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, 747 insertions, 0 deletions

diff --git a/arch/mips/kernel/bmips_5xxx_init.S b/arch/mips/kernel/bmips_5xxx_init.S
new file mode 100644
index 000000000..9e422d186
--- /dev/null
+++ b/arch/mips/kernel/bmips_5xxx_init.S
@@ -0,0 +1,747 @@
+
+/*
+ * 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) 2011-2012 by Broadcom Corporation
+ *
+ * Init for bmips 5000.
+ * Used to init second core in dual core 5000's.
+ */
+
+#include <linux/init.h>
+
+#include <asm/asm.h>
+#include <asm/asmmacro.h>
+#include <asm/cacheops.h>
+#include <asm/regdef.h>
+#include <asm/mipsregs.h>
+#include <asm/stackframe.h>
+#include <asm/addrspace.h>
+#include <asm/hazards.h>
+#include <asm/bmips.h>
+
+#ifdef CONFIG_CPU_BMIPS5000
+
+
+#define cacheop(kva, size, linesize, op) 	\
+	.set noreorder			;	\
+	addu		t1, kva, size	;	\
+	subu		t2, linesize, 1	;	\
+	not		t2		;	\
+	and		t0, kva, t2	;	\
+	addiu		t1, t1, -1	;	\
+	and		t1, t2		;	\
+9:	cache		op, 0(t0)	;	\
+	bne		t0, t1, 9b	;	\
+	 addu		t0, linesize	;	\
+	.set reorder			;
+
+
+
+#define	IS_SHIFT	22
+#define	IL_SHIFT	19
+#define	IA_SHIFT	16
+#define	DS_SHIFT	13
+#define	DL_SHIFT	10
+#define	DA_SHIFT	 7
+#define	IS_MASK		 7
+#define	IL_MASK		 7
+#define	IA_MASK		 7
+#define	DS_MASK		 7
+#define	DL_MASK		 7
+#define	DA_MASK		 7
+#define	ICE_MASK	0x80000000
+#define	DCE_MASK	0x40000000
+
+#define CP0_BRCM_CONFIG0	$22, 0
+#define CP0_BRCM_MODE		$22, 1
+#define	CP0_CONFIG_K0_MASK	7
+
+#define CP0_ICACHE_TAG_LO	$28
+#define CP0_ICACHE_DATA_LO	$28, 1
+#define CP0_DCACHE_TAG_LO	$28, 2
+#define CP0_D_SEC_CACHE_DATA_LO	$28, 3
+#define CP0_ICACHE_TAG_HI	$29
+#define CP0_ICACHE_DATA_HI	$29, 1
+#define CP0_DCACHE_TAG_HI	$29, 2
+
+#define CP0_BRCM_MODE_Luc_MASK		(1 << 11)
+#define	CP0_BRCM_CONFIG0_CWF_MASK	(1 << 20)
+#define	CP0_BRCM_CONFIG0_TSE_MASK	(1 << 19)
+#define CP0_BRCM_MODE_SET_MASK		(1 << 7)
+#define CP0_BRCM_MODE_ClkRATIO_MASK	(7 << 4)
+#define CP0_BRCM_MODE_BrPRED_MASK 	(3 << 24)
+#define CP0_BRCM_MODE_BrPRED_SHIFT	24
+#define CP0_BRCM_MODE_BrHIST_MASK 	(0x1f << 20)
+#define CP0_BRCM_MODE_BrHIST_SHIFT	20
+
+/* ZSC L2 Cache Register Access Register Definitions */
+#define BRCM_ZSC_ALL_REGS_SELECT		0x7 << 24
+
+#define BRCM_ZSC_CONFIG_REG			0 << 3
+#define BRCM_ZSC_REQ_BUFFER_REG			2 << 3
+#define BRCM_ZSC_RBUS_ADDR_MAPPING_REG0		4 << 3
+#define BRCM_ZSC_RBUS_ADDR_MAPPING_REG1		6 << 3
+#define BRCM_ZSC_RBUS_ADDR_MAPPING_REG2		8 << 3
+
+#define BRCM_ZSC_SCB0_ADDR_MAPPING_REG0		0xa << 3
+#define BRCM_ZSC_SCB0_ADDR_MAPPING_REG1		0xc << 3
+
+#define BRCM_ZSC_SCB1_ADDR_MAPPING_REG0		0xe << 3
+#define BRCM_ZSC_SCB1_ADDR_MAPPING_REG1		0x10 << 3
+
+#define BRCM_ZSC_CONFIG_LMB1En			1 << (15)
+#define BRCM_ZSC_CONFIG_LMB0En			1 << (14)
+
+/* branch predition values */
+
+#define BRCM_BrPRED_ALL_TAKEN		(0x0)
+#define BRCM_BrPRED_ALL_NOT_TAKEN	(0x1)
+#define BRCM_BrPRED_BHT_ENABLE		(0x2)
+#define BRCM_BrPRED_PREDICT_BACKWARD	(0x3)
+
+
+
+.align 2
+/*
+ * Function: 	size_i_cache
+ * Arguments: 	None
+ * Returns:	v0 = i cache size, v1 = I cache line size
+ * Description: compute the I-cache size and I-cache line size
+ * Trashes:	v0, v1, a0, t0
+ *
+ *	pseudo code:
+ *
+ */
+
+LEAF(size_i_cache)
+	.set	noreorder
+
+	mfc0	a0, CP0_CONFIG, 1
+	move	t0, a0
+
+	/*
+	 * Determine sets per way: IS
+	 *
+	 * This field contains the number of sets (i.e., indices) per way of
+	 * the instruction cache:
+	 * i) 0x0: 64, ii) 0x1: 128, iii) 0x2: 256, iv) 0x3: 512, v) 0x4: 1k
+	 * vi) 0x5 - 0x7: Reserved.
+	 */
+
+	srl	a0, a0, IS_SHIFT
+	and	a0, a0, IS_MASK
+
+	/* sets per way = (64<<IS) */
+
+	li	v0, 0x40
+	sllv	v0, v0, a0
+
+	/*
+	 * Determine line size
+	 *
+	 * This field contains the line size of the instruction cache:
+	 * i) 0x0: No I-cache present, i) 0x3: 16 bytes, ii) 0x4: 32 bytes, iii)
+	 * 0x5: 64 bytes, iv) the rest: Reserved.
+	 */
+
+	move	a0, t0
+
+	srl	a0, a0, IL_SHIFT
+	and	a0, a0, IL_MASK
+
+	beqz	a0, no_i_cache
+	nop
+
+	/* line size = 2 ^ (IL+1) */
+
+	addi	a0, a0, 1
+	li	v1, 1
+	sll	v1, v1, a0
+
+	/* v0 now have sets per way, multiply it by line size now
+	 * that will give the set size
+	 */
+
+	sll	v0, v0, a0
+
+	/*
+	 * Determine set associativity
+	 *
+	 * This field contains the set associativity of the instruction cache.
+	 * i) 0x0: Direct mapped, ii) 0x1: 2-way, iii) 0x2: 3-way, iv) 0x3:
+	 * 4-way, v) 0x4 - 0x7: Reserved.
+	 */
+
+	move	a0, t0
+
+	srl	a0, a0, IA_SHIFT
+	and	a0, a0, IA_MASK
+	addi	a0, a0, 0x1
+
+	/* v0 has the set size, multiply it by
+	 * set associativiy, to get the cache size
+	 */
+
+	multu	v0, a0	/*multu is interlocked, so no need to insert nops */
+	mflo	v0
+	b	1f
+	nop
+
+no_i_cache:
+	move	v0, zero
+	move	v1, zero
+1:
+	jr	ra
+	nop
+	.set	reorder
+
+END(size_i_cache)
+
+/*
+ * Function: 	size_d_cache
+ * Arguments: 	None
+ * Returns:	v0 = d cache size, v1 = d cache line size
+ * Description: compute the D-cache size and D-cache line size.
+ * Trashes:	v0, v1, a0, t0
+ *
+ */
+
+LEAF(size_d_cache)
+	.set	noreorder
+
+	mfc0	a0, CP0_CONFIG, 1
+	move	t0, a0
+
+	/*
+	 * Determine sets per way: IS
+	 *
+	 * This field contains the number of sets (i.e., indices) per way of
+	 * the instruction cache:
+	 * i) 0x0: 64, ii) 0x1: 128, iii) 0x2: 256, iv) 0x3: 512, v) 0x4: 1k
+	 * vi) 0x5 - 0x7: Reserved.
+	 */
+
+	srl	a0, a0, DS_SHIFT
+	and	a0, a0, DS_MASK
+
+	/* sets per way = (64<<IS) */
+
+	li	v0, 0x40
+	sllv	v0, v0, a0
+
+	/*
+	 * Determine line size
+	 *
+	 * This field contains the line size of the instruction cache:
+	 * i) 0x0: No I-cache present, i) 0x3: 16 bytes, ii) 0x4: 32 bytes, iii)
+	 * 0x5: 64 bytes, iv) the rest: Reserved.
+	 */
+	move	a0, t0
+
+	srl	a0, a0, DL_SHIFT
+	and	a0, a0, DL_MASK
+
+	beqz	a0, no_d_cache
+	nop
+
+	/* line size = 2 ^ (IL+1) */
+
+	addi	a0, a0, 1
+	li	v1, 1
+	sll	v1, v1, a0
+
+	/* v0 now have sets per way, multiply it by line size now
+	 * that will give the set size
+	 */
+
+	sll	v0, v0, a0
+
+	/* determine set associativity
+	 *
+	 * This field contains the set associativity of the instruction cache.
+	 * i) 0x0: Direct mapped, ii) 0x1: 2-way, iii) 0x2: 3-way, iv) 0x3:
+	 * 4-way, v) 0x4 - 0x7: Reserved.
+	 */
+
+	move	a0, t0
+
+	srl	a0, a0, DA_SHIFT
+	and	a0, a0, DA_MASK
+	addi	a0, a0, 0x1
+
+	/* v0 has the set size, multiply it by
+	 * set associativiy, to get the cache size
+	 */
+
+	multu	v0, a0	/*multu is interlocked, so no need to insert nops */
+	mflo	v0
+
+	b	1f
+	nop
+
+no_d_cache:
+	move	v0, zero
+	move	v1, zero
+1:
+	jr	ra
+	nop
+	.set	reorder
+
+END(size_d_cache)
+
+
+/*
+ * Function: enable_ID
+ * Arguments: 	None
+ * Returns:	None
+ * Description: Enable I and D caches, initialize I and D-caches, also set
+ *		hardware delay for d-cache (TP0).
+ * Trashes:	t0
+ *
+ */
+	.global	enable_ID
+	.ent	enable_ID
+	.set	noreorder
+enable_ID:
+	mfc0	t0, CP0_BRCM_CONFIG0
+	or	t0, t0, (ICE_MASK | DCE_MASK)
+	mtc0	t0, CP0_BRCM_CONFIG0
+	jr	ra
+	nop
+
+	.end	enable_ID
+	.set	reorder
+
+
+/*
+ * Function: l1_init
+ * Arguments: 	None
+ * Returns:	None
+ * Description: Enable I and D caches, and initialize I and D-caches
+ * Trashes:	a0, v0, v1, t0, t1, t2, t8
+ *
+ */
+	.globl	l1_init
+	.ent	l1_init
+	.set	noreorder
+l1_init:
+
+	/* save return address */
+	move	t8, ra
+
+
+	/* initialize I and D cache Data and Tag registers.  */
+	mtc0	zero, CP0_ICACHE_TAG_LO
+	mtc0	zero, CP0_ICACHE_TAG_HI
+	mtc0	zero, CP0_ICACHE_DATA_LO
+	mtc0	zero, CP0_ICACHE_DATA_HI
+	mtc0	zero, CP0_DCACHE_TAG_LO
+	mtc0	zero, CP0_DCACHE_TAG_HI
+
+	/* Enable Caches before Clearing. If the caches are disabled
+	 * then the cache operations to clear the cache will be ignored
+	 */
+
+	jal	enable_ID
+	nop
+
+	jal	size_i_cache	/* v0 = i-cache size, v1 = i-cache line size */
+	nop
+
+	/* run uncached in kseg 1 */
+	la	k0, 1f
+	lui	k1, 0x2000
+	or	k0, k1, k0
+	jr	k0
+	nop
+1:
+
+	/*
+	 * set K0 cache mode
+	 */
+
+	mfc0	t0, CP0_CONFIG
+	and	t0, t0, ~CP0_CONFIG_K0_MASK
+	or	t0, t0, 3	/* Write Back mode */
+	mtc0	t0, CP0_CONFIG
+
+	/*
+	 * Initialize instruction cache.
+	 */
+
+	li	a0, KSEG0
+	cacheop(a0, v0, v1, Index_Store_Tag_I)
+
+	/*
+	 * Now we can run from I-$, kseg 0
+	 */
+	la	k0, 1f
+	lui	k1, 0x2000
+	or	k0, k1, k0
+	xor	k0, k1, k0
+	jr	k0
+	nop
+1:
+	/*
+	 * Initialize data cache.
+	 */
+
+	jal	size_d_cache	/* v0 = d-cache size, v1 = d-cache line size */
+	nop
+
+
+	li	a0, KSEG0
+	cacheop(a0, v0, v1, Index_Store_Tag_D)
+
+	jr	t8
+	nop
+
+	.end 	l1_init
+	.set	reorder
+
+
+/*
+ * Function: 	set_other_config
+ * Arguments:	none
+ * Returns:	None
+ * Description: initialize other remainder configuration to defaults.
+ * Trashes:	t0, t1
+ *
+ *	pseudo code:
+ *
+ */
+LEAF(set_other_config)
+	.set noreorder
+
+	/* enable Bus error for I-fetch */
+	mfc0	t0, CP0_CACHEERR, 0
+	li	t1, 0x4
+	or	t0, t1
+	mtc0	t0, CP0_CACHEERR, 0
+
+	/* enable Bus error for Load */
+	mfc0	t0, CP0_CACHEERR, 1
+	li	t1, 0x4
+	or	t0, t1
+	mtc0	t0, CP0_CACHEERR, 1
+
+	/* enable Bus Error for Store */
+	mfc0	t0, CP0_CACHEERR, 2
+	li	t1, 0x4
+	or	t0, t1
+	mtc0	t0, CP0_CACHEERR, 2
+
+	jr	ra
+	nop
+	.set reorder
+END(set_other_config)
+
+/*
+ * Function: 	set_branch_pred
+ * Arguments:	none
+ * Returns:	None
+ * Description:
+ * Trashes:	t0, t1
+ *
+ *	pseudo code:
+ *
+ */
+
+LEAF(set_branch_pred)
+	.set noreorder
+	mfc0	t0, CP0_BRCM_MODE
+	li	t1, ~(CP0_BRCM_MODE_BrPRED_MASK | CP0_BRCM_MODE_BrHIST_MASK )
+	and	t0, t0, t1
+
+	/* enable Branch prediction */
+	li	t1, BRCM_BrPRED_BHT_ENABLE
+	sll	t1, CP0_BRCM_MODE_BrPRED_SHIFT
+	or	t0, t0, t1
+
+	/* set history count to 8 */
+	li	t1, 8
+	sll	t1, CP0_BRCM_MODE_BrHIST_SHIFT
+	or	t0, t0, t1
+
+	mtc0	t0, CP0_BRCM_MODE
+	jr	ra
+	nop
+	.set	reorder
+END(set_branch_pred)
+
+
+/*
+ * Function: 	set_luc
+ * Arguments:	set link uncached.
+ * Returns:	None
+ * Description:
+ * Trashes:	t0, t1
+ *
+ */
+LEAF(set_luc)
+	.set noreorder
+	mfc0	t0, CP0_BRCM_MODE
+	li	t1, ~(CP0_BRCM_MODE_Luc_MASK)
+	and	t0, t0, t1
+
+	/* set Luc */
+	ori	t0, t0, CP0_BRCM_MODE_Luc_MASK
+
+	mtc0	t0, CP0_BRCM_MODE
+	jr	ra
+	nop
+	.set	reorder
+END(set_luc)
+
+/*
+ * Function: 	set_cwf_tse
+ * Arguments:	set CWF and TSE bits
+ * Returns:	None
+ * Description:
+ * Trashes:	t0, t1
+ *
+ */
+LEAF(set_cwf_tse)
+	.set noreorder
+	mfc0	t0, CP0_BRCM_CONFIG0
+	li	t1, (CP0_BRCM_CONFIG0_CWF_MASK | CP0_BRCM_CONFIG0_TSE_MASK)
+	or	t0, t0, t1
+
+	mtc0	t0, CP0_BRCM_CONFIG0
+	jr	ra
+	nop
+	.set	reorder
+END(set_cwf_tse)
+
+/*
+ * Function: 	set_clock_ratio
+ * Arguments:	set clock ratio specified by a0
+ * Returns:	None
+ * Description:
+ * Trashes:	v0, v1, a0, a1
+ *
+ *	pseudo code:
+ *
+ */
+LEAF(set_clock_ratio)
+	.set noreorder
+
+	mfc0	t0, CP0_BRCM_MODE
+	li	t1, ~(CP0_BRCM_MODE_SET_MASK | CP0_BRCM_MODE_ClkRATIO_MASK)
+	and	t0, t0, t1
+	li	t1, CP0_BRCM_MODE_SET_MASK
+	or	t0, t0, t1
+	or	t0, t0, a0
+	mtc0	t0, CP0_BRCM_MODE
+	jr	ra
+	nop
+	.set	reorder
+END(set_clock_ratio)
+/*
+ * Function: set_zephyr
+ * Arguments:	None
+ * Returns:	None
+ * Description: Set any zephyr bits
+ * Trashes:	t0 & t1
+ *
+ */
+LEAF(set_zephyr)
+	.set	noreorder
+
+	/* enable read/write of CP0 #22 sel. 8 */
+	li	t0, 0x5a455048
+	.word	0x4088b00f	/* mtc0    t0, $22, 15 */
+
+	.word	0x4008b008	/* mfc0    t0, $22, 8 */
+	li	t1, 0x09008000	/* turn off pref, jtb */
+	or	t0, t0, t1
+	.word	0x4088b008	/* mtc0    t0, $22, 8 */
+	sync
+
+	/* disable read/write of CP0 #22 sel 8 */
+	li	t0, 0x0
+	.word	0x4088b00f	/* mtc0    t0, $22, 15 */
+
+
+	jr	ra
+	nop
+	.set reorder
+
+END(set_zephyr)
+
+
+/*
+ * Function:	set_llmb
+ * Arguments:	a0=0 disable llmb, a0=1 enables llmb
+ * Returns:	None
+ * Description:
+ * Trashes:	t0, t1, t2
+ *
+ *      pseudo code:
+ *
+ */
+LEAF(set_llmb)
+	.set noreorder
+
+	li	t2, 0x90000000 | BRCM_ZSC_ALL_REGS_SELECT | BRCM_ZSC_CONFIG_REG
+	sync
+	cache	0x7, 0x0(t2)
+	sync
+	mfc0	t0, CP0_D_SEC_CACHE_DATA_LO
+	li	t1, ~(BRCM_ZSC_CONFIG_LMB1En | BRCM_ZSC_CONFIG_LMB0En)
+	and	t0, t0, t1
+
+	beqz	a0, svlmb
+	nop
+
+enable_lmb:
+	li	t1, (BRCM_ZSC_CONFIG_LMB1En | BRCM_ZSC_CONFIG_LMB0En)
+	or	t0, t0, t1
+
+svlmb:
+	mtc0	t0, CP0_D_SEC_CACHE_DATA_LO
+	sync
+	cache	0xb, 0x0(t2)
+	sync
+
+	jr	ra
+	nop
+	.set reorder
+
+END(set_llmb)
+/*
+ * Function: 	core_init
+ * Arguments:	none
+ * Returns:	None
+ * Description: initialize core related configuration
+ * Trashes:	v0,v1,a0,a1,t8
+ *
+ *	pseudo code:
+ *
+ */
+	.globl	core_init
+	.ent	core_init
+	.set	noreorder
+core_init:
+	move	t8, ra
+
+	/* set Zephyr bits. */
+	bal	set_zephyr
+	nop
+
+	/* set low latency memory bus */
+	li	a0, 1
+	bal	set_llmb
+	nop
+
+	/* set branch prediction (TP0 only) */
+	bal	set_branch_pred
+	nop
+
+	/* set link uncached */
+	bal	set_luc
+	nop
+
+	/* set CWF and TSE */
+	bal	set_cwf_tse
+	nop
+
+	/*
+	 *set clock ratio by setting 1 to 'set'
+	 * and 0 to ClkRatio, (TP0 only)
+	 */
+	li	a0, 0
+	bal	set_clock_ratio
+	nop
+
+	/* set other configuration to defaults */
+	bal	set_other_config
+	nop
+
+	move	ra, t8
+	jr	ra
+	nop
+
+	.set reorder
+	.end	core_init
+
+/*
+ * Function: 	clear_jump_target_buffer
+ * Arguments:	None
+ * Returns:	None
+ * Description:
+ * Trashes:	t0, t1, t2
+ *
+ */
+#define RESET_CALL_RETURN_STACK_THIS_THREAD		(0x06<<16)
+#define RESET_JUMP_TARGET_BUFFER_THIS_THREAD		(0x04<<16)
+#define JTB_CS_CNTL_MASK				(0xFF<<16)
+
+	.globl	clear_jump_target_buffer
+	.ent	clear_jump_target_buffer
+	.set	noreorder
+clear_jump_target_buffer:
+
+	mfc0	t0, $22, 2
+	nop
+	nop
+
+	li	t1, ~JTB_CS_CNTL_MASK
+	and	t0, t0, t1
+	li	t2, RESET_CALL_RETURN_STACK_THIS_THREAD
+	or	t0, t0, t2
+	mtc0	t0, $22, 2
+	nop
+	nop
+
+	and	t0, t0, t1
+	li	t2, RESET_JUMP_TARGET_BUFFER_THIS_THREAD
+	or	t0, t0, t2
+	mtc0	t0, $22, 2
+	nop
+	nop
+	jr	ra
+	nop
+
+	.end	clear_jump_target_buffer
+	.set	reorder
+/*
+ * Function: 	bmips_cache_init
+ * Arguments: 	None
+ * Returns:	None
+ * Description: Enable I and D caches, and initialize I and D-caches
+ * Trashes:	v0, v1, t0, t1, t2, t5, t7, t8
+ *
+ */
+	.globl	bmips_5xxx_init
+	.ent	bmips_5xxx_init
+	.set	noreorder
+bmips_5xxx_init:
+
+	/* save return address and A0 */
+	move	t7, ra
+	move	t5, a0
+
+	jal	l1_init
+	nop
+
+	jal	core_init
+	nop
+
+	jal	clear_jump_target_buffer
+	nop
+
+	mtc0	zero, CP0_CAUSE
+
+	move 	a0, t5
+	jr	t7
+	nop
+
+	.end 	bmips_5xxx_init
+	.set	reorder
+
+
+#endif