Merge android-4.4.163 (0ca3fca) into msm-4.4

* refs/heads/tmp-0ca3fca
  Linux 4.4.163
  x86/time: Correct the attribute on jiffies' definition
  l2tp: hold tunnel socket when handling control frames in l2tp_ip and l2tp_ip6
  cpuidle: Do not access cpuidle_devices when !CONFIG_CPU_IDLE
  x86/percpu: Fix this_cpu_read()
  sched/fair: Fix throttle_list starvation with low CFS quota
  Input: elan_i2c - add ACPI ID for Lenovo IdeaPad 330-15IGM
  USB: fix the usbfs flag sanitization for control transfers
  usb: gadget: storage: Fix Spectre v1 vulnerability
  cdc-acm: correct counting of UART states in serial state notification
  IB/ucm: Fix Spectre v1 vulnerability
  RDMA/ucma: Fix Spectre v1 vulnerability
  ptp: fix Spectre v1 vulnerability
  cachefiles: fix the race between cachefiles_bury_object() and rmdir(2)
  ahci: don't ignore result code of ahci_reset_controller()
  crypto: shash - Fix a sleep-in-atomic bug in shash_setkey_unaligned
  mremap: properly flush TLB before releasing the page
  rtnetlink: Disallow FDB configuration for non-Ethernet device
  vhost: Fix Spectre V1 vulnerability
  net: drop skb on failure in ip_check_defrag()
  sctp: fix race on sctp_id2asoc
  r8169: fix NAPI handling under high load
  net: stmmac: Fix stmmac_mdio_reset() when building stmmac as modules
  net: socket: fix a missing-check bug
  net: sched: gred: pass the right attribute to gred_change_table_def()
  net/ipv6: Fix index counter for unicast addresses in in6_dump_addrs
  ipv6/ndisc: Preserve IPv6 control buffer if protocol error handlers are called
  ipv6: mcast: fix a use-after-free in inet6_mc_check
  net: bridge: remove ipv6 zero address check in mcast queries
  bridge: do not add port to router list when receives query with source 0.0.0.0
  perf tools: Disable parallelism for 'make clean'
  mtd: spi-nor: Add support for is25wp series chips
  fs/fat/fatent.c: add cond_resched() to fat_count_free_clusters()
  ARM: dts: imx53-qsb: disable 1.2GHz OPP
  MIPS: DEC: Fix an int-handler.S CPU_DADDI_WORKAROUNDS regression
  igb: Remove superfluous reset to PHY and page 0 selection
  MIPS: microMIPS: Fix decoding of swsp16 instruction
  scsi: aacraid: Fix typo in blink status
  bonding: avoid defaulting hard_header_len to ETH_HLEN on slave removal
  PM / devfreq: tegra: fix error return code in tegra_devfreq_probe()
  ASoC: spear: fix error return code in spdif_in_probe()
  spi: xlp: fix error return code in xlp_spi_probe()
  spi/bcm63xx: fix error return code in bcm63xx_spi_probe()
  MIPS: Handle non word sized instructions when examining frame
  spi/bcm63xx-hspi: fix error return code in bcm63xx_hsspi_probe()
  usb: dwc3: omap: fix error return code in dwc3_omap_probe()
  usb: ehci-omap: fix error return code in ehci_hcd_omap_probe()
  usb: imx21-hcd: fix error return code in imx21_probe()
  gpio: msic: fix error return code in platform_msic_gpio_probe()
  sparc64: Fix exception handling in UltraSPARC-III memcpy.
  gpu: host1x: fix error return code in host1x_probe()
  sparc64 mm: Fix more TSB sizing issues
  video: fbdev: pxa3xx_gcu: fix error return code in pxa3xx_gcu_probe()
  tty: serial: sprd: fix error return code in sprd_probe()
  l2tp: hold socket before dropping lock in l2tp_ip{, 6}_recv()
  brcmfmac: Fix glom_skb leak in brcmf_sdiod_recv_chain
  gro: Allow tunnel stacking in the case of FOU/GUE
  vti6: flush x-netns xfrm cache when vti interface is removed
  ALSA: timer: Fix zero-division by continue of uninitialized instance
  ixgbe: Correct X550EM_x revision check
  ixgbe: fix RSS limit for X550
  net/mlx5e: Correctly handle RSS indirection table when changing number of channels
  net/mlx5e: Fix LRO modify
  ixgbevf: Fix handling of NAPI budget when multiple queues are enabled per vector
  fuse: Dont call set_page_dirty_lock() for ITER_BVEC pages for async_dio
  drm/nouveau/fbcon: fix oops without fbdev emulation
  bpf: generally move prog destruction to RCU deferral
  usb-storage: fix bogus hardware error messages for ATA pass-thru devices
  sch_red: update backlog as well
  sparc/pci: Refactor dev_archdata initialization into pci_init_dev_archdata
  scsi: Add STARGET_CREATED_REMOVE state to scsi_target_state
  xfrm: Clear sk_dst_cache when applying per-socket policy.
  arm64: Fix potential race with hardware DBM in ptep_set_access_flags()
  CIFS: handle guest access errors to Windows shares
  ASoC: wm8940: Enable cache usage to fix crashes on resume
  ASoC: ak4613: Enable cache usage to fix crashes on resume
  MIPS: Fix FCSR Cause bit handling for correct SIGFPE issue
  usbvision: revert commit 588afcc1
  perf/core: Don't leak event in the syscall error path
  aacraid: Start adapter after updating number of MSIX vectors
  x86/PCI: Mark Broadwell-EP Home Agent 1 as having non-compliant BARs
  tpm: fix: return rc when devm_add_action() fails
  thermal: allow u8500-thermal driver to be a module
  thermal: allow spear-thermal driver to be a module
  btrfs: don't create or leak aliased root while cleaning up orphans
  sched/cgroup: Fix cgroup entity load tracking tear-down
  um: Avoid longjmp/setjmp symbol clashes with libpthread.a
  ipv6: orphan skbs in reassembly unit
  net/mlx4_en: Resolve dividing by zero in 32-bit system
  af_iucv: Move sockaddr length checks to before accessing sa_family in bind and connect handlers
  radix-tree: fix radix_tree_iter_retry() for tagged iterators.
  x86/mm/pat: Prevent hang during boot when mapping pages
  ARM: dts: apq8064: add ahci ports-implemented mask
  tracing: Skip more functions when doing stack tracing of events
  ser_gigaset: use container_of() instead of detour
  net: drop write-only stack variable
  ipv6: suppress sparse warnings in IP6_ECN_set_ce()
  KEYS: put keyring if install_session_keyring_to_cred() fails
  net: cxgb3_main: fix a missing-check bug
  perf/ring_buffer: Prevent concurent ring buffer access
  smsc95xx: Check for Wake-on-LAN modes
  smsc75xx: Check for Wake-on-LAN modes
  r8152: Check for supported Wake-on-LAN Modes
  sr9800: Check for supported Wake-on-LAN modes
  lan78xx: Check for supported Wake-on-LAN modes
  ax88179_178a: Check for supported Wake-on-LAN modes
  asix: Check for supported Wake-on-LAN modes
  pxa168fb: prepare the clock
  Bluetooth: SMP: fix crash in unpairing
  mac80211_hwsim: do not omit multicast announce of first added radio
  xfrm: validate template mode
  ARM: 8799/1: mm: fix pci_ioremap_io() offset check
  cfg80211: reg: Init wiphy_idx in regulatory_hint_core()
  mac80211: Always report TX status
  xfrm6: call kfree_skb when skb is toobig
  xfrm: Validate address prefix lengths in the xfrm selector.
  BACKPORT: xfrm: Allow Output Mark to be Updated Using UPDSA
  ANDROID: sdcardfs: Add option to drop unused dentries
  f2fs: guarantee journalled quota data by checkpoint
  f2fs: cleanup dirty pages if recover failed
  f2fs: fix data corruption issue with hardware encryption
  f2fs: fix to recover inode->i_flags of inode block during POR
  f2fs: spread f2fs_set_inode_flags()
  f2fs: fix to spread clear_cold_data()
  Revert "f2fs: fix to clear PG_checked flag in set_page_dirty()"
  f2fs: account read IOs and use IO counts for is_idle
  f2fs: fix to account IO correctly for cgroup writeback
  f2fs: fix to account IO correctly
  f2fs: remove request_list check in is_idle()
  f2fs: allow to mount, if quota is failed
  f2fs: update REQ_TIME in f2fs_cross_rename()
  f2fs: do not update REQ_TIME in case of error conditions
  f2fs: remove unneeded disable_nat_bits()
  f2fs: remove unused sbi->trigger_ssr_threshold
  f2fs: shrink sbi->sb_lock coverage in set_file_temperature()
  f2fs: fix to recover cold bit of inode block during POR
  f2fs: submit cached bio to avoid endless PageWriteback
  f2fs: checkpoint disabling
  f2fs: clear PageError on the read path
  f2fs: allow out-place-update for direct IO in LFS mode
  f2fs: refactor ->page_mkwrite() flow
  Revert: "f2fs: check last page index in cached bio to decide submission"
  f2fs: support superblock checksum
  f2fs: add to account skip count of background GC
  f2fs: add to account meta IO
  f2fs: keep lazytime on remount
  f2fs: fix missing up_read
  f2fs: return correct errno in f2fs_gc
  f2fs: avoid f2fs_bug_on if f2fs_get_meta_page_nofail got EIO
  f2fs: mark inode dirty explicitly in recover_inode()
  f2fs: fix to recover inode's crtime during POR
  f2fs: fix to recover inode's i_gc_failures during POR
  f2fs: fix to recover inode's i_flags during POR
  f2fs: fix to recover inode's project id during POR
  f2fs: update i_size after DIO completion
  f2fs: report ENOENT correctly in f2fs_rename
  f2fs: fix remount problem of option io_bits
  f2fs: fix to recover inode's uid/gid during POR
  f2fs: avoid infinite loop in f2fs_alloc_nid
  f2fs: add new idle interval timing for discard and gc paths
  f2fs: split IO error injection according to RW
  f2fs: add SPDX license identifiers
  f2fs: surround fault_injection related option parsing using CONFIG_F2FS_FAULT_INJECTION
  f2fs: avoid sleeping under spin_lock
  f2fs: plug readahead IO in readdir()
  f2fs: fix to do sanity check with current segment number
  f2fs: fix memory leak of percpu counter in fill_super()
  f2fs: fix memory leak of write_io in fill_super()
  f2fs: cache NULL when both default_acl and acl are NULL
  f2fs: fix to flush all dirty inodes recovered in readonly fs
  f2fs: report error if quota off error during umount
  f2fs: submit bio after shutdown
  f2fs: avoid wrong decrypted data from disk
  Revert "f2fs: use printk_ratelimited for f2fs_msg"
  f2fs: fix unnecessary periodic wakeup of discard thread when dev is busy
  f2fs: fix to avoid NULL pointer dereference on se->discard_map
  f2fs: add additional sanity check in f2fs_acl_from_disk()
  Revert "BACKPORT, FROMLIST: fscrypt: add Speck128/256 support"
  Build fix for 076c36fce1ea0.
  Revert "BACKPORT, FROMGIT: crypto: speck - add support for the Speck block cipher"
  Revert "FROMGIT: crypto: speck - export common helpers"
  Revert "BACKPORT, FROMGIT: crypto: arm/speck - add NEON-accelerated implementation of Speck-XTS"
  Revert "BACKPORT, FROMGIT: crypto: speck - add test vectors for Speck128-XTS"
  Revert "BACKPORT, FROMGIT: crypto: speck - add test vectors for Speck64-XTS"
  Revert "BACKPORT, FROMLIST: crypto: arm64/speck - add NEON-accelerated implementation of Speck-XTS"
  Revert "fscrypt: add Speck128/256 support"
  UPSTREAM: loop: Add LOOP_SET_BLOCK_SIZE in compat ioctl
  BACKPORT: block/loop: set hw_sectors
  UPSTREAM: loop: add ioctl for changing logical block size

Conflicts:
	fs/ext4/crypto.c
	fs/ext4/ext4.h

Change-Id: I8cb2f70b27906879f8e8fdd90e67f438e39701b8
Signed-off-by: Srinivasarao P <spathi@codeaurora.org>

29 files changed, 149 insertions, 1518 deletions

diff --git a/arch/arm/boot/dts/imx53-qsb-common.dtsi b/arch/arm/boot/dts/imx53-qsb-common.dtsi
index 53fd75c8ffcf..47894b41e4e2 100644
--- a/arch/arm/boot/dts/imx53-qsb-common.dtsi
+++ b/arch/arm/boot/dts/imx53-qsb-common.dtsi
@@ -130,6 +130,17 @@
 	};
 };
 
+&cpu0 {
+	/* CPU rated to 1GHz, not 1.2GHz as per the default settings */
+	operating-points = <
+		/* kHz   uV */
+		166666  850000
+		400000  900000
+		800000  1050000
+		1000000 1200000
+	>;
+};
+
 &esdhc1 {
 	pinctrl-names = "default";
 	pinctrl-0 = <&pinctrl_esdhc1>;
diff --git a/arch/arm/boot/dts/qcom-apq8064.dtsi b/arch/arm/boot/dts/qcom-apq8064.dtsi
index e00d50ef678f..3ff5ea16ebb3 100644
--- a/arch/arm/boot/dts/qcom-apq8064.dtsi
+++ b/arch/arm/boot/dts/qcom-apq8064.dtsi
@@ -577,7 +577,7 @@
 		};
 
 		sata0: sata@29000000 {
-			compatible		= "generic-ahci";
+			compatible		= "qcom,apq8064-ahci", "generic-ahci";
 			status			= "disabled";
 			reg			= <0x29000000 0x180>;
 			interrupts		= <GIC_SPI 209 IRQ_TYPE_NONE>;
@@ -599,6 +599,7 @@
 
 			phys			= <&sata_phy0>;
 			phy-names		= "sata-phy";
+			ports-implemented	= <0x1>;
 		};
 
 		/* Temporary fixed regulator */
diff --git a/arch/arm/crypto/Kconfig b/arch/arm/crypto/Kconfig
index 72aa5ecd5580..27ed1b1cd1d7 100644
--- a/arch/arm/crypto/Kconfig
+++ b/arch/arm/crypto/Kconfig
@@ -120,11 +120,4 @@ config CRYPTO_GHASH_ARM_CE
 	  that uses the 64x64 to 128 bit polynomial multiplication (vmull.p64)
 	  that is part of the ARMv8 Crypto Extensions
 
-config CRYPTO_SPECK_NEON
-	tristate "NEON accelerated Speck cipher algorithms"
-	depends on KERNEL_MODE_NEON
-	select CRYPTO_BLKCIPHER
-	select CRYPTO_GF128MUL
-	select CRYPTO_SPECK
-
 endif
diff --git a/arch/arm/crypto/Makefile b/arch/arm/crypto/Makefile
index 1d0448a875ee..fc5150702b64 100644
--- a/arch/arm/crypto/Makefile
+++ b/arch/arm/crypto/Makefile
@@ -8,7 +8,6 @@ obj-$(CONFIG_CRYPTO_SHA1_ARM) += sha1-arm.o
 obj-$(CONFIG_CRYPTO_SHA1_ARM_NEON) += sha1-arm-neon.o
 obj-$(CONFIG_CRYPTO_SHA256_ARM) += sha256-arm.o
 obj-$(CONFIG_CRYPTO_SHA512_ARM) += sha512-arm.o
-obj-$(CONFIG_CRYPTO_SPECK_NEON) += speck-neon.o
 
 ce-obj-$(CONFIG_CRYPTO_AES_ARM_CE) += aes-arm-ce.o
 ce-obj-$(CONFIG_CRYPTO_SHA1_ARM_CE) += sha1-arm-ce.o
@@ -37,7 +36,6 @@ sha1-arm-ce-y	:= sha1-ce-core.o sha1-ce-glue.o
 sha2-arm-ce-y	:= sha2-ce-core.o sha2-ce-glue.o
 aes-arm-ce-y	:= aes-ce-core.o aes-ce-glue.o
 ghash-arm-ce-y	:= ghash-ce-core.o ghash-ce-glue.o
-speck-neon-y := speck-neon-core.o speck-neon-glue.o
 
 quiet_cmd_perl = PERL    $@
       cmd_perl = $(PERL) $(<) > $(@)
diff --git a/arch/arm/crypto/speck-neon-core.S b/arch/arm/crypto/speck-neon-core.S
deleted file mode 100644
index 3c1e203e53b9..000000000000
--- a/arch/arm/crypto/speck-neon-core.S
+++ /dev/null
@@ -1,432 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * NEON-accelerated implementation of Speck128-XTS and Speck64-XTS
- *
- * Copyright (c) 2018 Google, Inc
- *
- * Author: Eric Biggers <ebiggers@google.com>
- */
-
-#include <linux/linkage.h>
-
-	.text
-	.fpu		neon
-
-	// arguments
-	ROUND_KEYS	.req	r0	// const {u64,u32} *round_keys
-	NROUNDS		.req	r1	// int nrounds
-	DST		.req	r2	// void *dst
-	SRC		.req	r3	// const void *src
-	NBYTES		.req	r4	// unsigned int nbytes
-	TWEAK		.req	r5	// void *tweak
-
-	// registers which hold the data being encrypted/decrypted
-	X0		.req	q0
-	X0_L		.req	d0
-	X0_H		.req	d1
-	Y0		.req	q1
-	Y0_H		.req	d3
-	X1		.req	q2
-	X1_L		.req	d4
-	X1_H		.req	d5
-	Y1		.req	q3
-	Y1_H		.req	d7
-	X2		.req	q4
-	X2_L		.req	d8
-	X2_H		.req	d9
-	Y2		.req	q5
-	Y2_H		.req	d11
-	X3		.req	q6
-	X3_L		.req	d12
-	X3_H		.req	d13
-	Y3		.req	q7
-	Y3_H		.req	d15
-
-	// the round key, duplicated in all lanes
-	ROUND_KEY	.req	q8
-	ROUND_KEY_L	.req	d16
-	ROUND_KEY_H	.req	d17
-
-	// index vector for vtbl-based 8-bit rotates
-	ROTATE_TABLE	.req	d18
-
-	// multiplication table for updating XTS tweaks
-	GF128MUL_TABLE	.req	d19
-	GF64MUL_TABLE	.req	d19
-
-	// current XTS tweak value(s)
-	TWEAKV		.req	q10
-	TWEAKV_L	.req	d20
-	TWEAKV_H	.req	d21
-
-	TMP0		.req	q12
-	TMP0_L		.req	d24
-	TMP0_H		.req	d25
-	TMP1		.req	q13
-	TMP2		.req	q14
-	TMP3		.req	q15
-
-	.align		4
-.Lror64_8_table:
-	.byte		1, 2, 3, 4, 5, 6, 7, 0
-.Lror32_8_table:
-	.byte		1, 2, 3, 0, 5, 6, 7, 4
-.Lrol64_8_table:
-	.byte		7, 0, 1, 2, 3, 4, 5, 6
-.Lrol32_8_table:
-	.byte		3, 0, 1, 2, 7, 4, 5, 6
-.Lgf128mul_table:
-	.byte		0, 0x87
-	.fill		14
-.Lgf64mul_table:
-	.byte		0, 0x1b, (0x1b << 1), (0x1b << 1) ^ 0x1b
-	.fill		12
-
-/*
- * _speck_round_128bytes() - Speck encryption round on 128 bytes at a time
- *
- * Do one Speck encryption round on the 128 bytes (8 blocks for Speck128, 16 for
- * Speck64) stored in X0-X3 and Y0-Y3, using the round key stored in all lanes
- * of ROUND_KEY.  'n' is the lane size: 64 for Speck128, or 32 for Speck64.
- *
- * The 8-bit rotates are implemented using vtbl instead of vshr + vsli because
- * the vtbl approach is faster on some processors and the same speed on others.
- */
-.macro _speck_round_128bytes	n
-
-	// x = ror(x, 8)
-	vtbl.8		X0_L, {X0_L}, ROTATE_TABLE
-	vtbl.8		X0_H, {X0_H}, ROTATE_TABLE
-	vtbl.8		X1_L, {X1_L}, ROTATE_TABLE
-	vtbl.8		X1_H, {X1_H}, ROTATE_TABLE
-	vtbl.8		X2_L, {X2_L}, ROTATE_TABLE
-	vtbl.8		X2_H, {X2_H}, ROTATE_TABLE
-	vtbl.8		X3_L, {X3_L}, ROTATE_TABLE
-	vtbl.8		X3_H, {X3_H}, ROTATE_TABLE
-
-	// x += y
-	vadd.u\n	X0, Y0
-	vadd.u\n	X1, Y1
-	vadd.u\n	X2, Y2
-	vadd.u\n	X3, Y3
-
-	// x ^= k
-	veor		X0, ROUND_KEY
-	veor		X1, ROUND_KEY
-	veor		X2, ROUND_KEY
-	veor		X3, ROUND_KEY
-
-	// y = rol(y, 3)
-	vshl.u\n	TMP0, Y0, #3
-	vshl.u\n	TMP1, Y1, #3
-	vshl.u\n	TMP2, Y2, #3
-	vshl.u\n	TMP3, Y3, #3
-	vsri.u\n	TMP0, Y0, #(\n - 3)
-	vsri.u\n	TMP1, Y1, #(\n - 3)
-	vsri.u\n	TMP2, Y2, #(\n - 3)
-	vsri.u\n	TMP3, Y3, #(\n - 3)
-
-	// y ^= x
-	veor		Y0, TMP0, X0
-	veor		Y1, TMP1, X1
-	veor		Y2, TMP2, X2
-	veor		Y3, TMP3, X3
-.endm
-
-/*
- * _speck_unround_128bytes() - Speck decryption round on 128 bytes at a time
- *
- * This is the inverse of _speck_round_128bytes().
- */
-.macro _speck_unround_128bytes	n
-
-	// y ^= x
-	veor		TMP0, Y0, X0
-	veor		TMP1, Y1, X1
-	veor		TMP2, Y2, X2
-	veor		TMP3, Y3, X3
-
-	// y = ror(y, 3)
-	vshr.u\n	Y0, TMP0, #3
-	vshr.u\n	Y1, TMP1, #3
-	vshr.u\n	Y2, TMP2, #3
-	vshr.u\n	Y3, TMP3, #3
-	vsli.u\n	Y0, TMP0, #(\n - 3)
-	vsli.u\n	Y1, TMP1, #(\n - 3)
-	vsli.u\n	Y2, TMP2, #(\n - 3)
-	vsli.u\n	Y3, TMP3, #(\n - 3)
-
-	// x ^= k
-	veor		X0, ROUND_KEY
-	veor		X1, ROUND_KEY
-	veor		X2, ROUND_KEY
-	veor		X3, ROUND_KEY
-
-	// x -= y
-	vsub.u\n	X0, Y0
-	vsub.u\n	X1, Y1
-	vsub.u\n	X2, Y2
-	vsub.u\n	X3, Y3
-
-	// x = rol(x, 8);
-	vtbl.8		X0_L, {X0_L}, ROTATE_TABLE
-	vtbl.8		X0_H, {X0_H}, ROTATE_TABLE
-	vtbl.8		X1_L, {X1_L}, ROTATE_TABLE
-	vtbl.8		X1_H, {X1_H}, ROTATE_TABLE
-	vtbl.8		X2_L, {X2_L}, ROTATE_TABLE
-	vtbl.8		X2_H, {X2_H}, ROTATE_TABLE
-	vtbl.8		X3_L, {X3_L}, ROTATE_TABLE
-	vtbl.8		X3_H, {X3_H}, ROTATE_TABLE
-.endm
-
-.macro _xts128_precrypt_one	dst_reg, tweak_buf, tmp
-
-	// Load the next source block
-	vld1.8		{\dst_reg}, [SRC]!
-
-	// Save the current tweak in the tweak buffer
-	vst1.8		{TWEAKV}, [\tweak_buf:128]!
-
-	// XOR the next source block with the current tweak
-	veor		\dst_reg, TWEAKV
-
-	/*
-	 * Calculate the next tweak by multiplying the current one by x,
-	 * modulo p(x) = x^128 + x^7 + x^2 + x + 1.
-	 */
-	vshr.u64	\tmp, TWEAKV, #63
-	vshl.u64	TWEAKV, #1
-	veor		TWEAKV_H, \tmp\()_L
-	vtbl.8		\tmp\()_H, {GF128MUL_TABLE}, \tmp\()_H
-	veor		TWEAKV_L, \tmp\()_H
-.endm
-
-.macro _xts64_precrypt_two	dst_reg, tweak_buf, tmp
-
-	// Load the next two source blocks
-	vld1.8		{\dst_reg}, [SRC]!
-
-	// Save the current two tweaks in the tweak buffer
-	vst1.8		{TWEAKV}, [\tweak_buf:128]!
-
-	// XOR the next two source blocks with the current two tweaks
-	veor		\dst_reg, TWEAKV
-
-	/*
-	 * Calculate the next two tweaks by multiplying the current ones by x^2,
-	 * modulo p(x) = x^64 + x^4 + x^3 + x + 1.
-	 */
-	vshr.u64	\tmp, TWEAKV, #62
-	vshl.u64	TWEAKV, #2
-	vtbl.8		\tmp\()_L, {GF64MUL_TABLE}, \tmp\()_L
-	vtbl.8		\tmp\()_H, {GF64MUL_TABLE}, \tmp\()_H
-	veor		TWEAKV, \tmp
-.endm
-
-/*
- * _speck_xts_crypt() - Speck-XTS encryption/decryption
- *
- * Encrypt or decrypt NBYTES bytes of data from the SRC buffer to the DST buffer
- * using Speck-XTS, specifically the variant with a block size of '2n' and round
- * count given by NROUNDS.  The expanded round keys are given in ROUND_KEYS, and
- * the current XTS tweak value is given in TWEAK.  It's assumed that NBYTES is a
- * nonzero multiple of 128.
- */
-.macro _speck_xts_crypt	n, decrypting
-	push		{r4-r7}
-	mov		r7, sp
-
-	/*
-	 * The first four parameters were passed in registers r0-r3.  Load the
-	 * additional parameters, which were passed on the stack.
-	 */
-	ldr		NBYTES, [sp, #16]
-	ldr		TWEAK, [sp, #20]
-
-	/*
-	 * If decrypting, modify the ROUND_KEYS parameter to point to the last
-	 * round key rather than the first, since for decryption the round keys
-	 * are used in reverse order.
-	 */
-.if \decrypting
-.if \n == 64
-	add		ROUND_KEYS, ROUND_KEYS, NROUNDS, lsl #3
-	sub		ROUND_KEYS, #8
-.else
-	add		ROUND_KEYS, ROUND_KEYS, NROUNDS, lsl #2
-	sub		ROUND_KEYS, #4
-.endif
-.endif
-
-	// Load the index vector for vtbl-based 8-bit rotates
-.if \decrypting
-	ldr		r12, =.Lrol\n\()_8_table
-.else
-	ldr		r12, =.Lror\n\()_8_table
-.endif
-	vld1.8		{ROTATE_TABLE}, [r12:64]
-
-	// One-time XTS preparation
-
-	/*
-	 * Allocate stack space to store 128 bytes worth of tweaks.  For
-	 * performance, this space is aligned to a 16-byte boundary so that we
-	 * can use the load/store instructions that declare 16-byte alignment.
-	 */
-	sub		sp, #128
-	bic		sp, #0xf
-
-.if \n == 64
-	// Load first tweak
-	vld1.8		{TWEAKV}, [TWEAK]
-
-	// Load GF(2^128) multiplication table
-	ldr		r12, =.Lgf128mul_table
-	vld1.8		{GF128MUL_TABLE}, [r12:64]
-.else
-	// Load first tweak
-	vld1.8		{TWEAKV_L}, [TWEAK]
-
-	// Load GF(2^64) multiplication table
-	ldr		r12, =.Lgf64mul_table
-	vld1.8		{GF64MUL_TABLE}, [r12:64]
-
-	// Calculate second tweak, packing it together with the first
-	vshr.u64	TMP0_L, TWEAKV_L, #63
-	vtbl.u8		TMP0_L, {GF64MUL_TABLE}, TMP0_L
-	vshl.u64	TWEAKV_H, TWEAKV_L, #1
-	veor		TWEAKV_H, TMP0_L
-.endif
-
-.Lnext_128bytes_\@:
-
-	/*
-	 * Load the source blocks into {X,Y}[0-3], XOR them with their XTS tweak
-	 * values, and save the tweaks on the stack for later.  Then
-	 * de-interleave the 'x' and 'y' elements of each block, i.e. make it so
-	 * that the X[0-3] registers contain only the second halves of blocks,
-	 * and the Y[0-3] registers contain only the first halves of blocks.
-	 * (Speck uses the order (y, x) rather than the more intuitive (x, y).)
-	 */
-	mov		r12, sp
-.if \n == 64
-	_xts128_precrypt_one	X0, r12, TMP0
-	_xts128_precrypt_one	Y0, r12, TMP0
-	_xts128_precrypt_one	X1, r12, TMP0
-	_xts128_precrypt_one	Y1, r12, TMP0
-	_xts128_precrypt_one	X2, r12, TMP0
-	_xts128_precrypt_one	Y2, r12, TMP0
-	_xts128_precrypt_one	X3, r12, TMP0
-	_xts128_precrypt_one	Y3, r12, TMP0
-	vswp		X0_L, Y0_H
-	vswp		X1_L, Y1_H
-	vswp		X2_L, Y2_H
-	vswp		X3_L, Y3_H
-.else
-	_xts64_precrypt_two	X0, r12, TMP0
-	_xts64_precrypt_two	Y0, r12, TMP0
-	_xts64_precrypt_two	X1, r12, TMP0
-	_xts64_precrypt_two	Y1, r12, TMP0
-	_xts64_precrypt_two	X2, r12, TMP0
-	_xts64_precrypt_two	Y2, r12, TMP0
-	_xts64_precrypt_two	X3, r12, TMP0
-	_xts64_precrypt_two	Y3, r12, TMP0
-	vuzp.32		Y0, X0
-	vuzp.32		Y1, X1
-	vuzp.32		Y2, X2
-	vuzp.32		Y3, X3
-.endif
-
-	// Do the cipher rounds
-
-	mov		r12, ROUND_KEYS
-	mov		r6, NROUNDS
-
-.Lnext_round_\@:
-.if \decrypting
-.if \n == 64
-	vld1.64		ROUND_KEY_L, [r12]
-	sub		r12, #8
-	vmov		ROUND_KEY_H, ROUND_KEY_L
-.else
-	vld1.32		{ROUND_KEY_L[],ROUND_KEY_H[]}, [r12]
-	sub		r12, #4
-.endif
-	_speck_unround_128bytes	\n
-.else
-.if \n == 64
-	vld1.64		ROUND_KEY_L, [r12]!
-	vmov		ROUND_KEY_H, ROUND_KEY_L
-.else
-	vld1.32		{ROUND_KEY_L[],ROUND_KEY_H[]}, [r12]!
-.endif
-	_speck_round_128bytes	\n
-.endif
-	subs		r6, r6, #1
-	bne		.Lnext_round_\@
-
-	// Re-interleave the 'x' and 'y' elements of each block
-.if \n == 64
-	vswp		X0_L, Y0_H
-	vswp		X1_L, Y1_H
-	vswp		X2_L, Y2_H
-	vswp		X3_L, Y3_H
-.else
-	vzip.32		Y0, X0
-	vzip.32		Y1, X1
-	vzip.32		Y2, X2
-	vzip.32		Y3, X3
-.endif
-
-	// XOR the encrypted/decrypted blocks with the tweaks we saved earlier
-	mov		r12, sp
-	vld1.8		{TMP0, TMP1}, [r12:128]!
-	vld1.8		{TMP2, TMP3}, [r12:128]!
-	veor		X0, TMP0
-	veor		Y0, TMP1
-	veor		X1, TMP2
-	veor		Y1, TMP3
-	vld1.8		{TMP0, TMP1}, [r12:128]!
-	vld1.8		{TMP2, TMP3}, [r12:128]!
-	veor		X2, TMP0
-	veor		Y2, TMP1
-	veor		X3, TMP2
-	veor		Y3, TMP3
-
-	// Store the ciphertext in the destination buffer
-	vst1.8		{X0, Y0}, [DST]!
-	vst1.8		{X1, Y1}, [DST]!
-	vst1.8		{X2, Y2}, [DST]!
-	vst1.8		{X3, Y3}, [DST]!
-
-	// Continue if there are more 128-byte chunks remaining, else return
-	subs		NBYTES, #128
-	bne		.Lnext_128bytes_\@
-
-	// Store the next tweak
-.if \n == 64
-	vst1.8		{TWEAKV}, [TWEAK]
-.else
-	vst1.8		{TWEAKV_L}, [TWEAK]
-.endif
-
-	mov		sp, r7
-	pop		{r4-r7}
-	bx		lr
-.endm
-
-ENTRY(speck128_xts_encrypt_neon)
-	_speck_xts_crypt	n=64, decrypting=0
-ENDPROC(speck128_xts_encrypt_neon)
-
-ENTRY(speck128_xts_decrypt_neon)
-	_speck_xts_crypt	n=64, decrypting=1
-ENDPROC(speck128_xts_decrypt_neon)
-
-ENTRY(speck64_xts_encrypt_neon)
-	_speck_xts_crypt	n=32, decrypting=0
-ENDPROC(speck64_xts_encrypt_neon)
-
-ENTRY(speck64_xts_decrypt_neon)
-	_speck_xts_crypt	n=32, decrypting=1
-ENDPROC(speck64_xts_decrypt_neon)
diff --git a/arch/arm/crypto/speck-neon-glue.c b/arch/arm/crypto/speck-neon-glue.c
deleted file mode 100644
index ea36c3a6f1d9..000000000000
--- a/arch/arm/crypto/speck-neon-glue.c
+++ /dev/null
@@ -1,314 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * NEON-accelerated implementation of Speck128-XTS and Speck64-XTS
- *
- * Copyright (c) 2018 Google, Inc
- *
- * Note: the NIST recommendation for XTS only specifies a 128-bit block size,
- * but a 64-bit version (needed for Speck64) is fairly straightforward; the math
- * is just done in GF(2^64) instead of GF(2^128), with the reducing polynomial
- * x^64 + x^4 + x^3 + x + 1 from the original XEX paper (Rogaway, 2004:
- * "Efficient Instantiations of Tweakable Blockciphers and Refinements to Modes
- * OCB and PMAC"), represented as 0x1B.
- */
-
-#include <asm/hwcap.h>
-#include <asm/neon.h>
-#include <asm/simd.h>
-#include <crypto/algapi.h>
-#include <crypto/gf128mul.h>
-#include <crypto/speck.h>
-#include <crypto/xts.h>
-#include <linux/kernel.h>
-#include <linux/module.h>
-
-/* The assembly functions only handle multiples of 128 bytes */
-#define SPECK_NEON_CHUNK_SIZE	128
-
-/* Speck128 */
-
-struct speck128_xts_tfm_ctx {
-	struct speck128_tfm_ctx main_key;
-	struct speck128_tfm_ctx tweak_key;
-};
-
-asmlinkage void speck128_xts_encrypt_neon(const u64 *round_keys, int nrounds,
-					  void *dst, const void *src,
-					  unsigned int nbytes, void *tweak);
-
-asmlinkage void speck128_xts_decrypt_neon(const u64 *round_keys, int nrounds,
-					  void *dst, const void *src,
-					  unsigned int nbytes, void *tweak);
-
-typedef void (*speck128_crypt_one_t)(const struct speck128_tfm_ctx *,
-				     u8 *, const u8 *);
-typedef void (*speck128_xts_crypt_many_t)(const u64 *, int, void *,
-					  const void *, unsigned int, void *);
-
-static __always_inline int
-__speck128_xts_crypt(struct blkcipher_desc *desc, struct scatterlist *dst,
-		     struct scatterlist *src, unsigned int nbytes,
-		     speck128_crypt_one_t crypt_one,
-		     speck128_xts_crypt_many_t crypt_many)
-{
-	struct crypto_blkcipher *tfm = desc->tfm;
-	const struct speck128_xts_tfm_ctx *ctx = crypto_blkcipher_ctx(tfm);
-	struct blkcipher_walk walk;
-	le128 tweak;
-	int err;
-
-	blkcipher_walk_init(&walk, dst, src, nbytes);
-	err = blkcipher_walk_virt_block(desc, &walk, SPECK_NEON_CHUNK_SIZE);
-
-	crypto_speck128_encrypt(&ctx->tweak_key, (u8 *)&tweak, walk.iv);
-
-	while (walk.nbytes > 0) {
-		unsigned int nbytes = walk.nbytes;
-		u8 *dst = walk.dst.virt.addr;
-		const u8 *src = walk.src.virt.addr;
-
-		if (nbytes >= SPECK_NEON_CHUNK_SIZE && may_use_simd()) {
-			unsigned int count;
-
-			count = round_down(nbytes, SPECK_NEON_CHUNK_SIZE);
-			kernel_neon_begin();
-			(*crypt_many)(ctx->main_key.round_keys,
-				      ctx->main_key.nrounds,
-				      dst, src, count, &tweak);
-			kernel_neon_end();
-			dst += count;
-			src += count;
-			nbytes -= count;
-		}
-
-		/* Handle any remainder with generic code */
-		while (nbytes >= sizeof(tweak)) {
-			le128_xor((le128 *)dst, (const le128 *)src, &tweak);
-			(*crypt_one)(&ctx->main_key, dst, dst);
-			le128_xor((le128 *)dst, (const le128 *)dst, &tweak);
-			gf128mul_x_ble((be128 *)&tweak, (const be128 *)&tweak);
-
-			dst += sizeof(tweak);
-			src += sizeof(tweak);
-			nbytes -= sizeof(tweak);
-		}
-		err = blkcipher_walk_done(desc, &walk, nbytes);
-	}
-
-	return err;
-}
-
-static int speck128_xts_encrypt(struct blkcipher_desc *desc,
-				struct scatterlist *dst,
-				struct scatterlist *src,
-				unsigned int nbytes)
-{
-	return __speck128_xts_crypt(desc, dst, src, nbytes,
-				    crypto_speck128_encrypt,
-				    speck128_xts_encrypt_neon);
-}
-
-static int speck128_xts_decrypt(struct blkcipher_desc *desc,
-				struct scatterlist *dst,
-				struct scatterlist *src,
-				unsigned int nbytes)
-{
-	return __speck128_xts_crypt(desc, dst, src, nbytes,
-				    crypto_speck128_decrypt,
-				    speck128_xts_decrypt_neon);
-}
-
-static int speck128_xts_setkey(struct crypto_tfm *tfm, const u8 *key,
-			       unsigned int keylen)
-{
-	struct speck128_xts_tfm_ctx *ctx = crypto_tfm_ctx(tfm);
-	int err;
-
-	if (keylen % 2)
-		return -EINVAL;
-
-	keylen /= 2;
-
-	err = crypto_speck128_setkey(&ctx->main_key, key, keylen);
-	if (err)
-		return err;
-
-	return crypto_speck128_setkey(&ctx->tweak_key, key + keylen, keylen);
-}
-
-/* Speck64 */
-
-struct speck64_xts_tfm_ctx {
-	struct speck64_tfm_ctx main_key;
-	struct speck64_tfm_ctx tweak_key;
-};
-
-asmlinkage void speck64_xts_encrypt_neon(const u32 *round_keys, int nrounds,
-					 void *dst, const void *src,
-					 unsigned int nbytes, void *tweak);
-
-asmlinkage void speck64_xts_decrypt_neon(const u32 *round_keys, int nrounds,
-					 void *dst, const void *src,
-					 unsigned int nbytes, void *tweak);
-
-typedef void (*speck64_crypt_one_t)(const struct speck64_tfm_ctx *,
-				    u8 *, const u8 *);
-typedef void (*speck64_xts_crypt_many_t)(const u32 *, int, void *,
-					 const void *, unsigned int, void *);
-
-static __always_inline int
-__speck64_xts_crypt(struct blkcipher_desc *desc, struct scatterlist *dst,
-		    struct scatterlist *src, unsigned int nbytes,
-		    speck64_crypt_one_t crypt_one,
-		    speck64_xts_crypt_many_t crypt_many)
-{
-	struct crypto_blkcipher *tfm = desc->tfm;
-	const struct speck64_xts_tfm_ctx *ctx = crypto_blkcipher_ctx(tfm);
-	struct blkcipher_walk walk;
-	__le64 tweak;
-	int err;
-
-	blkcipher_walk_init(&walk, dst, src, nbytes);
-	err = blkcipher_walk_virt_block(desc, &walk, SPECK_NEON_CHUNK_SIZE);
-
-	crypto_speck64_encrypt(&ctx->tweak_key, (u8 *)&tweak, walk.iv);
-
-	while (walk.nbytes > 0) {
-		unsigned int nbytes = walk.nbytes;
-		u8 *dst = walk.dst.virt.addr;
-		const u8 *src = walk.src.virt.addr;
-
-		if (nbytes >= SPECK_NEON_CHUNK_SIZE && may_use_simd()) {
-			unsigned int count;
-
-			count = round_down(nbytes, SPECK_NEON_CHUNK_SIZE);
-			kernel_neon_begin();
-			(*crypt_many)(ctx->main_key.round_keys,
-				      ctx->main_key.nrounds,
-				      dst, src, count, &tweak);
-			kernel_neon_end();
-			dst += count;
-			src += count;
-			nbytes -= count;
-		}
-
-		/* Handle any remainder with generic code */
-		while (nbytes >= sizeof(tweak)) {
-			*(__le64 *)dst = *(__le64 *)src ^ tweak;
-			(*crypt_one)(&ctx->main_key, dst, dst);
-			*(__le64 *)dst ^= tweak;
-			tweak = cpu_to_le64((le64_to_cpu(tweak) << 1) ^
-					    ((tweak & cpu_to_le64(1ULL << 63)) ?
-					     0x1B : 0));
-			dst += sizeof(tweak);
-			src += sizeof(tweak);
-			nbytes -= sizeof(tweak);
-		}
-		err = blkcipher_walk_done(desc, &walk, nbytes);
-	}
-
-	return err;
-}
-
-static int speck64_xts_encrypt(struct blkcipher_desc *desc,
-			       struct scatterlist *dst, struct scatterlist *src,
-			       unsigned int nbytes)
-{
-	return __speck64_xts_crypt(desc, dst, src, nbytes,
-				   crypto_speck64_encrypt,
-				   speck64_xts_encrypt_neon);
-}
-
-static int speck64_xts_decrypt(struct blkcipher_desc *desc,
-			       struct scatterlist *dst, struct scatterlist *src,
-			       unsigned int nbytes)
-{
-	return __speck64_xts_crypt(desc, dst, src, nbytes,
-				   crypto_speck64_decrypt,
-				   speck64_xts_decrypt_neon);
-}
-
-static int speck64_xts_setkey(struct crypto_tfm *tfm, const u8 *key,
-			      unsigned int keylen)
-{
-	struct speck64_xts_tfm_ctx *ctx = crypto_tfm_ctx(tfm);
-	int err;
-
-	if (keylen % 2)
-		return -EINVAL;
-
-	keylen /= 2;
-
-	err = crypto_speck64_setkey(&ctx->main_key, key, keylen);
-	if (err)
-		return err;
-
-	return crypto_speck64_setkey(&ctx->tweak_key, key + keylen, keylen);
-}
-
-static struct crypto_alg speck_algs[] = {
-	{
-		.cra_name		= "xts(speck128)",
-		.cra_driver_name	= "xts-speck128-neon",
-		.cra_priority		= 300,
-		.cra_flags		= CRYPTO_ALG_TYPE_BLKCIPHER,
-		.cra_blocksize		= SPECK128_BLOCK_SIZE,
-		.cra_type		= &crypto_blkcipher_type,
-		.cra_ctxsize		= sizeof(struct speck128_xts_tfm_ctx),
-		.cra_alignmask		= 7,
-		.cra_module		= THIS_MODULE,
-		.cra_u = {
-			.blkcipher = {
-				.min_keysize		= 2 * SPECK128_128_KEY_SIZE,
-				.max_keysize		= 2 * SPECK128_256_KEY_SIZE,
-				.ivsize			= SPECK128_BLOCK_SIZE,
-				.setkey			= speck128_xts_setkey,
-				.encrypt		= speck128_xts_encrypt,
-				.decrypt		= speck128_xts_decrypt,
-			}
-		}
-	}, {
-		.cra_name		= "xts(speck64)",
-		.cra_driver_name	= "xts-speck64-neon",
-		.cra_priority		= 300,
-		.cra_flags		= CRYPTO_ALG_TYPE_BLKCIPHER,
-		.cra_blocksize		= SPECK64_BLOCK_SIZE,
-		.cra_type		= &crypto_blkcipher_type,
-		.cra_ctxsize		= sizeof(struct speck64_xts_tfm_ctx),
-		.cra_alignmask		= 7,
-		.cra_module		= THIS_MODULE,
-		.cra_u = {
-			.blkcipher = {
-				.min_keysize		= 2 * SPECK64_96_KEY_SIZE,
-				.max_keysize		= 2 * SPECK64_128_KEY_SIZE,
-				.ivsize			= SPECK64_BLOCK_SIZE,
-				.setkey			= speck64_xts_setkey,
-				.encrypt		= speck64_xts_encrypt,
-				.decrypt		= speck64_xts_decrypt,
-			}
-		}
-	}
-};
-
-static int __init speck_neon_module_init(void)
-{
-	if (!(elf_hwcap & HWCAP_NEON))
-		return -ENODEV;
-	return crypto_register_algs(speck_algs, ARRAY_SIZE(speck_algs));
-}
-
-static void __exit speck_neon_module_exit(void)
-{
-	crypto_unregister_algs(speck_algs, ARRAY_SIZE(speck_algs));
-}
-
-module_init(speck_neon_module_init);
-module_exit(speck_neon_module_exit);
-
-MODULE_DESCRIPTION("Speck block cipher (NEON-accelerated)");
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Eric Biggers <ebiggers@google.com>");
-MODULE_ALIAS_CRYPTO("xts(speck128)");
-MODULE_ALIAS_CRYPTO("xts-speck128-neon");
-MODULE_ALIAS_CRYPTO("xts(speck64)");
-MODULE_ALIAS_CRYPTO("xts-speck64-neon");
diff --git a/arch/arm/mm/ioremap.c b/arch/arm/mm/ioremap.c
index 7ffe365b5f03..322dfe584b19 100644
--- a/arch/arm/mm/ioremap.c
+++ b/arch/arm/mm/ioremap.c
@@ -461,7 +461,7 @@ void pci_ioremap_set_mem_type(int mem_type)
 
 int pci_ioremap_io(unsigned int offset, phys_addr_t phys_addr)
 {
-	BUG_ON(offset + SZ_64K > IO_SPACE_LIMIT);
+	BUG_ON(offset + SZ_64K - 1 > IO_SPACE_LIMIT);
 
 	return ioremap_page_range(PCI_IO_VIRT_BASE + offset,
 				  PCI_IO_VIRT_BASE + offset + SZ_64K,
diff --git a/arch/arm64/crypto/Kconfig b/arch/arm64/crypto/Kconfig
index 487cd382d333..de1aab4b5da8 100644
--- a/arch/arm64/crypto/Kconfig
+++ b/arch/arm64/crypto/Kconfig
@@ -58,11 +58,4 @@ config CRYPTO_CRC32_ARM64
 	tristate "CRC32 and CRC32C using optional ARMv8 instructions"
 	depends on ARM64
 	select CRYPTO_HASH
-
-config CRYPTO_SPECK_NEON
-	tristate "NEON accelerated Speck cipher algorithms"
-	depends on KERNEL_MODE_NEON
-	select CRYPTO_BLKCIPHER
-	select CRYPTO_GF128MUL
-	select CRYPTO_SPECK
 endif
diff --git a/arch/arm64/crypto/Makefile b/arch/arm64/crypto/Makefile
index 28a71246e0a3..f0a8f2475ea3 100644
--- a/arch/arm64/crypto/Makefile
+++ b/arch/arm64/crypto/Makefile
@@ -32,9 +32,6 @@ aes-ce-blk-y := aes-glue-ce.o aes-ce.o
 obj-$(CONFIG_CRYPTO_AES_ARM64_NEON_BLK) += aes-neon-blk.o
 aes-neon-blk-y := aes-glue-neon.o aes-neon.o
 
-obj-$(CONFIG_CRYPTO_SPECK_NEON) += speck-neon.o
-speck-neon-y := speck-neon-core.o speck-neon-glue.o
-
 AFLAGS_aes-ce.o		:= -DINTERLEAVE=4
 AFLAGS_aes-neon.o	:= -DINTERLEAVE=4
 
diff --git a/arch/arm64/crypto/speck-neon-core.S b/arch/arm64/crypto/speck-neon-core.S
deleted file mode 100644
index b14463438b09..000000000000
--- a/arch/arm64/crypto/speck-neon-core.S
+++ /dev/null
@@ -1,352 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * ARM64 NEON-accelerated implementation of Speck128-XTS and Speck64-XTS
- *
- * Copyright (c) 2018 Google, Inc
- *
- * Author: Eric Biggers <ebiggers@google.com>
- */
-
-#include <linux/linkage.h>
-
-	.text
-
-	// arguments
-	ROUND_KEYS	.req	x0	// const {u64,u32} *round_keys
-	NROUNDS		.req	w1	// int nrounds
-	NROUNDS_X	.req	x1
-	DST		.req	x2	// void *dst
-	SRC		.req	x3	// const void *src
-	NBYTES		.req	w4	// unsigned int nbytes
-	TWEAK		.req	x5	// void *tweak
-
-	// registers which hold the data being encrypted/decrypted
-	// (underscores avoid a naming collision with ARM64 registers x0-x3)
-	X_0		.req	v0
-	Y_0		.req	v1
-	X_1		.req	v2
-	Y_1		.req	v3
-	X_2		.req	v4
-	Y_2		.req	v5
-	X_3		.req	v6
-	Y_3		.req	v7
-
-	// the round key, duplicated in all lanes
-	ROUND_KEY	.req	v8
-
-	// index vector for tbl-based 8-bit rotates
-	ROTATE_TABLE	.req	v9
-	ROTATE_TABLE_Q	.req	q9
-
-	// temporary registers
-	TMP0		.req	v10
-	TMP1		.req	v11
-	TMP2		.req	v12
-	TMP3		.req	v13
-
-	// multiplication table for updating XTS tweaks
-	GFMUL_TABLE	.req	v14
-	GFMUL_TABLE_Q	.req	q14
-
-	// next XTS tweak value(s)
-	TWEAKV_NEXT	.req	v15
-
-	// XTS tweaks for the blocks currently being encrypted/decrypted
-	TWEAKV0		.req	v16
-	TWEAKV1		.req	v17
-	TWEAKV2		.req	v18
-	TWEAKV3		.req	v19
-	TWEAKV4		.req	v20
-	TWEAKV5		.req	v21
-	TWEAKV6		.req	v22
-	TWEAKV7		.req	v23
-
-	.align		4
-.Lror64_8_table:
-	.octa		0x080f0e0d0c0b0a090007060504030201
-.Lror32_8_table:
-	.octa		0x0c0f0e0d080b0a090407060500030201
-.Lrol64_8_table:
-	.octa		0x0e0d0c0b0a09080f0605040302010007
-.Lrol32_8_table:
-	.octa		0x0e0d0c0f0a09080b0605040702010003
-.Lgf128mul_table:
-	.octa		0x00000000000000870000000000000001
-.Lgf64mul_table:
-	.octa		0x0000000000000000000000002d361b00
-
-/*
- * _speck_round_128bytes() - Speck encryption round on 128 bytes at a time
- *
- * Do one Speck encryption round on the 128 bytes (8 blocks for Speck128, 16 for
- * Speck64) stored in X0-X3 and Y0-Y3, using the round key stored in all lanes
- * of ROUND_KEY.  'n' is the lane size: 64 for Speck128, or 32 for Speck64.
- * 'lanes' is the lane specifier: "2d" for Speck128 or "4s" for Speck64.
- */
-.macro _speck_round_128bytes	n, lanes
-
-	// x = ror(x, 8)
-	tbl		X_0.16b, {X_0.16b}, ROTATE_TABLE.16b
-	tbl		X_1.16b, {X_1.16b}, ROTATE_TABLE.16b
-	tbl		X_2.16b, {X_2.16b}, ROTATE_TABLE.16b
-	tbl		X_3.16b, {X_3.16b}, ROTATE_TABLE.16b
-
-	// x += y
-	add		X_0.\lanes, X_0.\lanes, Y_0.\lanes
-	add		X_1.\lanes, X_1.\lanes, Y_1.\lanes
-	add		X_2.\lanes, X_2.\lanes, Y_2.\lanes
-	add		X_3.\lanes, X_3.\lanes, Y_3.\lanes
-
-	// x ^= k
-	eor		X_0.16b, X_0.16b, ROUND_KEY.16b
-	eor		X_1.16b, X_1.16b, ROUND_KEY.16b
-	eor		X_2.16b, X_2.16b, ROUND_KEY.16b
-	eor		X_3.16b, X_3.16b, ROUND_KEY.16b
-
-	// y = rol(y, 3)
-	shl		TMP0.\lanes, Y_0.\lanes, #3
-	shl		TMP1.\lanes, Y_1.\lanes, #3
-	shl		TMP2.\lanes, Y_2.\lanes, #3
-	shl		TMP3.\lanes, Y_3.\lanes, #3
-	sri		TMP0.\lanes, Y_0.\lanes, #(\n - 3)
-	sri		TMP1.\lanes, Y_1.\lanes, #(\n - 3)
-	sri		TMP2.\lanes, Y_2.\lanes, #(\n - 3)
-	sri		TMP3.\lanes, Y_3.\lanes, #(\n - 3)
-
-	// y ^= x
-	eor		Y_0.16b, TMP0.16b, X_0.16b
-	eor		Y_1.16b, TMP1.16b, X_1.16b
-	eor		Y_2.16b, TMP2.16b, X_2.16b
-	eor		Y_3.16b, TMP3.16b, X_3.16b
-.endm
-
-/*
- * _speck_unround_128bytes() - Speck decryption round on 128 bytes at a time
- *
- * This is the inverse of _speck_round_128bytes().
- */
-.macro _speck_unround_128bytes	n, lanes
-
-	// y ^= x
-	eor		TMP0.16b, Y_0.16b, X_0.16b
-	eor		TMP1.16b, Y_1.16b, X_1.16b
-	eor		TMP2.16b, Y_2.16b, X_2.16b
-	eor		TMP3.16b, Y_3.16b, X_3.16b
-
-	// y = ror(y, 3)
-	ushr		Y_0.\lanes, TMP0.\lanes, #3
-	ushr		Y_1.\lanes, TMP1.\lanes, #3
-	ushr		Y_2.\lanes, TMP2.\lanes, #3
-	ushr		Y_3.\lanes, TMP3.\lanes, #3
-	sli		Y_0.\lanes, TMP0.\lanes, #(\n - 3)
-	sli		Y_1.\lanes, TMP1.\lanes, #(\n - 3)
-	sli		Y_2.\lanes, TMP2.\lanes, #(\n - 3)
-	sli		Y_3.\lanes, TMP3.\lanes, #(\n - 3)
-
-	// x ^= k
-	eor		X_0.16b, X_0.16b, ROUND_KEY.16b
-	eor		X_1.16b, X_1.16b, ROUND_KEY.16b
-	eor		X_2.16b, X_2.16b, ROUND_KEY.16b
-	eor		X_3.16b, X_3.16b, ROUND_KEY.16b
-
-	// x -= y
-	sub		X_0.\lanes, X_0.\lanes, Y_0.\lanes
-	sub		X_1.\lanes, X_1.\lanes, Y_1.\lanes
-	sub		X_2.\lanes, X_2.\lanes, Y_2.\lanes
-	sub		X_3.\lanes, X_3.\lanes, Y_3.\lanes
-
-	// x = rol(x, 8)
-	tbl		X_0.16b, {X_0.16b}, ROTATE_TABLE.16b
-	tbl		X_1.16b, {X_1.16b}, ROTATE_TABLE.16b
-	tbl		X_2.16b, {X_2.16b}, ROTATE_TABLE.16b
-	tbl		X_3.16b, {X_3.16b}, ROTATE_TABLE.16b
-.endm
-
-.macro _next_xts_tweak	next, cur, tmp, n
-.if \n == 64
-	/*
-	 * Calculate the next tweak by multiplying the current one by x,
-	 * modulo p(x) = x^128 + x^7 + x^2 + x + 1.
-	 */
-	sshr		\tmp\().2d, \cur\().2d, #63
-	and		\tmp\().16b, \tmp\().16b, GFMUL_TABLE.16b
-	shl		\next\().2d, \cur\().2d, #1
-	ext		\tmp\().16b, \tmp\().16b, \tmp\().16b, #8
-	eor		\next\().16b, \next\().16b, \tmp\().16b
-.else
-	/*
-	 * Calculate the next two tweaks by multiplying the current ones by x^2,
-	 * modulo p(x) = x^64 + x^4 + x^3 + x + 1.
-	 */
-	ushr		\tmp\().2d, \cur\().2d, #62
-	shl		\next\().2d, \cur\().2d, #2
-	tbl		\tmp\().16b, {GFMUL_TABLE.16b}, \tmp\().16b
-	eor		\next\().16b, \next\().16b, \tmp\().16b
-.endif
-.endm
-
-/*
- * _speck_xts_crypt() - Speck-XTS encryption/decryption
- *
- * Encrypt or decrypt NBYTES bytes of data from the SRC buffer to the DST buffer
- * using Speck-XTS, specifically the variant with a block size of '2n' and round
- * count given by NROUNDS.  The expanded round keys are given in ROUND_KEYS, and
- * the current XTS tweak value is given in TWEAK.  It's assumed that NBYTES is a
- * nonzero multiple of 128.
- */
-.macro _speck_xts_crypt	n, lanes, decrypting
-
-	/*
-	 * If decrypting, modify the ROUND_KEYS parameter to point to the last
-	 * round key rather than the first, since for decryption the round keys
-	 * are used in reverse order.
-	 */
-.if \decrypting
-	mov		NROUNDS, NROUNDS	/* zero the high 32 bits */
-.if \n == 64
-	add		ROUND_KEYS, ROUND_KEYS, NROUNDS_X, lsl #3
-	sub		ROUND_KEYS, ROUND_KEYS, #8
-.else
-	add		ROUND_KEYS, ROUND_KEYS, NROUNDS_X, lsl #2
-	sub		ROUND_KEYS, ROUND_KEYS, #4
-.endif
-.endif
-
-	// Load the index vector for tbl-based 8-bit rotates
-.if \decrypting
-	ldr		ROTATE_TABLE_Q, .Lrol\n\()_8_table
-.else
-	ldr		ROTATE_TABLE_Q, .Lror\n\()_8_table
-.endif
-
-	// One-time XTS preparation
-.if \n == 64
-	// Load first tweak
-	ld1		{TWEAKV0.16b}, [TWEAK]
-
-	// Load GF(2^128) multiplication table
-	ldr		GFMUL_TABLE_Q, .Lgf128mul_table
-.else
-	// Load first tweak
-	ld1		{TWEAKV0.8b}, [TWEAK]
-
-	// Load GF(2^64) multiplication table
-	ldr		GFMUL_TABLE_Q, .Lgf64mul_table
-
-	// Calculate second tweak, packing it together with the first
-	ushr		TMP0.2d, TWEAKV0.2d, #63
-	shl		TMP1.2d, TWEAKV0.2d, #1
-	tbl		TMP0.8b, {GFMUL_TABLE.16b}, TMP0.8b
-	eor		TMP0.8b, TMP0.8b, TMP1.8b
-	mov		TWEAKV0.d[1], TMP0.d[0]
-.endif
-
-.Lnext_128bytes_\@:
-
-	// Calculate XTS tweaks for next 128 bytes
-	_next_xts_tweak	TWEAKV1, TWEAKV0, TMP0, \n
-	_next_xts_tweak	TWEAKV2, TWEAKV1, TMP0, \n
-	_next_xts_tweak	TWEAKV3, TWEAKV2, TMP0, \n
-	_next_xts_tweak	TWEAKV4, TWEAKV3, TMP0, \n
-	_next_xts_tweak	TWEAKV5, TWEAKV4, TMP0, \n
-	_next_xts_tweak	TWEAKV6, TWEAKV5, TMP0, \n
-	_next_xts_tweak	TWEAKV7, TWEAKV6, TMP0, \n
-	_next_xts_tweak	TWEAKV_NEXT, TWEAKV7, TMP0, \n
-
-	// Load the next source blocks into {X,Y}[0-3]
-	ld1		{X_0.16b-Y_1.16b}, [SRC], #64
-	ld1		{X_2.16b-Y_3.16b}, [SRC], #64
-
-	// XOR the source blocks with their XTS tweaks
-	eor		TMP0.16b, X_0.16b, TWEAKV0.16b
-	eor		Y_0.16b,  Y_0.16b, TWEAKV1.16b
-	eor		TMP1.16b, X_1.16b, TWEAKV2.16b
-	eor		Y_1.16b,  Y_1.16b, TWEAKV3.16b
-	eor		TMP2.16b, X_2.16b, TWEAKV4.16b
-	eor		Y_2.16b,  Y_2.16b, TWEAKV5.16b
-	eor		TMP3.16b, X_3.16b, TWEAKV6.16b
-	eor		Y_3.16b,  Y_3.16b, TWEAKV7.16b
-
-	/*
-	 * De-interleave the 'x' and 'y' elements of each block, i.e. make it so
-	 * that the X[0-3] registers contain only the second halves of blocks,
-	 * and the Y[0-3] registers contain only the first halves of blocks.
-	 * (Speck uses the order (y, x) rather than the more intuitive (x, y).)
-	 */
-	uzp2		X_0.\lanes, TMP0.\lanes, Y_0.\lanes
-	uzp1		Y_0.\lanes, TMP0.\lanes, Y_0.\lanes
-	uzp2		X_1.\lanes, TMP1.\lanes, Y_1.\lanes
-	uzp1		Y_1.\lanes, TMP1.\lanes, Y_1.\lanes
-	uzp2		X_2.\lanes, TMP2.\lanes, Y_2.\lanes
-	uzp1		Y_2.\lanes, TMP2.\lanes, Y_2.\lanes
-	uzp2		X_3.\lanes, TMP3.\lanes, Y_3.\lanes
-	uzp1		Y_3.\lanes, TMP3.\lanes, Y_3.\lanes
-
-	// Do the cipher rounds
-	mov		x6, ROUND_KEYS
-	mov		w7, NROUNDS
-.Lnext_round_\@:
-.if \decrypting
-	ld1r		{ROUND_KEY.\lanes}, [x6]
-	sub		x6, x6, #( \n / 8 )
-	_speck_unround_128bytes	\n, \lanes
-.else
-	ld1r		{ROUND_KEY.\lanes}, [x6], #( \n / 8 )
-	_speck_round_128bytes	\n, \lanes
-.endif
-	subs		w7, w7, #1
-	bne		.Lnext_round_\@
-
-	// Re-interleave the 'x' and 'y' elements of each block
-	zip1		TMP0.\lanes, Y_0.\lanes, X_0.\lanes
-	zip2		Y_0.\lanes,  Y_0.\lanes, X_0.\lanes
-	zip1		TMP1.\lanes, Y_1.\lanes, X_1.\lanes
-	zip2		Y_1.\lanes,  Y_1.\lanes, X_1.\lanes
-	zip1		TMP2.\lanes, Y_2.\lanes, X_2.\lanes
-	zip2		Y_2.\lanes,  Y_2.\lanes, X_2.\lanes
-	zip1		TMP3.\lanes, Y_3.\lanes, X_3.\lanes
-	zip2		Y_3.\lanes,  Y_3.\lanes, X_3.\lanes
-
-	// XOR the encrypted/decrypted blocks with the tweaks calculated earlier
-	eor		X_0.16b, TMP0.16b, TWEAKV0.16b
-	eor		Y_0.16b, Y_0.16b,  TWEAKV1.16b
-	eor		X_1.16b, TMP1.16b, TWEAKV2.16b
-	eor		Y_1.16b, Y_1.16b,  TWEAKV3.16b
-	eor		X_2.16b, TMP2.16b, TWEAKV4.16b
-	eor		Y_2.16b, Y_2.16b,  TWEAKV5.16b
-	eor		X_3.16b, TMP3.16b, TWEAKV6.16b
-	eor		Y_3.16b, Y_3.16b,  TWEAKV7.16b
-	mov		TWEAKV0.16b, TWEAKV_NEXT.16b
-
-	// Store the ciphertext in the destination buffer
-	st1		{X_0.16b-Y_1.16b}, [DST], #64
-	st1		{X_2.16b-Y_3.16b}, [DST], #64
-
-	// Continue if there are more 128-byte chunks remaining
-	subs		NBYTES, NBYTES, #128
-	bne		.Lnext_128bytes_\@
-
-	// Store the next tweak and return
-.if \n == 64
-	st1		{TWEAKV_NEXT.16b}, [TWEAK]
-.else
-	st1		{TWEAKV_NEXT.8b}, [TWEAK]
-.endif
-	ret
-.endm
-
-ENTRY(speck128_xts_encrypt_neon)
-	_speck_xts_crypt	n=64, lanes=2d, decrypting=0
-ENDPROC(speck128_xts_encrypt_neon)
-
-ENTRY(speck128_xts_decrypt_neon)
-	_speck_xts_crypt	n=64, lanes=2d, decrypting=1
-ENDPROC(speck128_xts_decrypt_neon)
-
-ENTRY(speck64_xts_encrypt_neon)
-	_speck_xts_crypt	n=32, lanes=4s, decrypting=0
-ENDPROC(speck64_xts_encrypt_neon)
-
-ENTRY(speck64_xts_decrypt_neon)
-	_speck_xts_crypt	n=32, lanes=4s, decrypting=1
-ENDPROC(speck64_xts_decrypt_neon)
diff --git a/arch/arm64/crypto/speck-neon-glue.c b/arch/arm64/crypto/speck-neon-glue.c
deleted file mode 100644
index c7d18569d408..000000000000
--- a/arch/arm64/crypto/speck-neon-glue.c
+++ /dev/null
@@ -1,308 +0,0 @@
-// SPDX-License-Identifier: GPL-2.0
-/*
- * NEON-accelerated implementation of Speck128-XTS and Speck64-XTS
- * (64-bit version; based on the 32-bit version)
- *
- * Copyright (c) 2018 Google, Inc
- */
-
-#include <asm/hwcap.h>
-#include <asm/neon.h>
-#include <asm/simd.h>
-#include <crypto/algapi.h>
-#include <crypto/gf128mul.h>
-#include <crypto/speck.h>
-#include <crypto/xts.h>
-#include <linux/kernel.h>
-#include <linux/module.h>
-
-/* The assembly functions only handle multiples of 128 bytes */
-#define SPECK_NEON_CHUNK_SIZE	128
-
-/* Speck128 */
-
-struct speck128_xts_tfm_ctx {
-	struct speck128_tfm_ctx main_key;
-	struct speck128_tfm_ctx tweak_key;
-};
-
-asmlinkage void speck128_xts_encrypt_neon(const u64 *round_keys, int nrounds,
-					  void *dst, const void *src,
-					  unsigned int nbytes, void *tweak);
-
-asmlinkage void speck128_xts_decrypt_neon(const u64 *round_keys, int nrounds,
-					  void *dst, const void *src,
-					  unsigned int nbytes, void *tweak);
-
-typedef void (*speck128_crypt_one_t)(const struct speck128_tfm_ctx *,
-				     u8 *, const u8 *);
-typedef void (*speck128_xts_crypt_many_t)(const u64 *, int, void *,
-					  const void *, unsigned int, void *);
-
-static __always_inline int
-__speck128_xts_crypt(struct blkcipher_desc *desc, struct scatterlist *dst,
-		     struct scatterlist *src, unsigned int nbytes,
-		     speck128_crypt_one_t crypt_one,
-		     speck128_xts_crypt_many_t crypt_many)
-{
-	struct crypto_blkcipher *tfm = desc->tfm;
-	const struct speck128_xts_tfm_ctx *ctx = crypto_blkcipher_ctx(tfm);
-	struct blkcipher_walk walk;
-	le128 tweak;
-	int err;
-
-	blkcipher_walk_init(&walk, dst, src, nbytes);
-	err = blkcipher_walk_virt_block(desc, &walk, SPECK_NEON_CHUNK_SIZE);
-
-	crypto_speck128_encrypt(&ctx->tweak_key, (u8 *)&tweak, walk.iv);
-
-	while (walk.nbytes > 0) {
-		unsigned int nbytes = walk.nbytes;
-		u8 *dst = walk.dst.virt.addr;
-		const u8 *src = walk.src.virt.addr;
-
-		if (nbytes >= SPECK_NEON_CHUNK_SIZE && may_use_simd()) {
-			unsigned int count;
-
-			count = round_down(nbytes, SPECK_NEON_CHUNK_SIZE);
-			kernel_neon_begin();
-			(*crypt_many)(ctx->main_key.round_keys,
-				      ctx->main_key.nrounds,
-				      dst, src, count, &tweak);
-			kernel_neon_end();
-			dst += count;
-			src += count;
-			nbytes -= count;
-		}
-
-		/* Handle any remainder with generic code */
-		while (nbytes >= sizeof(tweak)) {
-			le128_xor((le128 *)dst, (const le128 *)src, &tweak);
-			(*crypt_one)(&ctx->main_key, dst, dst);
-			le128_xor((le128 *)dst, (const le128 *)dst, &tweak);
-			gf128mul_x_ble((be128 *)&tweak, (const be128 *)&tweak);
-
-			dst += sizeof(tweak);
-			src += sizeof(tweak);
-			nbytes -= sizeof(tweak);
-		}
-		err = blkcipher_walk_done(desc, &walk, nbytes);
-	}
-
-	return err;
-}
-
-static int speck128_xts_encrypt(struct blkcipher_desc *desc,
-				struct scatterlist *dst,
-				struct scatterlist *src,
-				unsigned int nbytes)
-{
-	return __speck128_xts_crypt(desc, dst, src, nbytes,
-				    crypto_speck128_encrypt,
-				    speck128_xts_encrypt_neon);
-}
-
-static int speck128_xts_decrypt(struct blkcipher_desc *desc,
-				struct scatterlist *dst,
-				struct scatterlist *src,
-				unsigned int nbytes)
-{
-	return __speck128_xts_crypt(desc, dst, src, nbytes,
-				    crypto_speck128_decrypt,
-				    speck128_xts_decrypt_neon);
-}
-
-static int speck128_xts_setkey(struct crypto_tfm *tfm, const u8 *key,
-			       unsigned int keylen)
-{
-	struct speck128_xts_tfm_ctx *ctx = crypto_tfm_ctx(tfm);
-	int err;
-
-	if (keylen % 2)
-		return -EINVAL;
-
-	keylen /= 2;
-
-	err = crypto_speck128_setkey(&ctx->main_key, key, keylen);
-	if (err)
-		return err;
-
-	return crypto_speck128_setkey(&ctx->tweak_key, key + keylen, keylen);
-}
-
-/* Speck64 */
-
-struct speck64_xts_tfm_ctx {
-	struct speck64_tfm_ctx main_key;
-	struct speck64_tfm_ctx tweak_key;
-};
-
-asmlinkage void speck64_xts_encrypt_neon(const u32 *round_keys, int nrounds,
-					 void *dst, const void *src,
-					 unsigned int nbytes, void *tweak);
-
-asmlinkage void speck64_xts_decrypt_neon(const u32 *round_keys, int nrounds,
-					 void *dst, const void *src,
-					 unsigned int nbytes, void *tweak);
-
-typedef void (*speck64_crypt_one_t)(const struct speck64_tfm_ctx *,
-				    u8 *, const u8 *);
-typedef void (*speck64_xts_crypt_many_t)(const u32 *, int, void *,
-					 const void *, unsigned int, void *);
-
-static __always_inline int
-__speck64_xts_crypt(struct blkcipher_desc *desc, struct scatterlist *dst,
-		    struct scatterlist *src, unsigned int nbytes,
-		    speck64_crypt_one_t crypt_one,
-		    speck64_xts_crypt_many_t crypt_many)
-{
-	struct crypto_blkcipher *tfm = desc->tfm;
-	const struct speck64_xts_tfm_ctx *ctx = crypto_blkcipher_ctx(tfm);
-	struct blkcipher_walk walk;
-	__le64 tweak;
-	int err;
-
-	blkcipher_walk_init(&walk, dst, src, nbytes);
-	err = blkcipher_walk_virt_block(desc, &walk, SPECK_NEON_CHUNK_SIZE);
-
-	crypto_speck64_encrypt(&ctx->tweak_key, (u8 *)&tweak, walk.iv);
-
-	while (walk.nbytes > 0) {
-		unsigned int nbytes = walk.nbytes;
-		u8 *dst = walk.dst.virt.addr;
-		const u8 *src = walk.src.virt.addr;
-
-		if (nbytes >= SPECK_NEON_CHUNK_SIZE && may_use_simd()) {
-			unsigned int count;
-
-			count = round_down(nbytes, SPECK_NEON_CHUNK_SIZE);
-			kernel_neon_begin();
-			(*crypt_many)(ctx->main_key.round_keys,
-				      ctx->main_key.nrounds,
-				      dst, src, count, &tweak);
-			kernel_neon_end();
-			dst += count;
-			src += count;
-			nbytes -= count;
-		}
-
-		/* Handle any remainder with generic code */
-		while (nbytes >= sizeof(tweak)) {
-			*(__le64 *)dst = *(__le64 *)src ^ tweak;
-			(*crypt_one)(&ctx->main_key, dst, dst);
-			*(__le64 *)dst ^= tweak;
-			tweak = cpu_to_le64((le64_to_cpu(tweak) << 1) ^
-					    ((tweak & cpu_to_le64(1ULL << 63)) ?
-					     0x1B : 0));
-			dst += sizeof(tweak);
-			src += sizeof(tweak);
-			nbytes -= sizeof(tweak);
-		}
-		err = blkcipher_walk_done(desc, &walk, nbytes);
-	}
-
-	return err;
-}
-
-static int speck64_xts_encrypt(struct blkcipher_desc *desc,
-			       struct scatterlist *dst, struct scatterlist *src,
-			       unsigned int nbytes)
-{
-	return __speck64_xts_crypt(desc, dst, src, nbytes,
-				   crypto_speck64_encrypt,
-				   speck64_xts_encrypt_neon);
-}
-
-static int speck64_xts_decrypt(struct blkcipher_desc *desc,
-			       struct scatterlist *dst, struct scatterlist *src,
-			       unsigned int nbytes)
-{
-	return __speck64_xts_crypt(desc, dst, src, nbytes,
-				   crypto_speck64_decrypt,
-				   speck64_xts_decrypt_neon);
-}
-
-static int speck64_xts_setkey(struct crypto_tfm *tfm, const u8 *key,
-			      unsigned int keylen)
-{
-	struct speck64_xts_tfm_ctx *ctx = crypto_tfm_ctx(tfm);
-	int err;
-
-	if (keylen % 2)
-		return -EINVAL;
-
-	keylen /= 2;
-
-	err = crypto_speck64_setkey(&ctx->main_key, key, keylen);
-	if (err)
-		return err;
-
-	return crypto_speck64_setkey(&ctx->tweak_key, key + keylen, keylen);
-}
-
-static struct crypto_alg speck_algs[] = {
-	{
-		.cra_name		= "xts(speck128)",
-		.cra_driver_name	= "xts-speck128-neon",
-		.cra_priority		= 300,
-		.cra_flags		= CRYPTO_ALG_TYPE_BLKCIPHER,
-		.cra_blocksize		= SPECK128_BLOCK_SIZE,
-		.cra_type		= &crypto_blkcipher_type,
-		.cra_ctxsize		= sizeof(struct speck128_xts_tfm_ctx),
-		.cra_alignmask		= 7,
-		.cra_module		= THIS_MODULE,
-		.cra_u = {
-			.blkcipher = {
-				.min_keysize		= 2 * SPECK128_128_KEY_SIZE,
-				.max_keysize		= 2 * SPECK128_256_KEY_SIZE,
-				.ivsize			= SPECK128_BLOCK_SIZE,
-				.setkey			= speck128_xts_setkey,
-				.encrypt		= speck128_xts_encrypt,
-				.decrypt		= speck128_xts_decrypt,
-			}
-		}
-	}, {
-		.cra_name		= "xts(speck64)",
-		.cra_driver_name	= "xts-speck64-neon",
-		.cra_priority		= 300,
-		.cra_flags		= CRYPTO_ALG_TYPE_BLKCIPHER,
-		.cra_blocksize		= SPECK64_BLOCK_SIZE,
-		.cra_type		= &crypto_blkcipher_type,
-		.cra_ctxsize		= sizeof(struct speck64_xts_tfm_ctx),
-		.cra_alignmask		= 7,
-		.cra_module		= THIS_MODULE,
-		.cra_u = {
-			.blkcipher = {
-				.min_keysize		= 2 * SPECK64_96_KEY_SIZE,
-				.max_keysize		= 2 * SPECK64_128_KEY_SIZE,
-				.ivsize			= SPECK64_BLOCK_SIZE,
-				.setkey			= speck64_xts_setkey,
-				.encrypt		= speck64_xts_encrypt,
-				.decrypt		= speck64_xts_decrypt,
-			}
-		}
-	}
-};
-
-static int __init speck_neon_module_init(void)
-{
-	if (!(elf_hwcap & HWCAP_ASIMD))
-		return -ENODEV;
-	return crypto_register_algs(speck_algs, ARRAY_SIZE(speck_algs));
-}
-
-static void __exit speck_neon_module_exit(void)
-{
-	crypto_unregister_algs(speck_algs, ARRAY_SIZE(speck_algs));
-}
-
-module_init(speck_neon_module_init);
-module_exit(speck_neon_module_exit);
-
-MODULE_DESCRIPTION("Speck block cipher (NEON-accelerated)");
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("Eric Biggers <ebiggers@google.com>");
-MODULE_ALIAS_CRYPTO("xts(speck128)");
-MODULE_ALIAS_CRYPTO("xts-speck128-neon");
-MODULE_ALIAS_CRYPTO("xts(speck64)");
-MODULE_ALIAS_CRYPTO("xts-speck64-neon");
diff --git a/arch/arm64/mm/fault.c b/arch/arm64/mm/fault.c
index 5cc29354a345..9b781cb32331 100644
--- a/arch/arm64/mm/fault.c
+++ b/arch/arm64/mm/fault.c
@@ -133,26 +133,27 @@ int ptep_set_access_flags(struct vm_area_struct *vma,
 	/* only preserve the access flags and write permission */
 	pte_val(entry) &= PTE_AF | PTE_WRITE | PTE_DIRTY;
 
-	/*
-	 * PTE_RDONLY is cleared by default in the asm below, so set it in
-	 * back if necessary (read-only or clean PTE).
-	 */
+	/* set PTE_RDONLY if actual read-only or clean PTE */
 	if (!pte_write(entry) || !pte_sw_dirty(entry))
 		pte_val(entry) |= PTE_RDONLY;
 
 	/*
 	 * Setting the flags must be done atomically to avoid racing with the
-	 * hardware update of the access/dirty state.
+	 * hardware update of the access/dirty state. The PTE_RDONLY bit must
+	 * be set to the most permissive (lowest value) of *ptep and entry
+	 * (calculated as: a & b == ~(~a | ~b)).
 	 */
+	pte_val(entry) ^= PTE_RDONLY;
 	asm volatile("//	ptep_set_access_flags\n"
 	"	prfm	pstl1strm, %2\n"
 	"1:	ldxr	%0, %2\n"
-	"	and	%0, %0, %3		// clear PTE_RDONLY\n"
+	"	eor	%0, %0, %3		// negate PTE_RDONLY in *ptep\n"
 	"	orr	%0, %0, %4		// set flags\n"
+	"	eor	%0, %0, %3		// negate final PTE_RDONLY\n"
 	"	stxr	%w1, %0, %2\n"
 	"	cbnz	%w1, 1b\n"
 	: "=&r" (old_pteval), "=&r" (tmp), "+Q" (pte_val(*ptep))
-	: "L" (~PTE_RDONLY), "r" (pte_val(entry)));
+	: "L" (PTE_RDONLY), "r" (pte_val(entry)));
 
 	flush_tlb_fix_spurious_fault(vma, address);
 	return 1;
diff --git a/arch/mips/dec/int-handler.S b/arch/mips/dec/int-handler.S
index 1910223a9c02..cea2bb1621e6 100644
--- a/arch/mips/dec/int-handler.S
+++ b/arch/mips/dec/int-handler.S
@@ -147,23 +147,12 @@
 		 * Find irq with highest priority
 		 */
 		# open coded PTR_LA t1, cpu_mask_nr_tbl
-#if (_MIPS_SZPTR == 32)
+#if defined(CONFIG_32BIT) || defined(KBUILD_64BIT_SYM32)
 		# open coded la t1, cpu_mask_nr_tbl
 		lui	t1, %hi(cpu_mask_nr_tbl)
 		addiu	t1, %lo(cpu_mask_nr_tbl)
-
-#endif
-#if (_MIPS_SZPTR == 64)
-		# open coded dla t1, cpu_mask_nr_tbl
-		.set	push
-		.set	noat
-		lui	t1, %highest(cpu_mask_nr_tbl)
-		lui	AT, %hi(cpu_mask_nr_tbl)
-		daddiu	t1, t1, %higher(cpu_mask_nr_tbl)
-		daddiu	AT, AT, %lo(cpu_mask_nr_tbl)
-		dsll	t1, 32
-		daddu	t1, t1, AT
-		.set	pop
+#else
+#error GCC `-msym32' option required for 64-bit DECstation builds
 #endif
 1:		lw	t2,(t1)
 		nop
@@ -214,23 +203,12 @@
 		 * Find irq with highest priority
 		 */
 		# open coded PTR_LA t1,asic_mask_nr_tbl
-#if (_MIPS_SZPTR == 32)
+#if defined(CONFIG_32BIT) || defined(KBUILD_64BIT_SYM32)
 		# open coded la t1, asic_mask_nr_tbl
 		lui	t1, %hi(asic_mask_nr_tbl)
 		addiu	t1, %lo(asic_mask_nr_tbl)
-
-#endif
-#if (_MIPS_SZPTR == 64)
-		# open coded dla t1, asic_mask_nr_tbl
-		.set	push
-		.set	noat
-		lui	t1, %highest(asic_mask_nr_tbl)
-		lui	AT, %hi(asic_mask_nr_tbl)
-		daddiu	t1, t1, %higher(asic_mask_nr_tbl)
-		daddiu	AT, AT, %lo(asic_mask_nr_tbl)
-		dsll	t1, 32
-		daddu	t1, t1, AT
-		.set	pop
+#else
+#error GCC `-msym32' option required for 64-bit DECstation builds
 #endif
 2:		lw	t2,(t1)
 		nop
diff --git a/arch/mips/include/uapi/asm/inst.h b/arch/mips/include/uapi/asm/inst.h
index bd817e626da1..65c2f97a4535 100644
--- a/arch/mips/include/uapi/asm/inst.h
+++ b/arch/mips/include/uapi/asm/inst.h
@@ -864,7 +864,7 @@ struct mm16_r3_format {		/* Load from global pointer format */
 struct mm16_r5_format {		/* Load/store from stack pointer format */
 	__BITFIELD_FIELD(unsigned int opcode : 6,
 	__BITFIELD_FIELD(unsigned int rt : 5,
-	__BITFIELD_FIELD(signed int simmediate : 5,
+	__BITFIELD_FIELD(unsigned int imm : 5,
 	__BITFIELD_FIELD(unsigned int : 16, /* Ignored */
 	;))))
 };
diff --git a/arch/mips/kernel/process.c b/arch/mips/kernel/process.c
index dd92540fbc75..33984e1b5583 100644
--- a/arch/mips/kernel/process.c
+++ b/arch/mips/kernel/process.c
@@ -211,7 +211,7 @@ static inline int is_ra_save_ins(union mips_instruction *ip, int *poff)
 			if (ip->mm16_r5_format.rt != 31)
 				return 0;
 
-			*poff = ip->mm16_r5_format.simmediate;
+			*poff = ip->mm16_r5_format.imm;
 			*poff = (*poff << 2) / sizeof(ulong);
 			return 1;
 
@@ -345,6 +345,7 @@ static int get_frame_info(struct mips_frame_info *info)
 	bool is_mmips = IS_ENABLED(CONFIG_CPU_MICROMIPS);
 	union mips_instruction insn, *ip, *ip_end;
 	const unsigned int max_insns = 128;
+	unsigned int last_insn_size = 0;
 	unsigned int i;
 
 	info->pc_offset = -1;
@@ -356,15 +357,19 @@ static int get_frame_info(struct mips_frame_info *info)
 
 	ip_end = (void *)ip + info->func_size;
 
-	for (i = 0; i < max_insns && ip < ip_end; i++, ip++) {
+	for (i = 0; i < max_insns && ip < ip_end; i++) {
+		ip = (void *)ip + last_insn_size;
 		if (is_mmips && mm_insn_16bit(ip->halfword[0])) {
 			insn.halfword[0] = 0;
 			insn.halfword[1] = ip->halfword[0];
+			last_insn_size = 2;
 		} else if (is_mmips) {
 			insn.halfword[0] = ip->halfword[1];
 			insn.halfword[1] = ip->halfword[0];
+			last_insn_size = 4;
 		} else {
 			insn.word = ip->word;
+			last_insn_size = 4;
 		}
 
 		if (is_jump_ins(&insn))
@@ -386,8 +391,6 @@ static int get_frame_info(struct mips_frame_info *info)
 						tmp = (ip->halfword[0] >> 1);
 						info->frame_size = -(signed short)(tmp & 0xf);
 					}
-					ip = (void *) &ip->halfword[1];
-					ip--;
 				} else
 #endif
 				info->frame_size = - ip->i_format.simmediate;
diff --git a/arch/sparc/include/asm/page_64.h b/arch/sparc/include/asm/page_64.h
index 8c2a8c937540..c1263fc390db 100644
--- a/arch/sparc/include/asm/page_64.h
+++ b/arch/sparc/include/asm/page_64.h
@@ -25,6 +25,7 @@
 #define HPAGE_MASK		(~(HPAGE_SIZE - 1UL))
 #define HUGETLB_PAGE_ORDER	(HPAGE_SHIFT - PAGE_SHIFT)
 #define HAVE_ARCH_HUGETLB_UNMAPPED_AREA
+#define REAL_HPAGE_PER_HPAGE	(_AC(1,UL) << (HPAGE_SHIFT - REAL_HPAGE_SHIFT))
 #endif
 
 #ifndef __ASSEMBLY__
diff --git a/arch/sparc/kernel/pci.c b/arch/sparc/kernel/pci.c
index 9f9614df9e1e..c2b202d763a1 100644
--- a/arch/sparc/kernel/pci.c
+++ b/arch/sparc/kernel/pci.c
@@ -245,6 +245,18 @@ static void pci_parse_of_addrs(struct platform_device *op,
 	}
 }
 
+static void pci_init_dev_archdata(struct dev_archdata *sd, void *iommu,
+				  void *stc, void *host_controller,
+				  struct platform_device  *op,
+				  int numa_node)
+{
+	sd->iommu = iommu;
+	sd->stc = stc;
+	sd->host_controller = host_controller;
+	sd->op = op;
+	sd->numa_node = numa_node;
+}
+
 static struct pci_dev *of_create_pci_dev(struct pci_pbm_info *pbm,
 					 struct device_node *node,
 					 struct pci_bus *bus, int devfn)
@@ -259,13 +271,10 @@ static struct pci_dev *of_create_pci_dev(struct pci_pbm_info *pbm,
 	if (!dev)
 		return NULL;
 
+	op = of_find_device_by_node(node);
 	sd = &dev->dev.archdata;
-	sd->iommu = pbm->iommu;
-	sd->stc = &pbm->stc;
-	sd->host_controller = pbm;
-	sd->op = op = of_find_device_by_node(node);
-	sd->numa_node = pbm->numa_node;
-
+	pci_init_dev_archdata(sd, pbm->iommu, &pbm->stc, pbm, op,
+			      pbm->numa_node);
 	sd = &op->dev.archdata;
 	sd->iommu = pbm->iommu;
 	sd->stc = &pbm->stc;
@@ -1003,9 +1012,13 @@ int pcibios_add_device(struct pci_dev *dev)
 	 * Copy dev_archdata from PF to VF
 	 */
 	if (dev->is_virtfn) {
+		struct dev_archdata *psd;
+
 		pdev = dev->physfn;
-		memcpy(&dev->dev.archdata, &pdev->dev.archdata,
-		       sizeof(struct dev_archdata));
+		psd = &pdev->dev.archdata;
+		pci_init_dev_archdata(&dev->dev.archdata, psd->iommu,
+				      psd->stc, psd->host_controller, NULL,
+				      psd->numa_node);
 	}
 	return 0;
 }
diff --git a/arch/sparc/lib/U3memcpy.S b/arch/sparc/lib/U3memcpy.S
index 54f98706b03b..5a8cb37f0a3b 100644
--- a/arch/sparc/lib/U3memcpy.S
+++ b/arch/sparc/lib/U3memcpy.S
@@ -145,13 +145,13 @@ ENDPROC(U3_retl_o2_plus_GS_plus_0x08)
 ENTRY(U3_retl_o2_and_7_plus_GS)
 	and	%o2, 7, %o2
 	retl
-	 add	%o2, GLOBAL_SPARE, %o2
+	 add	%o2, GLOBAL_SPARE, %o0
 ENDPROC(U3_retl_o2_and_7_plus_GS)
 ENTRY(U3_retl_o2_and_7_plus_GS_plus_8)
 	add	GLOBAL_SPARE, 8, GLOBAL_SPARE
 	and	%o2, 7, %o2
 	retl
-	 add	%o2, GLOBAL_SPARE, %o2
+	 add	%o2, GLOBAL_SPARE, %o0
 ENDPROC(U3_retl_o2_and_7_plus_GS_plus_8)
 #endif
 
diff --git a/arch/sparc/mm/fault_64.c b/arch/sparc/mm/fault_64.c
index e15f33715103..b01ec72522cb 100644
--- a/arch/sparc/mm/fault_64.c
+++ b/arch/sparc/mm/fault_64.c
@@ -487,6 +487,7 @@ good_area:
 		tsb_grow(mm, MM_TSB_BASE, mm_rss);
 #if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE)
 	mm_rss = mm->context.hugetlb_pte_count + mm->context.thp_pte_count;
+	mm_rss *= REAL_HPAGE_PER_HPAGE;
 	if (unlikely(mm_rss >
 		     mm->context.tsb_block[MM_TSB_HUGE].tsb_rss_limit)) {
 		if (mm->context.tsb_block[MM_TSB_HUGE].tsb)
diff --git a/arch/sparc/mm/tlb.c b/arch/sparc/mm/tlb.c
index 3659d37b4d81..c56a195c9071 100644
--- a/arch/sparc/mm/tlb.c
+++ b/arch/sparc/mm/tlb.c
@@ -174,10 +174,25 @@ void set_pmd_at(struct mm_struct *mm, unsigned long addr,
 		return;
 
 	if ((pmd_val(pmd) ^ pmd_val(orig)) & _PAGE_PMD_HUGE) {
-		if (pmd_val(pmd) & _PAGE_PMD_HUGE)
-			mm->context.thp_pte_count++;
-		else
-			mm->context.thp_pte_count--;
+		/*
+		 * Note that this routine only sets pmds for THP pages.
+		 * Hugetlb pages are handled elsewhere.  We need to check
+		 * for huge zero page.  Huge zero pages are like hugetlb
+		 * pages in that there is no RSS, but there is the need
+		 * for TSB entries.  So, huge zero page counts go into
+		 * hugetlb_pte_count.
+		 */
+		if (pmd_val(pmd) & _PAGE_PMD_HUGE) {
+			if (is_huge_zero_page(pmd_page(pmd)))
+				mm->context.hugetlb_pte_count++;
+			else
+				mm->context.thp_pte_count++;
+		} else {
+			if (is_huge_zero_page(pmd_page(orig)))
+				mm->context.hugetlb_pte_count--;
+			else
+				mm->context.thp_pte_count--;
+		}
 
 		/* Do not try to allocate the TSB hash table if we
 		 * don't have one already.  We have various locks held
@@ -204,6 +219,9 @@ void set_pmd_at(struct mm_struct *mm, unsigned long addr,
 	}
 }
 
+/*
+ * This routine is only called when splitting a THP
+ */
 void pmdp_invalidate(struct vm_area_struct *vma, unsigned long address,
 		     pmd_t *pmdp)
 {
@@ -213,6 +231,15 @@ void pmdp_invalidate(struct vm_area_struct *vma, unsigned long address,
 
 	set_pmd_at(vma->vm_mm, address, pmdp, entry);
 	flush_tlb_range(vma, address, address + HPAGE_PMD_SIZE);
+
+	/*
+	 * set_pmd_at() will not be called in a way to decrement
+	 * thp_pte_count when splitting a THP, so do it now.
+	 * Sanity check pmd before doing the actual decrement.
+	 */
+	if ((pmd_val(entry) & _PAGE_PMD_HUGE) &&
+	    !is_huge_zero_page(pmd_page(entry)))
+		(vma->vm_mm)->context.thp_pte_count--;
 }
 
 void pgtable_trans_huge_deposit(struct mm_struct *mm, pmd_t *pmdp,
diff --git a/arch/sparc/mm/tsb.c b/arch/sparc/mm/tsb.c
index 266411291634..84cd593117a6 100644
--- a/arch/sparc/mm/tsb.c
+++ b/arch/sparc/mm/tsb.c
@@ -489,8 +489,10 @@ retry_tsb_alloc:
 
 int init_new_context(struct task_struct *tsk, struct mm_struct *mm)
 {
+	unsigned long mm_rss = get_mm_rss(mm);
 #if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE)
-	unsigned long total_huge_pte_count;
+	unsigned long saved_hugetlb_pte_count;
+	unsigned long saved_thp_pte_count;
 #endif
 	unsigned int i;
 
@@ -503,10 +505,12 @@ int init_new_context(struct task_struct *tsk, struct mm_struct *mm)
 	 * will re-increment the counters as the parent PTEs are
 	 * copied into the child address space.
 	 */
-	total_huge_pte_count = mm->context.hugetlb_pte_count +
-			 mm->context.thp_pte_count;
+	saved_hugetlb_pte_count = mm->context.hugetlb_pte_count;
+	saved_thp_pte_count = mm->context.thp_pte_count;
 	mm->context.hugetlb_pte_count = 0;
 	mm->context.thp_pte_count = 0;
+
+	mm_rss -= saved_thp_pte_count * (HPAGE_SIZE / PAGE_SIZE);
 #endif
 
 	/* copy_mm() copies over the parent's mm_struct before calling
@@ -519,11 +523,13 @@ int init_new_context(struct task_struct *tsk, struct mm_struct *mm)
 	/* If this is fork, inherit the parent's TSB size.  We would
 	 * grow it to that size on the first page fault anyways.
 	 */
-	tsb_grow(mm, MM_TSB_BASE, get_mm_rss(mm));
+	tsb_grow(mm, MM_TSB_BASE, mm_rss);
 
 #if defined(CONFIG_HUGETLB_PAGE) || defined(CONFIG_TRANSPARENT_HUGEPAGE)
-	if (unlikely(total_huge_pte_count))
-		tsb_grow(mm, MM_TSB_HUGE, total_huge_pte_count);
+	if (unlikely(saved_hugetlb_pte_count + saved_thp_pte_count))
+		tsb_grow(mm, MM_TSB_HUGE,
+			 (saved_hugetlb_pte_count + saved_thp_pte_count) *
+			 REAL_HPAGE_PER_HPAGE);
 #endif
 
 	if (unlikely(!mm->context.tsb_block[MM_TSB_BASE].tsb))
diff --git a/arch/um/Makefile b/arch/um/Makefile
index 9ccf462131c4..d9cd7ed27834 100644
--- a/arch/um/Makefile
+++ b/arch/um/Makefile
@@ -59,10 +59,14 @@ KBUILD_CPPFLAGS += -I$(srctree)/$(HOST_DIR)/um
 # Same things for in6addr_loopback and mktime - found in libc. For these two we
 # only get link-time error, luckily.
 #
+# -Dlongjmp=kernel_longjmp prevents anything from referencing the libpthread.a
+# embedded copy of longjmp, same thing for setjmp.
+#
 # These apply to USER_CFLAGS to.
 
 KBUILD_CFLAGS += $(CFLAGS) $(CFLAGS-y) -D__arch_um__ \
 	$(ARCH_INCLUDE) $(MODE_INCLUDE) -Dvmap=kernel_vmap	\
+	-Dlongjmp=kernel_longjmp -Dsetjmp=kernel_setjmp \
 	-Din6addr_loopback=kernel_in6addr_loopback \
 	-Din6addr_any=kernel_in6addr_any -Dstrrchr=kernel_strrchr
 
diff --git a/arch/um/os-Linux/skas/process.c b/arch/um/os-Linux/skas/process.c
index b856c66ebd3a..6ae959b4d715 100644
--- a/arch/um/os-Linux/skas/process.c
+++ b/arch/um/os-Linux/skas/process.c
@@ -585,6 +585,8 @@ int start_idle_thread(void *stack, jmp_buf *switch_buf)
 		fatal_sigsegv();
 	}
 	longjmp(*switch_buf, 1);
+
+	return 0;
 }
 
 void initial_thread_cb_skas(void (*proc)(void *), void *arg)
diff --git a/arch/x86/include/asm/percpu.h b/arch/x86/include/asm/percpu.h
index e0ba66ca68c6..f5e780bfa2b3 100644
--- a/arch/x86/include/asm/percpu.h
+++ b/arch/x86/include/asm/percpu.h
@@ -184,22 +184,22 @@ do {									\
 	typeof(var) pfo_ret__;				\
 	switch (sizeof(var)) {				\
 	case 1:						\
-		asm(op "b "__percpu_arg(1)",%0"		\
+		asm volatile(op "b "__percpu_arg(1)",%0"\
 		    : "=q" (pfo_ret__)			\
 		    : "m" (var));			\
 		break;					\
 	case 2:						\
-		asm(op "w "__percpu_arg(1)",%0"		\
+		asm volatile(op "w "__percpu_arg(1)",%0"\
 		    : "=r" (pfo_ret__)			\
 		    : "m" (var));			\
 		break;					\
 	case 4:						\
-		asm(op "l "__percpu_arg(1)",%0"		\
+		asm volatile(op "l "__percpu_arg(1)",%0"\
 		    : "=r" (pfo_ret__)			\
 		    : "m" (var));			\
 		break;					\
 	case 8:						\
-		asm(op "q "__percpu_arg(1)",%0"		\
+		asm volatile(op "q "__percpu_arg(1)",%0"\
 		    : "=r" (pfo_ret__)			\
 		    : "m" (var));			\
 		break;					\
diff --git a/arch/x86/kernel/time.c b/arch/x86/kernel/time.c
index d39c09119db6..590c8fd2ed9b 100644
--- a/arch/x86/kernel/time.c
+++ b/arch/x86/kernel/time.c
@@ -23,7 +23,7 @@
 #include <asm/time.h>
 
 #ifdef CONFIG_X86_64
-__visible volatile unsigned long jiffies __cacheline_aligned = INITIAL_JIFFIES;
+__visible volatile unsigned long jiffies __cacheline_aligned_in_smp = INITIAL_JIFFIES;
 #endif
 
 unsigned long profile_pc(struct pt_regs *regs)
diff --git a/arch/x86/mm/pageattr.c b/arch/x86/mm/pageattr.c
index 17ea653bf281..0a5b27202b1a 100644
--- a/arch/x86/mm/pageattr.c
+++ b/arch/x86/mm/pageattr.c
@@ -955,11 +955,11 @@ static void populate_pte(struct cpa_data *cpa,
 	}
 }
 
-static int populate_pmd(struct cpa_data *cpa,
-			unsigned long start, unsigned long end,
-			unsigned num_pages, pud_t *pud, pgprot_t pgprot)
+static long populate_pmd(struct cpa_data *cpa,
+			 unsigned long start, unsigned long end,
+			 unsigned num_pages, pud_t *pud, pgprot_t pgprot)
 {
-	unsigned int cur_pages = 0;
+	long cur_pages = 0;
 	pmd_t *pmd;
 	pgprot_t pmd_pgprot;
 
@@ -1029,12 +1029,12 @@ static int populate_pmd(struct cpa_data *cpa,
 	return num_pages;
 }
 
-static int populate_pud(struct cpa_data *cpa, unsigned long start, pgd_t *pgd,
-			pgprot_t pgprot)
+static long populate_pud(struct cpa_data *cpa, unsigned long start, pgd_t *pgd,
+			 pgprot_t pgprot)
 {
 	pud_t *pud;
 	unsigned long end;
-	int cur_pages = 0;
+	long cur_pages = 0;
 	pgprot_t pud_pgprot;
 
 	end = start + (cpa->numpages << PAGE_SHIFT);
@@ -1090,7 +1090,7 @@ static int populate_pud(struct cpa_data *cpa, unsigned long start, pgd_t *pgd,
 
 	/* Map trailing leftover */
 	if (start < end) {
-		int tmp;
+		long tmp;
 
 		pud = pud_offset(pgd, start);
 		if (pud_none(*pud))
@@ -1116,7 +1116,7 @@ static int populate_pgd(struct cpa_data *cpa, unsigned long addr)
 	pgprot_t pgprot = __pgprot(_KERNPG_TABLE);
 	pud_t *pud = NULL;	/* shut up gcc */
 	pgd_t *pgd_entry;
-	int ret;
+	long ret;
 
 	pgd_entry = cpa->pgd + pgd_index(addr);
 
@@ -1351,7 +1351,8 @@ static int cpa_process_alias(struct cpa_data *cpa)
 
 static int __change_page_attr_set_clr(struct cpa_data *cpa, int checkalias)
 {
-	int ret, numpages = cpa->numpages;
+	unsigned long numpages = cpa->numpages;
+	int ret;
 
 	while (numpages) {
 		/*
diff --git a/arch/x86/pci/fixup.c b/arch/x86/pci/fixup.c
index 0ae7e9fa348d..89f90549c6a8 100644
--- a/arch/x86/pci/fixup.c
+++ b/arch/x86/pci/fixup.c
@@ -541,9 +541,16 @@ static void twinhead_reserve_killing_zone(struct pci_dev *dev)
 }
 DECLARE_PCI_FIXUP_HEADER(PCI_VENDOR_ID_INTEL, 0x27B9, twinhead_reserve_killing_zone);
 
+/*
+ * Broadwell EP Home Agent BARs erroneously return non-zero values when read.
+ *
+ * See http://www.intel.com/content/www/us/en/processors/xeon/xeon-e5-v4-spec-update.html
+ * entry BDF2.
+ */
 static void pci_bdwep_bar(struct pci_dev *dev)
 {
 	dev->non_compliant_bars = 1;
 }
+DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x6f60, pci_bdwep_bar);
 DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x6fa0, pci_bdwep_bar);
 DECLARE_PCI_FIXUP_EARLY(PCI_VENDOR_ID_INTEL, 0x6fc0, pci_bdwep_bar);
diff --git a/arch/x86/um/setjmp_32.S b/arch/x86/um/setjmp_32.S
index b766792c9933..39053192918d 100644
--- a/arch/x86/um/setjmp_32.S
+++ b/arch/x86/um/setjmp_32.S
@@ -16,9 +16,9 @@
 
 	.text
 	.align 4
-	.globl setjmp
-	.type setjmp, @function
-setjmp:
+	.globl kernel_setjmp
+	.type kernel_setjmp, @function
+kernel_setjmp:
 #ifdef _REGPARM
 	movl %eax,%edx
 #else
@@ -35,13 +35,13 @@ setjmp:
 	movl %ecx,20(%edx)		# Return address
 	ret
 
-	.size setjmp,.-setjmp
+	.size kernel_setjmp,.-kernel_setjmp
 
 	.text
 	.align 4
-	.globl longjmp
-	.type longjmp, @function
-longjmp:
+	.globl kernel_longjmp
+	.type kernel_longjmp, @function
+kernel_longjmp:
 #ifdef _REGPARM
 	xchgl %eax,%edx
 #else
@@ -55,4 +55,4 @@ longjmp:
 	movl 16(%edx),%edi
 	jmp *20(%edx)
 
-	.size longjmp,.-longjmp
+	.size kernel_longjmp,.-kernel_longjmp
diff --git a/arch/x86/um/setjmp_64.S b/arch/x86/um/setjmp_64.S
index 45f547b4043e..c56942e1a38c 100644
--- a/arch/x86/um/setjmp_64.S
+++ b/arch/x86/um/setjmp_64.S
@@ -18,9 +18,9 @@
 
 	.text
 	.align 4
-	.globl setjmp
-	.type setjmp, @function
-setjmp:
+	.globl kernel_setjmp
+	.type kernel_setjmp, @function
+kernel_setjmp:
 	pop  %rsi			# Return address, and adjust the stack
 	xorl %eax,%eax			# Return value
 	movq %rbx,(%rdi)
@@ -34,13 +34,13 @@ setjmp:
 	movq %rsi,56(%rdi)		# Return address
 	ret
 
-	.size setjmp,.-setjmp
+	.size kernel_setjmp,.-kernel_setjmp
 
 	.text
 	.align 4
-	.globl longjmp
-	.type longjmp, @function
-longjmp:
+	.globl kernel_longjmp
+	.type kernel_longjmp, @function
+kernel_longjmp:
 	movl %esi,%eax			# Return value (int)
 	movq (%rdi),%rbx
 	movq 8(%rdi),%rsp
@@ -51,4 +51,4 @@ longjmp:
 	movq 48(%rdi),%r15
 	jmp *56(%rdi)
 
-	.size longjmp,.-longjmp
+	.size kernel_longjmp,.-kernel_longjmp