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, 1043 insertions, 0 deletions

diff --git a/arch/arm/crypto/aes-neonbs-core.S b/arch/arm/crypto/aes-neonbs-core.S
new file mode 100644
index 000000000..7b61032f2
--- /dev/null
+++ b/arch/arm/crypto/aes-neonbs-core.S
@@ -0,0 +1,1043 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Bit sliced AES using NEON instructions
+ *
+ * Copyright (C) 2017 Linaro Ltd.
+ * Author: Ard Biesheuvel <ard.biesheuvel@linaro.org>
+ */
+
+/*
+ * The algorithm implemented here is described in detail by the paper
+ * 'Faster and Timing-Attack Resistant AES-GCM' by Emilia Kaesper and
+ * Peter Schwabe (https://eprint.iacr.org/2009/129.pdf)
+ *
+ * This implementation is based primarily on the OpenSSL implementation
+ * for 32-bit ARM written by Andy Polyakov <appro@openssl.org>
+ */
+
+#include <linux/linkage.h>
+#include <asm/assembler.h>
+
+	.text
+	.fpu		neon
+
+	rounds		.req	ip
+	bskey		.req	r4
+
+	q0l		.req	d0
+	q0h		.req	d1
+	q1l		.req	d2
+	q1h		.req	d3
+	q2l		.req	d4
+	q2h		.req	d5
+	q3l		.req	d6
+	q3h		.req	d7
+	q4l		.req	d8
+	q4h		.req	d9
+	q5l		.req	d10
+	q5h		.req	d11
+	q6l		.req	d12
+	q6h		.req	d13
+	q7l		.req	d14
+	q7h		.req	d15
+	q8l		.req	d16
+	q8h		.req	d17
+	q9l		.req	d18
+	q9h		.req	d19
+	q10l		.req	d20
+	q10h		.req	d21
+	q11l		.req	d22
+	q11h		.req	d23
+	q12l		.req	d24
+	q12h		.req	d25
+	q13l		.req	d26
+	q13h		.req	d27
+	q14l		.req	d28
+	q14h		.req	d29
+	q15l		.req	d30
+	q15h		.req	d31
+
+	.macro		__tbl, out, tbl, in, tmp
+	.ifc		\out, \tbl
+	.ifb		\tmp
+	.error		__tbl needs temp register if out == tbl
+	.endif
+	vmov		\tmp, \out
+	.endif
+	vtbl.8		\out\()l, {\tbl}, \in\()l
+	.ifc		\out, \tbl
+	vtbl.8		\out\()h, {\tmp}, \in\()h
+	.else
+	vtbl.8		\out\()h, {\tbl}, \in\()h
+	.endif
+	.endm
+
+	.macro		__ldr, out, sym
+	vldr		\out\()l, \sym
+	vldr		\out\()h, \sym + 8
+	.endm
+
+	.macro		in_bs_ch, b0, b1, b2, b3, b4, b5, b6, b7
+	veor		\b2, \b2, \b1
+	veor		\b5, \b5, \b6
+	veor		\b3, \b3, \b0
+	veor		\b6, \b6, \b2
+	veor		\b5, \b5, \b0
+	veor		\b6, \b6, \b3
+	veor		\b3, \b3, \b7
+	veor		\b7, \b7, \b5
+	veor		\b3, \b3, \b4
+	veor		\b4, \b4, \b5
+	veor		\b2, \b2, \b7
+	veor		\b3, \b3, \b1
+	veor		\b1, \b1, \b5
+	.endm
+
+	.macro		out_bs_ch, b0, b1, b2, b3, b4, b5, b6, b7
+	veor		\b0, \b0, \b6
+	veor		\b1, \b1, \b4
+	veor		\b4, \b4, \b6
+	veor		\b2, \b2, \b0
+	veor		\b6, \b6, \b1
+	veor		\b1, \b1, \b5
+	veor		\b5, \b5, \b3
+	veor		\b3, \b3, \b7
+	veor		\b7, \b7, \b5
+	veor		\b2, \b2, \b5
+	veor		\b4, \b4, \b7
+	.endm
+
+	.macro		inv_in_bs_ch, b6, b1, b2, b4, b7, b0, b3, b5
+	veor		\b1, \b1, \b7
+	veor		\b4, \b4, \b7
+	veor		\b7, \b7, \b5
+	veor		\b1, \b1, \b3
+	veor		\b2, \b2, \b5
+	veor		\b3, \b3, \b7
+	veor		\b6, \b6, \b1
+	veor		\b2, \b2, \b0
+	veor		\b5, \b5, \b3
+	veor		\b4, \b4, \b6
+	veor		\b0, \b0, \b6
+	veor		\b1, \b1, \b4
+	.endm
+
+	.macro		inv_out_bs_ch, b6, b5, b0, b3, b7, b1, b4, b2
+	veor		\b1, \b1, \b5
+	veor		\b2, \b2, \b7
+	veor		\b3, \b3, \b1
+	veor		\b4, \b4, \b5
+	veor		\b7, \b7, \b5
+	veor		\b3, \b3, \b4
+	veor 		\b5, \b5, \b0
+	veor		\b3, \b3, \b7
+	veor		\b6, \b6, \b2
+	veor		\b2, \b2, \b1
+	veor		\b6, \b6, \b3
+	veor		\b3, \b3, \b0
+	veor		\b5, \b5, \b6
+	.endm
+
+	.macro		mul_gf4, x0, x1, y0, y1, t0, t1
+	veor 		\t0, \y0, \y1
+	vand		\t0, \t0, \x0
+	veor		\x0, \x0, \x1
+	vand		\t1, \x1, \y0
+	vand		\x0, \x0, \y1
+	veor		\x1, \t1, \t0
+	veor		\x0, \x0, \t1
+	.endm
+
+	.macro		mul_gf4_n_gf4, x0, x1, y0, y1, t0, x2, x3, y2, y3, t1
+	veor		\t0, \y0, \y1
+	veor 		\t1, \y2, \y3
+	vand		\t0, \t0, \x0
+	vand		\t1, \t1, \x2
+	veor		\x0, \x0, \x1
+	veor		\x2, \x2, \x3
+	vand		\x1, \x1, \y0
+	vand		\x3, \x3, \y2
+	vand		\x0, \x0, \y1
+	vand		\x2, \x2, \y3
+	veor		\x1, \x1, \x0
+	veor		\x2, \x2, \x3
+	veor		\x0, \x0, \t0
+	veor		\x3, \x3, \t1
+	.endm
+
+	.macro		mul_gf16_2, x0, x1, x2, x3, x4, x5, x6, x7, \
+				    y0, y1, y2, y3, t0, t1, t2, t3
+	veor		\t0, \x0, \x2
+	veor		\t1, \x1, \x3
+	mul_gf4  	\x0, \x1, \y0, \y1, \t2, \t3
+	veor		\y0, \y0, \y2
+	veor		\y1, \y1, \y3
+	mul_gf4_n_gf4	\t0, \t1, \y0, \y1, \t3, \x2, \x3, \y2, \y3, \t2
+	veor		\x0, \x0, \t0
+	veor		\x2, \x2, \t0
+	veor		\x1, \x1, \t1
+	veor		\x3, \x3, \t1
+	veor		\t0, \x4, \x6
+	veor		\t1, \x5, \x7
+	mul_gf4_n_gf4	\t0, \t1, \y0, \y1, \t3, \x6, \x7, \y2, \y3, \t2
+	veor		\y0, \y0, \y2
+	veor		\y1, \y1, \y3
+	mul_gf4  	\x4, \x5, \y0, \y1, \t2, \t3
+	veor		\x4, \x4, \t0
+	veor		\x6, \x6, \t0
+	veor		\x5, \x5, \t1
+	veor		\x7, \x7, \t1
+	.endm
+
+	.macro		inv_gf256, x0, x1, x2, x3, x4, x5, x6, x7, \
+				   t0, t1, t2, t3, s0, s1, s2, s3
+	veor		\t3, \x4, \x6
+	veor		\t0, \x5, \x7
+	veor		\t1, \x1, \x3
+	veor		\s1, \x7, \x6
+	veor		\s0, \x0, \x2
+	veor		\s3, \t3, \t0
+	vorr		\t2, \t0, \t1
+	vand		\s2, \t3, \s0
+	vorr		\t3, \t3, \s0
+	veor		\s0, \s0, \t1
+	vand		\t0, \t0, \t1
+	veor		\t1, \x3, \x2
+	vand		\s3, \s3, \s0
+	vand		\s1, \s1, \t1
+	veor		\t1, \x4, \x5
+	veor		\s0, \x1, \x0
+	veor		\t3, \t3, \s1
+	veor		\t2, \t2, \s1
+	vand		\s1, \t1, \s0
+	vorr		\t1, \t1, \s0
+	veor		\t3, \t3, \s3
+	veor		\t0, \t0, \s1
+	veor		\t2, \t2, \s2
+	veor		\t1, \t1, \s3
+	veor		\t0, \t0, \s2
+	vand		\s0, \x7, \x3
+	veor		\t1, \t1, \s2
+	vand		\s1, \x6, \x2
+	vand		\s2, \x5, \x1
+	vorr		\s3, \x4, \x0
+	veor		\t3, \t3, \s0
+	veor		\t1, \t1, \s2
+	veor		\s0, \t0, \s3
+	veor		\t2, \t2, \s1
+	vand		\s2, \t3, \t1
+	veor		\s1, \t2, \s2
+	veor		\s3, \s0, \s2
+	vbsl		\s1, \t1, \s0
+	vmvn		\t0, \s0
+	vbsl		\s0, \s1, \s3
+	vbsl		\t0, \s1, \s3
+	vbsl		\s3, \t3, \t2
+	veor		\t3, \t3, \t2
+	vand		\s2, \s0, \s3
+	veor		\t1, \t1, \t0
+	veor		\s2, \s2, \t3
+	mul_gf16_2	\x0, \x1, \x2, \x3, \x4, \x5, \x6, \x7, \
+			\s3, \s2, \s1, \t1, \s0, \t0, \t2, \t3
+	.endm
+
+	.macro		sbox, b0, b1, b2, b3, b4, b5, b6, b7, \
+			      t0, t1, t2, t3, s0, s1, s2, s3
+	in_bs_ch	\b0, \b1, \b2, \b3, \b4, \b5, \b6, \b7
+	inv_gf256	\b6, \b5, \b0, \b3, \b7, \b1, \b4, \b2, \
+			\t0, \t1, \t2, \t3, \s0, \s1, \s2, \s3
+	out_bs_ch	\b7, \b1, \b4, \b2, \b6, \b5, \b0, \b3
+	.endm
+
+	.macro		inv_sbox, b0, b1, b2, b3, b4, b5, b6, b7, \
+				  t0, t1, t2, t3, s0, s1, s2, s3
+	inv_in_bs_ch	\b0, \b1, \b2, \b3, \b4, \b5, \b6, \b7
+	inv_gf256	\b5, \b1, \b2, \b6, \b3, \b7, \b0, \b4, \
+			\t0, \t1, \t2, \t3, \s0, \s1, \s2, \s3
+	inv_out_bs_ch	\b3, \b7, \b0, \b4, \b5, \b1, \b2, \b6
+	.endm
+
+	.macro		shift_rows, x0, x1, x2, x3, x4, x5, x6, x7, \
+				    t0, t1, t2, t3, mask
+	vld1.8		{\t0-\t1}, [bskey, :256]!
+	veor		\t0, \t0, \x0
+	vld1.8		{\t2-\t3}, [bskey, :256]!
+	veor		\t1, \t1, \x1
+	__tbl		\x0, \t0, \mask
+	veor		\t2, \t2, \x2
+	__tbl		\x1, \t1, \mask
+	vld1.8		{\t0-\t1}, [bskey, :256]!
+	veor		\t3, \t3, \x3
+	__tbl		\x2, \t2, \mask
+	__tbl		\x3, \t3, \mask
+	vld1.8		{\t2-\t3}, [bskey, :256]!
+	veor		\t0, \t0, \x4
+	veor		\t1, \t1, \x5
+	__tbl		\x4, \t0, \mask
+	veor		\t2, \t2, \x6
+	__tbl		\x5, \t1, \mask
+	veor		\t3, \t3, \x7
+	__tbl		\x6, \t2, \mask
+	__tbl		\x7, \t3, \mask
+	.endm
+
+	.macro		inv_shift_rows, x0, x1, x2, x3, x4, x5, x6, x7, \
+					t0, t1, t2, t3, mask
+	__tbl		\x0, \x0, \mask, \t0
+	__tbl		\x1, \x1, \mask, \t1
+	__tbl		\x2, \x2, \mask, \t2
+	__tbl		\x3, \x3, \mask, \t3
+	__tbl		\x4, \x4, \mask, \t0
+	__tbl		\x5, \x5, \mask, \t1
+	__tbl		\x6, \x6, \mask, \t2
+	__tbl		\x7, \x7, \mask, \t3
+	.endm
+
+	.macro		mix_cols, x0, x1, x2, x3, x4, x5, x6, x7, \
+				  t0, t1, t2, t3, t4, t5, t6, t7, inv
+	vext.8		\t0, \x0, \x0, #12
+	vext.8		\t1, \x1, \x1, #12
+	veor		\x0, \x0, \t0
+	vext.8		\t2, \x2, \x2, #12
+	veor		\x1, \x1, \t1
+	vext.8		\t3, \x3, \x3, #12
+	veor		\x2, \x2, \t2
+	vext.8		\t4, \x4, \x4, #12
+	veor		\x3, \x3, \t3
+	vext.8		\t5, \x5, \x5, #12
+	veor		\x4, \x4, \t4
+	vext.8		\t6, \x6, \x6, #12
+	veor		\x5, \x5, \t5
+	vext.8		\t7, \x7, \x7, #12
+	veor		\x6, \x6, \t6
+	veor		\t1, \t1, \x0
+	veor.8		\x7, \x7, \t7
+	vext.8		\x0, \x0, \x0, #8
+	veor		\t2, \t2, \x1
+	veor		\t0, \t0, \x7
+	veor		\t1, \t1, \x7
+	vext.8		\x1, \x1, \x1, #8
+	veor		\t5, \t5, \x4
+	veor		\x0, \x0, \t0
+	veor		\t6, \t6, \x5
+	veor		\x1, \x1, \t1
+	vext.8		\t0, \x4, \x4, #8
+	veor		\t4, \t4, \x3
+	vext.8		\t1, \x5, \x5, #8
+	veor		\t7, \t7, \x6
+	vext.8		\x4, \x3, \x3, #8
+	veor		\t3, \t3, \x2
+	vext.8		\x5, \x7, \x7, #8
+	veor		\t4, \t4, \x7
+	vext.8		\x3, \x6, \x6, #8
+	veor		\t3, \t3, \x7
+	vext.8		\x6, \x2, \x2, #8
+	veor		\x7, \t1, \t5
+	.ifb		\inv
+	veor		\x2, \t0, \t4
+	veor		\x4, \x4, \t3
+	veor		\x5, \x5, \t7
+	veor		\x3, \x3, \t6
+	veor		\x6, \x6, \t2
+	.else
+	veor		\t3, \t3, \x4
+	veor		\x5, \x5, \t7
+	veor		\x2, \x3, \t6
+	veor		\x3, \t0, \t4
+	veor		\x4, \x6, \t2
+	vmov		\x6, \t3
+	.endif
+	.endm
+
+	.macro		inv_mix_cols, x0, x1, x2, x3, x4, x5, x6, x7, \
+				      t0, t1, t2, t3, t4, t5, t6, t7
+	vld1.8		{\t0-\t1}, [bskey, :256]!
+	veor		\x0, \x0, \t0
+	vld1.8		{\t2-\t3}, [bskey, :256]!
+	veor		\x1, \x1, \t1
+	vld1.8		{\t4-\t5}, [bskey, :256]!
+	veor		\x2, \x2, \t2
+	vld1.8		{\t6-\t7}, [bskey, :256]
+	sub		bskey, bskey, #224
+	veor		\x3, \x3, \t3
+	veor		\x4, \x4, \t4
+	veor		\x5, \x5, \t5
+	veor		\x6, \x6, \t6
+	veor		\x7, \x7, \t7
+	vext.8		\t0, \x0, \x0, #8
+	vext.8		\t6, \x6, \x6, #8
+	vext.8		\t7, \x7, \x7, #8
+	veor		\t0, \t0, \x0
+	vext.8		\t1, \x1, \x1, #8
+	veor		\t6, \t6, \x6
+	vext.8		\t2, \x2, \x2, #8
+	veor		\t7, \t7, \x7
+	vext.8		\t3, \x3, \x3, #8
+	veor		\t1, \t1, \x1
+	vext.8		\t4, \x4, \x4, #8
+	veor		\t2, \t2, \x2
+	vext.8		\t5, \x5, \x5, #8
+	veor		\t3, \t3, \x3
+	veor		\t4, \t4, \x4
+	veor		\t5, \t5, \x5
+	veor		\x0, \x0, \t6
+	veor		\x1, \x1, \t6
+	veor		\x2, \x2, \t0
+	veor		\x4, \x4, \t2
+	veor		\x3, \x3, \t1
+	veor		\x1, \x1, \t7
+	veor		\x2, \x2, \t7
+	veor		\x4, \x4, \t6
+	veor		\x5, \x5, \t3
+	veor		\x3, \x3, \t6
+	veor		\x6, \x6, \t4
+	veor		\x4, \x4, \t7
+	veor		\x5, \x5, \t7
+	veor		\x7, \x7, \t5
+	mix_cols	\x0, \x1, \x2, \x3, \x4, \x5, \x6, \x7, \
+			\t0, \t1, \t2, \t3, \t4, \t5, \t6, \t7, 1
+	.endm
+
+	.macro		swapmove_2x, a0, b0, a1, b1, n, mask, t0, t1
+	vshr.u64	\t0, \b0, #\n
+	vshr.u64	\t1, \b1, #\n
+	veor		\t0, \t0, \a0
+	veor		\t1, \t1, \a1
+	vand		\t0, \t0, \mask
+	vand		\t1, \t1, \mask
+	veor		\a0, \a0, \t0
+	vshl.s64	\t0, \t0, #\n
+	veor		\a1, \a1, \t1
+	vshl.s64	\t1, \t1, #\n
+	veor		\b0, \b0, \t0
+	veor		\b1, \b1, \t1
+	.endm
+
+	.macro		bitslice, x7, x6, x5, x4, x3, x2, x1, x0, t0, t1, t2, t3
+	vmov.i8		\t0, #0x55
+	vmov.i8		\t1, #0x33
+	swapmove_2x	\x0, \x1, \x2, \x3, 1, \t0, \t2, \t3
+	swapmove_2x	\x4, \x5, \x6, \x7, 1, \t0, \t2, \t3
+	vmov.i8		\t0, #0x0f
+	swapmove_2x	\x0, \x2, \x1, \x3, 2, \t1, \t2, \t3
+	swapmove_2x	\x4, \x6, \x5, \x7, 2, \t1, \t2, \t3
+	swapmove_2x	\x0, \x4, \x1, \x5, 4, \t0, \t2, \t3
+	swapmove_2x	\x2, \x6, \x3, \x7, 4, \t0, \t2, \t3
+	.endm
+
+	.align		4
+M0:	.quad		0x02060a0e03070b0f, 0x0004080c0105090d
+
+	/*
+	 * void aesbs_convert_key(u8 out[], u32 const rk[], int rounds)
+	 */
+ENTRY(aesbs_convert_key)
+	vld1.32		{q7}, [r1]!		// load round 0 key
+	vld1.32		{q15}, [r1]!		// load round 1 key
+
+	vmov.i8		q8,  #0x01		// bit masks
+	vmov.i8		q9,  #0x02
+	vmov.i8		q10, #0x04
+	vmov.i8		q11, #0x08
+	vmov.i8		q12, #0x10
+	vmov.i8		q13, #0x20
+	__ldr		q14, M0
+
+	sub		r2, r2, #1
+	vst1.8		{q7}, [r0, :128]!	// save round 0 key
+
+.Lkey_loop:
+	__tbl		q7, q15, q14
+	vmov.i8		q6, #0x40
+	vmov.i8		q15, #0x80
+
+	vtst.8		q0, q7, q8
+	vtst.8		q1, q7, q9
+	vtst.8		q2, q7, q10
+	vtst.8		q3, q7, q11
+	vtst.8		q4, q7, q12
+	vtst.8		q5, q7, q13
+	vtst.8		q6, q7, q6
+	vtst.8		q7, q7, q15
+	vld1.32		{q15}, [r1]!		// load next round key
+	vmvn		q0, q0
+	vmvn		q1, q1
+	vmvn		q5, q5
+	vmvn		q6, q6
+
+	subs		r2, r2, #1
+	vst1.8		{q0-q1}, [r0, :256]!
+	vst1.8		{q2-q3}, [r0, :256]!
+	vst1.8		{q4-q5}, [r0, :256]!
+	vst1.8		{q6-q7}, [r0, :256]!
+	bne		.Lkey_loop
+
+	vmov.i8		q7, #0x63		// compose .L63
+	veor		q15, q15, q7
+	vst1.8		{q15}, [r0, :128]
+	bx		lr
+ENDPROC(aesbs_convert_key)
+
+	.align		4
+M0SR:	.quad		0x0a0e02060f03070b, 0x0004080c05090d01
+
+aesbs_encrypt8:
+	vld1.8		{q9}, [bskey, :128]!	// round 0 key
+	__ldr		q8, M0SR
+
+	veor		q10, q0, q9		// xor with round0 key
+	veor		q11, q1, q9
+	__tbl		q0, q10, q8
+	veor		q12, q2, q9
+	__tbl		q1, q11, q8
+	veor		q13, q3, q9
+	__tbl		q2, q12, q8
+	veor		q14, q4, q9
+	__tbl		q3, q13, q8
+	veor		q15, q5, q9
+	__tbl		q4, q14, q8
+	veor		q10, q6, q9
+	__tbl		q5, q15, q8
+	veor		q11, q7, q9
+	__tbl		q6, q10, q8
+	__tbl		q7, q11, q8
+
+	bitslice	q0, q1, q2, q3, q4, q5, q6, q7, q8, q9, q10, q11
+
+	sub		rounds, rounds, #1
+	b		.Lenc_sbox
+
+	.align		5
+SR:	.quad		0x0504070600030201, 0x0f0e0d0c0a09080b
+SRM0:	.quad		0x0304090e00050a0f, 0x01060b0c0207080d
+
+.Lenc_last:
+	__ldr		q12, SRM0
+.Lenc_loop:
+	shift_rows	q0, q1, q2, q3, q4, q5, q6, q7, q8, q9, q10, q11, q12
+.Lenc_sbox:
+	sbox		q0, q1, q2, q3, q4, q5, q6, q7, q8, q9, q10, q11, q12, \
+								q13, q14, q15
+	subs		rounds, rounds, #1
+	bcc		.Lenc_done
+
+	mix_cols	q0, q1, q4, q6, q3, q7, q2, q5, q8, q9, q10, q11, q12, \
+								q13, q14, q15
+
+	beq		.Lenc_last
+	__ldr		q12, SR
+	b		.Lenc_loop
+
+.Lenc_done:
+	vld1.8		{q12}, [bskey, :128]	// last round key
+
+	bitslice	q0, q1, q4, q6, q3, q7, q2, q5, q8, q9, q10, q11
+
+	veor		q0, q0, q12
+	veor		q1, q1, q12
+	veor		q4, q4, q12
+	veor		q6, q6, q12
+	veor		q3, q3, q12
+	veor		q7, q7, q12
+	veor		q2, q2, q12
+	veor		q5, q5, q12
+	bx		lr
+ENDPROC(aesbs_encrypt8)
+
+	.align		4
+M0ISR:	.quad		0x0a0e0206070b0f03, 0x0004080c0d010509
+
+aesbs_decrypt8:
+	add		bskey, bskey, rounds, lsl #7
+	sub		bskey, bskey, #112
+	vld1.8		{q9}, [bskey, :128]	// round 0 key
+	sub		bskey, bskey, #128
+	__ldr		q8, M0ISR
+
+	veor		q10, q0, q9		// xor with round0 key
+	veor		q11, q1, q9
+	__tbl		q0, q10, q8
+	veor		q12, q2, q9
+	__tbl		q1, q11, q8
+	veor		q13, q3, q9
+	__tbl		q2, q12, q8
+	veor		q14, q4, q9
+	__tbl		q3, q13, q8
+	veor		q15, q5, q9
+	__tbl		q4, q14, q8
+	veor		q10, q6, q9
+	__tbl		q5, q15, q8
+	veor		q11, q7, q9
+	__tbl		q6, q10, q8
+	__tbl		q7, q11, q8
+
+	bitslice	q0, q1, q2, q3, q4, q5, q6, q7, q8, q9, q10, q11
+
+	sub		rounds, rounds, #1
+	b		.Ldec_sbox
+
+	.align		5
+ISR:	.quad		0x0504070602010003, 0x0f0e0d0c080b0a09
+ISRM0:	.quad		0x01040b0e0205080f, 0x0306090c00070a0d
+
+.Ldec_last:
+	__ldr		q12, ISRM0
+.Ldec_loop:
+	inv_shift_rows	q0, q1, q2, q3, q4, q5, q6, q7, q8, q9, q10, q11, q12
+.Ldec_sbox:
+	inv_sbox	q0, q1, q2, q3, q4, q5, q6, q7, q8, q9, q10, q11, q12, \
+								q13, q14, q15
+	subs		rounds, rounds, #1
+	bcc		.Ldec_done
+
+	inv_mix_cols	q0, q1, q6, q4, q2, q7, q3, q5, q8, q9, q10, q11, q12, \
+								q13, q14, q15
+
+	beq		.Ldec_last
+	__ldr		q12, ISR
+	b		.Ldec_loop
+
+.Ldec_done:
+	add		bskey, bskey, #112
+	vld1.8		{q12}, [bskey, :128]	// last round key
+
+	bitslice	q0, q1, q6, q4, q2, q7, q3, q5, q8, q9, q10, q11
+
+	veor		q0, q0, q12
+	veor		q1, q1, q12
+	veor		q6, q6, q12
+	veor		q4, q4, q12
+	veor		q2, q2, q12
+	veor		q7, q7, q12
+	veor		q3, q3, q12
+	veor		q5, q5, q12
+	bx		lr
+ENDPROC(aesbs_decrypt8)
+
+	/*
+	 * aesbs_ecb_encrypt(u8 out[], u8 const in[], u8 const rk[], int rounds,
+	 *		     int blocks)
+	 * aesbs_ecb_decrypt(u8 out[], u8 const in[], u8 const rk[], int rounds,
+	 *		     int blocks)
+	 */
+	.macro		__ecb_crypt, do8, o0, o1, o2, o3, o4, o5, o6, o7
+	push		{r4-r6, lr}
+	ldr		r5, [sp, #16]		// number of blocks
+
+99:	adr		ip, 0f
+	and		lr, r5, #7
+	cmp		r5, #8
+	sub		ip, ip, lr, lsl #2
+	movlt		pc, ip			// computed goto if blocks < 8
+
+	vld1.8		{q0}, [r1]!
+	vld1.8		{q1}, [r1]!
+	vld1.8		{q2}, [r1]!
+	vld1.8		{q3}, [r1]!
+	vld1.8		{q4}, [r1]!
+	vld1.8		{q5}, [r1]!
+	vld1.8		{q6}, [r1]!
+	vld1.8		{q7}, [r1]!
+
+0:	mov		bskey, r2
+	mov		rounds, r3
+	bl		\do8
+
+	adr		ip, 1f
+	and		lr, r5, #7
+	cmp		r5, #8
+	sub		ip, ip, lr, lsl #2
+	movlt		pc, ip			// computed goto if blocks < 8
+
+	vst1.8		{\o0}, [r0]!
+	vst1.8		{\o1}, [r0]!
+	vst1.8		{\o2}, [r0]!
+	vst1.8		{\o3}, [r0]!
+	vst1.8		{\o4}, [r0]!
+	vst1.8		{\o5}, [r0]!
+	vst1.8		{\o6}, [r0]!
+	vst1.8		{\o7}, [r0]!
+
+1:	subs		r5, r5, #8
+	bgt		99b
+
+	pop		{r4-r6, pc}
+	.endm
+
+	.align		4
+ENTRY(aesbs_ecb_encrypt)
+	__ecb_crypt	aesbs_encrypt8, q0, q1, q4, q6, q3, q7, q2, q5
+ENDPROC(aesbs_ecb_encrypt)
+
+	.align		4
+ENTRY(aesbs_ecb_decrypt)
+	__ecb_crypt	aesbs_decrypt8, q0, q1, q6, q4, q2, q7, q3, q5
+ENDPROC(aesbs_ecb_decrypt)
+
+	/*
+	 * aesbs_cbc_decrypt(u8 out[], u8 const in[], u8 const rk[],
+	 *		     int rounds, int blocks, u8 iv[])
+	 */
+	.align		4
+ENTRY(aesbs_cbc_decrypt)
+	mov		ip, sp
+	push		{r4-r6, lr}
+	ldm		ip, {r5-r6}		// load args 4-5
+
+99:	adr		ip, 0f
+	and		lr, r5, #7
+	cmp		r5, #8
+	sub		ip, ip, lr, lsl #2
+	mov		lr, r1
+	movlt		pc, ip			// computed goto if blocks < 8
+
+	vld1.8		{q0}, [lr]!
+	vld1.8		{q1}, [lr]!
+	vld1.8		{q2}, [lr]!
+	vld1.8		{q3}, [lr]!
+	vld1.8		{q4}, [lr]!
+	vld1.8		{q5}, [lr]!
+	vld1.8		{q6}, [lr]!
+	vld1.8		{q7}, [lr]
+
+0:	mov		bskey, r2
+	mov		rounds, r3
+	bl		aesbs_decrypt8
+
+	vld1.8		{q8}, [r6]
+	vmov		q9, q8
+	vmov		q10, q8
+	vmov		q11, q8
+	vmov		q12, q8
+	vmov		q13, q8
+	vmov		q14, q8
+	vmov		q15, q8
+
+	adr		ip, 1f
+	and		lr, r5, #7
+	cmp		r5, #8
+	sub		ip, ip, lr, lsl #2
+	movlt		pc, ip			// computed goto if blocks < 8
+
+	vld1.8		{q9}, [r1]!
+	vld1.8		{q10}, [r1]!
+	vld1.8		{q11}, [r1]!
+	vld1.8		{q12}, [r1]!
+	vld1.8		{q13}, [r1]!
+	vld1.8		{q14}, [r1]!
+	vld1.8		{q15}, [r1]!
+	W(nop)
+
+1:	adr		ip, 2f
+	sub		ip, ip, lr, lsl #3
+	movlt		pc, ip			// computed goto if blocks < 8
+
+	veor		q0, q0, q8
+	vst1.8		{q0}, [r0]!
+	veor		q1, q1, q9
+	vst1.8		{q1}, [r0]!
+	veor		q6, q6, q10
+	vst1.8		{q6}, [r0]!
+	veor		q4, q4, q11
+	vst1.8		{q4}, [r0]!
+	veor		q2, q2, q12
+	vst1.8		{q2}, [r0]!
+	veor		q7, q7, q13
+	vst1.8		{q7}, [r0]!
+	veor		q3, q3, q14
+	vst1.8		{q3}, [r0]!
+	veor		q5, q5, q15
+	vld1.8		{q8}, [r1]!		// load next round's iv
+2:	vst1.8		{q5}, [r0]!
+
+	subs		r5, r5, #8
+	vst1.8		{q8}, [r6]		// store next round's iv
+	bgt		99b
+
+	pop		{r4-r6, pc}
+ENDPROC(aesbs_cbc_decrypt)
+
+	.macro		next_ctr, q
+	vmov		\q\()h, r9, r10
+	adds		r10, r10, #1
+	adcs		r9, r9, #0
+	vmov		\q\()l, r7, r8
+	adcs		r8, r8, #0
+	adc		r7, r7, #0
+	vrev32.8	\q, \q
+	.endm
+
+	/*
+	 * aesbs_ctr_encrypt(u8 out[], u8 const in[], u8 const rk[],
+	 *		     int rounds, int bytes, u8 ctr[])
+	 */
+ENTRY(aesbs_ctr_encrypt)
+	mov		ip, sp
+	push		{r4-r10, lr}
+
+	ldm		ip, {r5, r6}		// load args 4-5
+	vld1.8		{q0}, [r6]		// load counter
+	vrev32.8	q1, q0
+	vmov		r9, r10, d3
+	vmov		r7, r8, d2
+
+	adds		r10, r10, #1
+	adcs		r9, r9, #0
+	adcs		r8, r8, #0
+	adc		r7, r7, #0
+
+99:	vmov		q1, q0
+	sub		lr, r5, #1
+	vmov		q2, q0
+	adr		ip, 0f
+	vmov		q3, q0
+	and		lr, lr, #112
+	vmov		q4, q0
+	cmp		r5, #112
+	vmov		q5, q0
+	sub		ip, ip, lr, lsl #1
+	vmov		q6, q0
+	add		ip, ip, lr, lsr #2
+	vmov		q7, q0
+	movle		pc, ip			// computed goto if bytes < 112
+
+	next_ctr	q1
+	next_ctr	q2
+	next_ctr	q3
+	next_ctr	q4
+	next_ctr	q5
+	next_ctr	q6
+	next_ctr	q7
+
+0:	mov		bskey, r2
+	mov		rounds, r3
+	bl		aesbs_encrypt8
+
+	adr		ip, 1f
+	sub		lr, r5, #1
+	cmp		r5, #128
+	bic		lr, lr, #15
+	ands		r4, r5, #15		// preserves C flag
+	teqcs		r5, r5			// set Z flag if not last iteration
+	sub		ip, ip, lr, lsr #2
+	rsb		r4, r4, #16
+	movcc		pc, ip			// computed goto if bytes < 128
+
+	vld1.8		{q8}, [r1]!
+	vld1.8		{q9}, [r1]!
+	vld1.8		{q10}, [r1]!
+	vld1.8		{q11}, [r1]!
+	vld1.8		{q12}, [r1]!
+	vld1.8		{q13}, [r1]!
+	vld1.8		{q14}, [r1]!
+1:	subne		r1, r1, r4
+	vld1.8		{q15}, [r1]!
+
+	add		ip, ip, #2f - 1b
+
+	veor		q0, q0, q8
+	veor		q1, q1, q9
+	veor		q4, q4, q10
+	veor		q6, q6, q11
+	veor		q3, q3, q12
+	veor		q7, q7, q13
+	veor		q2, q2, q14
+	bne		3f
+	veor		q5, q5, q15
+
+	movcc		pc, ip			// computed goto if bytes < 128
+
+	vst1.8		{q0}, [r0]!
+	vst1.8		{q1}, [r0]!
+	vst1.8		{q4}, [r0]!
+	vst1.8		{q6}, [r0]!
+	vst1.8		{q3}, [r0]!
+	vst1.8		{q7}, [r0]!
+	vst1.8		{q2}, [r0]!
+2:	subne		r0, r0, r4
+	vst1.8		{q5}, [r0]!
+
+	next_ctr	q0
+
+	subs		r5, r5, #128
+	bgt		99b
+
+	vst1.8		{q0}, [r6]
+	pop		{r4-r10, pc}
+
+3:	adr		lr, .Lpermute_table + 16
+	cmp		r5, #16			// Z flag remains cleared
+	sub		lr, lr, r4
+	vld1.8		{q8-q9}, [lr]
+	vtbl.8		d16, {q5}, d16
+	vtbl.8		d17, {q5}, d17
+	veor		q5, q8, q15
+	bcc		4f			// have to reload prev if R5 < 16
+	vtbx.8		d10, {q2}, d18
+	vtbx.8		d11, {q2}, d19
+	mov		pc, ip			// branch back to VST sequence
+
+4:	sub		r0, r0, r4
+	vshr.s8		q9, q9, #7		// create mask for VBIF
+	vld1.8		{q8}, [r0]		// reload
+	vbif		q5, q8, q9
+	vst1.8		{q5}, [r0]
+	pop		{r4-r10, pc}
+ENDPROC(aesbs_ctr_encrypt)
+
+	.align		6
+.Lpermute_table:
+	.byte		0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff
+	.byte		0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff
+	.byte		0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07
+	.byte		0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f
+	.byte		0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff
+	.byte		0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff, 0xff
+
+	.macro		next_tweak, out, in, const, tmp
+	vshr.s64	\tmp, \in, #63
+	vand		\tmp, \tmp, \const
+	vadd.u64	\out, \in, \in
+	vext.8		\tmp, \tmp, \tmp, #8
+	veor		\out, \out, \tmp
+	.endm
+
+	/*
+	 * aesbs_xts_encrypt(u8 out[], u8 const in[], u8 const rk[], int rounds,
+	 *		     int blocks, u8 iv[], int reorder_last_tweak)
+	 * aesbs_xts_decrypt(u8 out[], u8 const in[], u8 const rk[], int rounds,
+	 *		     int blocks, u8 iv[], int reorder_last_tweak)
+	 */
+	.align		6
+__xts_prepare8:
+	vld1.8		{q14}, [r7]		// load iv
+	vmov.i32	d30, #0x87		// compose tweak mask vector
+	vmovl.u32	q15, d30
+	vshr.u64	d30, d31, #7
+	vmov		q12, q14
+
+	adr		ip, 0f
+	and		r4, r6, #7
+	cmp		r6, #8
+	sub		ip, ip, r4, lsl #5
+	mov		r4, sp
+	movlt		pc, ip			// computed goto if blocks < 8
+
+	vld1.8		{q0}, [r1]!
+	next_tweak	q12, q14, q15, q13
+	veor		q0, q0, q14
+	vst1.8		{q14}, [r4, :128]!
+
+	vld1.8		{q1}, [r1]!
+	next_tweak	q14, q12, q15, q13
+	veor		q1, q1, q12
+	vst1.8		{q12}, [r4, :128]!
+
+	vld1.8		{q2}, [r1]!
+	next_tweak	q12, q14, q15, q13
+	veor		q2, q2, q14
+	vst1.8		{q14}, [r4, :128]!
+
+	vld1.8		{q3}, [r1]!
+	next_tweak	q14, q12, q15, q13
+	veor		q3, q3, q12
+	vst1.8		{q12}, [r4, :128]!
+
+	vld1.8		{q4}, [r1]!
+	next_tweak	q12, q14, q15, q13
+	veor		q4, q4, q14
+	vst1.8		{q14}, [r4, :128]!
+
+	vld1.8		{q5}, [r1]!
+	next_tweak	q14, q12, q15, q13
+	veor		q5, q5, q12
+	vst1.8		{q12}, [r4, :128]!
+
+	vld1.8		{q6}, [r1]!
+	next_tweak	q12, q14, q15, q13
+	veor		q6, q6, q14
+	vst1.8		{q14}, [r4, :128]!
+
+	vld1.8		{q7}, [r1]!
+	next_tweak	q14, q12, q15, q13
+THUMB(	itt		le		)
+	W(cmple)	r8, #0
+	ble		1f
+0:	veor		q7, q7, q12
+	vst1.8		{q12}, [r4, :128]
+
+	vst1.8		{q14}, [r7]		// store next iv
+	bx		lr
+
+1:	vswp		q12, q14
+	b		0b
+ENDPROC(__xts_prepare8)
+
+	.macro		__xts_crypt, do8, o0, o1, o2, o3, o4, o5, o6, o7
+	push		{r4-r8, lr}
+	mov		r5, sp			// preserve sp
+	ldrd		r6, r7, [sp, #24]	// get blocks and iv args
+	rsb		r8, ip, #1
+	sub		ip, sp, #128		// make room for 8x tweak
+	bic		ip, ip, #0xf		// align sp to 16 bytes
+	mov		sp, ip
+
+99:	bl		__xts_prepare8
+
+	mov		bskey, r2
+	mov		rounds, r3
+	bl		\do8
+
+	adr		ip, 0f
+	and		lr, r6, #7
+	cmp		r6, #8
+	sub		ip, ip, lr, lsl #2
+	mov		r4, sp
+	movlt		pc, ip			// computed goto if blocks < 8
+
+	vld1.8		{q8}, [r4, :128]!
+	vld1.8		{q9}, [r4, :128]!
+	vld1.8		{q10}, [r4, :128]!
+	vld1.8		{q11}, [r4, :128]!
+	vld1.8		{q12}, [r4, :128]!
+	vld1.8		{q13}, [r4, :128]!
+	vld1.8		{q14}, [r4, :128]!
+	vld1.8		{q15}, [r4, :128]
+
+0:	adr		ip, 1f
+	sub		ip, ip, lr, lsl #3
+	movlt		pc, ip			// computed goto if blocks < 8
+
+	veor		\o0, \o0, q8
+	vst1.8		{\o0}, [r0]!
+	veor		\o1, \o1, q9
+	vst1.8		{\o1}, [r0]!
+	veor		\o2, \o2, q10
+	vst1.8		{\o2}, [r0]!
+	veor		\o3, \o3, q11
+	vst1.8		{\o3}, [r0]!
+	veor		\o4, \o4, q12
+	vst1.8		{\o4}, [r0]!
+	veor		\o5, \o5, q13
+	vst1.8		{\o5}, [r0]!
+	veor		\o6, \o6, q14
+	vst1.8		{\o6}, [r0]!
+	veor		\o7, \o7, q15
+	vst1.8		{\o7}, [r0]!
+
+1:	subs		r6, r6, #8
+	bgt		99b
+
+	mov		sp, r5
+	pop		{r4-r8, pc}
+	.endm
+
+ENTRY(aesbs_xts_encrypt)
+	mov		ip, #0			// never reorder final tweak
+	__xts_crypt	aesbs_encrypt8, q0, q1, q4, q6, q3, q7, q2, q5
+ENDPROC(aesbs_xts_encrypt)
+
+ENTRY(aesbs_xts_decrypt)
+	ldr		ip, [sp, #8]		// reorder final tweak?
+	__xts_crypt	aesbs_decrypt8, q0, q1, q6, q4, q2, q7, q3, q5
+ENDPROC(aesbs_xts_decrypt)