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, 537 insertions, 0 deletions

diff --git a/arch/arm/kernel/head-nommu.S b/arch/arm/kernel/head-nommu.S
new file mode 100644
index 000000000..950bef833
--- /dev/null
+++ b/arch/arm/kernel/head-nommu.S
@@ -0,0 +1,537 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ *  linux/arch/arm/kernel/head-nommu.S
+ *
+ *  Copyright (C) 1994-2002 Russell King
+ *  Copyright (C) 2003-2006 Hyok S. Choi
+ *
+ *  Common kernel startup code (non-paged MM)
+ */
+#include <linux/linkage.h>
+#include <linux/init.h>
+#include <linux/errno.h>
+
+#include <asm/assembler.h>
+#include <asm/ptrace.h>
+#include <asm/asm-offsets.h>
+#include <asm/memory.h>
+#include <asm/cp15.h>
+#include <asm/thread_info.h>
+#include <asm/v7m.h>
+#include <asm/mpu.h>
+#include <asm/page.h>
+
+/*
+ * Kernel startup entry point.
+ * ---------------------------
+ *
+ * This is normally called from the decompressor code.  The requirements
+ * are: MMU = off, D-cache = off, I-cache = dont care, r0 = 0,
+ * r1 = machine nr.
+ *
+ * See linux/arch/arm/tools/mach-types for the complete list of machine
+ * numbers for r1.
+ *
+ */
+
+	__HEAD
+
+#ifdef CONFIG_CPU_THUMBONLY
+	.thumb
+ENTRY(stext)
+#else
+	.arm
+ENTRY(stext)
+
+ THUMB(	badr	r9, 1f		)	@ Kernel is always entered in ARM.
+ THUMB(	bx	r9		)	@ If this is a Thumb-2 kernel,
+ THUMB(	.thumb			)	@ switch to Thumb now.
+ THUMB(1:			)
+#endif
+
+#ifdef CONFIG_ARM_VIRT_EXT
+	bl	__hyp_stub_install
+#endif
+	@ ensure svc mode and all interrupts masked
+	safe_svcmode_maskall r9
+						@ and irqs disabled
+#if defined(CONFIG_CPU_CP15)
+	mrc	p15, 0, r9, c0, c0		@ get processor id
+#elif defined(CONFIG_CPU_V7M)
+	ldr	r9, =BASEADDR_V7M_SCB
+	ldr	r9, [r9, V7M_SCB_CPUID]
+#else
+	ldr	r9, =CONFIG_PROCESSOR_ID
+#endif
+	bl	__lookup_processor_type		@ r5=procinfo r9=cpuid
+	movs	r10, r5				@ invalid processor (r5=0)?
+	beq	__error_p				@ yes, error 'p'
+
+#ifdef CONFIG_ARM_MPU
+	bl	__setup_mpu
+#endif
+
+	badr	lr, 1f				@ return (PIC) address
+	ldr	r12, [r10, #PROCINFO_INITFUNC]
+	add	r12, r12, r10
+	ret	r12
+1:	ldr	lr, =__mmap_switched
+	b	__after_proc_init
+ENDPROC(stext)
+
+#ifdef CONFIG_SMP
+	.text
+ENTRY(secondary_startup)
+	/*
+	 * Common entry point for secondary CPUs.
+	 *
+	 * Ensure that we're in SVC mode, and IRQs are disabled.  Lookup
+	 * the processor type - there is no need to check the machine type
+	 * as it has already been validated by the primary processor.
+	 */
+#ifdef CONFIG_ARM_VIRT_EXT
+	bl	__hyp_stub_install_secondary
+#endif
+	safe_svcmode_maskall r9
+
+#ifndef CONFIG_CPU_CP15
+	ldr	r9, =CONFIG_PROCESSOR_ID
+#else
+	mrc	p15, 0, r9, c0, c0		@ get processor id
+#endif
+	bl	__lookup_processor_type		@ r5=procinfo r9=cpuid
+	movs	r10, r5				@ invalid processor?
+	beq	__error_p			@ yes, error 'p'
+
+	ldr	r7, __secondary_data
+
+#ifdef CONFIG_ARM_MPU
+	bl      __secondary_setup_mpu		@ Initialize the MPU
+#endif
+
+	badr	lr, 1f				@ return (PIC) address
+	ldr	r12, [r10, #PROCINFO_INITFUNC]
+	add	r12, r12, r10
+	ret	r12
+1:	bl	__after_proc_init
+	ldr	r7, __secondary_data		@ reload r7
+	ldr	sp, [r7, #12]			@ set up the stack pointer
+	ldr	r0, [r7, #16]			@ set up task pointer
+	mov	fp, #0
+	b	secondary_start_kernel
+ENDPROC(secondary_startup)
+
+	.type	__secondary_data, %object
+__secondary_data:
+	.long	secondary_data
+#endif /* CONFIG_SMP */
+
+/*
+ * Set the Control Register and Read the process ID.
+ */
+	.text
+__after_proc_init:
+M_CLASS(movw	r12, #:lower16:BASEADDR_V7M_SCB)
+M_CLASS(movt	r12, #:upper16:BASEADDR_V7M_SCB)
+#ifdef CONFIG_ARM_MPU
+M_CLASS(ldr	r3, [r12, 0x50])
+AR_CLASS(mrc	p15, 0, r3, c0, c1, 4)          @ Read ID_MMFR0
+	and	r3, r3, #(MMFR0_PMSA)           @ PMSA field
+	teq	r3, #(MMFR0_PMSAv7)             @ PMSA v7
+	beq	1f
+	teq	r3, #(MMFR0_PMSAv8)		@ PMSA v8
+	/*
+	 * Memory region attributes for PMSAv8:
+	 *
+	 *   n = AttrIndx[2:0]
+	 *                      n       MAIR
+	 *   DEVICE_nGnRnE      000     00000000
+	 *   NORMAL             001     11111111
+	 */
+	ldreq	r3, =PMSAv8_MAIR(0x00, PMSAv8_RGN_DEVICE_nGnRnE) | \
+		     PMSAv8_MAIR(0xff, PMSAv8_RGN_NORMAL)
+AR_CLASS(mcreq	p15, 0, r3, c10, c2, 0)		@ MAIR 0
+M_CLASS(streq	r3, [r12, #PMSAv8_MAIR0])
+	moveq	r3, #0
+AR_CLASS(mcreq	p15, 0, r3, c10, c2, 1)		@ MAIR 1
+M_CLASS(streq	r3, [r12, #PMSAv8_MAIR1])
+
+1:
+#endif
+#ifdef CONFIG_CPU_CP15
+	/*
+	 * CP15 system control register value returned in r0 from
+	 * the CPU init function.
+	 */
+
+#ifdef CONFIG_ARM_MPU
+	biceq	r0, r0, #CR_BR			@ Disable the 'default mem-map'
+	orreq	r0, r0, #CR_M			@ Set SCTRL.M (MPU on)
+#endif
+#if defined(CONFIG_ALIGNMENT_TRAP) && __LINUX_ARM_ARCH__ < 6
+	orr	r0, r0, #CR_A
+#else
+	bic	r0, r0, #CR_A
+#endif
+#ifdef CONFIG_CPU_DCACHE_DISABLE
+	bic	r0, r0, #CR_C
+#endif
+#ifdef CONFIG_CPU_BPREDICT_DISABLE
+	bic	r0, r0, #CR_Z
+#endif
+#ifdef CONFIG_CPU_ICACHE_DISABLE
+	bic	r0, r0, #CR_I
+#endif
+	mcr	p15, 0, r0, c1, c0, 0		@ write control reg
+	instr_sync
+#elif defined (CONFIG_CPU_V7M)
+#ifdef CONFIG_ARM_MPU
+	ldreq	r3, [r12, MPU_CTRL]
+	biceq	r3, #MPU_CTRL_PRIVDEFENA
+	orreq	r3, #MPU_CTRL_ENABLE
+	streq	r3, [r12, MPU_CTRL]
+	isb
+#endif
+	/* For V7M systems we want to modify the CCR similarly to the SCTLR */
+#ifdef CONFIG_CPU_DCACHE_DISABLE
+	bic	r0, r0, #V7M_SCB_CCR_DC
+#endif
+#ifdef CONFIG_CPU_BPREDICT_DISABLE
+	bic	r0, r0, #V7M_SCB_CCR_BP
+#endif
+#ifdef CONFIG_CPU_ICACHE_DISABLE
+	bic	r0, r0, #V7M_SCB_CCR_IC
+#endif
+	str	r0, [r12, V7M_SCB_CCR]
+	/* Pass exc_ret to __mmap_switched */
+	mov	r0, r10
+#endif /* CONFIG_CPU_CP15 elif CONFIG_CPU_V7M */
+	ret	lr
+ENDPROC(__after_proc_init)
+	.ltorg
+
+#ifdef CONFIG_ARM_MPU
+
+
+#ifndef CONFIG_CPU_V7M
+/* Set which MPU region should be programmed */
+.macro set_region_nr tmp, rgnr, unused
+	mov	\tmp, \rgnr			@ Use static region numbers
+	mcr	p15, 0, \tmp, c6, c2, 0		@ Write RGNR
+.endm
+
+/* Setup a single MPU region, either D or I side (D-side for unified) */
+.macro setup_region bar, acr, sr, side = PMSAv7_DATA_SIDE, unused
+	mcr	p15, 0, \bar, c6, c1, (0 + \side)	@ I/DRBAR
+	mcr	p15, 0, \acr, c6, c1, (4 + \side)	@ I/DRACR
+	mcr	p15, 0, \sr, c6, c1, (2 + \side)		@ I/DRSR
+.endm
+#else
+.macro set_region_nr tmp, rgnr, base
+	mov	\tmp, \rgnr
+	str     \tmp, [\base, #PMSAv7_RNR]
+.endm
+
+.macro setup_region bar, acr, sr, unused, base
+	lsl     \acr, \acr, #16
+	orr     \acr, \acr, \sr
+	str     \bar, [\base, #PMSAv7_RBAR]
+	str     \acr, [\base, #PMSAv7_RASR]
+.endm
+
+#endif
+/*
+ * Setup the MPU and initial MPU Regions. We create the following regions:
+ * Region 0: Use this for probing the MPU details, so leave disabled.
+ * Region 1: Background region - covers the whole of RAM as strongly ordered
+ * Region 2: Normal, Shared, cacheable for RAM. From PHYS_OFFSET, size from r6
+ * Region 3: Normal, shared, inaccessible from PL0 to protect the vectors page
+ *
+ * r6: Value to be written to DRSR (and IRSR if required) for PMSAv7_RAM_REGION
+*/
+	__HEAD
+
+ENTRY(__setup_mpu)
+
+	/* Probe for v7 PMSA compliance */
+M_CLASS(movw	r12, #:lower16:BASEADDR_V7M_SCB)
+M_CLASS(movt	r12, #:upper16:BASEADDR_V7M_SCB)
+
+AR_CLASS(mrc	p15, 0, r0, c0, c1, 4)		@ Read ID_MMFR0
+M_CLASS(ldr	r0, [r12, 0x50])
+	and	r0, r0, #(MMFR0_PMSA)		@ PMSA field
+	teq	r0, #(MMFR0_PMSAv7)		@ PMSA v7
+	beq	__setup_pmsa_v7
+	teq	r0, #(MMFR0_PMSAv8)		@ PMSA v8
+	beq	__setup_pmsa_v8
+
+	ret	lr
+ENDPROC(__setup_mpu)
+
+ENTRY(__setup_pmsa_v7)
+	/* Calculate the size of a region covering just the kernel */
+	ldr	r5, =PLAT_PHYS_OFFSET		@ Region start: PHYS_OFFSET
+	ldr     r6, =(_end)			@ Cover whole kernel
+	sub	r6, r6, r5			@ Minimum size of region to map
+	clz	r6, r6				@ Region size must be 2^N...
+	rsb	r6, r6, #31			@ ...so round up region size
+	lsl	r6, r6, #PMSAv7_RSR_SZ		@ Put size in right field
+	orr	r6, r6, #(1 << PMSAv7_RSR_EN)	@ Set region enabled bit
+
+	/* Determine whether the D/I-side memory map is unified. We set the
+	 * flags here and continue to use them for the rest of this function */
+AR_CLASS(mrc	p15, 0, r0, c0, c0, 4)		@ MPUIR
+M_CLASS(ldr    r0, [r12, #MPU_TYPE])
+	ands	r5, r0, #MPUIR_DREGION_SZMASK	@ 0 size d region => No MPU
+	bxeq	lr
+	tst	r0, #MPUIR_nU			@ MPUIR_nU = 0 for unified
+
+	/* Setup second region first to free up r6 */
+	set_region_nr r0, #PMSAv7_RAM_REGION, r12
+	isb
+	/* Full access from PL0, PL1, shared for CONFIG_SMP, cacheable */
+	ldr	r0, =PLAT_PHYS_OFFSET		@ RAM starts at PHYS_OFFSET
+	ldr	r5,=(PMSAv7_AP_PL1RW_PL0RW | PMSAv7_RGN_NORMAL)
+
+	setup_region r0, r5, r6, PMSAv7_DATA_SIDE, r12	@ PHYS_OFFSET, shared, enabled
+	beq	1f					@ Memory-map not unified
+	setup_region r0, r5, r6, PMSAv7_INSTR_SIDE, r12	@ PHYS_OFFSET, shared, enabled
+1:	isb
+
+	/* First/background region */
+	set_region_nr r0, #PMSAv7_BG_REGION, r12
+	isb
+	/* Execute Never,  strongly ordered, inaccessible to PL0, rw PL1  */
+	mov	r0, #0				@ BG region starts at 0x0
+	ldr	r5,=(PMSAv7_ACR_XN | PMSAv7_RGN_STRONGLY_ORDERED | PMSAv7_AP_PL1RW_PL0NA)
+	mov	r6, #PMSAv7_RSR_ALL_MEM		@ 4GB region, enabled
+
+	setup_region r0, r5, r6, PMSAv7_DATA_SIDE, r12	@ 0x0, BG region, enabled
+	beq	2f					@ Memory-map not unified
+	setup_region r0, r5, r6, PMSAv7_INSTR_SIDE r12	@ 0x0, BG region, enabled
+2:	isb
+
+#ifdef CONFIG_XIP_KERNEL
+	set_region_nr r0, #PMSAv7_ROM_REGION, r12
+	isb
+
+	ldr	r5,=(PMSAv7_AP_PL1RO_PL0NA | PMSAv7_RGN_NORMAL)
+
+	ldr	r0, =CONFIG_XIP_PHYS_ADDR		@ ROM start
+	ldr     r6, =(_exiprom)				@ ROM end
+	sub	r6, r6, r0				@ Minimum size of region to map
+	clz	r6, r6					@ Region size must be 2^N...
+	rsb	r6, r6, #31				@ ...so round up region size
+	lsl	r6, r6, #PMSAv7_RSR_SZ			@ Put size in right field
+	orr	r6, r6, #(1 << PMSAv7_RSR_EN)		@ Set region enabled bit
+
+	setup_region r0, r5, r6, PMSAv7_DATA_SIDE, r12	@ XIP_PHYS_ADDR, shared, enabled
+	beq	3f					@ Memory-map not unified
+	setup_region r0, r5, r6, PMSAv7_INSTR_SIDE, r12	@ XIP_PHYS_ADDR, shared, enabled
+3:	isb
+#endif
+	ret	lr
+ENDPROC(__setup_pmsa_v7)
+
+ENTRY(__setup_pmsa_v8)
+	mov	r0, #0
+AR_CLASS(mcr	p15, 0, r0, c6, c2, 1)		@ PRSEL
+M_CLASS(str	r0, [r12, #PMSAv8_RNR])
+	isb
+
+#ifdef CONFIG_XIP_KERNEL
+	ldr	r5, =CONFIG_XIP_PHYS_ADDR		@ ROM start
+	ldr     r6, =(_exiprom)				@ ROM end
+	sub	r6, r6, #1
+	bic	r6, r6, #(PMSAv8_MINALIGN - 1)
+
+	orr	r5, r5, #(PMSAv8_AP_PL1RW_PL0NA | PMSAv8_RGN_SHARED)
+	orr	r6, r6, #(PMSAv8_LAR_IDX(PMSAv8_RGN_NORMAL) | PMSAv8_LAR_EN)
+
+AR_CLASS(mcr	p15, 0, r5, c6, c8, 0)			@ PRBAR0
+AR_CLASS(mcr	p15, 0, r6, c6, c8, 1)			@ PRLAR0
+M_CLASS(str	r5, [r12, #PMSAv8_RBAR_A(0)])
+M_CLASS(str	r6, [r12, #PMSAv8_RLAR_A(0)])
+#endif
+
+	ldr	r5, =KERNEL_START
+	ldr	r6, =KERNEL_END
+	sub	r6, r6, #1
+	bic	r6, r6, #(PMSAv8_MINALIGN - 1)
+
+	orr	r5, r5, #(PMSAv8_AP_PL1RW_PL0NA | PMSAv8_RGN_SHARED)
+	orr	r6, r6, #(PMSAv8_LAR_IDX(PMSAv8_RGN_NORMAL) | PMSAv8_LAR_EN)
+
+AR_CLASS(mcr	p15, 0, r5, c6, c8, 4)			@ PRBAR1
+AR_CLASS(mcr	p15, 0, r6, c6, c8, 5)			@ PRLAR1
+M_CLASS(str	r5, [r12, #PMSAv8_RBAR_A(1)])
+M_CLASS(str	r6, [r12, #PMSAv8_RLAR_A(1)])
+
+	/* Setup Background: 0x0 - min(KERNEL_START, XIP_PHYS_ADDR) */
+#ifdef CONFIG_XIP_KERNEL
+	ldr	r6, =KERNEL_START
+	ldr	r5, =CONFIG_XIP_PHYS_ADDR
+	cmp	r6, r5
+	movcs	r6, r5
+#else
+	ldr	r6, =KERNEL_START
+#endif
+	cmp	r6, #0
+	beq	1f
+
+	mov	r5, #0
+	sub	r6, r6, #1
+	bic	r6, r6, #(PMSAv8_MINALIGN - 1)
+
+	orr	r5, r5, #(PMSAv8_AP_PL1RW_PL0NA | PMSAv8_RGN_SHARED | PMSAv8_BAR_XN)
+	orr	r6, r6, #(PMSAv8_LAR_IDX(PMSAv8_RGN_DEVICE_nGnRnE) | PMSAv8_LAR_EN)
+
+AR_CLASS(mcr	p15, 0, r5, c6, c9, 0)			@ PRBAR2
+AR_CLASS(mcr	p15, 0, r6, c6, c9, 1)			@ PRLAR2
+M_CLASS(str	r5, [r12, #PMSAv8_RBAR_A(2)])
+M_CLASS(str	r6, [r12, #PMSAv8_RLAR_A(2)])
+
+1:
+	/* Setup Background: max(KERNEL_END, _exiprom) - 0xffffffff */
+#ifdef CONFIG_XIP_KERNEL
+	ldr	r5, =KERNEL_END
+	ldr	r6, =(_exiprom)
+	cmp	r5, r6
+	movcc	r5, r6
+#else
+	ldr	r5, =KERNEL_END
+#endif
+	mov	r6, #0xffffffff
+	bic	r6, r6, #(PMSAv8_MINALIGN - 1)
+
+	orr	r5, r5, #(PMSAv8_AP_PL1RW_PL0NA | PMSAv8_RGN_SHARED | PMSAv8_BAR_XN)
+	orr	r6, r6, #(PMSAv8_LAR_IDX(PMSAv8_RGN_DEVICE_nGnRnE) | PMSAv8_LAR_EN)
+
+AR_CLASS(mcr	p15, 0, r5, c6, c9, 4)			@ PRBAR3
+AR_CLASS(mcr	p15, 0, r6, c6, c9, 5)			@ PRLAR3
+M_CLASS(str	r5, [r12, #PMSAv8_RBAR_A(3)])
+M_CLASS(str	r6, [r12, #PMSAv8_RLAR_A(3)])
+
+#ifdef CONFIG_XIP_KERNEL
+	/* Setup Background: min(_exiprom, KERNEL_END) - max(KERNEL_START, XIP_PHYS_ADDR) */
+	ldr	r5, =(_exiprom)
+	ldr	r6, =KERNEL_END
+	cmp	r5, r6
+	movcs	r5, r6
+
+	ldr	r6, =KERNEL_START
+	ldr	r0, =CONFIG_XIP_PHYS_ADDR
+	cmp	r6, r0
+	movcc	r6, r0
+
+	sub	r6, r6, #1
+	bic	r6, r6, #(PMSAv8_MINALIGN - 1)
+
+	orr	r5, r5, #(PMSAv8_AP_PL1RW_PL0NA | PMSAv8_RGN_SHARED | PMSAv8_BAR_XN)
+	orr	r6, r6, #(PMSAv8_LAR_IDX(PMSAv8_RGN_DEVICE_nGnRnE) | PMSAv8_LAR_EN)
+
+#ifdef CONFIG_CPU_V7M
+	/* There is no alias for n == 4 */
+	mov	r0, #4
+	str	r0, [r12, #PMSAv8_RNR]			@ PRSEL
+	isb
+
+	str	r5, [r12, #PMSAv8_RBAR_A(0)]
+	str	r6, [r12, #PMSAv8_RLAR_A(0)]
+#else
+	mcr	p15, 0, r5, c6, c10, 0			@ PRBAR4
+	mcr	p15, 0, r6, c6, c10, 1			@ PRLAR4
+#endif
+#endif
+	ret	lr
+ENDPROC(__setup_pmsa_v8)
+
+#ifdef CONFIG_SMP
+/*
+ * r6: pointer at mpu_rgn_info
+ */
+
+	.text
+ENTRY(__secondary_setup_mpu)
+	/* Use MPU region info supplied by __cpu_up */
+	ldr	r6, [r7]			@ get secondary_data.mpu_rgn_info
+
+	/* Probe for v7 PMSA compliance */
+	mrc	p15, 0, r0, c0, c1, 4		@ Read ID_MMFR0
+	and	r0, r0, #(MMFR0_PMSA)		@ PMSA field
+	teq	r0, #(MMFR0_PMSAv7)		@ PMSA v7
+	beq	__secondary_setup_pmsa_v7
+	teq	r0, #(MMFR0_PMSAv8)		@ PMSA v8
+	beq	__secondary_setup_pmsa_v8
+	b	__error_p
+ENDPROC(__secondary_setup_mpu)
+
+/*
+ * r6: pointer at mpu_rgn_info
+ */
+ENTRY(__secondary_setup_pmsa_v7)
+	/* Determine whether the D/I-side memory map is unified. We set the
+	 * flags here and continue to use them for the rest of this function */
+	mrc	p15, 0, r0, c0, c0, 4		@ MPUIR
+	ands	r5, r0, #MPUIR_DREGION_SZMASK	@ 0 size d region => No MPU
+	beq	__error_p
+
+	ldr	r4, [r6, #MPU_RNG_INFO_USED]
+	mov	r5, #MPU_RNG_SIZE
+	add	r3, r6, #MPU_RNG_INFO_RNGS
+	mla	r3, r4, r5, r3
+
+1:
+	tst	r0, #MPUIR_nU			@ MPUIR_nU = 0 for unified
+	sub	r3, r3, #MPU_RNG_SIZE
+	sub	r4, r4, #1
+
+	set_region_nr r0, r4
+	isb
+
+	ldr	r0, [r3, #MPU_RGN_DRBAR]
+	ldr	r6, [r3, #MPU_RGN_DRSR]
+	ldr	r5, [r3, #MPU_RGN_DRACR]
+
+	setup_region r0, r5, r6, PMSAv7_DATA_SIDE
+	beq	2f
+	setup_region r0, r5, r6, PMSAv7_INSTR_SIDE
+2:	isb
+
+	mrc	p15, 0, r0, c0, c0, 4		@ Reevaluate the MPUIR
+	cmp	r4, #0
+	bgt	1b
+
+	ret	lr
+ENDPROC(__secondary_setup_pmsa_v7)
+
+ENTRY(__secondary_setup_pmsa_v8)
+	ldr	r4, [r6, #MPU_RNG_INFO_USED]
+#ifndef CONFIG_XIP_KERNEL
+	add	r4, r4, #1
+#endif
+	mov	r5, #MPU_RNG_SIZE
+	add	r3, r6, #MPU_RNG_INFO_RNGS
+	mla	r3, r4, r5, r3
+
+1:
+	sub	r3, r3, #MPU_RNG_SIZE
+	sub	r4, r4, #1
+
+	mcr	p15, 0, r4, c6, c2, 1		@ PRSEL
+	isb
+
+	ldr	r5, [r3, #MPU_RGN_PRBAR]
+	ldr	r6, [r3, #MPU_RGN_PRLAR]
+
+	mcr	p15, 0, r5, c6, c3, 0		@ PRBAR
+	mcr	p15, 0, r6, c6, c3, 1           @ PRLAR
+
+	cmp	r4, #0
+	bgt	1b
+
+	ret	lr
+ENDPROC(__secondary_setup_pmsa_v8)
+#endif /* CONFIG_SMP */
+#endif /* CONFIG_ARM_MPU */
+#include "head-common.S"