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, 467 insertions, 0 deletions

diff --git a/arch/arm/kernel/entry-header.S b/arch/arm/kernel/entry-header.S
new file mode 100644
index 000000000..99411fa91
--- /dev/null
+++ b/arch/arm/kernel/entry-header.S
@@ -0,0 +1,467 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#include <linux/init.h>
+#include <linux/linkage.h>
+
+#include <asm/assembler.h>
+#include <asm/asm-offsets.h>
+#include <asm/errno.h>
+#include <asm/thread_info.h>
+#include <asm/uaccess-asm.h>
+#include <asm/v7m.h>
+
+@ Bad Abort numbers
+@ -----------------
+@
+#define BAD_PREFETCH	0
+#define BAD_DATA	1
+#define BAD_ADDREXCPTN	2
+#define BAD_IRQ		3
+#define BAD_UNDEFINSTR	4
+
+@
+@ Most of the stack format comes from struct pt_regs, but with
+@ the addition of 8 bytes for storing syscall args 5 and 6.
+@ This _must_ remain a multiple of 8 for EABI.
+@
+#define S_OFF		8
+
+/* 
+ * The SWI code relies on the fact that R0 is at the bottom of the stack
+ * (due to slow/fast restore user regs).
+ */
+#if S_R0 != 0
+#error "Please fix"
+#endif
+
+	.macro	zero_fp
+#ifdef CONFIG_FRAME_POINTER
+	mov	fp, #0
+#endif
+	.endm
+
+#ifdef CONFIG_ALIGNMENT_TRAP
+#define ATRAP(x...) x
+#else
+#define ATRAP(x...)
+#endif
+
+	.macro	alignment_trap, rtmp1, rtmp2, label
+#ifdef CONFIG_ALIGNMENT_TRAP
+	mrc	p15, 0, \rtmp2, c1, c0, 0
+	ldr_va	\rtmp1, \label
+	teq	\rtmp1, \rtmp2
+	mcrne	p15, 0, \rtmp1, c1, c0, 0
+#endif
+	.endm
+
+#ifdef CONFIG_CPU_V7M
+/*
+ * ARMv7-M exception entry/exit macros.
+ *
+ * xPSR, ReturnAddress(), LR (R14), R12, R3, R2, R1, and R0 are
+ * automatically saved on the current stack (32 words) before
+ * switching to the exception stack (SP_main).
+ *
+ * If exception is taken while in user mode, SP_main is
+ * empty. Otherwise, SP_main is aligned to 64 bit automatically
+ * (CCR.STKALIGN set).
+ *
+ * Linux assumes that the interrupts are disabled when entering an
+ * exception handler and it may BUG if this is not the case. Interrupts
+ * are disabled during entry and reenabled in the exit macro.
+ *
+ * v7m_exception_slow_exit is used when returning from SVC or PendSV.
+ * When returning to kernel mode, we don't return from exception.
+ */
+	.macro	v7m_exception_entry
+	@ determine the location of the registers saved by the core during
+	@ exception entry. Depending on the mode the cpu was in when the
+	@ exception happend that is either on the main or the process stack.
+	@ Bit 2 of EXC_RETURN stored in the lr register specifies which stack
+	@ was used.
+	tst	lr, #EXC_RET_STACK_MASK
+	mrsne	r12, psp
+	moveq	r12, sp
+
+	@ we cannot rely on r0-r3 and r12 matching the value saved in the
+	@ exception frame because of tail-chaining. So these have to be
+	@ reloaded.
+	ldmia	r12!, {r0-r3}
+
+	@ Linux expects to have irqs off. Do it here before taking stack space
+	cpsid	i
+
+	sub	sp, #PT_REGS_SIZE-S_IP
+	stmdb	sp!, {r0-r11}
+
+	@ load saved r12, lr, return address and xPSR.
+	@ r0-r7 are used for signals and never touched from now on. Clobbering
+	@ r8-r12 is OK.
+	mov	r9, r12
+	ldmia	r9!, {r8, r10-r12}
+
+	@ calculate the original stack pointer value.
+	@ r9 currently points to the memory location just above the auto saved
+	@ xPSR.
+	@ The cpu might automatically 8-byte align the stack. Bit 9
+	@ of the saved xPSR specifies if stack aligning took place. In this case
+	@ another 32-bit value is included in the stack.
+
+	tst	r12, V7M_xPSR_FRAMEPTRALIGN
+	addne	r9, r9, #4
+
+	@ store saved r12 using str to have a register to hold the base for stm
+	str	r8, [sp, #S_IP]
+	add	r8, sp, #S_SP
+	@ store r13-r15, xPSR
+	stmia	r8!, {r9-r12}
+	@ store old_r0
+	str	r0, [r8]
+	.endm
+
+        /*
+	 * PENDSV and SVCALL are configured to have the same exception
+	 * priorities. As a kernel thread runs at SVCALL execution priority it
+	 * can never be preempted and so we will never have to return to a
+	 * kernel thread here.
+         */
+	.macro	v7m_exception_slow_exit ret_r0
+	cpsid	i
+	ldr	lr, =exc_ret
+	ldr	lr, [lr]
+
+	@ read original r12, sp, lr, pc and xPSR
+	add	r12, sp, #S_IP
+	ldmia	r12, {r1-r5}
+
+	@ an exception frame is always 8-byte aligned. To tell the hardware if
+	@ the sp to be restored is aligned or not set bit 9 of the saved xPSR
+	@ accordingly.
+	tst	r2, #4
+	subne	r2, r2, #4
+	orrne	r5, V7M_xPSR_FRAMEPTRALIGN
+	biceq	r5, V7M_xPSR_FRAMEPTRALIGN
+
+	@ ensure bit 0 is cleared in the PC, otherwise behaviour is
+	@ unpredictable
+	bic	r4, #1
+
+	@ write basic exception frame
+	stmdb	r2!, {r1, r3-r5}
+	ldmia	sp, {r1, r3-r5}
+	.if	\ret_r0
+	stmdb	r2!, {r0, r3-r5}
+	.else
+	stmdb	r2!, {r1, r3-r5}
+	.endif
+
+	@ restore process sp
+	msr	psp, r2
+
+	@ restore original r4-r11
+	ldmia	sp!, {r0-r11}
+
+	@ restore main sp
+	add	sp, sp, #PT_REGS_SIZE-S_IP
+
+	cpsie	i
+	bx	lr
+	.endm
+#endif	/* CONFIG_CPU_V7M */
+
+	@
+	@ Store/load the USER SP and LR registers by switching to the SYS
+	@ mode. Useful in Thumb-2 mode where "stm/ldm rd, {sp, lr}^" is not
+	@ available. Should only be called from SVC mode
+	@
+	.macro	store_user_sp_lr, rd, rtemp, offset = 0
+	mrs	\rtemp, cpsr
+	eor	\rtemp, \rtemp, #(SVC_MODE ^ SYSTEM_MODE)
+	msr	cpsr_c, \rtemp			@ switch to the SYS mode
+
+	str	sp, [\rd, #\offset]		@ save sp_usr
+	str	lr, [\rd, #\offset + 4]		@ save lr_usr
+
+	eor	\rtemp, \rtemp, #(SVC_MODE ^ SYSTEM_MODE)
+	msr	cpsr_c, \rtemp			@ switch back to the SVC mode
+	.endm
+
+	.macro	load_user_sp_lr, rd, rtemp, offset = 0
+	mrs	\rtemp, cpsr
+	eor	\rtemp, \rtemp, #(SVC_MODE ^ SYSTEM_MODE)
+	msr	cpsr_c, \rtemp			@ switch to the SYS mode
+
+	ldr	sp, [\rd, #\offset]		@ load sp_usr
+	ldr	lr, [\rd, #\offset + 4]		@ load lr_usr
+
+	eor	\rtemp, \rtemp, #(SVC_MODE ^ SYSTEM_MODE)
+	msr	cpsr_c, \rtemp			@ switch back to the SVC mode
+	.endm
+
+
+	.macro	svc_exit, rpsr, irq = 0
+	.if	\irq != 0
+	@ IRQs already off
+#ifdef CONFIG_TRACE_IRQFLAGS
+	@ The parent context IRQs must have been enabled to get here in
+	@ the first place, so there's no point checking the PSR I bit.
+	bl	trace_hardirqs_on
+#endif
+	.else
+	@ IRQs off again before pulling preserved data off the stack
+	disable_irq_notrace
+#ifdef CONFIG_TRACE_IRQFLAGS
+	tst	\rpsr, #PSR_I_BIT
+	bleq	trace_hardirqs_on
+	tst	\rpsr, #PSR_I_BIT
+	blne	trace_hardirqs_off
+#endif
+	.endif
+	uaccess_exit tsk, r0, r1
+
+#ifndef CONFIG_THUMB2_KERNEL
+	@ ARM mode SVC restore
+	msr	spsr_cxsf, \rpsr
+#if defined(CONFIG_CPU_V6) || defined(CONFIG_CPU_32v6K)
+	@ We must avoid clrex due to Cortex-A15 erratum #830321
+	sub	r0, sp, #4			@ uninhabited address
+	strex	r1, r2, [r0]			@ clear the exclusive monitor
+#endif
+	ldmia	sp, {r0 - pc}^			@ load r0 - pc, cpsr
+#else
+	@ Thumb mode SVC restore
+	ldr	lr, [sp, #S_SP]			@ top of the stack
+	ldrd	r0, r1, [sp, #S_LR]		@ calling lr and pc
+
+	@ We must avoid clrex due to Cortex-A15 erratum #830321
+	strex	r2, r1, [sp, #S_LR]		@ clear the exclusive monitor
+
+	stmdb	lr!, {r0, r1, \rpsr}		@ calling lr and rfe context
+	ldmia	sp, {r0 - r12}
+	mov	sp, lr
+	ldr	lr, [sp], #4
+	rfeia	sp!
+#endif
+	.endm
+
+	@
+	@ svc_exit_via_fiq - like svc_exit but switches to FIQ mode before exit
+	@
+	@ This macro acts in a similar manner to svc_exit but switches to FIQ
+	@ mode to restore the final part of the register state.
+	@
+	@ We cannot use the normal svc_exit procedure because that would
+	@ clobber spsr_svc (FIQ could be delivered during the first few
+	@ instructions of vector_swi meaning its contents have not been
+	@ saved anywhere).
+	@
+	@ Note that, unlike svc_exit, this macro also does not allow a caller
+	@ supplied rpsr. This is because the FIQ exceptions are not re-entrant
+	@ and the handlers cannot call into the scheduler (meaning the value
+	@ on the stack remains correct).
+	@
+	.macro  svc_exit_via_fiq
+	uaccess_exit tsk, r0, r1
+#ifndef CONFIG_THUMB2_KERNEL
+	@ ARM mode restore
+	mov	r0, sp
+	ldmib	r0, {r1 - r14}	@ abort is deadly from here onward (it will
+				@ clobber state restored below)
+	msr	cpsr_c, #FIQ_MODE | PSR_I_BIT | PSR_F_BIT
+	add	r8, r0, #S_PC
+	ldr	r9, [r0, #S_PSR]
+	msr	spsr_cxsf, r9
+	ldr	r0, [r0, #S_R0]
+	ldmia	r8, {pc}^
+#else
+	@ Thumb mode restore
+	add	r0, sp, #S_R2
+	ldr	lr, [sp, #S_LR]
+	ldr	sp, [sp, #S_SP] @ abort is deadly from here onward (it will
+			        @ clobber state restored below)
+	ldmia	r0, {r2 - r12}
+	mov	r1, #FIQ_MODE | PSR_I_BIT | PSR_F_BIT
+	msr	cpsr_c, r1
+	sub	r0, #S_R2
+	add	r8, r0, #S_PC
+	ldmia	r0, {r0 - r1}
+	rfeia	r8
+#endif
+	.endm
+
+
+	.macro	restore_user_regs, fast = 0, offset = 0
+#if defined(CONFIG_CPU_32v6K) && \
+    (!defined(CONFIG_CPU_V6) || defined(CONFIG_SMP))
+#ifdef CONFIG_CPU_V6
+ALT_SMP(nop)
+ALT_UP_B(.L1_\@)
+#endif
+	@ The TLS register update is deferred until return to user space so we
+	@ can use it for other things while running in the kernel
+	mrc	p15, 0, r1, c13, c0, 3		@ get current_thread_info pointer
+	ldr	r1, [r1, #TI_TP_VALUE]
+	mcr	p15, 0, r1, c13, c0, 3		@ set TLS register
+.L1_\@:
+#endif
+
+	uaccess_enable r1, isb=0
+#ifndef CONFIG_THUMB2_KERNEL
+	@ ARM mode restore
+	mov	r2, sp
+	ldr	r1, [r2, #\offset + S_PSR]	@ get calling cpsr
+	ldr	lr, [r2, #\offset + S_PC]!	@ get pc
+	tst	r1, #PSR_I_BIT | 0x0f
+	bne	1f
+	msr	spsr_cxsf, r1			@ save in spsr_svc
+#if defined(CONFIG_CPU_V6) || defined(CONFIG_CPU_32v6K)
+	@ We must avoid clrex due to Cortex-A15 erratum #830321
+	strex	r1, r2, [r2]			@ clear the exclusive monitor
+#endif
+	.if	\fast
+	ldmdb	r2, {r1 - lr}^			@ get calling r1 - lr
+	.else
+	ldmdb	r2, {r0 - lr}^			@ get calling r0 - lr
+	.endif
+	mov	r0, r0				@ ARMv5T and earlier require a nop
+						@ after ldm {}^
+	add	sp, sp, #\offset + PT_REGS_SIZE
+	movs	pc, lr				@ return & move spsr_svc into cpsr
+1:	bug	"Returning to usermode but unexpected PSR bits set?", \@
+#elif defined(CONFIG_CPU_V7M)
+	@ V7M restore.
+	@ Note that we don't need to do clrex here as clearing the local
+	@ monitor is part of the exception entry and exit sequence.
+	.if	\offset
+	add	sp, #\offset
+	.endif
+	v7m_exception_slow_exit ret_r0 = \fast
+#else
+	@ Thumb mode restore
+	mov	r2, sp
+	load_user_sp_lr r2, r3, \offset + S_SP	@ calling sp, lr
+	ldr	r1, [sp, #\offset + S_PSR]	@ get calling cpsr
+	ldr	lr, [sp, #\offset + S_PC]	@ get pc
+	add	sp, sp, #\offset + S_SP
+	tst	r1, #PSR_I_BIT | 0x0f
+	bne	1f
+	msr	spsr_cxsf, r1			@ save in spsr_svc
+
+	@ We must avoid clrex due to Cortex-A15 erratum #830321
+	strex	r1, r2, [sp]			@ clear the exclusive monitor
+
+	.if	\fast
+	ldmdb	sp, {r1 - r12}			@ get calling r1 - r12
+	.else
+	ldmdb	sp, {r0 - r12}			@ get calling r0 - r12
+	.endif
+	add	sp, sp, #PT_REGS_SIZE - S_SP
+	movs	pc, lr				@ return & move spsr_svc into cpsr
+1:	bug	"Returning to usermode but unexpected PSR bits set?", \@
+#endif	/* !CONFIG_THUMB2_KERNEL */
+	.endm
+
+/*
+ * Context tracking subsystem.  Used to instrument transitions
+ * between user and kernel mode.
+ */
+	.macro ct_user_exit, save = 1
+#ifdef CONFIG_CONTEXT_TRACKING_USER
+	.if	\save
+	stmdb   sp!, {r0-r3, ip, lr}
+	bl	user_exit_callable
+	ldmia	sp!, {r0-r3, ip, lr}
+	.else
+	bl	user_exit_callable
+	.endif
+#endif
+	.endm
+
+	.macro ct_user_enter, save = 1
+#ifdef CONFIG_CONTEXT_TRACKING_USER
+	.if	\save
+	stmdb   sp!, {r0-r3, ip, lr}
+	bl	user_enter_callable
+	ldmia	sp!, {r0-r3, ip, lr}
+	.else
+	bl	user_enter_callable
+	.endif
+#endif
+	.endm
+
+	.macro	invoke_syscall, table, nr, tmp, ret, reload=0
+#ifdef CONFIG_CPU_SPECTRE
+	mov	\tmp, \nr
+	cmp	\tmp, #NR_syscalls		@ check upper syscall limit
+	movcs	\tmp, #0
+	csdb
+	badr	lr, \ret			@ return address
+	.if	\reload
+	add	r1, sp, #S_R0 + S_OFF		@ pointer to regs
+	ldmiacc	r1, {r0 - r6}			@ reload r0-r6
+	stmiacc	sp, {r4, r5}			@ update stack arguments
+	.endif
+	ldrcc	pc, [\table, \tmp, lsl #2]	@ call sys_* routine
+#else
+	cmp	\nr, #NR_syscalls		@ check upper syscall limit
+	badr	lr, \ret			@ return address
+	.if	\reload
+	add	r1, sp, #S_R0 + S_OFF		@ pointer to regs
+	ldmiacc	r1, {r0 - r6}			@ reload r0-r6
+	stmiacc	sp, {r4, r5}			@ update stack arguments
+	.endif
+	ldrcc	pc, [\table, \nr, lsl #2]	@ call sys_* routine
+#endif
+	.endm
+
+/*
+ * These are the registers used in the syscall handler, and allow us to
+ * have in theory up to 7 arguments to a function - r0 to r6.
+ *
+ * r7 is reserved for the system call number for thumb mode.
+ *
+ * Note that tbl == why is intentional.
+ *
+ * We must set at least "tsk" and "why" when calling ret_with_reschedule.
+ */
+scno	.req	r7		@ syscall number
+tbl	.req	r8		@ syscall table pointer
+why	.req	r8		@ Linux syscall (!= 0)
+tsk	.req	r9		@ current thread_info
+
+	.macro	do_overflow_check, frame_size:req
+#ifdef CONFIG_VMAP_STACK
+	@
+	@ Test whether the SP has overflowed. Task and IRQ stacks are aligned
+	@ so that SP & BIT(THREAD_SIZE_ORDER + PAGE_SHIFT) should always be
+	@ zero.
+	@
+ARM(	tst	sp, #1 << (THREAD_SIZE_ORDER + PAGE_SHIFT)	)
+THUMB(	tst	r1, #1 << (THREAD_SIZE_ORDER + PAGE_SHIFT)	)
+THUMB(	it	ne						)
+	bne	.Lstack_overflow_check\@
+
+	.pushsection	.text
+.Lstack_overflow_check\@:
+	@
+	@ The stack pointer is not pointing to a valid vmap'ed stack, but it
+	@ may be pointing into the linear map instead, which may happen if we
+	@ are already running from the overflow stack. We cannot detect overflow
+	@ in such cases so just carry on.
+	@
+	str	ip, [r0, #12]			@ Stash IP on the mode stack
+	ldr_va	ip, high_memory			@ Start of VMALLOC space
+ARM(	cmp	sp, ip			)	@ SP in vmalloc space?
+THUMB(	cmp	r1, ip			)
+THUMB(	itt	lo			)
+	ldrlo	ip, [r0, #12]			@ Restore IP
+	blo	.Lout\@				@ Carry on
+
+THUMB(	sub	r1, sp, r1		)	@ Restore original R1
+THUMB(	sub	sp, r1			)	@ Restore original SP
+	add	sp, sp, #\frame_size		@ Undo svc_entry's SP change
+	b	__bad_stack			@ Handle VMAP stack overflow
+	.popsection
+.Lout\@:
+#endif
+	.endm