_stop)
+	LOAD_REG_ADDR(r8,__bss_start)
+	sub	r11,r11,r8		/* bss size			*/
+	addi	r11,r11,7		/* round up to an even double word */
+	srdi.	r11,r11,3		/* shift right by 3		*/
+	beq	4f
+	addi	r8,r8,-8
+	li	r0,0
+	mtctr	r11			/* zero this many doublewords	*/
+3:	stdu	r0,8(r8)
+	bdnz	3b
+4:
+
+#ifdef CONFIG_PPC_EARLY_DEBUG_OPAL
+	/* Setup OPAL entry */
+	LOAD_REG_ADDR(r11, opal)
+	std	r28,0(r11);
+	std	r29,8(r11);
+#endif
+
+#ifndef CONFIG_PPC_BOOK3E_64
+	mfmsr	r6
+	ori	r6,r6,MSR_RI
+	mtmsrd	r6			/* RI on */
+#endif
+
+#ifdef CONFIG_RELOCATABLE
+	/* Save the physical address we're running at in kernstart_addr */
+	LOAD_REG_ADDR(r4, kernstart_addr)
+	clrldi	r0,r25,2
+	std	r0,0(r4)
+#endif
+
+	/* set up a stack pointer */
+	LOAD_REG_ADDR(r3,init_thread_union)
+	LOAD_REG_IMMEDIATE(r1,THREAD_SIZE)
+	add	r1,r3,r1
+	li	r0,0
+	stdu	r0,-STACK_FRAME_MIN_SIZE(r1)
+
+	/*
+	 * Do very early kernel initializations, including initial hash table
+	 * and SLB setup before we turn on relocation.
+	 */
+
+#ifdef CONFIG_KASAN
+	bl	kasan_early_init
+#endif
+	/* Restore parameters passed from prom_init/kexec */
+	mr	r3,r31
+	LOAD_REG_ADDR(r12, DOTSYM(early_setup))
+	mtctr	r12
+	bctrl		/* also sets r13 and SPRG_PACA */
+
+	LOAD_REG_ADDR(r3, start_here_common)
+	ld	r4,PACAKMSR(r13)
+	mtspr	SPRN_SRR0,r3
+	mtspr	SPRN_SRR1,r4
+	RFI_TO_KERNEL
+	b	.	/* prevent speculative execution */
+
+	/* This is where all platforms converge execution */
+
+start_here_common:
+	/* relocation is on at this point */
+	std	r1,PACAKSAVE(r13)
+
+	/* Load the TOC (virtual address) */
+	LOAD_PACA_TOC()
+
+	/* Mark interrupts soft and hard disabled (they might be enabled
+	 * in the PACA when doing hotplug)
+	 */
+	li	r0,IRQS_DISABLED
+	stb	r0,PACAIRQSOFTMASK(r13)
+	li	r0,PACA_IRQ_HARD_DIS
+	stb	r0,PACAIRQHAPPENED(r13)
+
+	/* Generic kernel entry */
+	bl	start_kernel
+
+	/* Not reached */
+0:	trap
+	EMIT_BUG_ENTRY 0b, __FILE__, __LINE__, 0
+	.previous