Merge branch 'android-4.4@c71ad0f' into branch 'msm-4.4'

* refs/heads/tmp-c71ad0f:
  BACKPORT: arm64: dts: juno: fix cluster sleep state entry latency on all SoC versions
  staging: android: ashmem: lseek failed due to no FMODE_LSEEK.
  ANDROID: sdcardfs: update module info
  ANDROID: sdcardfs: use d_splice_alias
  ANDROID: sdcardfs: add read_iter/write_iter opeations
  ANDROID: sdcardfs: fix ->llseek to update upper and lower offset
  ANDROID: sdcardfs: copy lower inode attributes in ->ioctl
  ANDROID: sdcardfs: remove unnecessary call to do_munmap
  Merge 4.4.59 into android-4.4
  UPSTREAM: ipv6 addrconf: implement RFC7559 router solicitation backoff
  android: base-cfg: enable CONFIG_INET_DIAG_DESTROY
  ANDROID: android-base.cfg: add CONFIG_MODULES option
  ANDROID: android-base.cfg: add CONFIG_IKCONFIG option
  ANDROID: android-base.cfg: properly sort the file
  ANDROID: binder: add hwbinder,vndbinder to BINDER_DEVICES.
  ANDROID: sort android-recommended.cfg
  UPSTREAM: config/android: Remove CONFIG_IPV6_PRIVACY
  UPSTREAM: config: android: set SELinux as default security mode
  config: android: move device mapper options to recommended
  ANDROID: ARM64: Allow to choose appended kernel image
  UPSTREAM: arm64: vdso: constify vm_special_mapping used for aarch32 vectors page
  UPSTREAM: arm64: vdso: add __init section marker to alloc_vectors_page
  UPSTREAM: ARM: 8597/1: VDSO: put RO and RO after init objects into proper sections
  UPSTREAM: arm64: Add support for CLOCK_MONOTONIC_RAW in clock_gettime() vDSO
  UPSTREAM: arm64: Refactor vDSO time functions
  UPSTREAM: arm64: fix vdso-offsets.h dependency
  UPSTREAM: kbuild: drop FORCE from PHONY targets
  UPSTREAM: mm: add PHYS_PFN, use it in __phys_to_pfn()
  UPSTREAM: ARM: 8476/1: VDSO: use PTR_ERR_OR_ZERO for vma check
  Linux 4.4.58
  crypto: algif_hash - avoid zero-sized array
  fbcon: Fix vc attr at deinit
  serial: 8250_pci: Detach low-level driver during PCI error recovery
  ACPI / blacklist: Make Dell Latitude 3350 ethernet work
  ACPI / blacklist: add _REV quirks for Dell Precision 5520 and 3520
  uvcvideo: uvc_scan_fallback() for webcams with broken chain
  s390/zcrypt: Introduce CEX6 toleration
  block: allow WRITE_SAME commands with the SG_IO ioctl
  vfio/spapr: Postpone allocation of userspace version of TCE table
  PCI: Do any VF BAR updates before enabling the BARs
  PCI: Ignore BAR updates on virtual functions
  PCI: Update BARs using property bits appropriate for type
  PCI: Don't update VF BARs while VF memory space is enabled
  PCI: Decouple IORESOURCE_ROM_ENABLE and PCI_ROM_ADDRESS_ENABLE
  PCI: Add comments about ROM BAR updating
  PCI: Remove pci_resource_bar() and pci_iov_resource_bar()
  PCI: Separate VF BAR updates from standard BAR updates
  x86/hyperv: Handle unknown NMIs on one CPU when unknown_nmi_panic
  igb: add i211 to i210 PHY workaround
  igb: Workaround for igb i210 firmware issue
  xen: do not re-use pirq number cached in pci device msi msg data
  xfs: clear _XBF_PAGES from buffers when readahead page
  USB: usbtmc: add missing endpoint sanity check
  nl80211: fix dumpit error path RTNL deadlocks
  xfs: fix up xfs_swap_extent_forks inline extent handling
  xfs: don't allow di_size with high bit set
  libceph: don't set weight to IN when OSD is destroyed
  raid10: increment write counter after bio is split
  cpufreq: Restore policy min/max limits on CPU online
  ARM: dts: at91: sama5d2: add dma properties to UART nodes
  ARM: at91: pm: cpu_idle: switch DDR to power-down mode
  iommu/vt-d: Fix NULL pointer dereference in device_to_iommu
  xen/acpi: upload PM state from init-domain to Xen
  mmc: sdhci: Do not disable interrupts while waiting for clock
  ext4: mark inode dirty after converting inline directory
  parport: fix attempt to write duplicate procfiles
  iio: hid-sensor-trigger: Change get poll value function order to avoid sensor properties losing after resume from S3
  iio: adc: ti_am335x_adc: fix fifo overrun recovery
  mmc: ushc: fix NULL-deref at probe
  uwb: hwa-rc: fix NULL-deref at probe
  uwb: i1480-dfu: fix NULL-deref at probe
  usb: hub: Fix crash after failure to read BOS descriptor
  usb: musb: cppi41: don't check early-TX-interrupt for Isoch transfer
  USB: wusbcore: fix NULL-deref at probe
  USB: idmouse: fix NULL-deref at probe
  USB: lvtest: fix NULL-deref at probe
  USB: uss720: fix NULL-deref at probe
  usb-core: Add LINEAR_FRAME_INTR_BINTERVAL USB quirk
  usb: gadget: f_uvc: Fix SuperSpeed companion descriptor's wBytesPerInterval
  ACM gadget: fix endianness in notifications
  USB: serial: qcserial: add Dell DW5811e
  USB: serial: option: add Quectel UC15, UC20, EC21, and EC25 modems
  ALSA: hda - Adding a group of pin definition to fix headset problem
  ALSA: ctxfi: Fix the incorrect check of dma_set_mask() call
  ALSA: seq: Fix racy cell insertions during snd_seq_pool_done()
  Input: sur40 - validate number of endpoints before using them
  Input: kbtab - validate number of endpoints before using them
  Input: cm109 - validate number of endpoints before using them
  Input: yealink - validate number of endpoints before using them
  Input: hanwang - validate number of endpoints before using them
  Input: ims-pcu - validate number of endpoints before using them
  Input: iforce - validate number of endpoints before using them
  Input: i8042 - add noloop quirk for Dell Embedded Box PC 3000
  Input: elan_i2c - add ASUS EeeBook X205TA special touchpad fw
  tcp: initialize icsk_ack.lrcvtime at session start time
  socket, bpf: fix sk_filter use after free in sk_clone_lock
  ipv4: provide stronger user input validation in nl_fib_input()
  net: bcmgenet: remove bcmgenet_internal_phy_setup()
  net/mlx5e: Count LRO packets correctly
  net/mlx5: Increase number of max QPs in default profile
  net: unix: properly re-increment inflight counter of GC discarded candidates
  amd-xgbe: Fix jumbo MTU processing on newer hardware
  net: properly release sk_frag.page
  net: bcmgenet: Do not suspend PHY if Wake-on-LAN is enabled
  net/openvswitch: Set the ipv6 source tunnel key address attribute correctly
  Linux 4.4.57
  ext4: fix fencepost in s_first_meta_bg validation
  percpu: acquire pcpu_lock when updating pcpu_nr_empty_pop_pages
  gfs2: Avoid alignment hole in struct lm_lockname
  isdn/gigaset: fix NULL-deref at probe
  target: Fix VERIFY_16 handling in sbc_parse_cdb
  scsi: libiscsi: add lock around task lists to fix list corruption regression
  scsi: lpfc: Add shutdown method for kexec
  target/pscsi: Fix TYPE_TAPE + TYPE_MEDIMUM_CHANGER export
  md/raid1/10: fix potential deadlock
  powerpc/boot: Fix zImage TOC alignment
  cpufreq: Fix and clean up show_cpuinfo_cur_freq()
  perf/core: Fix event inheritance on fork()
  give up on gcc ilog2() constant optimizations
  kernek/fork.c: allocate idle task for a CPU always on its local node
  hv_netvsc: use skb_get_hash() instead of a homegrown implementation
  tpm_tis: Use devm_free_irq not free_irq
  drm/amdgpu: add missing irq.h include
  s390/pci: fix use after free in dma_init
  KVM: PPC: Book3S PR: Fix illegal opcode emulation
  xen/qspinlock: Don't kick CPU if IRQ is not initialized
  Drivers: hv: avoid vfree() on crash
  Drivers: hv: balloon: don't crash when memory is added in non-sorted order
  pinctrl: cherryview: Do not mask all interrupts in probe
  ACPI / video: skip evaluating _DOD when it does not exist
  cxlflash: Increase cmd_per_lun for better throughput
  crypto: mcryptd - Fix load failure
  crypto: cryptd - Assign statesize properly
  crypto: ghash-clmulni - Fix load failure
  USB: don't free bandwidth_mutex too early
  usb: core: hub: hub_port_init lock controller instead of bus
  ANDROID: sdcardfs: Fix style issues in macros
  ANDROID: sdcardfs: Use seq_puts over seq_printf
  ANDROID: sdcardfs: Use to kstrout
  ANDROID: sdcardfs: Use pr_[...] instead of printk
  ANDROID: sdcardfs: remove unneeded null check
  ANDROID: sdcardfs: Fix style issues with comments
  ANDROID: sdcardfs: Fix formatting
  ANDROID: sdcardfs: correct order of descriptors
  fix the deadlock in xt_qtaguid when enable DDEBUG
  net: ipv6: Add sysctl for minimum prefix len acceptable in RIOs.
  Linux 4.4.56
  futex: Add missing error handling to FUTEX_REQUEUE_PI
  futex: Fix potential use-after-free in FUTEX_REQUEUE_PI
  x86/perf: Fix CR4.PCE propagation to use active_mm instead of mm
  x86/kasan: Fix boot with KASAN=y and PROFILE_ANNOTATED_BRANCHES=y
  fscrypto: lock inode while setting encryption policy
  fscrypt: fix renaming and linking special files
  net sched actions: decrement module reference count after table flush.
  dccp: fix memory leak during tear-down of unsuccessful connection request
  dccp/tcp: fix routing redirect race
  bridge: drop netfilter fake rtable unconditionally
  ipv6: avoid write to a possibly cloned skb
  ipv6: make ECMP route replacement less greedy
  mpls: Send route delete notifications when router module is unloaded
  act_connmark: avoid crashing on malformed nlattrs with null parms
  uapi: fix linux/packet_diag.h userspace compilation error
  vrf: Fix use-after-free in vrf_xmit
  dccp: fix use-after-free in dccp_feat_activate_values
  net: fix socket refcounting in skb_complete_tx_timestamp()
  net: fix socket refcounting in skb_complete_wifi_ack()
  tcp: fix various issues for sockets morphing to listen state
  dccp: Unlock sock before calling sk_free()
  net: net_enable_timestamp() can be called from irq contexts
  net: don't call strlen() on the user buffer in packet_bind_spkt()
  l2tp: avoid use-after-free caused by l2tp_ip_backlog_recv
  ipv4: mask tos for input route
  vti6: return GRE_KEY for vti6
  vxlan: correctly validate VXLAN ID against VXLAN_N_VID
  netlink: remove mmapped netlink support
  ANDROID: mmc: core: export emmc revision
  BACKPORT: mmc: core: Export device lifetime information through sysfs
  ANDROID: android-verity: do not compile as independent module
  ANDROID: sched: fix duplicate sched_group_energy const specifiers
  config: disable CONFIG_USELIB and CONFIG_FHANDLE
  ANDROID: power: align wakeup_sources format
  ANDROID: dm: android-verity: allow disable dm-verity for Treble VTS
  uid_sys_stats: change to use rt_mutex
  ANDROID: vfs: user permission2 in notify_change2
  ANDROID: sdcardfs: Fix gid issue
  ANDROID: sdcardfs: Use tabs instead of spaces in multiuser.h
  ANDROID: sdcardfs: Remove uninformative prints
  ANDROID: sdcardfs: move path_put outside of spinlock
  ANDROID: sdcardfs: Use case insensitive hash function
  ANDROID: sdcardfs: declare MODULE_ALIAS_FS
  ANDROID: sdcardfs: Get the blocksize from the lower fs
  ANDROID: sdcardfs: Use d_invalidate instead of drop_recurisve
  ANDROID: sdcardfs: Switch to internal case insensitive compare
  ANDROID: sdcardfs: Use spin_lock_nested
  ANDROID: sdcardfs: Replace get/put with d_lock
  ANDROID: sdcardfs: rate limit warning print
  ANDROID: sdcardfs: Fix case insensitive lookup
  ANDROID: uid_sys_stats: account for fsync syscalls
  ANDROID: sched: add a counter to track fsync
  ANDROID: uid_sys_stats: fix negative write bytes.
  ANDROID: uid_sys_stats: allow writing same state
  ANDROID: uid_sys_stats: rename uid_cputime.c to uid_sys_stats.c
  ANDROID: uid_cputime: add per-uid IO usage accounting
  DTB: Add EAS compatible Juno Energy model to 'juno.dts'
  arm64: dts: juno: Add idle-states to device tree
  ANDROID: Replace spaces by '_' for some android filesystem tracepoints.
  usb: gadget: f_accessory: Fix for UsbAccessory clean unbind.
  android: binder: move global binder state into context struct.
  android: binder: add padding to binder_fd_array_object.
  binder: use group leader instead of open thread
  nf: IDLETIMER: Use fullsock when querying uid
  nf: IDLETIMER: Fix use after free condition during work
  ANDROID: dm: android-verity: fix table_make_digest() error handling
  ANDROID: usb: gadget: function: Fix commenting style
  cpufreq: interactive governor drops bits in time calculation
  ANDROID: sdcardfs: support direct-IO (DIO) operations
  ANDROID: sdcardfs: implement vm_ops->page_mkwrite
  ANDROID: sdcardfs: Don't bother deleting freelist
  ANDROID: sdcardfs: Add missing path_put
  ANDROID: sdcardfs: Fix incorrect hash
  ANDROID: ext4 crypto: Disables zeroing on truncation when there's no key
  ANDROID: ext4: add a non-reversible key derivation method
  ANDROID: ext4: allow encrypting filenames using HEH algorithm
  ANDROID: arm64/crypto: add ARMv8-CE optimized poly_hash algorithm
  ANDROID: crypto: heh - factor out poly_hash algorithm
  ANDROID: crypto: heh - Add Hash-Encrypt-Hash (HEH) algorithm
  ANDROID: crypto: gf128mul - Add ble multiplication functions
  ANDROID: crypto: gf128mul - Refactor gf128 overflow macros and tables
  UPSTREAM: crypto: gf128mul - Zero memory when freeing multiplication table
  ANDROID: crypto: shash - Add crypto_grab_shash() and crypto_spawn_shash_alg()
  ANDROID: crypto: allow blkcipher walks over ablkcipher data
  UPSTREAM: arm/arm64: crypto: assure that ECB modes don't require an IV
  ANDROID: Refactor fs readpage/write tracepoints.
  ANDROID: export security_path_chown
  Squashfs: optimize reading uncompressed data
  Squashfs: implement .readpages()
  Squashfs: replace buffer_head with BIO
  Squashfs: refactor page_actor
  Squashfs: remove the FILE_CACHE option
  ANDROID: android-recommended.cfg: CONFIG_CPU_SW_DOMAIN_PAN=y
  FROMLIST: 9p: fix a potential acl leak
  BACKPORT: posix_acl: Clear SGID bit when setting file permissions
  UPSTREAM: udp: properly support MSG_PEEK with truncated buffers
  UPSTREAM: arm64: Allow hw watchpoint of length 3,5,6 and 7
  BACKPORT: arm64: hw_breakpoint: Handle inexact watchpoint addresses
  UPSTREAM: arm64: Allow hw watchpoint at varied offset from base address
  BACKPORT: hw_breakpoint: Allow watchpoint of length 3,5,6 and 7
  ANDROID: sdcardfs: Switch strcasecmp for internal call
  ANDROID: sdcardfs: switch to full_name_hash and qstr
  ANDROID: sdcardfs: Add GID Derivation to sdcardfs
  ANDROID: sdcardfs: Remove redundant operation
  ANDROID: sdcardfs: add support for user permission isolation
  ANDROID: sdcardfs: Refactor configfs interface
  ANDROID: sdcardfs: Allow non-owners to touch
  ANDROID: binder: fix format specifier for type binder_size_t
  ANDROID: fs: Export vfs_rmdir2
  ANDROID: fs: Export free_fs_struct and set_fs_pwd
  BACKPORT: Input: xpad - validate USB endpoint count during probe
  BACKPORT: Input: xpad - fix oops when attaching an unknown Xbox One gamepad
  ANDROID: mnt: remount should propagate to slaves of slaves
  ANDROID: sdcardfs: Switch ->d_inode to d_inode()
  ANDROID: sdcardfs: Fix locking issue with permision fix up
  ANDROID: sdcardfs: Change magic value
  ANDROID: sdcardfs: Use per mount permissions
  ANDROID: sdcardfs: Add gid and mask to private mount data
  ANDROID: sdcardfs: User new permission2 functions
  ANDROID: vfs: Add setattr2 for filesystems with per mount permissions
  ANDROID: vfs: Add permission2 for filesystems with per mount permissions
  ANDROID: vfs: Allow filesystems to access their private mount data
  ANDROID: mnt: Add filesystem private data to mount points
  ANDROID: sdcardfs: Move directory unlock before touch
  ANDROID: sdcardfs: fix external storage exporting incorrect uid
  ANDROID: sdcardfs: Added top to sdcardfs_inode_info
  ANDROID: sdcardfs: Switch package list to RCU
  ANDROID: sdcardfs: Fix locking for permission fix up
  ANDROID: sdcardfs: Check for other cases on path lookup
  ANDROID: sdcardfs: override umask on mkdir and create
  arm64: kernel: Fix build warning
  DEBUG: sched/fair: Fix sched_load_avg_cpu events for task_groups
  DEBUG: sched/fair: Fix missing sched_load_avg_cpu events
  UPSTREAM: l2tp: fix racy SOCK_ZAPPED flag check in l2tp_ip{,6}_bind()
  UPSTREAM: packet: fix race condition in packet_set_ring
  UPSTREAM: netlink: Fix dump skb leak/double free
  UPSTREAM: net: avoid signed overflows for SO_{SND|RCV}BUFFORCE
  MIPS: Prevent "restoration" of MSA context in non-MSA kernels
  net: socket: don't set sk_uid to garbage value in ->setattr()
  ANDROID: configs: CONFIG_ARM64_SW_TTBR0_PAN=y
  UPSTREAM: arm64: Disable PAN on uaccess_enable()
  UPSTREAM: arm64: Enable CONFIG_ARM64_SW_TTBR0_PAN
  UPSTREAM: arm64: xen: Enable user access before a privcmd hvc call
  UPSTREAM: arm64: Handle faults caused by inadvertent user access with PAN enabled
  BACKPORT: arm64: Disable TTBR0_EL1 during normal kernel execution
  BACKPORT: arm64: Introduce uaccess_{disable,enable} functionality based on TTBR0_EL1
  BACKPORT: arm64: Factor out TTBR0_EL1 post-update workaround into a specific asm macro
  BACKPORT: arm64: Factor out PAN enabling/disabling into separate uaccess_* macros
  UPSTREAM: arm64: alternative: add auto-nop infrastructure
  UPSTREAM: arm64: barriers: introduce nops and __nops macros for NOP sequences
  Revert "FROMLIST: arm64: Factor out PAN enabling/disabling into separate uaccess_* macros"
  Revert "FROMLIST: arm64: Factor out TTBR0_EL1 post-update workaround into a specific asm macro"
  Revert "FROMLIST: arm64: Introduce uaccess_{disable,enable} functionality based on TTBR0_EL1"
  Revert "FROMLIST: arm64: Disable TTBR0_EL1 during normal kernel execution"
  Revert "FROMLIST: arm64: Handle faults caused by inadvertent user access with PAN enabled"
  Revert "FROMLIST: arm64: xen: Enable user access before a privcmd hvc call"
  Revert "FROMLIST: arm64: Enable CONFIG_ARM64_SW_TTBR0_PAN"
  ANDROID: sched/walt: fix build failure if FAIR_GROUP_SCHED=n
  ANDROID: trace: net: use %pK for kernel pointers
  ANDROID: android-base: Enable QUOTA related configs
  net: ipv4: Don't crash if passing a null sk to ip_rt_update_pmtu.
  net: inet: Support UID-based routing in IP protocols.
  net: core: add UID to flows, rules, and routes
  net: core: Add a UID field to struct sock.
  Revert "net: core: Support UID-based routing."
  UPSTREAM: efi/arm64: Don't apply MEMBLOCK_NOMAP to UEFI memory map mapping
  UPSTREAM: arm64: mm: always take dirty state from new pte in ptep_set_access_flags
  UPSTREAM: arm64: Implement pmdp_set_access_flags() for hardware AF/DBM
  UPSTREAM: arm64: Fix typo in the pmdp_huge_get_and_clear() definition
  UPSTREAM: arm64: enable CONFIG_DEBUG_RODATA by default
  goldfish: enable CONFIG_INET_DIAG_DESTROY
  sched/walt: kill {min,max}_capacity
  sched: fix wrong truncation of walt_avg
  build: fix build config kernel_dir
  ANDROID: dm verity: add minimum prefetch size
  build: add build server configs for goldfish
  usb: gadget: Fix compilation problem with tx_qlen field

Conflicts:
	android/configs/android-base.cfg
	arch/arm64/Makefile
	arch/arm64/include/asm/cpufeature.h
	arch/arm64/kernel/vdso/gettimeofday.S
	arch/arm64/mm/cache.S
	drivers/md/Kconfig
	drivers/misc/Makefile
	drivers/mmc/host/sdhci.c
	drivers/usb/core/hcd.c
	drivers/usb/gadget/function/u_ether.c
	fs/sdcardfs/derived_perm.c
	fs/sdcardfs/file.c
	fs/sdcardfs/inode.c
	fs/sdcardfs/lookup.c
	fs/sdcardfs/main.c
	fs/sdcardfs/multiuser.h
	fs/sdcardfs/packagelist.c
	fs/sdcardfs/sdcardfs.h
	fs/sdcardfs/super.c
	include/linux/mmc/card.h
	include/linux/mmc/mmc.h
	include/trace/events/android_fs.h
	include/trace/events/android_fs_template.h
	drivers/android/binder.c
	fs/exec.c
	fs/ext4/crypto_key.c
	fs/ext4/ext4.h
	fs/ext4/inline.c
	fs/ext4/inode.c
	fs/ext4/readpage.c
	fs/f2fs/data.c
	fs/f2fs/inline.c
	fs/mpage.c
	include/linux/dcache.h
	include/trace/events/sched.h
	include/uapi/linux/ipv6.h
	net/ipv4/tcp_ipv4.c
	net/netfilter/xt_IDLETIMER.c

Change-Id: Ie345db6a14869fe0aa794aef4b71b5d0d503690b
Signed-off-by: Blagovest Kolenichev <bkolenichev@codeaurora.org>

1 files changed, 136 insertions, 35 deletions

diff --git a/crypto/gf128mul.c b/crypto/gf128mul.c
index 5276607c72d0..f3d9f6da0767 100644
--- a/crypto/gf128mul.c
+++ b/crypto/gf128mul.c
@@ -44,7 +44,7 @@
  ---------------------------------------------------------------------------
  Issue 31/01/2006
 
- This file provides fast multiplication in GF(128) as required by several
+ This file provides fast multiplication in GF(2^128) as required by several
  cryptographic authentication modes
 */
 
@@ -88,37 +88,52 @@
 	q(0xf8), q(0xf9), q(0xfa), q(0xfb), q(0xfc), q(0xfd), q(0xfe), q(0xff) \
 }
 
-/*	Given the value i in 0..255 as the byte overflow when a field element
-    in GHASH is multiplied by x^8, this function will return the values that
-    are generated in the lo 16-bit word of the field value by applying the
-    modular polynomial. The values lo_byte and hi_byte are returned via the
-    macro xp_fun(lo_byte, hi_byte) so that the values can be assembled into
-    memory as required by a suitable definition of this macro operating on
-    the table above
-*/
-
-#define xx(p, q)	0x##p##q
+/*
+ * Given a value i in 0..255 as the byte overflow when a field element
+ * in GF(2^128) is multiplied by x^8, the following macro returns the
+ * 16-bit value that must be XOR-ed into the low-degree end of the
+ * product to reduce it modulo the irreducible polynomial x^128 + x^7 +
+ * x^2 + x + 1.
+ *
+ * There are two versions of the macro, and hence two tables: one for
+ * the "be" convention where the highest-order bit is the coefficient of
+ * the highest-degree polynomial term, and one for the "le" convention
+ * where the highest-order bit is the coefficient of the lowest-degree
+ * polynomial term.  In both cases the values are stored in CPU byte
+ * endianness such that the coefficients are ordered consistently across
+ * bytes, i.e. in the "be" table bits 15..0 of the stored value
+ * correspond to the coefficients of x^15..x^0, and in the "le" table
+ * bits 15..0 correspond to the coefficients of x^0..x^15.
+ *
+ * Therefore, provided that the appropriate byte endianness conversions
+ * are done by the multiplication functions (and these must be in place
+ * anyway to support both little endian and big endian CPUs), the "be"
+ * table can be used for multiplications of both "bbe" and "ble"
+ * elements, and the "le" table can be used for multiplications of both
+ * "lle" and "lbe" elements.
+ */
 
-#define xda_bbe(i) ( \
-	(i & 0x80 ? xx(43, 80) : 0) ^ (i & 0x40 ? xx(21, c0) : 0) ^ \
-	(i & 0x20 ? xx(10, e0) : 0) ^ (i & 0x10 ? xx(08, 70) : 0) ^ \
-	(i & 0x08 ? xx(04, 38) : 0) ^ (i & 0x04 ? xx(02, 1c) : 0) ^ \
-	(i & 0x02 ? xx(01, 0e) : 0) ^ (i & 0x01 ? xx(00, 87) : 0) \
+#define xda_be(i) ( \
+	(i & 0x80 ? 0x4380 : 0) ^ (i & 0x40 ? 0x21c0 : 0) ^ \
+	(i & 0x20 ? 0x10e0 : 0) ^ (i & 0x10 ? 0x0870 : 0) ^ \
+	(i & 0x08 ? 0x0438 : 0) ^ (i & 0x04 ? 0x021c : 0) ^ \
+	(i & 0x02 ? 0x010e : 0) ^ (i & 0x01 ? 0x0087 : 0) \
 )
 
-#define xda_lle(i) ( \
-	(i & 0x80 ? xx(e1, 00) : 0) ^ (i & 0x40 ? xx(70, 80) : 0) ^ \
-	(i & 0x20 ? xx(38, 40) : 0) ^ (i & 0x10 ? xx(1c, 20) : 0) ^ \
-	(i & 0x08 ? xx(0e, 10) : 0) ^ (i & 0x04 ? xx(07, 08) : 0) ^ \
-	(i & 0x02 ? xx(03, 84) : 0) ^ (i & 0x01 ? xx(01, c2) : 0) \
+#define xda_le(i) ( \
+	(i & 0x80 ? 0xe100 : 0) ^ (i & 0x40 ? 0x7080 : 0) ^ \
+	(i & 0x20 ? 0x3840 : 0) ^ (i & 0x10 ? 0x1c20 : 0) ^ \
+	(i & 0x08 ? 0x0e10 : 0) ^ (i & 0x04 ? 0x0708 : 0) ^ \
+	(i & 0x02 ? 0x0384 : 0) ^ (i & 0x01 ? 0x01c2 : 0) \
 )
 
-static const u16 gf128mul_table_lle[256] = gf128mul_dat(xda_lle);
-static const u16 gf128mul_table_bbe[256] = gf128mul_dat(xda_bbe);
+static const u16 gf128mul_table_le[256] = gf128mul_dat(xda_le);
+static const u16 gf128mul_table_be[256] = gf128mul_dat(xda_be);
 
-/* These functions multiply a field element by x, by x^4 and by x^8
- * in the polynomial field representation. It uses 32-bit word operations
- * to gain speed but compensates for machine endianess and hence works
+/*
+ * The following functions multiply a field element by x or by x^8 in
+ * the polynomial field representation.  They use 64-bit word operations
+ * to gain speed but compensate for machine endianness and hence work
  * correctly on both styles of machine.
  */
 
@@ -126,7 +141,7 @@ static void gf128mul_x_lle(be128 *r, const be128 *x)
 {
 	u64 a = be64_to_cpu(x->a);
 	u64 b = be64_to_cpu(x->b);
-	u64 _tt = gf128mul_table_lle[(b << 7) & 0xff];
+	u64 _tt = gf128mul_table_le[(b << 7) & 0xff];
 
 	r->b = cpu_to_be64((b >> 1) | (a << 63));
 	r->a = cpu_to_be64((a >> 1) ^ (_tt << 48));
@@ -136,7 +151,7 @@ static void gf128mul_x_bbe(be128 *r, const be128 *x)
 {
 	u64 a = be64_to_cpu(x->a);
 	u64 b = be64_to_cpu(x->b);
-	u64 _tt = gf128mul_table_bbe[a >> 63];
+	u64 _tt = gf128mul_table_be[a >> 63];
 
 	r->a = cpu_to_be64((a << 1) | (b >> 63));
 	r->b = cpu_to_be64((b << 1) ^ _tt);
@@ -146,7 +161,7 @@ void gf128mul_x_ble(be128 *r, const be128 *x)
 {
 	u64 a = le64_to_cpu(x->a);
 	u64 b = le64_to_cpu(x->b);
-	u64 _tt = gf128mul_table_bbe[b >> 63];
+	u64 _tt = gf128mul_table_be[b >> 63];
 
 	r->a = cpu_to_le64((a << 1) ^ _tt);
 	r->b = cpu_to_le64((b << 1) | (a >> 63));
@@ -157,7 +172,7 @@ static void gf128mul_x8_lle(be128 *x)
 {
 	u64 a = be64_to_cpu(x->a);
 	u64 b = be64_to_cpu(x->b);
-	u64 _tt = gf128mul_table_lle[b & 0xff];
+	u64 _tt = gf128mul_table_le[b & 0xff];
 
 	x->b = cpu_to_be64((b >> 8) | (a << 56));
 	x->a = cpu_to_be64((a >> 8) ^ (_tt << 48));
@@ -167,12 +182,22 @@ static void gf128mul_x8_bbe(be128 *x)
 {
 	u64 a = be64_to_cpu(x->a);
 	u64 b = be64_to_cpu(x->b);
-	u64 _tt = gf128mul_table_bbe[a >> 56];
+	u64 _tt = gf128mul_table_be[a >> 56];
 
 	x->a = cpu_to_be64((a << 8) | (b >> 56));
 	x->b = cpu_to_be64((b << 8) ^ _tt);
 }
 
+static void gf128mul_x8_ble(be128 *x)
+{
+	u64 a = le64_to_cpu(x->b);
+	u64 b = le64_to_cpu(x->a);
+	u64 _tt = gf128mul_table_be[a >> 56];
+
+	x->b = cpu_to_le64((a << 8) | (b >> 56));
+	x->a = cpu_to_le64((b << 8) ^ _tt);
+}
+
 void gf128mul_lle(be128 *r, const be128 *b)
 {
 	be128 p[8];
@@ -249,9 +274,48 @@ void gf128mul_bbe(be128 *r, const be128 *b)
 }
 EXPORT_SYMBOL(gf128mul_bbe);
 
+void gf128mul_ble(be128 *r, const be128 *b)
+{
+	be128 p[8];
+	int i;
+
+	p[0] = *r;
+	for (i = 0; i < 7; ++i)
+		gf128mul_x_ble((be128 *)&p[i + 1], (be128 *)&p[i]);
+
+	memset(r, 0, sizeof(*r));
+	for (i = 0;;) {
+		u8 ch = ((u8 *)b)[15 - i];
+
+		if (ch & 0x80)
+			be128_xor(r, r, &p[7]);
+		if (ch & 0x40)
+			be128_xor(r, r, &p[6]);
+		if (ch & 0x20)
+			be128_xor(r, r, &p[5]);
+		if (ch & 0x10)
+			be128_xor(r, r, &p[4]);
+		if (ch & 0x08)
+			be128_xor(r, r, &p[3]);
+		if (ch & 0x04)
+			be128_xor(r, r, &p[2]);
+		if (ch & 0x02)
+			be128_xor(r, r, &p[1]);
+		if (ch & 0x01)
+			be128_xor(r, r, &p[0]);
+
+		if (++i >= 16)
+			break;
+
+		gf128mul_x8_ble(r);
+	}
+}
+EXPORT_SYMBOL(gf128mul_ble);
+
+
 /*      This version uses 64k bytes of table space.
     A 16 byte buffer has to be multiplied by a 16 byte key
-    value in GF(128).  If we consider a GF(128) value in
+    value in GF(2^128).  If we consider a GF(2^128) value in
     the buffer's lowest byte, we can construct a table of
     the 256 16 byte values that result from the 256 values
     of this byte.  This requires 4096 bytes. But we also
@@ -352,8 +416,8 @@ void gf128mul_free_64k(struct gf128mul_64k *t)
 	int i;
 
 	for (i = 0; i < 16; i++)
-		kfree(t->t[i]);
-	kfree(t);
+		kzfree(t->t[i]);
+	kzfree(t);
 }
 EXPORT_SYMBOL(gf128mul_free_64k);
 
@@ -385,7 +449,7 @@ EXPORT_SYMBOL(gf128mul_64k_bbe);
 
 /*      This version uses 4k bytes of table space.
     A 16 byte buffer has to be multiplied by a 16 byte key
-    value in GF(128).  If we consider a GF(128) value in a
+    value in GF(2^128).  If we consider a GF(2^128) value in a
     single byte, we can construct a table of the 256 16 byte
     values that result from the 256 values of this byte.
     This requires 4096 bytes. If we take the highest byte in
@@ -443,6 +507,28 @@ out:
 }
 EXPORT_SYMBOL(gf128mul_init_4k_bbe);
 
+struct gf128mul_4k *gf128mul_init_4k_ble(const be128 *g)
+{
+	struct gf128mul_4k *t;
+	int j, k;
+
+	t = kzalloc(sizeof(*t), GFP_KERNEL);
+	if (!t)
+		goto out;
+
+	t->t[1] = *g;
+	for (j = 1; j <= 64; j <<= 1)
+		gf128mul_x_ble(&t->t[j + j], &t->t[j]);
+
+	for (j = 2; j < 256; j += j)
+		for (k = 1; k < j; ++k)
+			be128_xor(&t->t[j + k], &t->t[j], &t->t[k]);
+
+out:
+	return t;
+}
+EXPORT_SYMBOL(gf128mul_init_4k_ble);
+
 void gf128mul_4k_lle(be128 *a, struct gf128mul_4k *t)
 {
 	u8 *ap = (u8 *)a;
@@ -473,5 +559,20 @@ void gf128mul_4k_bbe(be128 *a, struct gf128mul_4k *t)
 }
 EXPORT_SYMBOL(gf128mul_4k_bbe);
 
+void gf128mul_4k_ble(be128 *a, struct gf128mul_4k *t)
+{
+	u8 *ap = (u8 *)a;
+	be128 r[1];
+	int i = 15;
+
+	*r = t->t[ap[15]];
+	while (i--) {
+		gf128mul_x8_ble(r);
+		be128_xor(r, r, &t->t[ap[i]]);
+	}
+	*a = *r;
+}
+EXPORT_SYMBOL(gf128mul_4k_ble);
+
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("Functions for multiplying elements of GF(2^128)");