147 files changed, 10969 insertions, 2619 deletions

diff --git a/lib/.gitignore b/lib/.gitignore
index 3bef1ea94c99..09aae85418ab 100644
--- a/lib/.gitignore
+++ b/lib/.gitignore
@@ -3,4 +3,4 @@
 #
 gen_crc32table
 crc32table.h
-
+oid_registry_data.c
diff --git a/lib/Kconfig b/lib/Kconfig
index 6c695ff9caba..4b31a46fb307 100644
--- a/lib/Kconfig
+++ b/lib/Kconfig
@@ -16,9 +16,32 @@ config BITREVERSE
 config RATIONAL
         boolean
 
+config GENERIC_STRNCPY_FROM_USER
+        bool
+
+config GENERIC_STRNLEN_USER
+        bool
+
 config GENERIC_FIND_FIRST_BIT
         bool
 
+config NO_GENERIC_PCI_IOPORT_MAP
+        bool
+
+config GENERIC_PCI_IOMAP
+        bool
+
+config GENERIC_IOMAP
+        bool
+        select GENERIC_PCI_IOMAP
+
+config GENERIC_IO
+        boolean
+        default n
+
+config STMP_DEVICE
+        bool
+
 config CRC_CCITT
         tristate "CRC-CCITT functions"
         help
@@ -51,14 +74,71 @@ config CRC_ITU_T
           functions require M here.
 
 config CRC32
-        tristate "CRC32 functions"
+        tristate "CRC32/CRC32c functions"
         default y
         select BITREVERSE
         help
           This option is provided for the case where no in-kernel-tree
-          modules require CRC32 functions, but a module built outside the
-          kernel tree does. Such modules that use library CRC32 functions
-          require M here.
+          modules require CRC32/CRC32c functions, but a module built outside
+          the kernel tree does. Such modules that use library CRC32/CRC32c
+          functions require M here.
+
+config CRC32_SELFTEST
+        bool "CRC32 perform self test on init"
+        default n
+        depends on CRC32
+        help
+          This option enables the CRC32 library functions to perform a
+          self test on initialization. The self test computes crc32_le
+          and crc32_be over byte strings with random alignment and length
+          and computes the total elapsed time and number of bytes processed.
+
+choice
+        prompt "CRC32 implementation"
+        depends on CRC32
+        default CRC32_SLICEBY8
+        help
+          This option allows a kernel builder to override the default choice
+          of CRC32 algorithm.  Choose the default ("slice by 8") unless you
+          know that you need one of the others.
+
+config CRC32_SLICEBY8
+        bool "Slice by 8 bytes"
+        help
+          Calculate checksum 8 bytes at a time with a clever slicing algorithm.
+          This is the fastest algorithm, but comes with a 8KiB lookup table.
+          Most modern processors have enough cache to hold this table without
+          thrashing the cache.
+
+          This is the default implementation choice.  Choose this one unless
+          you have a good reason not to.
+
+config CRC32_SLICEBY4
+        bool "Slice by 4 bytes"
+        help
+          Calculate checksum 4 bytes at a time with a clever slicing algorithm.
+          This is a bit slower than slice by 8, but has a smaller 4KiB lookup
+          table.
+
+          Only choose this option if you know what you are doing.
+
+config CRC32_SARWATE
+        bool "Sarwate's Algorithm (one byte at a time)"
+        help
+          Calculate checksum a byte at a time using Sarwate's algorithm.  This
+          is not particularly fast, but has a small 256 byte lookup table.
+
+          Only choose this option if you know what you are doing.
+
+config CRC32_BIT
+        bool "Classic Algorithm (one bit at a time)"
+        help
+          Calculate checksum one bit at a time.  This is VERY slow, but has
+          no lookup table.  This is provided as a debugging option.
+
+          Only choose this option if you are debugging crc32.
+
+endchoice
 
 config CRC7
         tristate "CRC7 functions"
@@ -214,6 +294,7 @@ config BTREE
 config HAS_IOMEM
         boolean
         depends on !NO_IOMEM
+        select GENERIC_IO
         default y
 
 config HAS_IOPORT
@@ -244,6 +325,9 @@ config CPU_RMAP
         bool
         depends on SMP
 
+config DQL
+        bool
+
 #
 # Netlink attribute parsing support is select'ed if needed
 #
@@ -256,6 +340,9 @@ config NLATTR
 config GENERIC_ATOMIC64
        bool
 
+config ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE
+        def_bool y if GENERIC_ATOMIC64
+
 config LRU_CACHE
         tristate
 
@@ -269,14 +356,49 @@ config AVERAGE
 
           If unsure, say N.
 
+config CLZ_TAB
+        bool
+
 config CORDIC
-        tristate "Cordic function"
+        tristate "CORDIC algorithm"
+        help
+          This option provides an implementation of the CORDIC algorithm;
+          calculations are in fixed point. Module will be called cordic.
+
+config DDR
+        bool "JEDEC DDR data"
+        help
+          Data from JEDEC specs for DDR SDRAM memories,
+          particularly the AC timing parameters and addressing
+          information. This data is useful for drivers handling
+          DDR SDRAM controllers.
+
+config MPILIB
+        tristate
+        select CLZ_TAB
+        help
+          Multiprecision maths library from GnuPG.
+          It is used to implement RSA digital signature verification,
+          which is used by IMA/EVM digital signature extension.
+
+config SIGNATURE
+        tristate
+        depends on KEYS && CRYPTO
+        select CRYPTO_SHA1
+        select MPILIB
         help
-          The option provides arithmetic function using cordic algorithm
-          so its calculations are in fixed point. Modules can select this
-          when they require this function. Module will be called cordic.
+          Digital signature verification. Currently only RSA is supported.
+          Implementation is done using GnuPG MPI library
 
-config LLIST
+#
+# libfdt files, only selected if needed.
+#
+config LIBFDT
         bool
 
+config OID_REGISTRY
+        tristate
+        help
+          Enable fast lookup object identifier registry.
+
 endmenu
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index c0cb9c4bc46d..28e9d6c98941 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -3,12 +3,16 @@ config PRINTK_TIME
         bool "Show timing information on printks"
         depends on PRINTK
         help
-          Selecting this option causes timing information to be
-          included in printk output.  This allows you to measure
-          the interval between kernel operations, including bootup
-          operations.  This is useful for identifying long delays
-          in kernel startup.  Or add printk.time=1 at boot-time.
-          See Documentation/kernel-parameters.txt
+          Selecting this option causes time stamps of the printk()
+          messages to be added to the output of the syslog() system
+          call and at the console.
+
+          The timestamp is always recorded internally, and exported
+          to /dev/kmsg. This flag just specifies if the timestamp should
+          be included, not that the timestamp is recorded.
+
+          The behavior is also controlled by the kernel command line
+          parameter printk.time=1. See Documentation/kernel-parameters.txt
 
 config DEFAULT_MESSAGE_LOGLEVEL
         int "Default message log level (1-7)"
@@ -70,6 +74,15 @@ config STRIP_ASM_SYMS
           that look like '.Lxxx') so they don't pollute the output of
           get_wchan() and suchlike.
 
+config READABLE_ASM
+        bool "Generate readable assembler code"
+        depends on DEBUG_KERNEL
+        help
+          Disable some compiler optimizations that tend to generate human unreadable
+          assembler output. This may make the kernel slightly slower, but it helps
+          to keep kernel developers who have to stare a lot at assembler listings
+          sane.
+
 config UNUSED_SYMBOLS
         bool "Enable unused/obsolete exported symbols"
         default y if X86
@@ -117,31 +130,31 @@ config DEBUG_SECTION_MISMATCH
         help
           The section mismatch analysis checks if there are illegal
           references from one section to another section.
-          Linux will during link or during runtime drop some sections
-          and any use of code/data previously in these sections will
+          During linktime or runtime, some sections are dropped;
+          any use of code/data previously in these sections would
           most likely result in an oops.
-          In the code functions and variables are annotated with
-          __init, __devinit etc. (see full list in include/linux/init.h)
+          In the code, functions and variables are annotated with
+          __init, __devinit, etc. (see the full list in include/linux/init.h),
           which results in the code/data being placed in specific sections.
-          The section mismatch analysis is always done after a full
-          kernel build but enabling this option will in addition
-          do the following:
-          - Add the option -fno-inline-functions-called-once to gcc
-            When inlining a function annotated __init in a non-init
-            function we would lose the section information and thus
+          The section mismatch analysis is always performed after a full
+          kernel build, and enabling this option causes the following
+          additional steps to occur:
+          - Add the option -fno-inline-functions-called-once to gcc commands.
+            When inlining a function annotated with __init in a non-init
+            function, we would lose the section information and thus
             the analysis would not catch the illegal reference.
-            This option tells gcc to inline less but will also
-            result in a larger kernel.
-          - Run the section mismatch analysis for each module/built-in.o
-            When we run the section mismatch analysis on vmlinux.o we
+            This option tells gcc to inline less (but it does result in
+            a larger kernel).
+          - Run the section mismatch analysis for each module/built-in.o file.
+            When we run the section mismatch analysis on vmlinux.o, we
             lose valueble information about where the mismatch was
             introduced.
             Running the analysis for each module/built-in.o file
-            will tell where the mismatch happens much closer to the
-            source. The drawback is that we will report the same
-            mismatch at least twice.
-          - Enable verbose reporting from modpost to help solving
-            the section mismatches reported.
+            tells where the mismatch happens much closer to the
+            source. The drawback is that the same mismatch is
+            reported at least twice.
+          - Enable verbose reporting from modpost in order to help resolve
+            the section mismatches that are reported.
 
 config DEBUG_KERNEL
         bool "Kernel debugging"
@@ -166,36 +179,41 @@ config LOCKUP_DETECTOR
           hard and soft lockups.
 
           Softlockups are bugs that cause the kernel to loop in kernel
-          mode for more than 60 seconds, without giving other tasks a
+          mode for more than 20 seconds, without giving other tasks a
           chance to run.  The current stack trace is displayed upon
           detection and the system will stay locked up.
 
           Hardlockups are bugs that cause the CPU to loop in kernel mode
-          for more than 60 seconds, without letting other interrupts have a
+          for more than 10 seconds, without letting other interrupts have a
           chance to run.  The current stack trace is displayed upon detection
           and the system will stay locked up.
 
           The overhead should be minimal.  A periodic hrtimer runs to
-          generate interrupts and kick the watchdog task every 10-12 seconds.
-          An NMI is generated every 60 seconds or so to check for hardlockups.
+          generate interrupts and kick the watchdog task every 4 seconds.
+          An NMI is generated every 10 seconds or so to check for hardlockups.
+
+          The frequency of hrtimer and NMI events and the soft and hard lockup
+          thresholds can be controlled through the sysctl watchdog_thresh.
 
 config HARDLOCKUP_DETECTOR
-        def_bool LOCKUP_DETECTOR && PERF_EVENTS && HAVE_PERF_EVENTS_NMI && \
-                 !ARCH_HAS_NMI_WATCHDOG
+        def_bool y
+        depends on LOCKUP_DETECTOR && !HAVE_NMI_WATCHDOG
+        depends on PERF_EVENTS && HAVE_PERF_EVENTS_NMI
 
 config BOOTPARAM_HARDLOCKUP_PANIC
         bool "Panic (Reboot) On Hard Lockups"
-        depends on LOCKUP_DETECTOR
+        depends on HARDLOCKUP_DETECTOR
         help
           Say Y here to enable the kernel to panic on "hard lockups",
           which are bugs that cause the kernel to loop in kernel
-          mode with interrupts disabled for more than 60 seconds.
+          mode with interrupts disabled for more than 10 seconds (configurable
+          using the watchdog_thresh sysctl).
 
           Say N if unsure.
 
 config BOOTPARAM_HARDLOCKUP_PANIC_VALUE
         int
-        depends on LOCKUP_DETECTOR
+        depends on HARDLOCKUP_DETECTOR
         range 0 1
         default 0 if !BOOTPARAM_HARDLOCKUP_PANIC
         default 1 if BOOTPARAM_HARDLOCKUP_PANIC
@@ -206,8 +224,8 @@ config BOOTPARAM_SOFTLOCKUP_PANIC
         help
           Say Y here to enable the kernel to panic on "soft lockups",
           which are bugs that cause the kernel to loop in kernel
-          mode for more than 60 seconds, without giving other tasks a
-          chance to run.
+          mode for more than 20 seconds (configurable using the watchdog_thresh
+          sysctl), without giving other tasks a chance to run.
 
           The panic can be used in combination with panic_timeout,
           to cause the system to reboot automatically after a
@@ -224,6 +242,26 @@ config BOOTPARAM_SOFTLOCKUP_PANIC_VALUE
         default 0 if !BOOTPARAM_SOFTLOCKUP_PANIC
         default 1 if BOOTPARAM_SOFTLOCKUP_PANIC
 
+config PANIC_ON_OOPS
+        bool "Panic on Oops" if EXPERT
+        default n
+        help
+          Say Y here to enable the kernel to panic when it oopses. This
+          has the same effect as setting oops=panic on the kernel command
+          line.
+
+          This feature is useful to ensure that the kernel does not do
+          anything erroneous after an oops which could result in data
+          corruption or other issues.
+
+          Say N if unsure.
+
+config PANIC_ON_OOPS_VALUE
+        int
+        range 0 1
+        default 0 if !PANIC_ON_OOPS
+        default 1 if PANIC_ON_OOPS
+
 config DETECT_HUNG_TASK
         bool "Detect Hung Tasks"
         depends on DEBUG_KERNEL
@@ -248,8 +286,9 @@ config DEFAULT_HUNG_TASK_TIMEOUT
           to determine when a task has become non-responsive and should
           be considered hung.
 
-          It can be adjusted at runtime via the kernel.hung_task_timeout
-          sysctl or by writing a value to /proc/sys/kernel/hung_task_timeout.
+          It can be adjusted at runtime via the kernel.hung_task_timeout_secs
+          sysctl or by writing a value to
+          /proc/sys/kernel/hung_task_timeout_secs.
 
           A timeout of 0 disables the check.  The default is two minutes.
           Keeping the default should be fine in most cases.
@@ -411,11 +450,12 @@ config SLUB_STATS
           out which slabs are relevant to a particular load.
           Try running: slabinfo -DA
 
+config HAVE_DEBUG_KMEMLEAK
+        bool
+
 config DEBUG_KMEMLEAK
         bool "Kernel memory leak detector"
-        depends on DEBUG_KERNEL && EXPERIMENTAL && !MEMORY_HOTPLUG && \
-                (X86 || ARM || PPC || MIPS || S390 || SPARC64 || SUPERH || MICROBLAZE || TILE)
-
+        depends on DEBUG_KERNEL && EXPERIMENTAL && HAVE_DEBUG_KMEMLEAK
         select DEBUG_FS
         select STACKTRACE if STACKTRACE_SUPPORT
         select KALLSYMS
@@ -494,6 +534,7 @@ config RT_MUTEX_TESTER
 config DEBUG_SPINLOCK
         bool "Spinlock and rw-lock debugging: basic checks"
         depends on DEBUG_KERNEL
+        select UNINLINE_SPIN_UNLOCK
         help
           Say Y here and build SMP to catch missing spinlock initialization
           and certain other kinds of spinlock errors commonly made.  This is
@@ -590,6 +631,20 @@ config PROVE_RCU_REPEATEDLY
 
          Say N if you are unsure.
 
+config PROVE_RCU_DELAY
+        bool "RCU debugging: preemptible RCU race provocation"
+        depends on DEBUG_KERNEL && PREEMPT_RCU
+        default n
+        help
+         There is a class of races that involve an unlikely preemption
+         of __rcu_read_unlock() just after ->rcu_read_lock_nesting has
+         been set to INT_MIN.  This feature inserts a delay at that
+         point to increase the probability of these races.
+
+         Say Y to increase probability of preemption of __rcu_read_unlock().
+
+         Say N if you are unsure.
+
 config SPARSE_RCU_POINTER
         bool "RCU debugging: sparse-based checks for pointer usage"
         default n
@@ -675,7 +730,7 @@ config STACKTRACE
 
 config DEBUG_STACK_USAGE
         bool "Stack utilization instrumentation"
-        depends on DEBUG_KERNEL
+        depends on DEBUG_KERNEL && !IA64 && !PARISC
         help
           Enables the display of the minimum amount of free stack which each
           task has ever had available in the sysrq-T and sysrq-P debug output.
@@ -696,11 +751,12 @@ config DEBUG_HIGHMEM
           This options enables addition error checking for high memory systems.
           Disable for production systems.
 
+config HAVE_DEBUG_BUGVERBOSE
+        bool
+
 config DEBUG_BUGVERBOSE
         bool "Verbose BUG() reporting (adds 70K)" if DEBUG_KERNEL && EXPERT
-        depends on BUG
-        depends on ARM || AVR32 || M32R || M68K || SPARC32 || SPARC64 || \
-                   FRV || SUPERH || GENERIC_BUG || BLACKFIN || MN10300 || TILE
+        depends on BUG && (GENERIC_BUG || HAVE_DEBUG_BUGVERBOSE)
         default y
         help
           Say Y here to make BUG() panics output the file name and line number
@@ -742,6 +798,15 @@ config DEBUG_VM
 
           If unsure, say N.
 
+config DEBUG_VM_RB
+        bool "Debug VM red-black trees"
+        depends on DEBUG_VM
+        help
+          Enable this to turn on more extended checks in the virtual-memory
+          system that may impact performance.
+
+          If unsure, say N.
+
 config DEBUG_VIRTUAL
         bool "Debug VM translations"
         depends on DEBUG_KERNEL && X86
@@ -835,7 +900,7 @@ config DEBUG_CREDENTIALS
 
 #
 # Select this config option from the architecture Kconfig, if it
-# it is preferred to always offer frame pointers as a config
+# is preferred to always offer frame pointers as a config
 # option on the architecture (regardless of KERNEL_DEBUG):
 #
 config ARCH_WANT_FRAME_POINTERS
@@ -926,6 +991,30 @@ config RCU_CPU_STALL_VERBOSE
 
           Say Y if you want to enable such checks.
 
+config RCU_CPU_STALL_INFO
+        bool "Print additional diagnostics on RCU CPU stall"
+        depends on (TREE_RCU || TREE_PREEMPT_RCU) && DEBUG_KERNEL
+        default n
+        help
+          For each stalled CPU that is aware of the current RCU grace
+          period, print out additional per-CPU diagnostic information
+          regarding scheduling-clock ticks, idle state, and,
+          for RCU_FAST_NO_HZ kernels, idle-entry state.
+
+          Say N if you are unsure.
+
+          Say Y if you want to enable such diagnostics.
+
+config RCU_TRACE
+        bool "Enable tracing for RCU"
+        depends on DEBUG_KERNEL
+        help
+          This option provides tracing in RCU which presents stats
+          in debugfs for debugging RCU implementation.
+
+          Say Y here if you want to enable RCU tracing
+          Say N if you are unsure.
+
 config KPROBES_SANITY_TEST
         bool "Kprobes sanity tests"
         depends on DEBUG_KERNEL
@@ -1021,18 +1110,105 @@ config LKDTM
         Documentation on how to use the module can be found in
         Documentation/fault-injection/provoke-crashes.txt
 
+config NOTIFIER_ERROR_INJECTION
+        tristate "Notifier error injection"
+        depends on DEBUG_KERNEL
+        select DEBUG_FS
+        help
+          This option provides the ability to inject artifical errors to
+          specified notifier chain callbacks. It is useful to test the error
+          handling of notifier call chain failures.
+
+          Say N if unsure.
+
 config CPU_NOTIFIER_ERROR_INJECT
         tristate "CPU notifier error injection module"
-        depends on HOTPLUG_CPU && DEBUG_KERNEL
+        depends on HOTPLUG_CPU && NOTIFIER_ERROR_INJECTION
         help
           This option provides a kernel module that can be used to test
-          the error handling of the cpu notifiers
+          the error handling of the cpu notifiers by injecting artifical
+          errors to CPU notifier chain callbacks.  It is controlled through
+          debugfs interface under /sys/kernel/debug/notifier-error-inject/cpu
+
+          If the notifier call chain should be failed with some events
+          notified, write the error code to "actions/<notifier event>/error".
+
+          Example: Inject CPU offline error (-1 == -EPERM)
+
+          # cd /sys/kernel/debug/notifier-error-inject/cpu
+          # echo -1 > actions/CPU_DOWN_PREPARE/error
+          # echo 0 > /sys/devices/system/cpu/cpu1/online
+          bash: echo: write error: Operation not permitted
 
           To compile this code as a module, choose M here: the module will
           be called cpu-notifier-error-inject.
 
           If unsure, say N.
 
+config PM_NOTIFIER_ERROR_INJECT
+        tristate "PM notifier error injection module"
+        depends on PM && NOTIFIER_ERROR_INJECTION
+        default m if PM_DEBUG
+        help
+          This option provides the ability to inject artifical errors to
+          PM notifier chain callbacks.  It is controlled through debugfs
+          interface /sys/kernel/debug/notifier-error-inject/pm
+
+          If the notifier call chain should be failed with some events
+          notified, write the error code to "actions/<notifier event>/error".
+
+          Example: Inject PM suspend error (-12 = -ENOMEM)
+
+          # cd /sys/kernel/debug/notifier-error-inject/pm/
+          # echo -12 > actions/PM_SUSPEND_PREPARE/error
+          # echo mem > /sys/power/state
+          bash: echo: write error: Cannot allocate memory
+
+          To compile this code as a module, choose M here: the module will
+          be called pm-notifier-error-inject.
+
+          If unsure, say N.
+
+config MEMORY_NOTIFIER_ERROR_INJECT
+        tristate "Memory hotplug notifier error injection module"
+        depends on MEMORY_HOTPLUG_SPARSE && NOTIFIER_ERROR_INJECTION
+        help
+          This option provides the ability to inject artifical errors to
+          memory hotplug notifier chain callbacks.  It is controlled through
+          debugfs interface under /sys/kernel/debug/notifier-error-inject/memory
+
+          If the notifier call chain should be failed with some events
+          notified, write the error code to "actions/<notifier event>/error".
+
+          Example: Inject memory hotplug offline error (-12 == -ENOMEM)
+
+          # cd /sys/kernel/debug/notifier-error-inject/memory
+          # echo -12 > actions/MEM_GOING_OFFLINE/error
+          # echo offline > /sys/devices/system/memory/memoryXXX/state
+          bash: echo: write error: Cannot allocate memory
+
+          To compile this code as a module, choose M here: the module will
+          be called pSeries-reconfig-notifier-error-inject.
+
+          If unsure, say N.
+
+config PSERIES_RECONFIG_NOTIFIER_ERROR_INJECT
+        tristate "pSeries reconfig notifier error injection module"
+        depends on PPC_PSERIES && NOTIFIER_ERROR_INJECTION
+        help
+          This option provides the ability to inject artifical errors to
+          pSeries reconfig notifier chain callbacks.  It is controlled
+          through debugfs interface under
+          /sys/kernel/debug/notifier-error-inject/pSeries-reconfig/
+
+          If the notifier call chain should be failed with some events
+          notified, write the error code to "actions/<notifier event>/error".
+
+          To compile this code as a module, choose M here: the module will
+          be called memory-notifier-error-inject.
+
+          If unsure, say N.
+
 config FAULT_INJECTION
         bool "Fault-injection framework"
         depends on DEBUG_KERNEL
@@ -1070,6 +1246,17 @@ config FAIL_IO_TIMEOUT
           Only works with drivers that use the generic timeout handling,
           for others it wont do anything.
 
+config FAIL_MMC_REQUEST
+        bool "Fault-injection capability for MMC IO"
+        select DEBUG_FS
+        depends on FAULT_INJECTION && MMC
+        help
+          Provide fault-injection capability for MMC IO.
+          This will make the mmc core return data errors. This is
+          useful to test the error handling in the mmc block device
+          and to test how the mmc host driver handles retries from
+          the block device.
+
 config FAULT_INJECTION_DEBUG_FS
         bool "Debugfs entries for fault-injection capabilities"
         depends on FAULT_INJECTION && SYSFS && DEBUG_FS
@@ -1081,7 +1268,7 @@ config FAULT_INJECTION_STACKTRACE_FILTER
         depends on FAULT_INJECTION_DEBUG_FS && STACKTRACE_SUPPORT
         depends on !X86_64
         select STACKTRACE
-        select FRAME_POINTER if !PPC && !S390 && !MICROBLAZE
+        select FRAME_POINTER if !PPC && !S390 && !MICROBLAZE && !ARM_UNWIND
         help
           Provide stacktrace filter for fault-injection capabilities
 
@@ -1091,7 +1278,7 @@ config LATENCYTOP
         depends on DEBUG_KERNEL
         depends on STACKTRACE_SUPPORT
         depends on PROC_FS
-        select FRAME_POINTER if !MIPS && !PPC && !S390 && !MICROBLAZE
+        select FRAME_POINTER if !MIPS && !PPC && !S390 && !MICROBLAZE && !ARM_UNWIND
         select KALLSYMS
         select KALLSYMS_ALL
         select STACKTRACE
@@ -1101,17 +1288,22 @@ config LATENCYTOP
           Enable this option if you want to use the LatencyTOP tool
           to find out which userspace is blocking on what kernel operations.
 
-config SYSCTL_SYSCALL_CHECK
-        bool "Sysctl checks"
-        depends on SYSCTL
-        ---help---
-          sys_sysctl uses binary paths that have been found challenging
-          to properly maintain and use. This enables checks that help
-          you to keep things correct.
-
 source mm/Kconfig.debug
 source kernel/trace/Kconfig
 
+config RBTREE_TEST
+        tristate "Red-Black tree test"
+        depends on m && DEBUG_KERNEL
+        help
+          A benchmark measuring the performance of the rbtree library.
+          Also includes rbtree invariant checks.
+
+config INTERVAL_TREE_TEST
+        tristate "Interval tree test"
+        depends on m && DEBUG_KERNEL
+        help
+          A benchmark measuring the performance of the interval tree library
+
 config PROVIDE_OHCI1394_DMA_INIT
         bool "Remote debugging over FireWire early on boot"
         depends on PCI && X86
@@ -1172,8 +1364,13 @@ config DYNAMIC_DEBUG
           otherwise be available at runtime. These messages can then be
           enabled/disabled based on various levels of scope - per source file,
           function, module, format string, and line number. This mechanism
-          implicitly enables all pr_debug() and dev_dbg() calls. The impact of
-          this compile option is a larger kernel text size of about 2%.
+          implicitly compiles in all pr_debug() and dev_dbg() calls, which
+          enlarges the kernel text size by about 2%.
+
+          If a source file is compiled with DEBUG flag set, any
+          pr_debug() calls in it are enabled by default, but can be
+          disabled at runtime as below.  Note that DEBUG flag is
+          turned on by many CONFIG_*DEBUG* options.
 
           Usage:
 
@@ -1190,16 +1387,16 @@ config DYNAMIC_DEBUG
           lineno : line number of the debug statement
           module : module that contains the debug statement
           function : function that contains the debug statement
-          flags : 'p' means the line is turned 'on' for printing
+          flags : '=p' means the line is turned 'on' for printing
           format : the format used for the debug statement
 
           From a live system:
 
                 nullarbor:~ # cat <debugfs>/dynamic_debug/control
                 # filename:lineno [module]function flags format
-                fs/aio.c:222 [aio]__put_ioctx - "__put_ioctx:\040freeing\040%p\012"
-                fs/aio.c:248 [aio]ioctx_alloc - "ENOMEM:\040nr_events\040too\040high\012"
-                fs/aio.c:1770 [aio]sys_io_cancel - "calling\040cancel\012"
+                fs/aio.c:222 [aio]__put_ioctx =_ "__put_ioctx:\040freeing\040%p\012"
+                fs/aio.c:248 [aio]ioctx_alloc =_ "ENOMEM:\040nr_events\040too\040high\012"
+                fs/aio.c:1770 [aio]sys_io_cancel =_ "calling\040cancel\012"
 
           Example usage:
 
diff --git a/lib/Makefile b/lib/Makefile
index d5d175c8a6ca..821a16229111 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -9,20 +9,20 @@ endif
 
 lib-y := ctype.o string.o vsprintf.o cmdline.o \
          rbtree.o radix-tree.o dump_stack.o timerqueue.o\
-         idr.o int_sqrt.o extable.o prio_tree.o \
+         idr.o int_sqrt.o extable.o \
          sha1.o md5.o irq_regs.o reciprocal_div.o argv_split.o \
-         proportions.o prio_heap.o ratelimit.o show_mem.o \
-         is_single_threaded.o plist.o decompress.o find_next_bit.o
+         proportions.o flex_proportions.o prio_heap.o ratelimit.o show_mem.o \
+         is_single_threaded.o plist.o decompress.o
 
 lib-$(CONFIG_MMU) += ioremap.o
 lib-$(CONFIG_SMP) += cpumask.o
 
-lib-y   += kobject.o kref.o klist.o
+lib-y   += kobject.o klist.o
 
 obj-y += bcd.o div64.o sort.o parser.o halfmd4.o debug_locks.o random32.o \
          bust_spinlocks.o hexdump.o kasprintf.o bitmap.o scatterlist.o \
          string_helpers.o gcd.o lcm.o list_sort.o uuid.o flex_array.o \
-         bsearch.o find_last_bit.o
+         bsearch.o find_last_bit.o find_next_bit.o llist.o memweight.o
 obj-y += kstrtox.o
 obj-$(CONFIG_TEST_KSTRTOX) += test-kstrtox.o
 
@@ -33,6 +33,7 @@ endif
 
 lib-$(CONFIG_HOTPLUG) += kobject_uevent.o
 obj-$(CONFIG_GENERIC_IOMAP) += iomap.o
+obj-$(CONFIG_GENERIC_PCI_IOMAP) += pci_iomap.o
 obj-$(CONFIG_HAS_IOMEM) += iomap_copy.o devres.o
 obj-$(CONFIG_CHECK_SIGNATURE) += check_signature.o
 obj-$(CONFIG_DEBUG_LOCKING_API_SELFTESTS) += locking-selftest.o
@@ -89,7 +90,12 @@ obj-$(CONFIG_AUDIT_GENERIC) += audit.o
 obj-$(CONFIG_SWIOTLB) += swiotlb.o
 obj-$(CONFIG_IOMMU_HELPER) += iommu-helper.o
 obj-$(CONFIG_FAULT_INJECTION) += fault-inject.o
+obj-$(CONFIG_NOTIFIER_ERROR_INJECTION) += notifier-error-inject.o
 obj-$(CONFIG_CPU_NOTIFIER_ERROR_INJECT) += cpu-notifier-error-inject.o
+obj-$(CONFIG_PM_NOTIFIER_ERROR_INJECT) += pm-notifier-error-inject.o
+obj-$(CONFIG_MEMORY_NOTIFIER_ERROR_INJECT) += memory-notifier-error-inject.o
+obj-$(CONFIG_PSERIES_RECONFIG_NOTIFIER_ERROR_INJECT) += \
+        pSeries-reconfig-notifier-error-inject.o
 
 lib-$(CONFIG_GENERIC_BUG) += bug.o
 
@@ -115,7 +121,31 @@ obj-$(CONFIG_CPU_RMAP) += cpu_rmap.o
 
 obj-$(CONFIG_CORDIC) += cordic.o
 
-obj-$(CONFIG_LLIST) += llist.o
+obj-$(CONFIG_DQL) += dynamic_queue_limits.o
+
+obj-$(CONFIG_MPILIB) += mpi/
+obj-$(CONFIG_SIGNATURE) += digsig.o
+
+obj-$(CONFIG_CLZ_TAB) += clz_tab.o
+
+obj-$(CONFIG_DDR) += jedec_ddr_data.o
+
+obj-$(CONFIG_GENERIC_STRNCPY_FROM_USER) += strncpy_from_user.o
+obj-$(CONFIG_GENERIC_STRNLEN_USER) += strnlen_user.o
+
+obj-$(CONFIG_STMP_DEVICE) += stmp_device.o
+
+libfdt_files = fdt.o fdt_ro.o fdt_wip.o fdt_rw.o fdt_sw.o fdt_strerror.o
+$(foreach file, $(libfdt_files), \
+        $(eval CFLAGS_$(file) = -I$(src)/../scripts/dtc/libfdt))
+lib-$(CONFIG_LIBFDT) += $(libfdt_files)
+
+obj-$(CONFIG_RBTREE_TEST) += rbtree_test.o
+obj-$(CONFIG_INTERVAL_TREE_TEST) += interval_tree_test.o
+
+interval_tree_test-objs := interval_tree_test_main.o interval_tree.o
+
+obj-$(CONFIG_ASN1) += asn1_decoder.o
 
 hostprogs-y     := gen_crc32table
 clean-files     := crc32table.h
@@ -127,3 +157,19 @@ quiet_cmd_crc32 = GEN     $@
 
 $(obj)/crc32table.h: $(obj)/gen_crc32table
         $(call cmd,crc32)
+
+#
+# Build a fast OID lookip registry from include/linux/oid_registry.h
+#
+obj-$(CONFIG_OID_REGISTRY) += oid_registry.o
+
+$(obj)/oid_registry.c: $(obj)/oid_registry_data.c
+
+$(obj)/oid_registry_data.c: $(srctree)/include/linux/oid_registry.h \
+                            $(src)/build_OID_registry
+        $(call cmd,build_OID_registry)
+
+quiet_cmd_build_OID_registry = GEN     $@
+      cmd_build_OID_registry = perl $(srctree)/$(src)/build_OID_registry $< $@
+
+clean-files     += oid_registry_data.c
diff --git a/lib/argv_split.c b/lib/argv_split.c
index 4b1b083f219c..1e9a6cbc3689 100644
--- a/lib/argv_split.c
+++ b/lib/argv_split.c
@@ -6,7 +6,7 @@
 #include <linux/ctype.h>
 #include <linux/string.h>
 #include <linux/slab.h>
-#include <linux/module.h>
+#include <linux/export.h>
 
 static const char *skip_arg(const char *cp)
 {
diff --git a/lib/asn1_decoder.c b/lib/asn1_decoder.c
new file mode 100644
index 000000000000..de2c8b5a715b
--- /dev/null
+++ b/lib/asn1_decoder.c
@@ -0,0 +1,487 @@
+/* Decoder for ASN.1 BER/DER/CER encoded bytestream
+ *
+ * Copyright (C) 2012 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+
+#include <linux/export.h>
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/asn1_decoder.h>
+#include <linux/asn1_ber_bytecode.h>
+
+static const unsigned char asn1_op_lengths[ASN1_OP__NR] = {
+        /*                                      OPC TAG JMP ACT */
+        [ASN1_OP_MATCH]                         = 1 + 1,
+        [ASN1_OP_MATCH_OR_SKIP]                 = 1 + 1,
+        [ASN1_OP_MATCH_ACT]                     = 1 + 1     + 1,
+        [ASN1_OP_MATCH_ACT_OR_SKIP]             = 1 + 1     + 1,
+        [ASN1_OP_MATCH_JUMP]                    = 1 + 1 + 1,
+        [ASN1_OP_MATCH_JUMP_OR_SKIP]            = 1 + 1 + 1,
+        [ASN1_OP_MATCH_ANY]                     = 1,
+        [ASN1_OP_MATCH_ANY_ACT]                 = 1         + 1,
+        [ASN1_OP_COND_MATCH_OR_SKIP]            = 1 + 1,
+        [ASN1_OP_COND_MATCH_ACT_OR_SKIP]        = 1 + 1     + 1,
+        [ASN1_OP_COND_MATCH_JUMP_OR_SKIP]       = 1 + 1 + 1,
+        [ASN1_OP_COND_MATCH_ANY]                = 1,
+        [ASN1_OP_COND_MATCH_ANY_ACT]            = 1         + 1,
+        [ASN1_OP_COND_FAIL]                     = 1,
+        [ASN1_OP_COMPLETE]                      = 1,
+        [ASN1_OP_ACT]                           = 1         + 1,
+        [ASN1_OP_RETURN]                        = 1,
+        [ASN1_OP_END_SEQ]                       = 1,
+        [ASN1_OP_END_SEQ_OF]                    = 1     + 1,
+        [ASN1_OP_END_SET]                       = 1,
+        [ASN1_OP_END_SET_OF]                    = 1     + 1,
+        [ASN1_OP_END_SEQ_ACT]                   = 1         + 1,
+        [ASN1_OP_END_SEQ_OF_ACT]                = 1     + 1 + 1,
+        [ASN1_OP_END_SET_ACT]                   = 1         + 1,
+        [ASN1_OP_END_SET_OF_ACT]                = 1     + 1 + 1,
+};
+
+/*
+ * Find the length of an indefinite length object
+ * @data: The data buffer
+ * @datalen: The end of the innermost containing element in the buffer
+ * @_dp: The data parse cursor (updated before returning)
+ * @_len: Where to return the size of the element.
+ * @_errmsg: Where to return a pointer to an error message on error
+ */
+static int asn1_find_indefinite_length(const unsigned char *data, size_t datalen,
+                                       size_t *_dp, size_t *_len,
+                                       const char **_errmsg)
+{
+        unsigned char tag, tmp;
+        size_t dp = *_dp, len, n;
+        int indef_level = 1;
+
+next_tag:
+        if (unlikely(datalen - dp < 2)) {
+                if (datalen == dp)
+                        goto missing_eoc;
+                goto data_overrun_error;
+        }
+
+        /* Extract a tag from the data */
+        tag = data[dp++];
+        if (tag == 0) {
+                /* It appears to be an EOC. */
+                if (data[dp++] != 0)
+                        goto invalid_eoc;
+                if (--indef_level <= 0) {
+                        *_len = dp - *_dp;
+                        *_dp = dp;
+                        return 0;
+                }
+                goto next_tag;
+        }
+
+        if (unlikely((tag & 0x1f) == 0x1f)) {
+                do {
+                        if (unlikely(datalen - dp < 2))
+                                goto data_overrun_error;
+                        tmp = data[dp++];
+                } while (tmp & 0x80);
+        }
+
+        /* Extract the length */
+        len = data[dp++];
+        if (len < 0x7f) {
+                dp += len;
+                goto next_tag;
+        }
+
+        if (unlikely(len == 0x80)) {
+                /* Indefinite length */
+                if (unlikely((tag & ASN1_CONS_BIT) == ASN1_PRIM << 5))
+                        goto indefinite_len_primitive;
+                indef_level++;
+                goto next_tag;
+        }
+
+        n = len - 0x80;
+        if (unlikely(n > sizeof(size_t) - 1))
+                goto length_too_long;
+        if (unlikely(n > datalen - dp))
+                goto data_overrun_error;
+        for (len = 0; n > 0; n--) {
+                len <<= 8;
+                len |= data[dp++];
+        }
+        dp += len;
+        goto next_tag;
+
+length_too_long:
+        *_errmsg = "Unsupported length";
+        goto error;
+indefinite_len_primitive:
+        *_errmsg = "Indefinite len primitive not permitted";
+        goto error;
+invalid_eoc:
+        *_errmsg = "Invalid length EOC";
+        goto error;
+data_overrun_error:
+        *_errmsg = "Data overrun error";
+        goto error;
+missing_eoc:
+        *_errmsg = "Missing EOC in indefinite len cons";
+error:
+        *_dp = dp;
+        return -1;
+}
+
+/**
+ * asn1_ber_decoder - Decoder BER/DER/CER ASN.1 according to pattern
+ * @decoder: The decoder definition (produced by asn1_compiler)
+ * @context: The caller's context (to be passed to the action functions)
+ * @data: The encoded data
+ * @datasize: The size of the encoded data
+ *
+ * Decode BER/DER/CER encoded ASN.1 data according to a bytecode pattern
+ * produced by asn1_compiler.  Action functions are called on marked tags to
+ * allow the caller to retrieve significant data.
+ *
+ * LIMITATIONS:
+ *
+ * To keep down the amount of stack used by this function, the following limits
+ * have been imposed:
+ *
+ *  (1) This won't handle datalen > 65535 without increasing the size of the
+ *      cons stack elements and length_too_long checking.
+ *
+ *  (2) The stack of constructed types is 10 deep.  If the depth of non-leaf
+ *      constructed types exceeds this, the decode will fail.
+ *
+ *  (3) The SET type (not the SET OF type) isn't really supported as tracking
+ *      what members of the set have been seen is a pain.
+ */
+int asn1_ber_decoder(const struct asn1_decoder *decoder,
+                     void *context,
+                     const unsigned char *data,
+                     size_t datalen)
+{
+        const unsigned char *machine = decoder->machine;
+        const asn1_action_t *actions = decoder->actions;
+        size_t machlen = decoder->machlen;
+        enum asn1_opcode op;
+        unsigned char tag = 0, csp = 0, jsp = 0, optag = 0, hdr = 0;
+        const char *errmsg;
+        size_t pc = 0, dp = 0, tdp = 0, len = 0;
+        int ret;
+
+        unsigned char flags = 0;
+#define FLAG_INDEFINITE_LENGTH  0x01
+#define FLAG_MATCHED            0x02
+#define FLAG_CONS               0x20 /* Corresponds to CONS bit in the opcode tag
+                                      * - ie. whether or not we are going to parse
+                                      *   a compound type.
+                                      */
+
+#define NR_CONS_STACK 10
+        unsigned short cons_dp_stack[NR_CONS_STACK];
+        unsigned short cons_datalen_stack[NR_CONS_STACK];
+        unsigned char cons_hdrlen_stack[NR_CONS_STACK];
+#define NR_JUMP_STACK 10
+        unsigned char jump_stack[NR_JUMP_STACK];
+
+        if (datalen > 65535)
+                return -EMSGSIZE;
+
+next_op:
+        pr_debug("next_op: pc=\e[32m%zu\e[m/%zu dp=\e[33m%zu\e[m/%zu C=%d J=%d\n",
+                 pc, machlen, dp, datalen, csp, jsp);
+        if (unlikely(pc >= machlen))
+                goto machine_overrun_error;
+        op = machine[pc];
+        if (unlikely(pc + asn1_op_lengths[op] > machlen))
+                goto machine_overrun_error;
+
+        /* If this command is meant to match a tag, then do that before
+         * evaluating the command.
+         */
+        if (op <= ASN1_OP__MATCHES_TAG) {
+                unsigned char tmp;
+
+                /* Skip conditional matches if possible */
+                if ((op & ASN1_OP_MATCH__COND &&
+                     flags & FLAG_MATCHED) ||
+                    dp == datalen) {
+                        pc += asn1_op_lengths[op];
+                        goto next_op;
+                }
+
+                flags = 0;
+                hdr = 2;
+
+                /* Extract a tag from the data */
+                if (unlikely(dp >= datalen - 1))
+                        goto data_overrun_error;
+                tag = data[dp++];
+                if (unlikely((tag & 0x1f) == 0x1f))
+                        goto long_tag_not_supported;
+
+                if (op & ASN1_OP_MATCH__ANY) {
+                        pr_debug("- any %02x\n", tag);
+                } else {
+                        /* Extract the tag from the machine
+                         * - Either CONS or PRIM are permitted in the data if
+                         *   CONS is not set in the op stream, otherwise CONS
+                         *   is mandatory.
+                         */
+                        optag = machine[pc + 1];
+                        flags |= optag & FLAG_CONS;
+
+                        /* Determine whether the tag matched */
+                        tmp = optag ^ tag;
+                        tmp &= ~(optag & ASN1_CONS_BIT);
+                        pr_debug("- match? %02x %02x %02x\n", tag, optag, tmp);
+                        if (tmp != 0) {
+                                /* All odd-numbered tags are MATCH_OR_SKIP. */
+                                if (op & ASN1_OP_MATCH__SKIP) {
+                                        pc += asn1_op_lengths[op];
+                                        dp--;
+                                        goto next_op;
+                                }
+                                goto tag_mismatch;
+                        }
+                }
+                flags |= FLAG_MATCHED;
+
+                len = data[dp++];
+                if (len > 0x7f) {
+                        if (unlikely(len == 0x80)) {
+                                /* Indefinite length */
+                                if (unlikely(!(tag & ASN1_CONS_BIT)))
+                                        goto indefinite_len_primitive;
+                                flags |= FLAG_INDEFINITE_LENGTH;
+                                if (unlikely(2 > datalen - dp))
+                                        goto data_overrun_error;
+                        } else {
+                                int n = len - 0x80;
+                                if (unlikely(n > 2))
+                                        goto length_too_long;
+                                if (unlikely(dp >= datalen - n))
+                                        goto data_overrun_error;
+                                hdr += n;
+                                for (len = 0; n > 0; n--) {
+                                        len <<= 8;
+                                        len |= data[dp++];
+                                }
+                                if (unlikely(len > datalen - dp))
+                                        goto data_overrun_error;
+                        }
+                }
+
+                if (flags & FLAG_CONS) {
+                        /* For expected compound forms, we stack the positions
+                         * of the start and end of the data.
+                         */
+                        if (unlikely(csp >= NR_CONS_STACK))
+                                goto cons_stack_overflow;
+                        cons_dp_stack[csp] = dp;
+                        cons_hdrlen_stack[csp] = hdr;
+                        if (!(flags & FLAG_INDEFINITE_LENGTH)) {
+                                cons_datalen_stack[csp] = datalen;
+                                datalen = dp + len;
+                        } else {
+                                cons_datalen_stack[csp] = 0;
+                        }
+                        csp++;
+                }
+
+                pr_debug("- TAG: %02x %zu%s\n",
+                         tag, len, flags & FLAG_CONS ? " CONS" : "");
+                tdp = dp;
+        }
+
+        /* Decide how to handle the operation */
+        switch (op) {
+        case ASN1_OP_MATCH_ANY_ACT:
+        case ASN1_OP_COND_MATCH_ANY_ACT:
+                ret = actions[machine[pc + 1]](context, hdr, tag, data + dp, len);
+                if (ret < 0)
+                        return ret;
+                goto skip_data;
+
+        case ASN1_OP_MATCH_ACT:
+        case ASN1_OP_MATCH_ACT_OR_SKIP:
+        case ASN1_OP_COND_MATCH_ACT_OR_SKIP:
+                ret = actions[machine[pc + 2]](context, hdr, tag, data + dp, len);
+                if (ret < 0)
+                        return ret;
+                goto skip_data;
+
+        case ASN1_OP_MATCH:
+        case ASN1_OP_MATCH_OR_SKIP:
+        case ASN1_OP_MATCH_ANY:
+        case ASN1_OP_COND_MATCH_OR_SKIP:
+        case ASN1_OP_COND_MATCH_ANY:
+        skip_data:
+                if (!(flags & FLAG_CONS)) {
+                        if (flags & FLAG_INDEFINITE_LENGTH) {
+                                ret = asn1_find_indefinite_length(
+                                        data, datalen, &dp, &len, &errmsg);
+                                if (ret < 0)
+                                        goto error;
+                        } else {
+                                dp += len;
+                        }
+                        pr_debug("- LEAF: %zu\n", len);
+                }
+                pc += asn1_op_lengths[op];
+                goto next_op;
+
+        case ASN1_OP_MATCH_JUMP:
+        case ASN1_OP_MATCH_JUMP_OR_SKIP:
+        case ASN1_OP_COND_MATCH_JUMP_OR_SKIP:
+                pr_debug("- MATCH_JUMP\n");
+                if (unlikely(jsp == NR_JUMP_STACK))
+                        goto jump_stack_overflow;
+                jump_stack[jsp++] = pc + asn1_op_lengths[op];
+                pc = machine[pc + 2];
+                goto next_op;
+
+        case ASN1_OP_COND_FAIL:
+                if (unlikely(!(flags & FLAG_MATCHED)))
+                        goto tag_mismatch;
+                pc += asn1_op_lengths[op];
+                goto next_op;
+
+        case ASN1_OP_COMPLETE:
+                if (unlikely(jsp != 0 || csp != 0)) {
+                        pr_err("ASN.1 decoder error: Stacks not empty at completion (%u, %u)\n",
+                               jsp, csp);
+                        return -EBADMSG;
+                }
+                return 0;
+
+        case ASN1_OP_END_SET:
+        case ASN1_OP_END_SET_ACT:
+                if (unlikely(!(flags & FLAG_MATCHED)))
+                        goto tag_mismatch;
+        case ASN1_OP_END_SEQ:
+        case ASN1_OP_END_SET_OF:
+        case ASN1_OP_END_SEQ_OF:
+        case ASN1_OP_END_SEQ_ACT:
+        case ASN1_OP_END_SET_OF_ACT:
+        case ASN1_OP_END_SEQ_OF_ACT:
+                if (unlikely(csp <= 0))
+                        goto cons_stack_underflow;
+                csp--;
+                tdp = cons_dp_stack[csp];
+                hdr = cons_hdrlen_stack[csp];
+                len = datalen;
+                datalen = cons_datalen_stack[csp];
+                pr_debug("- end cons t=%zu dp=%zu l=%zu/%zu\n",
+                         tdp, dp, len, datalen);
+                if (datalen == 0) {
+                        /* Indefinite length - check for the EOC. */
+                        datalen = len;
+                        if (unlikely(datalen - dp < 2))
+                                goto data_overrun_error;
+                        if (data[dp++] != 0) {
+                                if (op & ASN1_OP_END__OF) {
+                                        dp--;
+                                        csp++;
+                                        pc = machine[pc + 1];
+                                        pr_debug("- continue\n");
+                                        goto next_op;
+                                }
+                                goto missing_eoc;
+                        }
+                        if (data[dp++] != 0)
+                                goto invalid_eoc;
+                        len = dp - tdp - 2;
+                } else {
+                        if (dp < len && (op & ASN1_OP_END__OF)) {
+                                datalen = len;
+                                csp++;
+                                pc = machine[pc + 1];
+                                pr_debug("- continue\n");
+                                goto next_op;
+                        }
+                        if (dp != len)
+                                goto cons_length_error;
+                        len -= tdp;
+                        pr_debug("- cons len l=%zu d=%zu\n", len, dp - tdp);
+                }
+
+                if (op & ASN1_OP_END__ACT) {
+                        unsigned char act;
+                        if (op & ASN1_OP_END__OF)
+                                act = machine[pc + 2];
+                        else
+                                act = machine[pc + 1];
+                        ret = actions[act](context, hdr, 0, data + tdp, len);
+                }
+                pc += asn1_op_lengths[op];
+                goto next_op;
+
+        case ASN1_OP_ACT:
+                ret = actions[machine[pc + 1]](context, hdr, tag, data + tdp, len);
+                pc += asn1_op_lengths[op];
+                goto next_op;
+
+        case ASN1_OP_RETURN:
+                if (unlikely(jsp <= 0))
+                        goto jump_stack_underflow;
+                pc = jump_stack[--jsp];
+                goto next_op;
+
+        default:
+                break;
+        }
+
+        /* Shouldn't reach here */
+        pr_err("ASN.1 decoder error: Found reserved opcode (%u)\n", op);
+        return -EBADMSG;
+
+data_overrun_error:
+        errmsg = "Data overrun error";
+        goto error;
+machine_overrun_error:
+        errmsg = "Machine overrun error";
+        goto error;
+jump_stack_underflow:
+        errmsg = "Jump stack underflow";
+        goto error;
+jump_stack_overflow:
+        errmsg = "Jump stack overflow";
+        goto error;
+cons_stack_underflow:
+        errmsg = "Cons stack underflow";
+        goto error;
+cons_stack_overflow:
+        errmsg = "Cons stack overflow";
+        goto error;
+cons_length_error:
+        errmsg = "Cons length error";
+        goto error;
+missing_eoc:
+        errmsg = "Missing EOC in indefinite len cons";
+        goto error;
+invalid_eoc:
+        errmsg = "Invalid length EOC";
+        goto error;
+length_too_long:
+        errmsg = "Unsupported length";
+        goto error;
+indefinite_len_primitive:
+        errmsg = "Indefinite len primitive not permitted";
+        goto error;
+tag_mismatch:
+        errmsg = "Unexpected tag";
+        goto error;
+long_tag_not_supported:
+        errmsg = "Long tag not supported";
+error:
+        pr_debug("\nASN1: %s [m=%zu d=%zu ot=%02x t=%02x l=%zu]\n",
+                 errmsg, pc, dp, optag, tag, len);
+        return -EBADMSG;
+}
+EXPORT_SYMBOL_GPL(asn1_ber_decoder);
diff --git a/lib/atomic64.c b/lib/atomic64.c
index e12ae0dd08a8..978537809d84 100644
--- a/lib/atomic64.c
+++ b/lib/atomic64.c
@@ -13,7 +13,7 @@
 #include <linux/cache.h>
 #include <linux/spinlock.h>
 #include <linux/init.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/atomic.h>
 
 /*
@@ -29,11 +29,11 @@
  * Ensure each lock is in a separate cacheline.
  */
 static union {
-        spinlock_t lock;
+        raw_spinlock_t lock;
         char pad[L1_CACHE_BYTES];
 } atomic64_lock[NR_LOCKS] __cacheline_aligned_in_smp;
 
-static inline spinlock_t *lock_addr(const atomic64_t *v)
+static inline raw_spinlock_t *lock_addr(const atomic64_t *v)
 {
         unsigned long addr = (unsigned long) v;
 
@@ -45,12 +45,12 @@ static inline spinlock_t *lock_addr(const atomic64_t *v)
 long long atomic64_read(const atomic64_t *v)
 {
         unsigned long flags;
-        spinlock_t *lock = lock_addr(v);
+        raw_spinlock_t *lock = lock_addr(v);
         long long val;
 
-        spin_lock_irqsave(lock, flags);
+        raw_spin_lock_irqsave(lock, flags);
         val = v->counter;
-        spin_unlock_irqrestore(lock, flags);
+        raw_spin_unlock_irqrestore(lock, flags);
         return val;
 }
 EXPORT_SYMBOL(atomic64_read);
@@ -58,34 +58,34 @@ EXPORT_SYMBOL(atomic64_read);
 void atomic64_set(atomic64_t *v, long long i)
 {
         unsigned long flags;
-        spinlock_t *lock = lock_addr(v);
+        raw_spinlock_t *lock = lock_addr(v);
 
-        spin_lock_irqsave(lock, flags);
+        raw_spin_lock_irqsave(lock, flags);
         v->counter = i;
-        spin_unlock_irqrestore(lock, flags);
+        raw_spin_unlock_irqrestore(lock, flags);
 }
 EXPORT_SYMBOL(atomic64_set);
 
 void atomic64_add(long long a, atomic64_t *v)
 {
         unsigned long flags;
-        spinlock_t *lock = lock_addr(v);
+        raw_spinlock_t *lock = lock_addr(v);
 
-        spin_lock_irqsave(lock, flags);
+        raw_spin_lock_irqsave(lock, flags);
         v->counter += a;
-        spin_unlock_irqrestore(lock, flags);
+        raw_spin_unlock_irqrestore(lock, flags);
 }
 EXPORT_SYMBOL(atomic64_add);
 
 long long atomic64_add_return(long long a, atomic64_t *v)
 {
         unsigned long flags;
-        spinlock_t *lock = lock_addr(v);
+        raw_spinlock_t *lock = lock_addr(v);
         long long val;
 
-        spin_lock_irqsave(lock, flags);
+        raw_spin_lock_irqsave(lock, flags);
         val = v->counter += a;
-        spin_unlock_irqrestore(lock, flags);
+        raw_spin_unlock_irqrestore(lock, flags);
         return val;
 }
 EXPORT_SYMBOL(atomic64_add_return);
@@ -93,23 +93,23 @@ EXPORT_SYMBOL(atomic64_add_return);
 void atomic64_sub(long long a, atomic64_t *v)
 {
         unsigned long flags;
-        spinlock_t *lock = lock_addr(v);
+        raw_spinlock_t *lock = lock_addr(v);
 
-        spin_lock_irqsave(lock, flags);
+        raw_spin_lock_irqsave(lock, flags);
         v->counter -= a;
-        spin_unlock_irqrestore(lock, flags);
+        raw_spin_unlock_irqrestore(lock, flags);
 }
 EXPORT_SYMBOL(atomic64_sub);
 
 long long atomic64_sub_return(long long a, atomic64_t *v)
 {
         unsigned long flags;
-        spinlock_t *lock = lock_addr(v);
+        raw_spinlock_t *lock = lock_addr(v);
         long long val;
 
-        spin_lock_irqsave(lock, flags);
+        raw_spin_lock_irqsave(lock, flags);
         val = v->counter -= a;
-        spin_unlock_irqrestore(lock, flags);
+        raw_spin_unlock_irqrestore(lock, flags);
         return val;
 }
 EXPORT_SYMBOL(atomic64_sub_return);
@@ -117,14 +117,14 @@ EXPORT_SYMBOL(atomic64_sub_return);
 long long atomic64_dec_if_positive(atomic64_t *v)
 {
         unsigned long flags;
-        spinlock_t *lock = lock_addr(v);
+        raw_spinlock_t *lock = lock_addr(v);
         long long val;
 
-        spin_lock_irqsave(lock, flags);
+        raw_spin_lock_irqsave(lock, flags);
         val = v->counter - 1;
         if (val >= 0)
                 v->counter = val;
-        spin_unlock_irqrestore(lock, flags);
+        raw_spin_unlock_irqrestore(lock, flags);
         return val;
 }
 EXPORT_SYMBOL(atomic64_dec_if_positive);
@@ -132,14 +132,14 @@ EXPORT_SYMBOL(atomic64_dec_if_positive);
 long long atomic64_cmpxchg(atomic64_t *v, long long o, long long n)
 {
         unsigned long flags;
-        spinlock_t *lock = lock_addr(v);
+        raw_spinlock_t *lock = lock_addr(v);
         long long val;
 
-        spin_lock_irqsave(lock, flags);
+        raw_spin_lock_irqsave(lock, flags);
         val = v->counter;
         if (val == o)
                 v->counter = n;
-        spin_unlock_irqrestore(lock, flags);
+        raw_spin_unlock_irqrestore(lock, flags);
         return val;
 }
 EXPORT_SYMBOL(atomic64_cmpxchg);
@@ -147,13 +147,13 @@ EXPORT_SYMBOL(atomic64_cmpxchg);
 long long atomic64_xchg(atomic64_t *v, long long new)
 {
         unsigned long flags;
-        spinlock_t *lock = lock_addr(v);
+        raw_spinlock_t *lock = lock_addr(v);
         long long val;
 
-        spin_lock_irqsave(lock, flags);
+        raw_spin_lock_irqsave(lock, flags);
         val = v->counter;
         v->counter = new;
-        spin_unlock_irqrestore(lock, flags);
+        raw_spin_unlock_irqrestore(lock, flags);
         return val;
 }
 EXPORT_SYMBOL(atomic64_xchg);
@@ -161,15 +161,15 @@ EXPORT_SYMBOL(atomic64_xchg);
 int atomic64_add_unless(atomic64_t *v, long long a, long long u)
 {
         unsigned long flags;
-        spinlock_t *lock = lock_addr(v);
+        raw_spinlock_t *lock = lock_addr(v);
         int ret = 0;
 
-        spin_lock_irqsave(lock, flags);
+        raw_spin_lock_irqsave(lock, flags);
         if (v->counter != u) {
                 v->counter += a;
                 ret = 1;
         }
-        spin_unlock_irqrestore(lock, flags);
+        raw_spin_unlock_irqrestore(lock, flags);
         return ret;
 }
 EXPORT_SYMBOL(atomic64_add_unless);
@@ -179,7 +179,7 @@ static int init_atomic64_lock(void)
         int i;
 
         for (i = 0; i < NR_LOCKS; ++i)
-                spin_lock_init(&atomic64_lock[i].lock);
+                raw_spin_lock_init(&atomic64_lock[i].lock);
         return 0;
 }
 
diff --git a/lib/atomic64_test.c b/lib/atomic64_test.c
index 0c33cde2a1e6..00bca223d1e1 100644
--- a/lib/atomic64_test.c
+++ b/lib/atomic64_test.c
@@ -9,6 +9,7 @@
  * (at your option) any later version.
  */
 #include <linux/init.h>
+#include <linux/bug.h>
 #include <linux/kernel.h>
 #include <linux/atomic.h>
 
@@ -113,8 +114,7 @@ static __init int test_atomic64(void)
         r += one;
         BUG_ON(v.counter != r);
 
-#if defined(CONFIG_X86) || defined(CONFIG_MIPS) || defined(CONFIG_PPC) || \
-    defined(CONFIG_S390) || defined(_ASM_GENERIC_ATOMIC64_H) || defined(CONFIG_ARM)
+#ifdef CONFIG_ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE
         INIT(onestwos);
         BUG_ON(atomic64_dec_if_positive(&v) != (onestwos - 1));
         r -= one;
@@ -128,7 +128,7 @@ static __init int test_atomic64(void)
         BUG_ON(atomic64_dec_if_positive(&v) != (-one - one));
         BUG_ON(v.counter != r);
 #else
-#warning Please implement atomic64_dec_if_positive for your architecture, and add it to the IF above
+#warning Please implement atomic64_dec_if_positive for your architecture and select the above Kconfig symbol
 #endif
 
         INIT(onestwos);
diff --git a/lib/average.c b/lib/average.c
index 5576c2841496..99a67e662b3c 100644
--- a/lib/average.c
+++ b/lib/average.c
@@ -5,8 +5,9 @@
  * Version 2.  See the file COPYING for more details.
  */
 
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/average.h>
+#include <linux/kernel.h>
 #include <linux/bug.h>
 #include <linux/log2.h>
 
diff --git a/lib/bcd.c b/lib/bcd.c
index d74257fd0fe7..40d304efe272 100644
--- a/lib/bcd.c
+++ b/lib/bcd.c
@@ -1,14 +1,14 @@
 #include <linux/bcd.h>
-#include <linux/module.h>
+#include <linux/export.h>
 
-unsigned bcd2bin(unsigned char val)
+unsigned _bcd2bin(unsigned char val)
 {
         return (val & 0x0f) + (val >> 4) * 10;
 }
-EXPORT_SYMBOL(bcd2bin);
+EXPORT_SYMBOL(_bcd2bin);
 
-unsigned char bin2bcd(unsigned val)
+unsigned char _bin2bcd(unsigned val)
 {
         return ((val / 10) << 4) + val % 10;
 }
-EXPORT_SYMBOL(bin2bcd);
+EXPORT_SYMBOL(_bin2bcd);
diff --git a/lib/bitmap.c b/lib/bitmap.c
index 2f4412e4d071..06fdfa1aeba7 100644
--- a/lib/bitmap.c
+++ b/lib/bitmap.c
@@ -5,11 +5,13 @@
  * This source code is licensed under the GNU General Public License,
  * Version 2.  See the file COPYING for more details.
  */
-#include <linux/module.h>
+#include <linux/export.h>
+#include <linux/thread_info.h>
 #include <linux/ctype.h>
 #include <linux/errno.h>
 #include <linux/bitmap.h>
 #include <linux/bitops.h>
+#include <linux/bug.h>
 #include <asm/uaccess.h>
 
 /*
@@ -367,7 +369,8 @@ EXPORT_SYMBOL(bitmap_find_next_zero_area);
  * @nmaskbits: size of bitmap, in bits
  *
  * Exactly @nmaskbits bits are displayed.  Hex digits are grouped into
- * comma-separated sets of eight digits per set.
+ * comma-separated sets of eight digits per set.  Returns the number of
+ * characters which were written to *buf, excluding the trailing \0.
  */
 int bitmap_scnprintf(char *buf, unsigned int buflen,
         const unsigned long *maskp, int nmaskbits)
@@ -419,7 +422,7 @@ int __bitmap_parse(const char *buf, unsigned int buflen,
 {
         int c, old_c, totaldigits, ndigits, nchunks, nbits;
         u32 chunk;
-        const char __user *ubuf = buf;
+        const char __user __force *ubuf = (const char __user __force *)buf;
 
         bitmap_zero(maskp, nmaskbits);
 
@@ -504,7 +507,9 @@ int bitmap_parse_user(const char __user *ubuf,
 {
         if (!access_ok(VERIFY_READ, ubuf, ulen))
                 return -EFAULT;
-        return __bitmap_parse((const char *)ubuf, ulen, 1, maskp, nmaskbits);
+        return __bitmap_parse((const char __force *)ubuf,
+                                ulen, 1, maskp, nmaskbits);
+
 }
 EXPORT_SYMBOL(bitmap_parse_user);
 
@@ -513,8 +518,8 @@ EXPORT_SYMBOL(bitmap_parse_user);
  *
  * Helper routine for bitmap_scnlistprintf().  Write decimal number
  * or range to buf, suppressing output past buf+buflen, with optional
- * comma-prefix.  Return len of what would be written to buf, if it
- * all fit.
+ * comma-prefix.  Return len of what was written to *buf, excluding the
+ * trailing \0.
  */
 static inline int bscnl_emit(char *buf, int buflen, int rbot, int rtop, int len)
 {
@@ -540,9 +545,8 @@ static inline int bscnl_emit(char *buf, int buflen, int rbot, int rtop, int len)
  * the range.  Output format is compatible with the format
  * accepted as input by bitmap_parselist().
  *
- * The return value is the number of characters which would be
- * generated for the given input, excluding the trailing '\0', as
- * per ISO C99.
+ * The return value is the number of characters which were written to *buf
+ * excluding the trailing '\0', as per ISO C99's scnprintf.
  */
 int bitmap_scnlistprintf(char *buf, unsigned int buflen,
         const unsigned long *maskp, int nmaskbits)
@@ -594,7 +598,7 @@ static int __bitmap_parselist(const char *buf, unsigned int buflen,
 {
         unsigned a, b;
         int c, old_c, totaldigits;
-        const char __user *ubuf = buf;
+        const char __user __force *ubuf = (const char __user __force *)buf;
         int exp_digit, in_range;
 
         totaldigits = c = 0;
@@ -694,7 +698,7 @@ int bitmap_parselist_user(const char __user *ubuf,
 {
         if (!access_ok(VERIFY_READ, ubuf, ulen))
                 return -EFAULT;
-        return __bitmap_parselist((const char *)ubuf,
+        return __bitmap_parselist((const char __force *)ubuf,
                                         ulen, 1, maskp, nmaskbits);
 }
 EXPORT_SYMBOL(bitmap_parselist_user);
diff --git a/lib/bsearch.c b/lib/bsearch.c
index 5b54758e2afb..e33c179089db 100644
--- a/lib/bsearch.c
+++ b/lib/bsearch.c
@@ -9,7 +9,7 @@
  * published by the Free Software Foundation; version 2.
  */
 
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/bsearch.h>
 
 /*
diff --git a/lib/btree.c b/lib/btree.c
index 2a34392bcecc..f9a484676cb6 100644
--- a/lib/btree.c
+++ b/lib/btree.c
@@ -319,8 +319,8 @@ void *btree_get_prev(struct btree_head *head, struct btree_geo *geo,
 
         if (head->height == 0)
                 return NULL;
-retry:
         longcpy(key, __key, geo->keylen);
+retry:
         dec_key(geo, key);
 
         node = head->node;
@@ -351,12 +351,13 @@ retry:
         }
 miss:
         if (retry_key) {
-                __key = retry_key;
+                longcpy(key, retry_key, geo->keylen);
                 retry_key = NULL;
                 goto retry;
         }
         return NULL;
 }
+EXPORT_SYMBOL_GPL(btree_get_prev);
 
 static int getpos(struct btree_geo *geo, unsigned long *node,
                 unsigned long *key)
@@ -508,6 +509,7 @@ retry:
 int btree_insert(struct btree_head *head, struct btree_geo *geo,
                 unsigned long *key, void *val, gfp_t gfp)
 {
+        BUG_ON(!val);
         return btree_insert_level(head, geo, key, val, 1, gfp);
 }
 EXPORT_SYMBOL_GPL(btree_insert);
diff --git a/lib/bug.c b/lib/bug.c
index 19552096d16b..a28c1415357c 100644
--- a/lib/bug.c
+++ b/lib/bug.c
@@ -169,7 +169,7 @@ enum bug_trap_type report_bug(unsigned long bugaddr, struct pt_regs *regs)
                 return BUG_TRAP_TYPE_WARN;
         }
 
-        printk(KERN_EMERG "------------[ cut here ]------------\n");
+        printk(KERN_DEFAULT "------------[ cut here ]------------\n");
 
         if (file)
                 printk(KERN_CRIT "kernel BUG at %s:%u!\n",
diff --git a/lib/build_OID_registry b/lib/build_OID_registry
new file mode 100755
index 000000000000..dfbdaab81bc8
--- /dev/null
+++ b/lib/build_OID_registry
@@ -0,0 +1,209 @@
+#!/usr/bin/perl -w
+#
+# Build a static ASN.1 Object Identified (OID) registry
+#
+# Copyright (C) 2012 Red Hat, Inc. All Rights Reserved.
+# Written by David Howells (dhowells@redhat.com)
+#
+# This program is free software; you can redistribute it and/or
+# modify it under the terms of the GNU General Public Licence
+# as published by the Free Software Foundation; either version
+# 2 of the Licence, or (at your option) any later version.
+#
+
+use strict;
+
+my @names = ();
+my @oids = ();
+
+if ($#ARGV != 1) {
+    print STDERR "Format: ", $0, " <in-h-file> <out-c-file>\n";
+    exit(2);
+}
+
+#
+# Open the file to read from
+#
+open IN_FILE, "<$ARGV[0]" || die;
+while (<IN_FILE>) {
+    chomp;
+    if (m!\s+OID_([a-zA-z][a-zA-Z0-9_]+),\s+/[*]\s+([012][.0-9]*)\s+[*]/!) {
+        push @names, $1;
+        push @oids, $2;
+    }
+}
+close IN_FILE || die;
+
+#
+# Open the files to write into
+#
+open C_FILE, ">$ARGV[1]" or die;
+print C_FILE "/*\n";
+print C_FILE " * Automatically generated by ", $0, ".  Do not edit\n";
+print C_FILE " */\n";
+
+#
+# Split the data up into separate lists and also determine the lengths of the
+# encoded data arrays.
+#
+my @indices = ();
+my @lengths = ();
+my $total_length = 0;
+
+print "Compiling ", $#names + 1, " OIDs\n";
+
+for (my $i = 0; $i <= $#names; $i++) {
+    my $name = $names[$i];
+    my $oid = $oids[$i];
+
+    my @components = split(/[.]/, $oid);
+
+    # Determine the encoded length of this OID
+    my $size = $#components;
+    for (my $loop = 2; $loop <= $#components; $loop++) {
+        my $c = $components[$loop];
+
+        # We will base128 encode the number
+        my $tmp = ($c == 0) ? 0 : int(log($c)/log(2));
+        $tmp = int($tmp / 7);
+        $size += $tmp;
+    }
+    push @lengths, $size;
+    push @indices, $total_length;
+    $total_length += $size;
+}
+
+#
+# Emit the look-up-by-OID index table
+#
+print C_FILE "\n";
+if ($total_length <= 255) {
+    print C_FILE "static const unsigned char oid_index[OID__NR + 1] = {\n";
+} else {
+    print C_FILE "static const unsigned short oid_index[OID__NR + 1] = {\n";
+}
+for (my $i = 0; $i <= $#names; $i++) {
+    print C_FILE "\t[OID_", $names[$i], "] = ", $indices[$i], ",\n"
+}
+print C_FILE "\t[OID__NR] = ", $total_length, "\n";
+print C_FILE "};\n";
+
+#
+# Encode the OIDs
+#
+my @encoded_oids = ();
+
+for (my $i = 0; $i <= $#names; $i++) {
+    my @octets = ();
+
+    my @components = split(/[.]/, $oids[$i]);
+
+    push @octets, $components[0] * 40 + $components[1];
+
+    for (my $loop = 2; $loop <= $#components; $loop++) {
+        my $c = $components[$loop];
+
+        # Base128 encode the number
+        my $tmp = ($c == 0) ? 0 : int(log($c)/log(2));
+        $tmp = int($tmp / 7);
+
+        for (; $tmp > 0; $tmp--) {
+            push @octets, (($c >> $tmp * 7) & 0x7f) | 0x80;
+        }
+        push @octets, $c & 0x7f;
+    }
+
+    push @encoded_oids, \@octets;
+}
+
+#
+# Create a hash value for each OID
+#
+my @hash_values = ();
+for (my $i = 0; $i <= $#names; $i++) {
+    my @octets = @{$encoded_oids[$i]};
+
+    my $hash = $#octets;
+    foreach (@octets) {
+        $hash += $_ * 33;
+    }
+
+    $hash = ($hash >> 24) ^ ($hash >> 16) ^ ($hash >> 8) ^ ($hash);
+
+    push @hash_values, $hash & 0xff;
+}
+
+#
+# Emit the OID data
+#
+print C_FILE "\n";
+print C_FILE "static const unsigned char oid_data[", $total_length, "] = {\n";
+for (my $i = 0; $i <= $#names; $i++) {
+    my @octets = @{$encoded_oids[$i]};
+    print C_FILE "\t";
+    print C_FILE $_, ", " foreach (@octets);
+    print C_FILE "\t// ", $names[$i];
+    print C_FILE "\n";
+}
+print C_FILE "};\n";
+
+#
+# Build the search index table (ordered by length then hash then content)
+#
+my @index_table = ( 0 .. $#names );
+
+@index_table = sort {
+    my @octets_a = @{$encoded_oids[$a]};
+    my @octets_b = @{$encoded_oids[$b]};
+
+    return $hash_values[$a] <=> $hash_values[$b]
+        if ($hash_values[$a] != $hash_values[$b]);
+    return $#octets_a <=> $#octets_b
+        if ($#octets_a != $#octets_b);
+    for (my $i = $#octets_a; $i >= 0; $i--) {
+        return $octets_a[$i] <=> $octets_b[$i]
+            if ($octets_a[$i] != $octets_b[$i]);
+    }
+    return 0;
+
+} @index_table;
+
+#
+# Emit the search index and hash value table
+#
+print C_FILE "\n";
+print C_FILE "static const struct {\n";
+print C_FILE "\tunsigned char hash;\n";
+if ($#names <= 255) {
+    print C_FILE "\tenum OID oid : 8;\n";
+} else {
+    print C_FILE "\tenum OID oid : 16;\n";
+}
+print C_FILE "} oid_search_table[OID__NR] = {\n";
+for (my $i = 0; $i <= $#names; $i++) {
+    my @octets = @{$encoded_oids[$index_table[$i]]};
+    printf(C_FILE "\t[%3u] = { %3u, OID_%-35s }, // ",
+           $i,
+           $hash_values[$index_table[$i]],
+           $names[$index_table[$i]]);
+    printf C_FILE "%02x", $_ foreach (@octets);
+    print C_FILE "\n";
+}
+print C_FILE "};\n";
+
+#
+# Emit the OID debugging name table
+#
+#print C_FILE "\n";
+#print C_FILE "const char *const oid_name_table[OID__NR + 1] = {\n";
+#
+#for (my $i = 0; $i <= $#names; $i++) {
+#    print C_FILE "\t\"", $names[$i], "\",\n"
+#}
+#print C_FILE "\t\"Unknown-OID\"\n";
+#print C_FILE "};\n";
+
+#
+# Polish off
+#
+close C_FILE or die;
diff --git a/lib/check_signature.c b/lib/check_signature.c
index fd6af199247b..6b49797980c4 100644
--- a/lib/check_signature.c
+++ b/lib/check_signature.c
@@ -1,5 +1,5 @@
 #include <linux/io.h>
-#include <linux/module.h>
+#include <linux/export.h>
 
 /**
  *      check_signature         -       find BIOS signatures
diff --git a/lib/checksum.c b/lib/checksum.c
index 8df2f91e6d98..12dceb27ff20 100644
--- a/lib/checksum.c
+++ b/lib/checksum.c
@@ -32,7 +32,7 @@
 /* Revised by Kenneth Albanowski for m68knommu. Basic problem: unaligned access
  kills, so most of the assembly has to go. */
 
-#include <linux/module.h>
+#include <linux/export.h>
 #include <net/checksum.h>
 
 #include <asm/byteorder.h>
diff --git a/lib/clz_tab.c b/lib/clz_tab.c
new file mode 100644
index 000000000000..7287b4a991a7
--- /dev/null
+++ b/lib/clz_tab.c
@@ -0,0 +1,18 @@
+const unsigned char __clz_tab[] = {
+        0, 1, 2, 2, 3, 3, 3, 3, 4, 4, 4, 4, 4, 4, 4, 4, 5, 5, 5, 5, 5, 5, 5, 5,
+            5, 5, 5, 5, 5, 5, 5, 5,
+        6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6, 6,
+            6, 6, 6, 6, 6, 6, 6, 6,
+        7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7,
+            7, 7, 7, 7, 7, 7, 7, 7,
+        7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7, 7,
+            7, 7, 7, 7, 7, 7, 7, 7,
+        8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8,
+            8, 8, 8, 8, 8, 8, 8, 8,
+        8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8,
+            8, 8, 8, 8, 8, 8, 8, 8,
+        8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8,
+            8, 8, 8, 8, 8, 8, 8, 8,
+        8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8, 8,
+            8, 8, 8, 8, 8, 8, 8, 8,
+};
diff --git a/lib/cmdline.c b/lib/cmdline.c
index f5f3ad8b62ff..eb6791188cf5 100644
--- a/lib/cmdline.c
+++ b/lib/cmdline.c
@@ -12,7 +12,7 @@
  *
  */
 
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/kernel.h>
 #include <linux/string.h>
 
diff --git a/lib/cordic.c b/lib/cordic.c
index aa27a88d7e04..6cf477839ebd 100644
--- a/lib/cordic.c
+++ b/lib/cordic.c
@@ -96,6 +96,6 @@ struct cordic_iq cordic_calc_iq(s32 theta)
 }
 EXPORT_SYMBOL(cordic_calc_iq);
 
-MODULE_DESCRIPTION("Cordic functions");
+MODULE_DESCRIPTION("CORDIC algorithm");
 MODULE_AUTHOR("Broadcom Corporation");
 MODULE_LICENSE("Dual BSD/GPL");
diff --git a/lib/cpu-notifier-error-inject.c b/lib/cpu-notifier-error-inject.c
index 4dc20321b0d5..707ca24f7b18 100644
--- a/lib/cpu-notifier-error-inject.c
+++ b/lib/cpu-notifier-error-inject.c
@@ -1,58 +1,45 @@
 #include <linux/kernel.h>
-#include <linux/cpu.h>
 #include <linux/module.h>
-#include <linux/notifier.h>
+#include <linux/cpu.h>
 
-static int priority;
-static int cpu_up_prepare_error;
-static int cpu_down_prepare_error;
+#include "notifier-error-inject.h"
 
+static int priority;
 module_param(priority, int, 0);
 MODULE_PARM_DESC(priority, "specify cpu notifier priority");
 
-module_param(cpu_up_prepare_error, int, 0644);
-MODULE_PARM_DESC(cpu_up_prepare_error,
-                "specify error code to inject CPU_UP_PREPARE action");
-
-module_param(cpu_down_prepare_error, int, 0644);
-MODULE_PARM_DESC(cpu_down_prepare_error,
-                "specify error code to inject CPU_DOWN_PREPARE action");
-
-static int err_inject_cpu_callback(struct notifier_block *nfb,
-                                unsigned long action, void *hcpu)
-{
-        int err = 0;
-
-        switch (action) {
-        case CPU_UP_PREPARE:
-        case CPU_UP_PREPARE_FROZEN:
-                err = cpu_up_prepare_error;
-                break;
-        case CPU_DOWN_PREPARE:
-        case CPU_DOWN_PREPARE_FROZEN:
-                err = cpu_down_prepare_error;
-                break;
+static struct notifier_err_inject cpu_notifier_err_inject = {
+        .actions = {
+                { NOTIFIER_ERR_INJECT_ACTION(CPU_UP_PREPARE) },
+                { NOTIFIER_ERR_INJECT_ACTION(CPU_UP_PREPARE_FROZEN) },
+                { NOTIFIER_ERR_INJECT_ACTION(CPU_DOWN_PREPARE) },
+                { NOTIFIER_ERR_INJECT_ACTION(CPU_DOWN_PREPARE_FROZEN) },
+                {}
         }
-        if (err)
-                printk(KERN_INFO "Injecting error (%d) at cpu notifier\n", err);
-
-        return notifier_from_errno(err);
-}
-
-static struct notifier_block err_inject_cpu_notifier = {
-        .notifier_call = err_inject_cpu_callback,
 };
 
+static struct dentry *dir;
+
 static int err_inject_init(void)
 {
-        err_inject_cpu_notifier.priority = priority;
+        int err;
+
+        dir = notifier_err_inject_init("cpu", notifier_err_inject_dir,
+                                        &cpu_notifier_err_inject, priority);
+        if (IS_ERR(dir))
+                return PTR_ERR(dir);
+
+        err = register_hotcpu_notifier(&cpu_notifier_err_inject.nb);
+        if (err)
+                debugfs_remove_recursive(dir);
 
-        return register_hotcpu_notifier(&err_inject_cpu_notifier);
+        return err;
 }
 
 static void err_inject_exit(void)
 {
-        unregister_hotcpu_notifier(&err_inject_cpu_notifier);
+        unregister_hotcpu_notifier(&cpu_notifier_err_inject.nb);
+        debugfs_remove_recursive(dir);
 }
 
 module_init(err_inject_init);
diff --git a/lib/cpu_rmap.c b/lib/cpu_rmap.c
index 987acfafeb83..145dec5267c9 100644
--- a/lib/cpu_rmap.c
+++ b/lib/cpu_rmap.c
@@ -11,7 +11,7 @@
 #ifdef CONFIG_GENERIC_HARDIRQS
 #include <linux/interrupt.h>
 #endif
-#include <linux/module.h>
+#include <linux/export.h>
 
 /*
  * These functions maintain a mapping from CPUs to some ordered set of
diff --git a/lib/cpumask.c b/lib/cpumask.c
index af3e5817de98..402a54ac35cb 100644
--- a/lib/cpumask.c
+++ b/lib/cpumask.c
@@ -2,7 +2,7 @@
 #include <linux/kernel.h>
 #include <linux/bitops.h>
 #include <linux/cpumask.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/bootmem.h>
 
 int __first_cpu(const cpumask_t *srcp)
@@ -26,18 +26,6 @@ int __next_cpu_nr(int n, const cpumask_t *srcp)
 EXPORT_SYMBOL(__next_cpu_nr);
 #endif
 
-int __any_online_cpu(const cpumask_t *mask)
-{
-        int cpu;
-
-        for_each_cpu(cpu, mask) {
-                if (cpu_online(cpu))
-                        break;
-        }
-        return cpu;
-}
-EXPORT_SYMBOL(__any_online_cpu);
-
 /**
  * cpumask_next_and - get the next cpu in *src1p & *src2p
  * @n: the cpu prior to the place to search (ie. return will be > @n)
diff --git a/lib/crc32.c b/lib/crc32.c
index a6e633a48cea..072fbd8234d5 100644
--- a/lib/crc32.c
+++ b/lib/crc32.c
@@ -1,4 +1,8 @@
 /*
+ * Aug 8, 2011 Bob Pearson with help from Joakim Tjernlund and George Spelvin
+ * cleaned up code to current version of sparse and added the slicing-by-8
+ * algorithm to the closely similar existing slicing-by-4 algorithm.
+ *
  * Oct 15, 2000 Matt Domsch <Matt_Domsch@dell.com>
  * Nicer crc32 functions/docs submitted by linux@horizon.com.  Thanks!
  * Code was from the public domain, copyright abandoned.  Code was
@@ -20,51 +24,60 @@
  * Version 2.  See the file COPYING for more details.
  */
 
+/* see: Documentation/crc32.txt for a description of algorithms */
+
 #include <linux/crc32.h>
-#include <linux/kernel.h>
 #include <linux/module.h>
-#include <linux/compiler.h>
 #include <linux/types.h>
-#include <linux/init.h>
-#include <linux/atomic.h>
 #include "crc32defs.h"
-#if CRC_LE_BITS == 8
-# define tole(x) __constant_cpu_to_le32(x)
+
+#if CRC_LE_BITS > 8
+# define tole(x) ((__force u32) __constant_cpu_to_le32(x))
 #else
 # define tole(x) (x)
 #endif
 
-#if CRC_BE_BITS == 8
-# define tobe(x) __constant_cpu_to_be32(x)
+#if CRC_BE_BITS > 8
+# define tobe(x) ((__force u32) __constant_cpu_to_be32(x))
 #else
 # define tobe(x) (x)
 #endif
+
 #include "crc32table.h"
 
 MODULE_AUTHOR("Matt Domsch <Matt_Domsch@dell.com>");
-MODULE_DESCRIPTION("Ethernet CRC32 calculations");
+MODULE_DESCRIPTION("Various CRC32 calculations");
 MODULE_LICENSE("GPL");
 
-#if CRC_LE_BITS == 8 || CRC_BE_BITS == 8
+#if CRC_LE_BITS > 8 || CRC_BE_BITS > 8
 
+/* implements slicing-by-4 or slicing-by-8 algorithm */
 static inline u32
 crc32_body(u32 crc, unsigned char const *buf, size_t len, const u32 (*tab)[256])
 {
 # ifdef __LITTLE_ENDIAN
-#  define DO_CRC(x) crc = tab[0][(crc ^ (x)) & 255] ^ (crc >> 8)
-#  define DO_CRC4 crc = tab[3][(crc) & 255] ^ \
-                tab[2][(crc >> 8) & 255] ^ \
-                tab[1][(crc >> 16) & 255] ^ \
-                tab[0][(crc >> 24) & 255]
+#  define DO_CRC(x) crc = t0[(crc ^ (x)) & 255] ^ (crc >> 8)
+#  define DO_CRC4 (t3[(q) & 255] ^ t2[(q >> 8) & 255] ^ \
+                   t1[(q >> 16) & 255] ^ t0[(q >> 24) & 255])
+#  define DO_CRC8 (t7[(q) & 255] ^ t6[(q >> 8) & 255] ^ \
+                   t5[(q >> 16) & 255] ^ t4[(q >> 24) & 255])
 # else
-#  define DO_CRC(x) crc = tab[0][((crc >> 24) ^ (x)) & 255] ^ (crc << 8)
-#  define DO_CRC4 crc = tab[0][(crc) & 255] ^ \
-                tab[1][(crc >> 8) & 255] ^ \
-                tab[2][(crc >> 16) & 255] ^ \
-                tab[3][(crc >> 24) & 255]
+#  define DO_CRC(x) crc = t0[((crc >> 24) ^ (x)) & 255] ^ (crc << 8)
+#  define DO_CRC4 (t0[(q) & 255] ^ t1[(q >> 8) & 255] ^ \
+                   t2[(q >> 16) & 255] ^ t3[(q >> 24) & 255])
+#  define DO_CRC8 (t4[(q) & 255] ^ t5[(q >> 8) & 255] ^ \
+                   t6[(q >> 16) & 255] ^ t7[(q >> 24) & 255])
 # endif
         const u32 *b;
         size_t    rem_len;
+# ifdef CONFIG_X86
+        size_t i;
+# endif
+        const u32 *t0=tab[0], *t1=tab[1], *t2=tab[2], *t3=tab[3];
+# if CRC_LE_BITS != 32
+        const u32 *t4 = tab[4], *t5 = tab[5], *t6 = tab[6], *t7 = tab[7];
+# endif
+        u32 q;
 
         /* Align it */
         if (unlikely((long)buf & 3 && len)) {
@@ -72,27 +85,51 @@ crc32_body(u32 crc, unsigned char const *buf, size_t len, const u32 (*tab)[256])
                         DO_CRC(*buf++);
                 } while ((--len) && ((long)buf)&3);
         }
+
+# if CRC_LE_BITS == 32
         rem_len = len & 3;
-        /* load data 32 bits wide, xor data 32 bits wide. */
         len = len >> 2;
+# else
+        rem_len = len & 7;
+        len = len >> 3;
+# endif
+
         b = (const u32 *)buf;
+# ifdef CONFIG_X86
+        --b;
+        for (i = 0; i < len; i++) {
+# else
         for (--b; len; --len) {
-                crc ^= *++b; /* use pre increment for speed */
-                DO_CRC4;
+# endif
+                q = crc ^ *++b; /* use pre increment for speed */
+# if CRC_LE_BITS == 32
+                crc = DO_CRC4;
+# else
+                crc = DO_CRC8;
+                q = *++b;
+                crc ^= DO_CRC4;
+# endif
         }
         len = rem_len;
         /* And the last few bytes */
         if (len) {
                 u8 *p = (u8 *)(b + 1) - 1;
+# ifdef CONFIG_X86
+                for (i = 0; i < len; i++)
+                        DO_CRC(*++p); /* use pre increment for speed */
+# else
                 do {
                         DO_CRC(*++p); /* use pre increment for speed */
                 } while (--len);
+# endif
         }
         return crc;
 #undef DO_CRC
 #undef DO_CRC4
+#undef DO_CRC8
 }
 #endif
+
 /**
  * crc32_le() - Calculate bitwise little-endian Ethernet AUTODIN II CRC32
  * @crc: seed value for computation.  ~0 for Ethernet, sometimes 0 for
@@ -100,53 +137,68 @@ crc32_body(u32 crc, unsigned char const *buf, size_t len, const u32 (*tab)[256])
  * @p: pointer to buffer over which CRC is run
  * @len: length of buffer @p
  */
-u32 __pure crc32_le(u32 crc, unsigned char const *p, size_t len);
-
-#if CRC_LE_BITS == 1
-/*
- * In fact, the table-based code will work in this case, but it can be
- * simplified by inlining the table in ?: form.
- */
-
-u32 __pure crc32_le(u32 crc, unsigned char const *p, size_t len)
+static inline u32 __pure crc32_le_generic(u32 crc, unsigned char const *p,
+                                          size_t len, const u32 (*tab)[256],
+                                          u32 polynomial)
 {
+#if CRC_LE_BITS == 1
         int i;
         while (len--) {
                 crc ^= *p++;
                 for (i = 0; i < 8; i++)
-                        crc = (crc >> 1) ^ ((crc & 1) ? CRCPOLY_LE : 0);
+                        crc = (crc >> 1) ^ ((crc & 1) ? polynomial : 0);
+        }
+# elif CRC_LE_BITS == 2
+        while (len--) {
+                crc ^= *p++;
+                crc = (crc >> 2) ^ tab[0][crc & 3];
+                crc = (crc >> 2) ^ tab[0][crc & 3];
+                crc = (crc >> 2) ^ tab[0][crc & 3];
+                crc = (crc >> 2) ^ tab[0][crc & 3];
         }
-        return crc;
-}
-#else                           /* Table-based approach */
-
-u32 __pure crc32_le(u32 crc, unsigned char const *p, size_t len)
-{
-# if CRC_LE_BITS == 8
-        const u32      (*tab)[] = crc32table_le;
-
-        crc = __cpu_to_le32(crc);
-        crc = crc32_body(crc, p, len, tab);
-        return __le32_to_cpu(crc);
 # elif CRC_LE_BITS == 4
         while (len--) {
                 crc ^= *p++;
-                crc = (crc >> 4) ^ crc32table_le[crc & 15];
-                crc = (crc >> 4) ^ crc32table_le[crc & 15];
+                crc = (crc >> 4) ^ tab[0][crc & 15];
+                crc = (crc >> 4) ^ tab[0][crc & 15];
         }
-        return crc;
-# elif CRC_LE_BITS == 2
+# elif CRC_LE_BITS == 8
+        /* aka Sarwate algorithm */
         while (len--) {
                 crc ^= *p++;
-                crc = (crc >> 2) ^ crc32table_le[crc & 3];
-                crc = (crc >> 2) ^ crc32table_le[crc & 3];
-                crc = (crc >> 2) ^ crc32table_le[crc & 3];
-                crc = (crc >> 2) ^ crc32table_le[crc & 3];
+                crc = (crc >> 8) ^ tab[0][crc & 255];
         }
+# else
+        crc = (__force u32) __cpu_to_le32(crc);
+        crc = crc32_body(crc, p, len, tab);
+        crc = __le32_to_cpu((__force __le32)crc);
+#endif
         return crc;
-# endif
+}
+
+#if CRC_LE_BITS == 1
+u32 __pure crc32_le(u32 crc, unsigned char const *p, size_t len)
+{
+        return crc32_le_generic(crc, p, len, NULL, CRCPOLY_LE);
+}
+u32 __pure __crc32c_le(u32 crc, unsigned char const *p, size_t len)
+{
+        return crc32_le_generic(crc, p, len, NULL, CRC32C_POLY_LE);
+}
+#else
+u32 __pure crc32_le(u32 crc, unsigned char const *p, size_t len)
+{
+        return crc32_le_generic(crc, p, len,
+                        (const u32 (*)[256])crc32table_le, CRCPOLY_LE);
+}
+u32 __pure __crc32c_le(u32 crc, unsigned char const *p, size_t len)
+{
+        return crc32_le_generic(crc, p, len,
+                        (const u32 (*)[256])crc32ctable_le, CRC32C_POLY_LE);
 }
 #endif
+EXPORT_SYMBOL(crc32_le);
+EXPORT_SYMBOL(__crc32c_le);
 
 /**
  * crc32_be() - Calculate bitwise big-endian Ethernet AUTODIN II CRC32
@@ -155,317 +207,914 @@ u32 __pure crc32_le(u32 crc, unsigned char const *p, size_t len)
  * @p: pointer to buffer over which CRC is run
  * @len: length of buffer @p
  */
-u32 __pure crc32_be(u32 crc, unsigned char const *p, size_t len);
-
-#if CRC_BE_BITS == 1
-/*
- * In fact, the table-based code will work in this case, but it can be
- * simplified by inlining the table in ?: form.
- */
-
-u32 __pure crc32_be(u32 crc, unsigned char const *p, size_t len)
+static inline u32 __pure crc32_be_generic(u32 crc, unsigned char const *p,
+                                          size_t len, const u32 (*tab)[256],
+                                          u32 polynomial)
 {
+#if CRC_BE_BITS == 1
         int i;
         while (len--) {
                 crc ^= *p++ << 24;
                 for (i = 0; i < 8; i++)
                         crc =
-                            (crc << 1) ^ ((crc & 0x80000000) ? CRCPOLY_BE :
+                            (crc << 1) ^ ((crc & 0x80000000) ? polynomial :
                                           0);
         }
-        return crc;
-}
-
-#else                           /* Table-based approach */
-u32 __pure crc32_be(u32 crc, unsigned char const *p, size_t len)
-{
-# if CRC_BE_BITS == 8
-        const u32      (*tab)[] = crc32table_be;
-
-        crc = __cpu_to_be32(crc);
-        crc = crc32_body(crc, p, len, tab);
-        return __be32_to_cpu(crc);
+# elif CRC_BE_BITS == 2
+        while (len--) {
+                crc ^= *p++ << 24;
+                crc = (crc << 2) ^ tab[0][crc >> 30];
+                crc = (crc << 2) ^ tab[0][crc >> 30];
+                crc = (crc << 2) ^ tab[0][crc >> 30];
+                crc = (crc << 2) ^ tab[0][crc >> 30];
+        }
 # elif CRC_BE_BITS == 4
         while (len--) {
                 crc ^= *p++ << 24;
-                crc = (crc << 4) ^ crc32table_be[crc >> 28];
-                crc = (crc << 4) ^ crc32table_be[crc >> 28];
+                crc = (crc << 4) ^ tab[0][crc >> 28];
+                crc = (crc << 4) ^ tab[0][crc >> 28];
         }
-        return crc;
-# elif CRC_BE_BITS == 2
+# elif CRC_BE_BITS == 8
         while (len--) {
                 crc ^= *p++ << 24;
-                crc = (crc << 2) ^ crc32table_be[crc >> 30];
-                crc = (crc << 2) ^ crc32table_be[crc >> 30];
-                crc = (crc << 2) ^ crc32table_be[crc >> 30];
-                crc = (crc << 2) ^ crc32table_be[crc >> 30];
+                crc = (crc << 8) ^ tab[0][crc >> 24];
         }
-        return crc;
+# else
+        crc = (__force u32) __cpu_to_be32(crc);
+        crc = crc32_body(crc, p, len, tab);
+        crc = __be32_to_cpu((__force __be32)crc);
 # endif
+        return crc;
 }
-#endif
 
-EXPORT_SYMBOL(crc32_le);
+#if CRC_LE_BITS == 1
+u32 __pure crc32_be(u32 crc, unsigned char const *p, size_t len)
+{
+        return crc32_be_generic(crc, p, len, NULL, CRCPOLY_BE);
+}
+#else
+u32 __pure crc32_be(u32 crc, unsigned char const *p, size_t len)
+{
+        return crc32_be_generic(crc, p, len,
+                        (const u32 (*)[256])crc32table_be, CRCPOLY_BE);
+}
+#endif
 EXPORT_SYMBOL(crc32_be);
 
-/*
- * A brief CRC tutorial.
- *
- * A CRC is a long-division remainder.  You add the CRC to the message,
- * and the whole thing (message+CRC) is a multiple of the given
- * CRC polynomial.  To check the CRC, you can either check that the
- * CRC matches the recomputed value, *or* you can check that the
- * remainder computed on the message+CRC is 0.  This latter approach
- * is used by a lot of hardware implementations, and is why so many
- * protocols put the end-of-frame flag after the CRC.
- *
- * It's actually the same long division you learned in school, except that
- * - We're working in binary, so the digits are only 0 and 1, and
- * - When dividing polynomials, there are no carries.  Rather than add and
- *   subtract, we just xor.  Thus, we tend to get a bit sloppy about
- *   the difference between adding and subtracting.
- *
- * A 32-bit CRC polynomial is actually 33 bits long.  But since it's
- * 33 bits long, bit 32 is always going to be set, so usually the CRC
- * is written in hex with the most significant bit omitted.  (If you're
- * familiar with the IEEE 754 floating-point format, it's the same idea.)
- *
- * Note that a CRC is computed over a string of *bits*, so you have
- * to decide on the endianness of the bits within each byte.  To get
- * the best error-detecting properties, this should correspond to the
- * order they're actually sent.  For example, standard RS-232 serial is
- * little-endian; the most significant bit (sometimes used for parity)
- * is sent last.  And when appending a CRC word to a message, you should
- * do it in the right order, matching the endianness.
- *
- * Just like with ordinary division, the remainder is always smaller than
- * the divisor (the CRC polynomial) you're dividing by.  Each step of the
- * division, you take one more digit (bit) of the dividend and append it
- * to the current remainder.  Then you figure out the appropriate multiple
- * of the divisor to subtract to being the remainder back into range.
- * In binary, it's easy - it has to be either 0 or 1, and to make the
- * XOR cancel, it's just a copy of bit 32 of the remainder.
- *
- * When computing a CRC, we don't care about the quotient, so we can
- * throw the quotient bit away, but subtract the appropriate multiple of
- * the polynomial from the remainder and we're back to where we started,
- * ready to process the next bit.
- *
- * A big-endian CRC written this way would be coded like:
- * for (i = 0; i < input_bits; i++) {
- *      multiple = remainder & 0x80000000 ? CRCPOLY : 0;
- *      remainder = (remainder << 1 | next_input_bit()) ^ multiple;
- * }
- * Notice how, to get at bit 32 of the shifted remainder, we look
- * at bit 31 of the remainder *before* shifting it.
- *
- * But also notice how the next_input_bit() bits we're shifting into
- * the remainder don't actually affect any decision-making until
- * 32 bits later.  Thus, the first 32 cycles of this are pretty boring.
- * Also, to add the CRC to a message, we need a 32-bit-long hole for it at
- * the end, so we have to add 32 extra cycles shifting in zeros at the
- * end of every message,
- *
- * So the standard trick is to rearrage merging in the next_input_bit()
- * until the moment it's needed.  Then the first 32 cycles can be precomputed,
- * and merging in the final 32 zero bits to make room for the CRC can be
- * skipped entirely.
- * This changes the code to:
- * for (i = 0; i < input_bits; i++) {
- *      remainder ^= next_input_bit() << 31;
- *      multiple = (remainder & 0x80000000) ? CRCPOLY : 0;
- *      remainder = (remainder << 1) ^ multiple;
- * }
- * With this optimization, the little-endian code is simpler:
- * for (i = 0; i < input_bits; i++) {
- *      remainder ^= next_input_bit();
- *      multiple = (remainder & 1) ? CRCPOLY : 0;
- *      remainder = (remainder >> 1) ^ multiple;
- * }
- *
- * Note that the other details of endianness have been hidden in CRCPOLY
- * (which must be bit-reversed) and next_input_bit().
- *
- * However, as long as next_input_bit is returning the bits in a sensible
- * order, we can actually do the merging 8 or more bits at a time rather
- * than one bit at a time:
- * for (i = 0; i < input_bytes; i++) {
- *      remainder ^= next_input_byte() << 24;
- *      for (j = 0; j < 8; j++) {
- *              multiple = (remainder & 0x80000000) ? CRCPOLY : 0;
- *              remainder = (remainder << 1) ^ multiple;
- *      }
- * }
- * Or in little-endian:
- * for (i = 0; i < input_bytes; i++) {
- *      remainder ^= next_input_byte();
- *      for (j = 0; j < 8; j++) {
- *              multiple = (remainder & 1) ? CRCPOLY : 0;
- *              remainder = (remainder << 1) ^ multiple;
- *      }
- * }
- * If the input is a multiple of 32 bits, you can even XOR in a 32-bit
- * word at a time and increase the inner loop count to 32.
- *
- * You can also mix and match the two loop styles, for example doing the
- * bulk of a message byte-at-a-time and adding bit-at-a-time processing
- * for any fractional bytes at the end.
- *
- * The only remaining optimization is to the byte-at-a-time table method.
- * Here, rather than just shifting one bit of the remainder to decide
- * in the correct multiple to subtract, we can shift a byte at a time.
- * This produces a 40-bit (rather than a 33-bit) intermediate remainder,
- * but again the multiple of the polynomial to subtract depends only on
- * the high bits, the high 8 bits in this case.  
- *
- * The multiple we need in that case is the low 32 bits of a 40-bit
- * value whose high 8 bits are given, and which is a multiple of the
- * generator polynomial.  This is simply the CRC-32 of the given
- * one-byte message.
- *
- * Two more details: normally, appending zero bits to a message which
- * is already a multiple of a polynomial produces a larger multiple of that
- * polynomial.  To enable a CRC to detect this condition, it's common to
- * invert the CRC before appending it.  This makes the remainder of the
- * message+crc come out not as zero, but some fixed non-zero value.
- *
- * The same problem applies to zero bits prepended to the message, and
- * a similar solution is used.  Instead of starting with a remainder of
- * 0, an initial remainder of all ones is used.  As long as you start
- * the same way on decoding, it doesn't make a difference.
- */
-
-#ifdef UNITTEST
+#ifdef CONFIG_CRC32_SELFTEST
 
-#include <stdlib.h>
-#include <stdio.h>
+/* 4096 random bytes */
+static u8 __attribute__((__aligned__(8))) test_buf[] =
+{
+        0x5b, 0x85, 0x21, 0xcb, 0x09, 0x68, 0x7d, 0x30,
+        0xc7, 0x69, 0xd7, 0x30, 0x92, 0xde, 0x59, 0xe4,
+        0xc9, 0x6e, 0x8b, 0xdb, 0x98, 0x6b, 0xaa, 0x60,
+        0xa8, 0xb5, 0xbc, 0x6c, 0xa9, 0xb1, 0x5b, 0x2c,
+        0xea, 0xb4, 0x92, 0x6a, 0x3f, 0x79, 0x91, 0xe4,
+        0xe9, 0x70, 0x51, 0x8c, 0x7f, 0x95, 0x6f, 0x1a,
+        0x56, 0xa1, 0x5c, 0x27, 0x03, 0x67, 0x9f, 0x3a,
+        0xe2, 0x31, 0x11, 0x29, 0x6b, 0x98, 0xfc, 0xc4,
+        0x53, 0x24, 0xc5, 0x8b, 0xce, 0x47, 0xb2, 0xb9,
+        0x32, 0xcb, 0xc1, 0xd0, 0x03, 0x57, 0x4e, 0xd4,
+        0xe9, 0x3c, 0xa1, 0x63, 0xcf, 0x12, 0x0e, 0xca,
+        0xe1, 0x13, 0xd1, 0x93, 0xa6, 0x88, 0x5c, 0x61,
+        0x5b, 0xbb, 0xf0, 0x19, 0x46, 0xb4, 0xcf, 0x9e,
+        0xb6, 0x6b, 0x4c, 0x3a, 0xcf, 0x60, 0xf9, 0x7a,
+        0x8d, 0x07, 0x63, 0xdb, 0x40, 0xe9, 0x0b, 0x6f,
+        0xad, 0x97, 0xf1, 0xed, 0xd0, 0x1e, 0x26, 0xfd,
+        0xbf, 0xb7, 0xc8, 0x04, 0x94, 0xf8, 0x8b, 0x8c,
+        0xf1, 0xab, 0x7a, 0xd4, 0xdd, 0xf3, 0xe8, 0x88,
+        0xc3, 0xed, 0x17, 0x8a, 0x9b, 0x40, 0x0d, 0x53,
+        0x62, 0x12, 0x03, 0x5f, 0x1b, 0x35, 0x32, 0x1f,
+        0xb4, 0x7b, 0x93, 0x78, 0x0d, 0xdb, 0xce, 0xa4,
+        0xc0, 0x47, 0xd5, 0xbf, 0x68, 0xe8, 0x5d, 0x74,
+        0x8f, 0x8e, 0x75, 0x1c, 0xb2, 0x4f, 0x9a, 0x60,
+        0xd1, 0xbe, 0x10, 0xf4, 0x5c, 0xa1, 0x53, 0x09,
+        0xa5, 0xe0, 0x09, 0x54, 0x85, 0x5c, 0xdc, 0x07,
+        0xe7, 0x21, 0x69, 0x7b, 0x8a, 0xfd, 0x90, 0xf1,
+        0x22, 0xd0, 0xb4, 0x36, 0x28, 0xe6, 0xb8, 0x0f,
+        0x39, 0xde, 0xc8, 0xf3, 0x86, 0x60, 0x34, 0xd2,
+        0x5e, 0xdf, 0xfd, 0xcf, 0x0f, 0xa9, 0x65, 0xf0,
+        0xd5, 0x4d, 0x96, 0x40, 0xe3, 0xdf, 0x3f, 0x95,
+        0x5a, 0x39, 0x19, 0x93, 0xf4, 0x75, 0xce, 0x22,
+        0x00, 0x1c, 0x93, 0xe2, 0x03, 0x66, 0xf4, 0x93,
+        0x73, 0x86, 0x81, 0x8e, 0x29, 0x44, 0x48, 0x86,
+        0x61, 0x7c, 0x48, 0xa3, 0x43, 0xd2, 0x9c, 0x8d,
+        0xd4, 0x95, 0xdd, 0xe1, 0x22, 0x89, 0x3a, 0x40,
+        0x4c, 0x1b, 0x8a, 0x04, 0xa8, 0x09, 0x69, 0x8b,
+        0xea, 0xc6, 0x55, 0x8e, 0x57, 0xe6, 0x64, 0x35,
+        0xf0, 0xc7, 0x16, 0x9f, 0x5d, 0x5e, 0x86, 0x40,
+        0x46, 0xbb, 0xe5, 0x45, 0x88, 0xfe, 0xc9, 0x63,
+        0x15, 0xfb, 0xf5, 0xbd, 0x71, 0x61, 0xeb, 0x7b,
+        0x78, 0x70, 0x07, 0x31, 0x03, 0x9f, 0xb2, 0xc8,
+        0xa7, 0xab, 0x47, 0xfd, 0xdf, 0xa0, 0x78, 0x72,
+        0xa4, 0x2a, 0xe4, 0xb6, 0xba, 0xc0, 0x1e, 0x86,
+        0x71, 0xe6, 0x3d, 0x18, 0x37, 0x70, 0xe6, 0xff,
+        0xe0, 0xbc, 0x0b, 0x22, 0xa0, 0x1f, 0xd3, 0xed,
+        0xa2, 0x55, 0x39, 0xab, 0xa8, 0x13, 0x73, 0x7c,
+        0x3f, 0xb2, 0xd6, 0x19, 0xac, 0xff, 0x99, 0xed,
+        0xe8, 0xe6, 0xa6, 0x22, 0xe3, 0x9c, 0xf1, 0x30,
+        0xdc, 0x01, 0x0a, 0x56, 0xfa, 0xe4, 0xc9, 0x99,
+        0xdd, 0xa8, 0xd8, 0xda, 0x35, 0x51, 0x73, 0xb4,
+        0x40, 0x86, 0x85, 0xdb, 0x5c, 0xd5, 0x85, 0x80,
+        0x14, 0x9c, 0xfd, 0x98, 0xa9, 0x82, 0xc5, 0x37,
+        0xff, 0x32, 0x5d, 0xd0, 0x0b, 0xfa, 0xdc, 0x04,
+        0x5e, 0x09, 0xd2, 0xca, 0x17, 0x4b, 0x1a, 0x8e,
+        0x15, 0xe1, 0xcc, 0x4e, 0x52, 0x88, 0x35, 0xbd,
+        0x48, 0xfe, 0x15, 0xa0, 0x91, 0xfd, 0x7e, 0x6c,
+        0x0e, 0x5d, 0x79, 0x1b, 0x81, 0x79, 0xd2, 0x09,
+        0x34, 0x70, 0x3d, 0x81, 0xec, 0xf6, 0x24, 0xbb,
+        0xfb, 0xf1, 0x7b, 0xdf, 0x54, 0xea, 0x80, 0x9b,
+        0xc7, 0x99, 0x9e, 0xbd, 0x16, 0x78, 0x12, 0x53,
+        0x5e, 0x01, 0xa7, 0x4e, 0xbd, 0x67, 0xe1, 0x9b,
+        0x4c, 0x0e, 0x61, 0x45, 0x97, 0xd2, 0xf0, 0x0f,
+        0xfe, 0x15, 0x08, 0xb7, 0x11, 0x4c, 0xe7, 0xff,
+        0x81, 0x53, 0xff, 0x91, 0x25, 0x38, 0x7e, 0x40,
+        0x94, 0xe5, 0xe0, 0xad, 0xe6, 0xd9, 0x79, 0xb6,
+        0x92, 0xc9, 0xfc, 0xde, 0xc3, 0x1a, 0x23, 0xbb,
+        0xdd, 0xc8, 0x51, 0x0c, 0x3a, 0x72, 0xfa, 0x73,
+        0x6f, 0xb7, 0xee, 0x61, 0x39, 0x03, 0x01, 0x3f,
+        0x7f, 0x94, 0x2e, 0x2e, 0xba, 0x3a, 0xbb, 0xb4,
+        0xfa, 0x6a, 0x17, 0xfe, 0xea, 0xef, 0x5e, 0x66,
+        0x97, 0x3f, 0x32, 0x3d, 0xd7, 0x3e, 0xb1, 0xf1,
+        0x6c, 0x14, 0x4c, 0xfd, 0x37, 0xd3, 0x38, 0x80,
+        0xfb, 0xde, 0xa6, 0x24, 0x1e, 0xc8, 0xca, 0x7f,
+        0x3a, 0x93, 0xd8, 0x8b, 0x18, 0x13, 0xb2, 0xe5,
+        0xe4, 0x93, 0x05, 0x53, 0x4f, 0x84, 0x66, 0xa7,
+        0x58, 0x5c, 0x7b, 0x86, 0x52, 0x6d, 0x0d, 0xce,
+        0xa4, 0x30, 0x7d, 0xb6, 0x18, 0x9f, 0xeb, 0xff,
+        0x22, 0xbb, 0x72, 0x29, 0xb9, 0x44, 0x0b, 0x48,
+        0x1e, 0x84, 0x71, 0x81, 0xe3, 0x6d, 0x73, 0x26,
+        0x92, 0xb4, 0x4d, 0x2a, 0x29, 0xb8, 0x1f, 0x72,
+        0xed, 0xd0, 0xe1, 0x64, 0x77, 0xea, 0x8e, 0x88,
+        0x0f, 0xef, 0x3f, 0xb1, 0x3b, 0xad, 0xf9, 0xc9,
+        0x8b, 0xd0, 0xac, 0xc6, 0xcc, 0xa9, 0x40, 0xcc,
+        0x76, 0xf6, 0x3b, 0x53, 0xb5, 0x88, 0xcb, 0xc8,
+        0x37, 0xf1, 0xa2, 0xba, 0x23, 0x15, 0x99, 0x09,
+        0xcc, 0xe7, 0x7a, 0x3b, 0x37, 0xf7, 0x58, 0xc8,
+        0x46, 0x8c, 0x2b, 0x2f, 0x4e, 0x0e, 0xa6, 0x5c,
+        0xea, 0x85, 0x55, 0xba, 0x02, 0x0e, 0x0e, 0x48,
+        0xbc, 0xe1, 0xb1, 0x01, 0x35, 0x79, 0x13, 0x3d,
+        0x1b, 0xc0, 0x53, 0x68, 0x11, 0xe7, 0x95, 0x0f,
+        0x9d, 0x3f, 0x4c, 0x47, 0x7b, 0x4d, 0x1c, 0xae,
+        0x50, 0x9b, 0xcb, 0xdd, 0x05, 0x8d, 0x9a, 0x97,
+        0xfd, 0x8c, 0xef, 0x0c, 0x1d, 0x67, 0x73, 0xa8,
+        0x28, 0x36, 0xd5, 0xb6, 0x92, 0x33, 0x40, 0x75,
+        0x0b, 0x51, 0xc3, 0x64, 0xba, 0x1d, 0xc2, 0xcc,
+        0xee, 0x7d, 0x54, 0x0f, 0x27, 0x69, 0xa7, 0x27,
+        0x63, 0x30, 0x29, 0xd9, 0xc8, 0x84, 0xd8, 0xdf,
+        0x9f, 0x68, 0x8d, 0x04, 0xca, 0xa6, 0xc5, 0xc7,
+        0x7a, 0x5c, 0xc8, 0xd1, 0xcb, 0x4a, 0xec, 0xd0,
+        0xd8, 0x20, 0x69, 0xc5, 0x17, 0xcd, 0x78, 0xc8,
+        0x75, 0x23, 0x30, 0x69, 0xc9, 0xd4, 0xea, 0x5c,
+        0x4f, 0x6b, 0x86, 0x3f, 0x8b, 0xfe, 0xee, 0x44,
+        0xc9, 0x7c, 0xb7, 0xdd, 0x3e, 0xe5, 0xec, 0x54,
+        0x03, 0x3e, 0xaa, 0x82, 0xc6, 0xdf, 0xb2, 0x38,
+        0x0e, 0x5d, 0xb3, 0x88, 0xd9, 0xd3, 0x69, 0x5f,
+        0x8f, 0x70, 0x8a, 0x7e, 0x11, 0xd9, 0x1e, 0x7b,
+        0x38, 0xf1, 0x42, 0x1a, 0xc0, 0x35, 0xf5, 0xc7,
+        0x36, 0x85, 0xf5, 0xf7, 0xb8, 0x7e, 0xc7, 0xef,
+        0x18, 0xf1, 0x63, 0xd6, 0x7a, 0xc6, 0xc9, 0x0e,
+        0x4d, 0x69, 0x4f, 0x84, 0xef, 0x26, 0x41, 0x0c,
+        0xec, 0xc7, 0xe0, 0x7e, 0x3c, 0x67, 0x01, 0x4c,
+        0x62, 0x1a, 0x20, 0x6f, 0xee, 0x47, 0x4d, 0xc0,
+        0x99, 0x13, 0x8d, 0x91, 0x4a, 0x26, 0xd4, 0x37,
+        0x28, 0x90, 0x58, 0x75, 0x66, 0x2b, 0x0a, 0xdf,
+        0xda, 0xee, 0x92, 0x25, 0x90, 0x62, 0x39, 0x9e,
+        0x44, 0x98, 0xad, 0xc1, 0x88, 0xed, 0xe4, 0xb4,
+        0xaf, 0xf5, 0x8c, 0x9b, 0x48, 0x4d, 0x56, 0x60,
+        0x97, 0x0f, 0x61, 0x59, 0x9e, 0xa6, 0x27, 0xfe,
+        0xc1, 0x91, 0x15, 0x38, 0xb8, 0x0f, 0xae, 0x61,
+        0x7d, 0x26, 0x13, 0x5a, 0x73, 0xff, 0x1c, 0xa3,
+        0x61, 0x04, 0x58, 0x48, 0x55, 0x44, 0x11, 0xfe,
+        0x15, 0xca, 0xc3, 0xbd, 0xca, 0xc5, 0xb4, 0x40,
+        0x5d, 0x1b, 0x7f, 0x39, 0xb5, 0x9c, 0x35, 0xec,
+        0x61, 0x15, 0x32, 0x32, 0xb8, 0x4e, 0x40, 0x9f,
+        0x17, 0x1f, 0x0a, 0x4d, 0xa9, 0x91, 0xef, 0xb7,
+        0xb0, 0xeb, 0xc2, 0x83, 0x9a, 0x6c, 0xd2, 0x79,
+        0x43, 0x78, 0x5e, 0x2f, 0xe5, 0xdd, 0x1a, 0x3c,
+        0x45, 0xab, 0x29, 0x40, 0x3a, 0x37, 0x5b, 0x6f,
+        0xd7, 0xfc, 0x48, 0x64, 0x3c, 0x49, 0xfb, 0x21,
+        0xbe, 0xc3, 0xff, 0x07, 0xfb, 0x17, 0xe9, 0xc9,
+        0x0c, 0x4c, 0x5c, 0x15, 0x9e, 0x8e, 0x22, 0x30,
+        0x0a, 0xde, 0x48, 0x7f, 0xdb, 0x0d, 0xd1, 0x2b,
+        0x87, 0x38, 0x9e, 0xcc, 0x5a, 0x01, 0x16, 0xee,
+        0x75, 0x49, 0x0d, 0x30, 0x01, 0x34, 0x6a, 0xb6,
+        0x9a, 0x5a, 0x2a, 0xec, 0xbb, 0x48, 0xac, 0xd3,
+        0x77, 0x83, 0xd8, 0x08, 0x86, 0x4f, 0x48, 0x09,
+        0x29, 0x41, 0x79, 0xa1, 0x03, 0x12, 0xc4, 0xcd,
+        0x90, 0x55, 0x47, 0x66, 0x74, 0x9a, 0xcc, 0x4f,
+        0x35, 0x8c, 0xd6, 0x98, 0xef, 0xeb, 0x45, 0xb9,
+        0x9a, 0x26, 0x2f, 0x39, 0xa5, 0x70, 0x6d, 0xfc,
+        0xb4, 0x51, 0xee, 0xf4, 0x9c, 0xe7, 0x38, 0x59,
+        0xad, 0xf4, 0xbc, 0x46, 0xff, 0x46, 0x8e, 0x60,
+        0x9c, 0xa3, 0x60, 0x1d, 0xf8, 0x26, 0x72, 0xf5,
+        0x72, 0x9d, 0x68, 0x80, 0x04, 0xf6, 0x0b, 0xa1,
+        0x0a, 0xd5, 0xa7, 0x82, 0x3a, 0x3e, 0x47, 0xa8,
+        0x5a, 0xde, 0x59, 0x4f, 0x7b, 0x07, 0xb3, 0xe9,
+        0x24, 0x19, 0x3d, 0x34, 0x05, 0xec, 0xf1, 0xab,
+        0x6e, 0x64, 0x8f, 0xd3, 0xe6, 0x41, 0x86, 0x80,
+        0x70, 0xe3, 0x8d, 0x60, 0x9c, 0x34, 0x25, 0x01,
+        0x07, 0x4d, 0x19, 0x41, 0x4e, 0x3d, 0x5c, 0x7e,
+        0xa8, 0xf5, 0xcc, 0xd5, 0x7b, 0xe2, 0x7d, 0x3d,
+        0x49, 0x86, 0x7d, 0x07, 0xb7, 0x10, 0xe3, 0x35,
+        0xb8, 0x84, 0x6d, 0x76, 0xab, 0x17, 0xc6, 0x38,
+        0xb4, 0xd3, 0x28, 0x57, 0xad, 0xd3, 0x88, 0x5a,
+        0xda, 0xea, 0xc8, 0x94, 0xcc, 0x37, 0x19, 0xac,
+        0x9c, 0x9f, 0x4b, 0x00, 0x15, 0xc0, 0xc8, 0xca,
+        0x1f, 0x15, 0xaa, 0xe0, 0xdb, 0xf9, 0x2f, 0x57,
+        0x1b, 0x24, 0xc7, 0x6f, 0x76, 0x29, 0xfb, 0xed,
+        0x25, 0x0d, 0xc0, 0xfe, 0xbd, 0x5a, 0xbf, 0x20,
+        0x08, 0x51, 0x05, 0xec, 0x71, 0xa3, 0xbf, 0xef,
+        0x5e, 0x99, 0x75, 0xdb, 0x3c, 0x5f, 0x9a, 0x8c,
+        0xbb, 0x19, 0x5c, 0x0e, 0x93, 0x19, 0xf8, 0x6a,
+        0xbc, 0xf2, 0x12, 0x54, 0x2f, 0xcb, 0x28, 0x64,
+        0x88, 0xb3, 0x92, 0x0d, 0x96, 0xd1, 0xa6, 0xe4,
+        0x1f, 0xf1, 0x4d, 0xa4, 0xab, 0x1c, 0xee, 0x54,
+        0xf2, 0xad, 0x29, 0x6d, 0x32, 0x37, 0xb2, 0x16,
+        0x77, 0x5c, 0xdc, 0x2e, 0x54, 0xec, 0x75, 0x26,
+        0xc6, 0x36, 0xd9, 0x17, 0x2c, 0xf1, 0x7a, 0xdc,
+        0x4b, 0xf1, 0xe2, 0xd9, 0x95, 0xba, 0xac, 0x87,
+        0xc1, 0xf3, 0x8e, 0x58, 0x08, 0xd8, 0x87, 0x60,
+        0xc9, 0xee, 0x6a, 0xde, 0xa4, 0xd2, 0xfc, 0x0d,
+        0xe5, 0x36, 0xc4, 0x5c, 0x52, 0xb3, 0x07, 0x54,
+        0x65, 0x24, 0xc1, 0xb1, 0xd1, 0xb1, 0x53, 0x13,
+        0x31, 0x79, 0x7f, 0x05, 0x76, 0xeb, 0x37, 0x59,
+        0x15, 0x2b, 0xd1, 0x3f, 0xac, 0x08, 0x97, 0xeb,
+        0x91, 0x98, 0xdf, 0x6c, 0x09, 0x0d, 0x04, 0x9f,
+        0xdc, 0x3b, 0x0e, 0x60, 0x68, 0x47, 0x23, 0x15,
+        0x16, 0xc6, 0x0b, 0x35, 0xf8, 0x77, 0xa2, 0x78,
+        0x50, 0xd4, 0x64, 0x22, 0x33, 0xff, 0xfb, 0x93,
+        0x71, 0x46, 0x50, 0x39, 0x1b, 0x9c, 0xea, 0x4e,
+        0x8d, 0x0c, 0x37, 0xe5, 0x5c, 0x51, 0x3a, 0x31,
+        0xb2, 0x85, 0x84, 0x3f, 0x41, 0xee, 0xa2, 0xc1,
+        0xc6, 0x13, 0x3b, 0x54, 0x28, 0xd2, 0x18, 0x37,
+        0xcc, 0x46, 0x9f, 0x6a, 0x91, 0x3d, 0x5a, 0x15,
+        0x3c, 0x89, 0xa3, 0x61, 0x06, 0x7d, 0x2e, 0x78,
+        0xbe, 0x7d, 0x40, 0xba, 0x2f, 0x95, 0xb1, 0x2f,
+        0x87, 0x3b, 0x8a, 0xbe, 0x6a, 0xf4, 0xc2, 0x31,
+        0x74, 0xee, 0x91, 0xe0, 0x23, 0xaa, 0x5d, 0x7f,
+        0xdd, 0xf0, 0x44, 0x8c, 0x0b, 0x59, 0x2b, 0xfc,
+        0x48, 0x3a, 0xdf, 0x07, 0x05, 0x38, 0x6c, 0xc9,
+        0xeb, 0x18, 0x24, 0x68, 0x8d, 0x58, 0x98, 0xd3,
+        0x31, 0xa3, 0xe4, 0x70, 0x59, 0xb1, 0x21, 0xbe,
+        0x7e, 0x65, 0x7d, 0xb8, 0x04, 0xab, 0xf6, 0xe4,
+        0xd7, 0xda, 0xec, 0x09, 0x8f, 0xda, 0x6d, 0x24,
+        0x07, 0xcc, 0x29, 0x17, 0x05, 0x78, 0x1a, 0xc1,
+        0xb1, 0xce, 0xfc, 0xaa, 0x2d, 0xe7, 0xcc, 0x85,
+        0x84, 0x84, 0x03, 0x2a, 0x0c, 0x3f, 0xa9, 0xf8,
+        0xfd, 0x84, 0x53, 0x59, 0x5c, 0xf0, 0xd4, 0x09,
+        0xf0, 0xd2, 0x6c, 0x32, 0x03, 0xb0, 0xa0, 0x8c,
+        0x52, 0xeb, 0x23, 0x91, 0x88, 0x43, 0x13, 0x46,
+        0xf6, 0x1e, 0xb4, 0x1b, 0xf5, 0x8e, 0x3a, 0xb5,
+        0x3d, 0x00, 0xf6, 0xe5, 0x08, 0x3d, 0x5f, 0x39,
+        0xd3, 0x21, 0x69, 0xbc, 0x03, 0x22, 0x3a, 0xd2,
+        0x5c, 0x84, 0xf8, 0x15, 0xc4, 0x80, 0x0b, 0xbc,
+        0x29, 0x3c, 0xf3, 0x95, 0x98, 0xcd, 0x8f, 0x35,
+        0xbc, 0xa5, 0x3e, 0xfc, 0xd4, 0x13, 0x9e, 0xde,
+        0x4f, 0xce, 0x71, 0x9d, 0x09, 0xad, 0xf2, 0x80,
+        0x6b, 0x65, 0x7f, 0x03, 0x00, 0x14, 0x7c, 0x15,
+        0x85, 0x40, 0x6d, 0x70, 0xea, 0xdc, 0xb3, 0x63,
+        0x35, 0x4f, 0x4d, 0xe0, 0xd9, 0xd5, 0x3c, 0x58,
+        0x56, 0x23, 0x80, 0xe2, 0x36, 0xdd, 0x75, 0x1d,
+        0x94, 0x11, 0x41, 0x8e, 0xe0, 0x81, 0x8e, 0xcf,
+        0xe0, 0xe5, 0xf6, 0xde, 0xd1, 0xe7, 0x04, 0x12,
+        0x79, 0x92, 0x2b, 0x71, 0x2a, 0x79, 0x8b, 0x7c,
+        0x44, 0x79, 0x16, 0x30, 0x4e, 0xf4, 0xf6, 0x9b,
+        0xb7, 0x40, 0xa3, 0x5a, 0xa7, 0x69, 0x3e, 0xc1,
+        0x3a, 0x04, 0xd0, 0x88, 0xa0, 0x3b, 0xdd, 0xc6,
+        0x9e, 0x7e, 0x1e, 0x1e, 0x8f, 0x44, 0xf7, 0x73,
+        0x67, 0x1e, 0x1a, 0x78, 0xfa, 0x62, 0xf4, 0xa9,
+        0xa8, 0xc6, 0x5b, 0xb8, 0xfa, 0x06, 0x7d, 0x5e,
+        0x38, 0x1c, 0x9a, 0x39, 0xe9, 0x39, 0x98, 0x22,
+        0x0b, 0xa7, 0xac, 0x0b, 0xf3, 0xbc, 0xf1, 0xeb,
+        0x8c, 0x81, 0xe3, 0x48, 0x8a, 0xed, 0x42, 0xc2,
+        0x38, 0xcf, 0x3e, 0xda, 0xd2, 0x89, 0x8d, 0x9c,
+        0x53, 0xb5, 0x2f, 0x41, 0x01, 0x26, 0x84, 0x9c,
+        0xa3, 0x56, 0xf6, 0x49, 0xc7, 0xd4, 0x9f, 0x93,
+        0x1b, 0x96, 0x49, 0x5e, 0xad, 0xb3, 0x84, 0x1f,
+        0x3c, 0xa4, 0xe0, 0x9b, 0xd1, 0x90, 0xbc, 0x38,
+        0x6c, 0xdd, 0x95, 0x4d, 0x9d, 0xb1, 0x71, 0x57,
+        0x2d, 0x34, 0xe8, 0xb8, 0x42, 0xc7, 0x99, 0x03,
+        0xc7, 0x07, 0x30, 0x65, 0x91, 0x55, 0xd5, 0x90,
+        0x70, 0x97, 0x37, 0x68, 0xd4, 0x11, 0xf9, 0xe8,
+        0xce, 0xec, 0xdc, 0x34, 0xd5, 0xd3, 0xb7, 0xc4,
+        0xb8, 0x97, 0x05, 0x92, 0xad, 0xf8, 0xe2, 0x36,
+        0x64, 0x41, 0xc9, 0xc5, 0x41, 0x77, 0x52, 0xd7,
+        0x2c, 0xa5, 0x24, 0x2f, 0xd9, 0x34, 0x0b, 0x47,
+        0x35, 0xa7, 0x28, 0x8b, 0xc5, 0xcd, 0xe9, 0x46,
+        0xac, 0x39, 0x94, 0x3c, 0x10, 0xc6, 0x29, 0x73,
+        0x0e, 0x0e, 0x5d, 0xe0, 0x71, 0x03, 0x8a, 0x72,
+        0x0e, 0x26, 0xb0, 0x7d, 0x84, 0xed, 0x95, 0x23,
+        0x49, 0x5a, 0x45, 0x83, 0x45, 0x60, 0x11, 0x4a,
+        0x46, 0x31, 0xd4, 0xd8, 0x16, 0x54, 0x98, 0x58,
+        0xed, 0x6d, 0xcc, 0x5d, 0xd6, 0x50, 0x61, 0x9f,
+        0x9d, 0xc5, 0x3e, 0x9d, 0x32, 0x47, 0xde, 0x96,
+        0xe1, 0x5d, 0xd8, 0xf8, 0xb4, 0x69, 0x6f, 0xb9,
+        0x15, 0x90, 0x57, 0x7a, 0xf6, 0xad, 0xb0, 0x5b,
+        0xf5, 0xa6, 0x36, 0x94, 0xfd, 0x84, 0xce, 0x1c,
+        0x0f, 0x4b, 0xd0, 0xc2, 0x5b, 0x6b, 0x56, 0xef,
+        0x73, 0x93, 0x0b, 0xc3, 0xee, 0xd9, 0xcf, 0xd3,
+        0xa4, 0x22, 0x58, 0xcd, 0x50, 0x6e, 0x65, 0xf4,
+        0xe9, 0xb7, 0x71, 0xaf, 0x4b, 0xb3, 0xb6, 0x2f,
+        0x0f, 0x0e, 0x3b, 0xc9, 0x85, 0x14, 0xf5, 0x17,
+        0xe8, 0x7a, 0x3a, 0xbf, 0x5f, 0x5e, 0xf8, 0x18,
+        0x48, 0xa6, 0x72, 0xab, 0x06, 0x95, 0xe9, 0xc8,
+        0xa7, 0xf4, 0x32, 0x44, 0x04, 0x0c, 0x84, 0x98,
+        0x73, 0xe3, 0x89, 0x8d, 0x5f, 0x7e, 0x4a, 0x42,
+        0x8f, 0xc5, 0x28, 0xb1, 0x82, 0xef, 0x1c, 0x97,
+        0x31, 0x3b, 0x4d, 0xe0, 0x0e, 0x10, 0x10, 0x97,
+        0x93, 0x49, 0x78, 0x2f, 0x0d, 0x86, 0x8b, 0xa1,
+        0x53, 0xa9, 0x81, 0x20, 0x79, 0xe7, 0x07, 0x77,
+        0xb6, 0xac, 0x5e, 0xd2, 0x05, 0xcd, 0xe9, 0xdb,
+        0x8a, 0x94, 0x82, 0x8a, 0x23, 0xb9, 0x3d, 0x1c,
+        0xa9, 0x7d, 0x72, 0x4a, 0xed, 0x33, 0xa3, 0xdb,
+        0x21, 0xa7, 0x86, 0x33, 0x45, 0xa5, 0xaa, 0x56,
+        0x45, 0xb5, 0x83, 0x29, 0x40, 0x47, 0x79, 0x04,
+        0x6e, 0xb9, 0x95, 0xd0, 0x81, 0x77, 0x2d, 0x48,
+        0x1e, 0xfe, 0xc3, 0xc2, 0x1e, 0xe5, 0xf2, 0xbe,
+        0xfd, 0x3b, 0x94, 0x9f, 0xc4, 0xc4, 0x26, 0x9d,
+        0xe4, 0x66, 0x1e, 0x19, 0xee, 0x6c, 0x79, 0x97,
+        0x11, 0x31, 0x4b, 0x0d, 0x01, 0xcb, 0xde, 0xa8,
+        0xf6, 0x6d, 0x7c, 0x39, 0x46, 0x4e, 0x7e, 0x3f,
+        0x94, 0x17, 0xdf, 0xa1, 0x7d, 0xd9, 0x1c, 0x8e,
+        0xbc, 0x7d, 0x33, 0x7d, 0xe3, 0x12, 0x40, 0xca,
+        0xab, 0x37, 0x11, 0x46, 0xd4, 0xae, 0xef, 0x44,
+        0xa2, 0xb3, 0x6a, 0x66, 0x0e, 0x0c, 0x90, 0x7f,
+        0xdf, 0x5c, 0x66, 0x5f, 0xf2, 0x94, 0x9f, 0xa6,
+        0x73, 0x4f, 0xeb, 0x0d, 0xad, 0xbf, 0xc0, 0x63,
+        0x5c, 0xdc, 0x46, 0x51, 0xe8, 0x8e, 0x90, 0x19,
+        0xa8, 0xa4, 0x3c, 0x91, 0x79, 0xfa, 0x7e, 0x58,
+        0x85, 0x13, 0x55, 0xc5, 0x19, 0x82, 0x37, 0x1b,
+        0x0a, 0x02, 0x1f, 0x99, 0x6b, 0x18, 0xf1, 0x28,
+        0x08, 0xa2, 0x73, 0xb8, 0x0f, 0x2e, 0xcd, 0xbf,
+        0xf3, 0x86, 0x7f, 0xea, 0xef, 0xd0, 0xbb, 0xa6,
+        0x21, 0xdf, 0x49, 0x73, 0x51, 0xcc, 0x36, 0xd3,
+        0x3e, 0xa0, 0xf8, 0x44, 0xdf, 0xd3, 0xa6, 0xbe,
+        0x8a, 0xd4, 0x57, 0xdd, 0x72, 0x94, 0x61, 0x0f,
+        0x82, 0xd1, 0x07, 0xb8, 0x7c, 0x18, 0x83, 0xdf,
+        0x3a, 0xe5, 0x50, 0x6a, 0x82, 0x20, 0xac, 0xa9,
+        0xa8, 0xff, 0xd9, 0xf3, 0x77, 0x33, 0x5a, 0x9e,
+        0x7f, 0x6d, 0xfe, 0x5d, 0x33, 0x41, 0x42, 0xe7,
+        0x6c, 0x19, 0xe0, 0x44, 0x8a, 0x15, 0xf6, 0x70,
+        0x98, 0xb7, 0x68, 0x4d, 0xfa, 0x97, 0x39, 0xb0,
+        0x8e, 0xe8, 0x84, 0x8b, 0x75, 0x30, 0xb7, 0x7d,
+        0x92, 0x69, 0x20, 0x9c, 0x81, 0xfb, 0x4b, 0xf4,
+        0x01, 0x50, 0xeb, 0xce, 0x0c, 0x1c, 0x6c, 0xb5,
+        0x4a, 0xd7, 0x27, 0x0c, 0xce, 0xbb, 0xe5, 0x85,
+        0xf0, 0xb6, 0xee, 0xd5, 0x70, 0xdd, 0x3b, 0xfc,
+        0xd4, 0x99, 0xf1, 0x33, 0xdd, 0x8b, 0xc4, 0x2f,
+        0xae, 0xab, 0x74, 0x96, 0x32, 0xc7, 0x4c, 0x56,
+        0x3c, 0x89, 0x0f, 0x96, 0x0b, 0x42, 0xc0, 0xcb,
+        0xee, 0x0f, 0x0b, 0x8c, 0xfb, 0x7e, 0x47, 0x7b,
+        0x64, 0x48, 0xfd, 0xb2, 0x00, 0x80, 0x89, 0xa5,
+        0x13, 0x55, 0x62, 0xfc, 0x8f, 0xe2, 0x42, 0x03,
+        0xb7, 0x4e, 0x2a, 0x79, 0xb4, 0x82, 0xea, 0x23,
+        0x49, 0xda, 0xaf, 0x52, 0x63, 0x1e, 0x60, 0x03,
+        0x89, 0x06, 0x44, 0x46, 0x08, 0xc3, 0xc4, 0x87,
+        0x70, 0x2e, 0xda, 0x94, 0xad, 0x6b, 0xe0, 0xe4,
+        0xd1, 0x8a, 0x06, 0xc2, 0xa8, 0xc0, 0xa7, 0x43,
+        0x3c, 0x47, 0x52, 0x0e, 0xc3, 0x77, 0x81, 0x11,
+        0x67, 0x0e, 0xa0, 0x70, 0x04, 0x47, 0x29, 0x40,
+        0x86, 0x0d, 0x34, 0x56, 0xa7, 0xc9, 0x35, 0x59,
+        0x68, 0xdc, 0x93, 0x81, 0x70, 0xee, 0x86, 0xd9,
+        0x80, 0x06, 0x40, 0x4f, 0x1a, 0x0d, 0x40, 0x30,
+        0x0b, 0xcb, 0x96, 0x47, 0xc1, 0xb7, 0x52, 0xfd,
+        0x56, 0xe0, 0x72, 0x4b, 0xfb, 0xbd, 0x92, 0x45,
+        0x61, 0x71, 0xc2, 0x33, 0x11, 0xbf, 0x52, 0x83,
+        0x79, 0x26, 0xe0, 0x49, 0x6b, 0xb7, 0x05, 0x8b,
+        0xe8, 0x0e, 0x87, 0x31, 0xd7, 0x9d, 0x8a, 0xf5,
+        0xc0, 0x5f, 0x2e, 0x58, 0x4a, 0xdb, 0x11, 0xb3,
+        0x6c, 0x30, 0x2a, 0x46, 0x19, 0xe3, 0x27, 0x84,
+        0x1f, 0x63, 0x6e, 0xf6, 0x57, 0xc7, 0xc9, 0xd8,
+        0x5e, 0xba, 0xb3, 0x87, 0xd5, 0x83, 0x26, 0x34,
+        0x21, 0x9e, 0x65, 0xde, 0x42, 0xd3, 0xbe, 0x7b,
+        0xbc, 0x91, 0x71, 0x44, 0x4d, 0x99, 0x3b, 0x31,
+        0xe5, 0x3f, 0x11, 0x4e, 0x7f, 0x13, 0x51, 0x3b,
+        0xae, 0x79, 0xc9, 0xd3, 0x81, 0x8e, 0x25, 0x40,
+        0x10, 0xfc, 0x07, 0x1e, 0xf9, 0x7b, 0x9a, 0x4b,
+        0x6c, 0xe3, 0xb3, 0xad, 0x1a, 0x0a, 0xdd, 0x9e,
+        0x59, 0x0c, 0xa2, 0xcd, 0xae, 0x48, 0x4a, 0x38,
+        0x5b, 0x47, 0x41, 0x94, 0x65, 0x6b, 0xbb, 0xeb,
+        0x5b, 0xe3, 0xaf, 0x07, 0x5b, 0xd4, 0x4a, 0xa2,
+        0xc9, 0x5d, 0x2f, 0x64, 0x03, 0xd7, 0x3a, 0x2c,
+        0x6e, 0xce, 0x76, 0x95, 0xb4, 0xb3, 0xc0, 0xf1,
+        0xe2, 0x45, 0x73, 0x7a, 0x5c, 0xab, 0xc1, 0xfc,
+        0x02, 0x8d, 0x81, 0x29, 0xb3, 0xac, 0x07, 0xec,
+        0x40, 0x7d, 0x45, 0xd9, 0x7a, 0x59, 0xee, 0x34,
+        0xf0, 0xe9, 0xd5, 0x7b, 0x96, 0xb1, 0x3d, 0x95,
+        0xcc, 0x86, 0xb5, 0xb6, 0x04, 0x2d, 0xb5, 0x92,
+        0x7e, 0x76, 0xf4, 0x06, 0xa9, 0xa3, 0x12, 0x0f,
+        0xb1, 0xaf, 0x26, 0xba, 0x7c, 0xfc, 0x7e, 0x1c,
+        0xbc, 0x2c, 0x49, 0x97, 0x53, 0x60, 0x13, 0x0b,
+        0xa6, 0x61, 0x83, 0x89, 0x42, 0xd4, 0x17, 0x0c,
+        0x6c, 0x26, 0x52, 0xc3, 0xb3, 0xd4, 0x67, 0xf5,
+        0xe3, 0x04, 0xb7, 0xf4, 0xcb, 0x80, 0xb8, 0xcb,
+        0x77, 0x56, 0x3e, 0xaa, 0x57, 0x54, 0xee, 0xb4,
+        0x2c, 0x67, 0xcf, 0xf2, 0xdc, 0xbe, 0x55, 0xf9,
+        0x43, 0x1f, 0x6e, 0x22, 0x97, 0x67, 0x7f, 0xc4,
+        0xef, 0xb1, 0x26, 0x31, 0x1e, 0x27, 0xdf, 0x41,
+        0x80, 0x47, 0x6c, 0xe2, 0xfa, 0xa9, 0x8c, 0x2a,
+        0xf6, 0xf2, 0xab, 0xf0, 0x15, 0xda, 0x6c, 0xc8,
+        0xfe, 0xb5, 0x23, 0xde, 0xa9, 0x05, 0x3f, 0x06,
+        0x54, 0x4c, 0xcd, 0xe1, 0xab, 0xfc, 0x0e, 0x62,
+        0x33, 0x31, 0x73, 0x2c, 0x76, 0xcb, 0xb4, 0x47,
+        0x1e, 0x20, 0xad, 0xd8, 0xf2, 0x31, 0xdd, 0xc4,
+        0x8b, 0x0c, 0x77, 0xbe, 0xe1, 0x8b, 0x26, 0x00,
+        0x02, 0x58, 0xd6, 0x8d, 0xef, 0xad, 0x74, 0x67,
+        0xab, 0x3f, 0xef, 0xcb, 0x6f, 0xb0, 0xcc, 0x81,
+        0x44, 0x4c, 0xaf, 0xe9, 0x49, 0x4f, 0xdb, 0xa0,
+        0x25, 0xa4, 0xf0, 0x89, 0xf1, 0xbe, 0xd8, 0x10,
+        0xff, 0xb1, 0x3b, 0x4b, 0xfa, 0x98, 0xf5, 0x79,
+        0x6d, 0x1e, 0x69, 0x4d, 0x57, 0xb1, 0xc8, 0x19,
+        0x1b, 0xbd, 0x1e, 0x8c, 0x84, 0xb7, 0x7b, 0xe8,
+        0xd2, 0x2d, 0x09, 0x41, 0x41, 0x37, 0x3d, 0xb1,
+        0x6f, 0x26, 0x5d, 0x71, 0x16, 0x3d, 0xb7, 0x83,
+        0x27, 0x2c, 0xa7, 0xb6, 0x50, 0xbd, 0x91, 0x86,
+        0xab, 0x24, 0xa1, 0x38, 0xfd, 0xea, 0x71, 0x55,
+        0x7e, 0x9a, 0x07, 0x77, 0x4b, 0xfa, 0x61, 0x66,
+        0x20, 0x1e, 0x28, 0x95, 0x18, 0x1b, 0xa4, 0xa0,
+        0xfd, 0xc0, 0x89, 0x72, 0x43, 0xd9, 0x3b, 0x49,
+        0x5a, 0x3f, 0x9d, 0xbf, 0xdb, 0xb4, 0x46, 0xea,
+        0x42, 0x01, 0x77, 0x23, 0x68, 0x95, 0xb6, 0x24,
+        0xb3, 0xa8, 0x6c, 0x28, 0x3b, 0x11, 0x40, 0x7e,
+        0x18, 0x65, 0x6d, 0xd8, 0x24, 0x42, 0x7d, 0x88,
+        0xc0, 0x52, 0xd9, 0x05, 0xe4, 0x95, 0x90, 0x87,
+        0x8c, 0xf4, 0xd0, 0x6b, 0xb9, 0x83, 0x99, 0x34,
+        0x6d, 0xfe, 0x54, 0x40, 0x94, 0x52, 0x21, 0x4f,
+        0x14, 0x25, 0xc5, 0xd6, 0x5e, 0x95, 0xdc, 0x0a,
+        0x2b, 0x89, 0x20, 0x11, 0x84, 0x48, 0xd6, 0x3a,
+        0xcd, 0x5c, 0x24, 0xad, 0x62, 0xe3, 0xb1, 0x93,
+        0x25, 0x8d, 0xcd, 0x7e, 0xfc, 0x27, 0xa3, 0x37,
+        0xfd, 0x84, 0xfc, 0x1b, 0xb2, 0xf1, 0x27, 0x38,
+        0x5a, 0xb7, 0xfc, 0xf2, 0xfa, 0x95, 0x66, 0xd4,
+        0xfb, 0xba, 0xa7, 0xd7, 0xa3, 0x72, 0x69, 0x48,
+        0x48, 0x8c, 0xeb, 0x28, 0x89, 0xfe, 0x33, 0x65,
+        0x5a, 0x36, 0x01, 0x7e, 0x06, 0x79, 0x0a, 0x09,
+        0x3b, 0x74, 0x11, 0x9a, 0x6e, 0xbf, 0xd4, 0x9e,
+        0x58, 0x90, 0x49, 0x4f, 0x4d, 0x08, 0xd4, 0xe5,
+        0x4a, 0x09, 0x21, 0xef, 0x8b, 0xb8, 0x74, 0x3b,
+        0x91, 0xdd, 0x36, 0x85, 0x60, 0x2d, 0xfa, 0xd4,
+        0x45, 0x7b, 0x45, 0x53, 0xf5, 0x47, 0x87, 0x7e,
+        0xa6, 0x37, 0xc8, 0x78, 0x7a, 0x68, 0x9d, 0x8d,
+        0x65, 0x2c, 0x0e, 0x91, 0x5c, 0xa2, 0x60, 0xf0,
+        0x8e, 0x3f, 0xe9, 0x1a, 0xcd, 0xaa, 0xe7, 0xd5,
+        0x77, 0x18, 0xaf, 0xc9, 0xbc, 0x18, 0xea, 0x48,
+        0x1b, 0xfb, 0x22, 0x48, 0x70, 0x16, 0x29, 0x9e,
+        0x5b, 0xc1, 0x2c, 0x66, 0x23, 0xbc, 0xf0, 0x1f,
+        0xef, 0xaf, 0xe4, 0xd6, 0x04, 0x19, 0x82, 0x7a,
+        0x0b, 0xba, 0x4b, 0x46, 0xb1, 0x6a, 0x85, 0x5d,
+        0xb4, 0x73, 0xd6, 0x21, 0xa1, 0x71, 0x60, 0x14,
+        0xee, 0x0a, 0x77, 0xc4, 0x66, 0x2e, 0xf9, 0x69,
+        0x30, 0xaf, 0x41, 0x0b, 0xc8, 0x83, 0x3c, 0x53,
+        0x99, 0x19, 0x27, 0x46, 0xf7, 0x41, 0x6e, 0x56,
+        0xdc, 0x94, 0x28, 0x67, 0x4e, 0xb7, 0x25, 0x48,
+        0x8a, 0xc2, 0xe0, 0x60, 0x96, 0xcc, 0x18, 0xf4,
+        0x84, 0xdd, 0xa7, 0x5e, 0x3e, 0x05, 0x0b, 0x26,
+        0x26, 0xb2, 0x5c, 0x1f, 0x57, 0x1a, 0x04, 0x7e,
+        0x6a, 0xe3, 0x2f, 0xb4, 0x35, 0xb6, 0x38, 0x40,
+        0x40, 0xcd, 0x6f, 0x87, 0x2e, 0xef, 0xa3, 0xd7,
+        0xa9, 0xc2, 0xe8, 0x0d, 0x27, 0xdf, 0x44, 0x62,
+        0x99, 0xa0, 0xfc, 0xcf, 0x81, 0x78, 0xcb, 0xfe,
+        0xe5, 0xa0, 0x03, 0x4e, 0x6c, 0xd7, 0xf4, 0xaf,
+        0x7a, 0xbb, 0x61, 0x82, 0xfe, 0x71, 0x89, 0xb2,
+        0x22, 0x7c, 0x8e, 0x83, 0x04, 0xce, 0xf6, 0x5d,
+        0x84, 0x8f, 0x95, 0x6a, 0x7f, 0xad, 0xfd, 0x32,
+        0x9c, 0x5e, 0xe4, 0x9c, 0x89, 0x60, 0x54, 0xaa,
+        0x96, 0x72, 0xd2, 0xd7, 0x36, 0x85, 0xa9, 0x45,
+        0xd2, 0x2a, 0xa1, 0x81, 0x49, 0x6f, 0x7e, 0x04,
+        0xfa, 0xe2, 0xfe, 0x90, 0x26, 0x77, 0x5a, 0x33,
+        0xb8, 0x04, 0x9a, 0x7a, 0xe6, 0x4c, 0x4f, 0xad,
+        0x72, 0x96, 0x08, 0x28, 0x58, 0x13, 0xf8, 0xc4,
+        0x1c, 0xf0, 0xc3, 0x45, 0x95, 0x49, 0x20, 0x8c,
+        0x9f, 0x39, 0x70, 0xe1, 0x77, 0xfe, 0xd5, 0x4b,
+        0xaf, 0x86, 0xda, 0xef, 0x22, 0x06, 0x83, 0x36,
+        0x29, 0x12, 0x11, 0x40, 0xbc, 0x3b, 0x86, 0xaa,
+        0xaa, 0x65, 0x60, 0xc3, 0x80, 0xca, 0xed, 0xa9,
+        0xf3, 0xb0, 0x79, 0x96, 0xa2, 0x55, 0x27, 0x28,
+        0x55, 0x73, 0x26, 0xa5, 0x50, 0xea, 0x92, 0x4b,
+        0x3c, 0x5c, 0x82, 0x33, 0xf0, 0x01, 0x3f, 0x03,
+        0xc1, 0x08, 0x05, 0xbf, 0x98, 0xf4, 0x9b, 0x6d,
+        0xa5, 0xa8, 0xb4, 0x82, 0x0c, 0x06, 0xfa, 0xff,
+        0x2d, 0x08, 0xf3, 0x05, 0x4f, 0x57, 0x2a, 0x39,
+        0xd4, 0x83, 0x0d, 0x75, 0x51, 0xd8, 0x5b, 0x1b,
+        0xd3, 0x51, 0x5a, 0x32, 0x2a, 0x9b, 0x32, 0xb2,
+        0xf2, 0xa4, 0x96, 0x12, 0xf2, 0xae, 0x40, 0x34,
+        0x67, 0xa8, 0xf5, 0x44, 0xd5, 0x35, 0x53, 0xfe,
+        0xa3, 0x60, 0x96, 0x63, 0x0f, 0x1f, 0x6e, 0xb0,
+        0x5a, 0x42, 0xa6, 0xfc, 0x51, 0x0b, 0x60, 0x27,
+        0xbc, 0x06, 0x71, 0xed, 0x65, 0x5b, 0x23, 0x86,
+        0x4a, 0x07, 0x3b, 0x22, 0x07, 0x46, 0xe6, 0x90,
+        0x3e, 0xf3, 0x25, 0x50, 0x1b, 0x4c, 0x7f, 0x03,
+        0x08, 0xa8, 0x36, 0x6b, 0x87, 0xe5, 0xe3, 0xdb,
+        0x9a, 0x38, 0x83, 0xff, 0x9f, 0x1a, 0x9f, 0x57,
+        0xa4, 0x2a, 0xf6, 0x37, 0xbc, 0x1a, 0xff, 0xc9,
+        0x1e, 0x35, 0x0c, 0xc3, 0x7c, 0xa3, 0xb2, 0xe5,
+        0xd2, 0xc6, 0xb4, 0x57, 0x47, 0xe4, 0x32, 0x16,
+        0x6d, 0xa9, 0xae, 0x64, 0xe6, 0x2d, 0x8d, 0xc5,
+        0x8d, 0x50, 0x8e, 0xe8, 0x1a, 0x22, 0x34, 0x2a,
+        0xd9, 0xeb, 0x51, 0x90, 0x4a, 0xb1, 0x41, 0x7d,
+        0x64, 0xf9, 0xb9, 0x0d, 0xf6, 0x23, 0x33, 0xb0,
+        0x33, 0xf4, 0xf7, 0x3f, 0x27, 0x84, 0xc6, 0x0f,
+        0x54, 0xa5, 0xc0, 0x2e, 0xec, 0x0b, 0x3a, 0x48,
+        0x6e, 0x80, 0x35, 0x81, 0x43, 0x9b, 0x90, 0xb1,
+        0xd0, 0x2b, 0xea, 0x21, 0xdc, 0xda, 0x5b, 0x09,
+        0xf4, 0xcc, 0x10, 0xb4, 0xc7, 0xfe, 0x79, 0x51,
+        0xc3, 0xc5, 0xac, 0x88, 0x74, 0x84, 0x0b, 0x4b,
+        0xca, 0x79, 0x16, 0x29, 0xfb, 0x69, 0x54, 0xdf,
+        0x41, 0x7e, 0xe9, 0xc7, 0x8e, 0xea, 0xa5, 0xfe,
+        0xfc, 0x76, 0x0e, 0x90, 0xc4, 0x92, 0x38, 0xad,
+        0x7b, 0x48, 0xe6, 0x6e, 0xf7, 0x21, 0xfd, 0x4e,
+        0x93, 0x0a, 0x7b, 0x41, 0x83, 0x68, 0xfb, 0x57,
+        0x51, 0x76, 0x34, 0xa9, 0x6c, 0x00, 0xaa, 0x4f,
+        0x66, 0x65, 0x98, 0x4a, 0x4f, 0xa3, 0xa0, 0xef,
+        0x69, 0x3f, 0xe3, 0x1c, 0x92, 0x8c, 0xfd, 0xd8,
+        0xe8, 0xde, 0x7c, 0x7f, 0x3e, 0x84, 0x8e, 0x69,
+        0x3c, 0xf1, 0xf2, 0x05, 0x46, 0xdc, 0x2f, 0x9d,
+        0x5e, 0x6e, 0x4c, 0xfb, 0xb5, 0x99, 0x2a, 0x59,
+        0x63, 0xc1, 0x34, 0xbc, 0x57, 0xc0, 0x0d, 0xb9,
+        0x61, 0x25, 0xf3, 0x33, 0x23, 0x51, 0xb6, 0x0d,
+        0x07, 0xa6, 0xab, 0x94, 0x4a, 0xb7, 0x2a, 0xea,
+        0xee, 0xac, 0xa3, 0xc3, 0x04, 0x8b, 0x0e, 0x56,
+        0xfe, 0x44, 0xa7, 0x39, 0xe2, 0xed, 0xed, 0xb4,
+        0x22, 0x2b, 0xac, 0x12, 0x32, 0x28, 0x91, 0xd8,
+        0xa5, 0xab, 0xff, 0x5f, 0xe0, 0x4b, 0xda, 0x78,
+        0x17, 0xda, 0xf1, 0x01, 0x5b, 0xcd, 0xe2, 0x5f,
+        0x50, 0x45, 0x73, 0x2b, 0xe4, 0x76, 0x77, 0xf4,
+        0x64, 0x1d, 0x43, 0xfb, 0x84, 0x7a, 0xea, 0x91,
+        0xae, 0xf9, 0x9e, 0xb7, 0xb4, 0xb0, 0x91, 0x5f,
+        0x16, 0x35, 0x9a, 0x11, 0xb8, 0xc7, 0xc1, 0x8c,
+        0xc6, 0x10, 0x8d, 0x2f, 0x63, 0x4a, 0xa7, 0x57,
+        0x3a, 0x51, 0xd6, 0x32, 0x2d, 0x64, 0x72, 0xd4,
+        0x66, 0xdc, 0x10, 0xa6, 0x67, 0xd6, 0x04, 0x23,
+        0x9d, 0x0a, 0x11, 0x77, 0xdd, 0x37, 0x94, 0x17,
+        0x3c, 0xbf, 0x8b, 0x65, 0xb0, 0x2e, 0x5e, 0x66,
+        0x47, 0x64, 0xac, 0xdd, 0xf0, 0x84, 0xfd, 0x39,
+        0xfa, 0x15, 0x5d, 0xef, 0xae, 0xca, 0xc1, 0x36,
+        0xa7, 0x5c, 0xbf, 0xc7, 0x08, 0xc2, 0x66, 0x00,
+        0x74, 0x74, 0x4e, 0x27, 0x3f, 0x55, 0x8a, 0xb7,
+        0x38, 0x66, 0x83, 0x6d, 0xcf, 0x99, 0x9e, 0x60,
+        0x8f, 0xdd, 0x2e, 0x62, 0x22, 0x0e, 0xef, 0x0c,
+        0x98, 0xa7, 0x85, 0x74, 0x3b, 0x9d, 0xec, 0x9e,
+        0xa9, 0x19, 0x72, 0xa5, 0x7f, 0x2c, 0x39, 0xb7,
+        0x7d, 0xb7, 0xf1, 0x12, 0x65, 0x27, 0x4b, 0x5a,
+        0xde, 0x17, 0xfe, 0xad, 0x44, 0xf3, 0x20, 0x4d,
+        0xfd, 0xe4, 0x1f, 0xb5, 0x81, 0xb0, 0x36, 0x37,
+        0x08, 0x6f, 0xc3, 0x0c, 0xe9, 0x85, 0x98, 0x82,
+        0xa9, 0x62, 0x0c, 0xc4, 0x97, 0xc0, 0x50, 0xc8,
+        0xa7, 0x3c, 0x50, 0x9f, 0x43, 0xb9, 0xcd, 0x5e,
+        0x4d, 0xfa, 0x1c, 0x4b, 0x0b, 0xa9, 0x98, 0x85,
+        0x38, 0x92, 0xac, 0x8d, 0xe4, 0xad, 0x9b, 0x98,
+        0xab, 0xd9, 0x38, 0xac, 0x62, 0x52, 0xa3, 0x22,
+        0x63, 0x0f, 0xbf, 0x95, 0x48, 0xdf, 0x69, 0xe7,
+        0x8b, 0x33, 0xd5, 0xb2, 0xbd, 0x05, 0x49, 0x49,
+        0x9d, 0x57, 0x73, 0x19, 0x33, 0xae, 0xfa, 0x33,
+        0xf1, 0x19, 0xa8, 0x80, 0xce, 0x04, 0x9f, 0xbc,
+        0x1d, 0x65, 0x82, 0x1b, 0xe5, 0x3a, 0x51, 0xc8,
+        0x1c, 0x21, 0xe3, 0x5d, 0xf3, 0x7d, 0x9b, 0x2f,
+        0x2c, 0x1d, 0x4a, 0x7f, 0x9b, 0x68, 0x35, 0xa3,
+        0xb2, 0x50, 0xf7, 0x62, 0x79, 0xcd, 0xf4, 0x98,
+        0x4f, 0xe5, 0x63, 0x7c, 0x3e, 0x45, 0x31, 0x8c,
+        0x16, 0xa0, 0x12, 0xc8, 0x58, 0xce, 0x39, 0xa6,
+        0xbc, 0x54, 0xdb, 0xc5, 0xe0, 0xd5, 0xba, 0xbc,
+        0xb9, 0x04, 0xf4, 0x8d, 0xe8, 0x2f, 0x15, 0x9d,
+};
 
-#if 0                           /*Not used at present */
-static void
-buf_dump(char const *prefix, unsigned char const *buf, size_t len)
+/* 100 test cases */
+static struct crc_test {
+        u32 crc;        /* random starting crc */
+        u32 start;      /* random 6 bit offset in buf */
+        u32 length;     /* random 11 bit length of test */
+        u32 crc_le;     /* expected crc32_le result */
+        u32 crc_be;     /* expected crc32_be result */
+        u32 crc32c_le;  /* expected crc32c_le result */
+} test[] =
 {
-        fputs(prefix, stdout);
-        while (len--)
-                printf(" %02x", *buf++);
-        putchar('\n');
+        {0x674bf11d, 0x00000038, 0x00000542, 0x0af6d466, 0xd8b6e4c1,
+         0xf6e93d6c},
+        {0x35c672c6, 0x0000003a, 0x000001aa, 0xc6d3dfba, 0x28aaf3ad,
+         0x0fe92aca},
+        {0x496da28e, 0x00000039, 0x000005af, 0xd933660f, 0x5d57e81f,
+         0x52e1ebb8},
+        {0x09a9b90e, 0x00000027, 0x000001f8, 0xb45fe007, 0xf45fca9a,
+         0x0798af9a},
+        {0xdc97e5a9, 0x00000025, 0x000003b6, 0xf81a3562, 0xe0126ba2,
+         0x18eb3152},
+        {0x47c58900, 0x0000000a, 0x000000b9, 0x8e58eccf, 0xf3afc793,
+         0xd00d08c7},
+        {0x292561e8, 0x0000000c, 0x00000403, 0xa2ba8aaf, 0x0b797aed,
+         0x8ba966bc},
+        {0x415037f6, 0x00000003, 0x00000676, 0xa17d52e8, 0x7f0fdf35,
+         0x11d694a2},
+        {0x3466e707, 0x00000026, 0x00000042, 0x258319be, 0x75c484a2,
+         0x6ab3208d},
+        {0xafd1281b, 0x00000023, 0x000002ee, 0x4428eaf8, 0x06c7ad10,
+         0xba4603c5},
+        {0xd3857b18, 0x00000028, 0x000004a2, 0x5c430821, 0xb062b7cb,
+         0xe6071c6f},
+        {0x1d825a8f, 0x0000002b, 0x0000050b, 0xd2c45f0c, 0xd68634e0,
+         0x179ec30a},
+        {0x5033e3bc, 0x0000000b, 0x00000078, 0xa3ea4113, 0xac6d31fb,
+         0x0903beb8},
+        {0x94f1fb5e, 0x0000000f, 0x000003a2, 0xfbfc50b1, 0x3cfe50ed,
+         0x6a7cb4fa},
+        {0xc9a0fe14, 0x00000009, 0x00000473, 0x5fb61894, 0x87070591,
+         0xdb535801},
+        {0x88a034b1, 0x0000001c, 0x000005ad, 0xc1b16053, 0x46f95c67,
+         0x92bed597},
+        {0xf0f72239, 0x00000020, 0x0000026d, 0xa6fa58f3, 0xf8c2c1dd,
+         0x192a3f1b},
+        {0xcc20a5e3, 0x0000003b, 0x0000067a, 0x7740185a, 0x308b979a,
+         0xccbaec1a},
+        {0xce589c95, 0x0000002b, 0x00000641, 0xd055e987, 0x40aae25b,
+         0x7eabae4d},
+        {0x78edc885, 0x00000035, 0x000005be, 0xa39cb14b, 0x035b0d1f,
+         0x28c72982},
+        {0x9d40a377, 0x0000003b, 0x00000038, 0x1f47ccd2, 0x197fbc9d,
+         0xc3cd4d18},
+        {0x703d0e01, 0x0000003c, 0x000006f1, 0x88735e7c, 0xfed57c5a,
+         0xbca8f0e7},
+        {0x776bf505, 0x0000000f, 0x000005b2, 0x5cc4fc01, 0xf32efb97,
+         0x713f60b3},
+        {0x4a3e7854, 0x00000027, 0x000004b8, 0x8d923c82, 0x0cbfb4a2,
+         0xebd08fd5},
+        {0x209172dd, 0x0000003b, 0x00000356, 0xb89e9c2b, 0xd7868138,
+         0x64406c59},
+        {0x3ba4cc5b, 0x0000002f, 0x00000203, 0xe51601a9, 0x5b2a1032,
+         0x7421890e},
+        {0xfc62f297, 0x00000000, 0x00000079, 0x71a8e1a2, 0x5d88685f,
+         0xe9347603},
+        {0x64280b8b, 0x00000016, 0x000007ab, 0x0fa7a30c, 0xda3a455f,
+         0x1bef9060},
+        {0x97dd724b, 0x00000033, 0x000007ad, 0x5788b2f4, 0xd7326d32,
+         0x34720072},
+        {0x61394b52, 0x00000035, 0x00000571, 0xc66525f1, 0xcabe7fef,
+         0x48310f59},
+        {0x29b4faff, 0x00000024, 0x0000006e, 0xca13751e, 0x993648e0,
+         0x783a4213},
+        {0x29bfb1dc, 0x0000000b, 0x00000244, 0x436c43f7, 0x429f7a59,
+         0x9e8efd41},
+        {0x86ae934b, 0x00000035, 0x00000104, 0x0760ec93, 0x9cf7d0f4,
+         0xfc3d34a5},
+        {0xc4c1024e, 0x0000002e, 0x000006b1, 0x6516a3ec, 0x19321f9c,
+         0x17a52ae2},
+        {0x3287a80a, 0x00000026, 0x00000496, 0x0b257eb1, 0x754ebd51,
+         0x886d935a},
+        {0xa4db423e, 0x00000023, 0x0000045d, 0x9b3a66dc, 0x873e9f11,
+         0xeaaeaeb2},
+        {0x7a1078df, 0x00000015, 0x0000014a, 0x8c2484c5, 0x6a628659,
+         0x8e900a4b},
+        {0x6048bd5b, 0x00000006, 0x0000006a, 0x897e3559, 0xac9961af,
+         0xd74662b1},
+        {0xd8f9ea20, 0x0000003d, 0x00000277, 0x60eb905b, 0xed2aaf99,
+         0xd26752ba},
+        {0xea5ec3b4, 0x0000002a, 0x000004fe, 0x869965dc, 0x6c1f833b,
+         0x8b1fcd62},
+        {0x2dfb005d, 0x00000016, 0x00000345, 0x6a3b117e, 0xf05e8521,
+         0xf54342fe},
+        {0x5a214ade, 0x00000020, 0x000005b6, 0x467f70be, 0xcb22ccd3,
+         0x5b95b988},
+        {0xf0ab9cca, 0x00000032, 0x00000515, 0xed223df3, 0x7f3ef01d,
+         0x2e1176be},
+        {0x91b444f9, 0x0000002e, 0x000007f8, 0x84e9a983, 0x5676756f,
+         0x66120546},
+        {0x1b5d2ddb, 0x0000002e, 0x0000012c, 0xba638c4c, 0x3f42047b,
+         0xf256a5cc},
+        {0xd824d1bb, 0x0000003a, 0x000007b5, 0x6288653b, 0x3a3ebea0,
+         0x4af1dd69},
+        {0x0470180c, 0x00000034, 0x000001f0, 0x9d5b80d6, 0x3de08195,
+         0x56f0a04a},
+        {0xffaa3a3f, 0x00000036, 0x00000299, 0xf3a82ab8, 0x53e0c13d,
+         0x74f6b6b2},
+        {0x6406cfeb, 0x00000023, 0x00000600, 0xa920b8e8, 0xe4e2acf4,
+         0x085951fd},
+        {0xb24aaa38, 0x0000003e, 0x000004a1, 0x657cc328, 0x5077b2c3,
+         0xc65387eb},
+        {0x58b2ab7c, 0x00000039, 0x000002b4, 0x3a17ee7e, 0x9dcb3643,
+         0x1ca9257b},
+        {0x3db85970, 0x00000006, 0x000002b6, 0x95268b59, 0xb9812c10,
+         0xfd196d76},
+        {0x857830c5, 0x00000003, 0x00000590, 0x4ef439d5, 0xf042161d,
+         0x5ef88339},
+        {0xe1fcd978, 0x0000003e, 0x000007d8, 0xae8d8699, 0xce0a1ef5,
+         0x2c3714d9},
+        {0xb982a768, 0x00000016, 0x000006e0, 0x62fad3df, 0x5f8a067b,
+         0x58576548},
+        {0x1d581ce8, 0x0000001e, 0x0000058b, 0xf0f5da53, 0x26e39eee,
+         0xfd7c57de},
+        {0x2456719b, 0x00000025, 0x00000503, 0x4296ac64, 0xd50e4c14,
+         0xd5fedd59},
+        {0xfae6d8f2, 0x00000000, 0x0000055d, 0x057fdf2e, 0x2a31391a,
+         0x1cc3b17b},
+        {0xcba828e3, 0x00000039, 0x000002ce, 0xe3f22351, 0x8f00877b,
+         0x270eed73},
+        {0x13d25952, 0x0000000a, 0x0000072d, 0x76d4b4cc, 0x5eb67ec3,
+         0x91ecbb11},
+        {0x0342be3f, 0x00000015, 0x00000599, 0xec75d9f1, 0x9d4d2826,
+         0x05ed8d0c},
+        {0xeaa344e0, 0x00000014, 0x000004d8, 0x72a4c981, 0x2064ea06,
+         0x0b09ad5b},
+        {0xbbb52021, 0x0000003b, 0x00000272, 0x04af99fc, 0xaf042d35,
+         0xf8d511fb},
+        {0xb66384dc, 0x0000001d, 0x000007fc, 0xd7629116, 0x782bd801,
+         0x5ad832cc},
+        {0x616c01b6, 0x00000022, 0x000002c8, 0x5b1dab30, 0x783ce7d2,
+         0x1214d196},
+        {0xce2bdaad, 0x00000016, 0x0000062a, 0x932535c8, 0x3f02926d,
+         0x5747218a},
+        {0x00fe84d7, 0x00000005, 0x00000205, 0x850e50aa, 0x753d649c,
+         0xde8f14de},
+        {0xbebdcb4c, 0x00000006, 0x0000055d, 0xbeaa37a2, 0x2d8c9eba,
+         0x3563b7b9},
+        {0xd8b1a02a, 0x00000010, 0x00000387, 0x5017d2fc, 0x503541a5,
+         0x071475d0},
+        {0x3b96cad2, 0x00000036, 0x00000347, 0x1d2372ae, 0x926cd90b,
+         0x54c79d60},
+        {0xc94c1ed7, 0x00000005, 0x0000038b, 0x9e9fdb22, 0x144a9178,
+         0x4c53eee6},
+        {0x1aad454e, 0x00000025, 0x000002b2, 0xc3f6315c, 0x5c7a35b3,
+         0x10137a3c},
+        {0xa4fec9a6, 0x00000000, 0x000006d6, 0x90be5080, 0xa4107605,
+         0xaa9d6c73},
+        {0x1bbe71e2, 0x0000001f, 0x000002fd, 0x4e504c3b, 0x284ccaf1,
+         0xb63d23e7},
+        {0x4201c7e4, 0x00000002, 0x000002b7, 0x7822e3f9, 0x0cc912a9,
+         0x7f53e9cf},
+        {0x23fddc96, 0x00000003, 0x00000627, 0x8a385125, 0x07767e78,
+         0x13c1cd83},
+        {0xd82ba25c, 0x00000016, 0x0000063e, 0x98e4148a, 0x283330c9,
+         0x49ff5867},
+        {0x786f2032, 0x0000002d, 0x0000060f, 0xf201600a, 0xf561bfcd,
+         0x8467f211},
+        {0xfebe4e1f, 0x0000002a, 0x000004f2, 0x95e51961, 0xfd80dcab,
+         0x3f9683b2},
+        {0x1a6e0a39, 0x00000008, 0x00000672, 0x8af6c2a5, 0x78dd84cb,
+         0x76a3f874},
+        {0x56000ab8, 0x0000000e, 0x000000e5, 0x36bacb8f, 0x22ee1f77,
+         0x863b702f},
+        {0x4717fe0c, 0x00000000, 0x000006ec, 0x8439f342, 0x5c8e03da,
+         0xdc6c58ff},
+        {0xd5d5d68e, 0x0000003c, 0x000003a3, 0x46fff083, 0x177d1b39,
+         0x0622cc95},
+        {0xc25dd6c6, 0x00000024, 0x000006c0, 0x5ceb8eb4, 0x892b0d16,
+         0xe85605cd},
+        {0xe9b11300, 0x00000023, 0x00000683, 0x07a5d59a, 0x6c6a3208,
+         0x31da5f06},
+        {0x95cd285e, 0x00000001, 0x00000047, 0x7b3a4368, 0x0202c07e,
+         0xa1f2e784},
+        {0xd9245a25, 0x0000001e, 0x000003a6, 0xd33c1841, 0x1936c0d5,
+         0xb07cc616},
+        {0x103279db, 0x00000006, 0x0000039b, 0xca09b8a0, 0x77d62892,
+         0xbf943b6c},
+        {0x1cba3172, 0x00000027, 0x000001c8, 0xcb377194, 0xebe682db,
+         0x2c01af1c},
+        {0x8f613739, 0x0000000c, 0x000001df, 0xb4b0bc87, 0x7710bd43,
+         0x0fe5f56d},
+        {0x1c6aa90d, 0x0000001b, 0x0000053c, 0x70559245, 0xda7894ac,
+         0xf8943b2d},
+        {0xaabe5b93, 0x0000003d, 0x00000715, 0xcdbf42fa, 0x0c3b99e7,
+         0xe4d89272},
+        {0xf15dd038, 0x00000006, 0x000006db, 0x6e104aea, 0x8d5967f2,
+         0x7c2f6bbb},
+        {0x584dd49c, 0x00000020, 0x000007bc, 0x36b6cfd6, 0xad4e23b2,
+         0xabbf388b},
+        {0x5d8c9506, 0x00000020, 0x00000470, 0x4c62378e, 0x31d92640,
+         0x1dca1f4e},
+        {0xb80d17b0, 0x00000032, 0x00000346, 0x22a5bb88, 0x9a7ec89f,
+         0x5c170e23},
+        {0xdaf0592e, 0x00000023, 0x000007b0, 0x3cab3f99, 0x9b1fdd99,
+         0xc0e9d672},
+        {0x4793cc85, 0x0000000d, 0x00000706, 0xe82e04f6, 0xed3db6b7,
+         0xc18bdc86},
+        {0x82ebf64e, 0x00000009, 0x000007c3, 0x69d590a9, 0x9efa8499,
+         0xa874fcdd},
+        {0xb18a0319, 0x00000026, 0x000007db, 0x1cf98dcc, 0x8fa9ad6a,
+         0x9dc0bb48},
+};
 
-}
-#endif
+#include <linux/time.h>
 
-static void bytereverse(unsigned char *buf, size_t len)
+static int __init crc32c_test(void)
 {
-        while (len--) {
-                unsigned char x = bitrev8(*buf);
-                *buf++ = x;
+        int i;
+        int errors = 0;
+        int bytes = 0;
+        struct timespec start, stop;
+        u64 nsec;
+        unsigned long flags;
+
+        /* keep static to prevent cache warming code from
+         * getting eliminated by the compiler */
+        static u32 crc;
+
+        /* pre-warm the cache */
+        for (i = 0; i < 100; i++) {
+                bytes += 2*test[i].length;
+
+                crc ^= __crc32c_le(test[i].crc, test_buf +
+                    test[i].start, test[i].length);
         }
-}
 
-static void random_garbage(unsigned char *buf, size_t len)
-{
-        while (len--)
-                *buf++ = (unsigned char) random();
-}
+        /* reduce OS noise */
+        local_irq_save(flags);
+        local_irq_disable();
 
-#if 0                           /* Not used at present */
-static void store_le(u32 x, unsigned char *buf)
-{
-        buf[0] = (unsigned char) x;
-        buf[1] = (unsigned char) (x >> 8);
-        buf[2] = (unsigned char) (x >> 16);
-        buf[3] = (unsigned char) (x >> 24);
-}
-#endif
+        getnstimeofday(&start);
+        for (i = 0; i < 100; i++) {
+                if (test[i].crc32c_le != __crc32c_le(test[i].crc, test_buf +
+                    test[i].start, test[i].length))
+                        errors++;
+        }
+        getnstimeofday(&stop);
 
-static void store_be(u32 x, unsigned char *buf)
-{
-        buf[0] = (unsigned char) (x >> 24);
-        buf[1] = (unsigned char) (x >> 16);
-        buf[2] = (unsigned char) (x >> 8);
-        buf[3] = (unsigned char) x;
+        local_irq_restore(flags);
+        local_irq_enable();
+
+        nsec = stop.tv_nsec - start.tv_nsec +
+                1000000000 * (stop.tv_sec - start.tv_sec);
+
+        pr_info("crc32c: CRC_LE_BITS = %d\n", CRC_LE_BITS);
+
+        if (errors)
+                pr_warn("crc32c: %d self tests failed\n", errors);
+        else {
+                pr_info("crc32c: self tests passed, processed %d bytes in %lld nsec\n",
+                        bytes, nsec);
+        }
+
+        return 0;
 }
 
-/*
- * This checks that CRC(buf + CRC(buf)) = 0, and that
- * CRC commutes with bit-reversal.  This has the side effect
- * of bytewise bit-reversing the input buffer, and returns
- * the CRC of the reversed buffer.
- */
-static u32 test_step(u32 init, unsigned char *buf, size_t len)
+static int __init crc32_test(void)
 {
-        u32 crc1, crc2;
-        size_t i;
+        int i;
+        int errors = 0;
+        int bytes = 0;
+        struct timespec start, stop;
+        u64 nsec;
+        unsigned long flags;
+
+        /* keep static to prevent cache warming code from
+         * getting eliminated by the compiler */
+        static u32 crc;
+
+        /* pre-warm the cache */
+        for (i = 0; i < 100; i++) {
+                bytes += 2*test[i].length;
 
-        crc1 = crc32_be(init, buf, len);
-        store_be(crc1, buf + len);
-        crc2 = crc32_be(init, buf, len + 4);
-        if (crc2)
-                printf("\nCRC cancellation fail: 0x%08x should be 0\n",
-                       crc2);
-
-        for (i = 0; i <= len + 4; i++) {
-                crc2 = crc32_be(init, buf, i);
-                crc2 = crc32_be(crc2, buf + i, len + 4 - i);
-                if (crc2)
-                        printf("\nCRC split fail: 0x%08x\n", crc2);
+                crc ^= crc32_le(test[i].crc, test_buf +
+                    test[i].start, test[i].length);
+
+                crc ^= crc32_be(test[i].crc, test_buf +
+                    test[i].start, test[i].length);
         }
 
-        /* Now swap it around for the other test */
-
-        bytereverse(buf, len + 4);
-        init = bitrev32(init);
-        crc2 = bitrev32(crc1);
-        if (crc1 != bitrev32(crc2))
-                printf("\nBit reversal fail: 0x%08x -> 0x%08x -> 0x%08x\n",
-                       crc1, crc2, bitrev32(crc2));
-        crc1 = crc32_le(init, buf, len);
-        if (crc1 != crc2)
-                printf("\nCRC endianness fail: 0x%08x != 0x%08x\n", crc1,
-                       crc2);
-        crc2 = crc32_le(init, buf, len + 4);
-        if (crc2)
-                printf("\nCRC cancellation fail: 0x%08x should be 0\n",
-                       crc2);
-
-        for (i = 0; i <= len + 4; i++) {
-                crc2 = crc32_le(init, buf, i);
-                crc2 = crc32_le(crc2, buf + i, len + 4 - i);
-                if (crc2)
-                        printf("\nCRC split fail: 0x%08x\n", crc2);
+        /* reduce OS noise */
+        local_irq_save(flags);
+        local_irq_disable();
+
+        getnstimeofday(&start);
+        for (i = 0; i < 100; i++) {
+                if (test[i].crc_le != crc32_le(test[i].crc, test_buf +
+                    test[i].start, test[i].length))
+                        errors++;
+
+                if (test[i].crc_be != crc32_be(test[i].crc, test_buf +
+                    test[i].start, test[i].length))
+                        errors++;
         }
+        getnstimeofday(&stop);
 
-        return crc1;
-}
+        local_irq_restore(flags);
+        local_irq_enable();
 
-#define SIZE 64
-#define INIT1 0
-#define INIT2 0
+        nsec = stop.tv_nsec - start.tv_nsec +
+                1000000000 * (stop.tv_sec - start.tv_sec);
 
-int main(void)
-{
-        unsigned char buf1[SIZE + 4];
-        unsigned char buf2[SIZE + 4];
-        unsigned char buf3[SIZE + 4];
-        int i, j;
-        u32 crc1, crc2, crc3;
-
-        for (i = 0; i <= SIZE; i++) {
-                printf("\rTesting length %d...", i);
-                fflush(stdout);
-                random_garbage(buf1, i);
-                random_garbage(buf2, i);
-                for (j = 0; j < i; j++)
-                        buf3[j] = buf1[j] ^ buf2[j];
-
-                crc1 = test_step(INIT1, buf1, i);
-                crc2 = test_step(INIT2, buf2, i);
-                /* Now check that CRC(buf1 ^ buf2) = CRC(buf1) ^ CRC(buf2) */
-                crc3 = test_step(INIT1 ^ INIT2, buf3, i);
-                if (crc3 != (crc1 ^ crc2))
-                        printf("CRC XOR fail: 0x%08x != 0x%08x ^ 0x%08x\n",
-                               crc3, crc1, crc2);
+        pr_info("crc32: CRC_LE_BITS = %d, CRC_BE BITS = %d\n",
+                 CRC_LE_BITS, CRC_BE_BITS);
+
+        if (errors)
+                pr_warn("crc32: %d self tests failed\n", errors);
+        else {
+                pr_info("crc32: self tests passed, processed %d bytes in %lld nsec\n",
+                        bytes, nsec);
         }
-        printf("\nAll test complete.  No failures expected.\n");
+
         return 0;
 }
 
-#endif                          /* UNITTEST */
+static int __init crc32test_init(void)
+{
+        crc32_test();
+        crc32c_test();
+        return 0;
+}
+
+static void __exit crc32_exit(void)
+{
+}
+
+module_init(crc32test_init);
+module_exit(crc32_exit);
+#endif /* CONFIG_CRC32_SELFTEST */
diff --git a/lib/crc32defs.h b/lib/crc32defs.h
index 9b6773d73749..64cba2c3c700 100644
--- a/lib/crc32defs.h
+++ b/lib/crc32defs.h
@@ -6,27 +6,67 @@
 #define CRCPOLY_LE 0xedb88320
 #define CRCPOLY_BE 0x04c11db7
 
-/* How many bits at a time to use.  Requires a table of 4<<CRC_xx_BITS bytes. */
-/* For less performance-sensitive, use 4 */
-#ifndef CRC_LE_BITS 
+/*
+ * This is the CRC32c polynomial, as outlined by Castagnoli.
+ * x^32+x^28+x^27+x^26+x^25+x^23+x^22+x^20+x^19+x^18+x^14+x^13+x^11+x^10+x^9+
+ * x^8+x^6+x^0
+ */
+#define CRC32C_POLY_LE 0x82F63B78
+
+/* Try to choose an implementation variant via Kconfig */
+#ifdef CONFIG_CRC32_SLICEBY8
+# define CRC_LE_BITS 64
+# define CRC_BE_BITS 64
+#endif
+#ifdef CONFIG_CRC32_SLICEBY4
+# define CRC_LE_BITS 32
+# define CRC_BE_BITS 32
+#endif
+#ifdef CONFIG_CRC32_SARWATE
 # define CRC_LE_BITS 8
+# define CRC_BE_BITS 8
+#endif
+#ifdef CONFIG_CRC32_BIT
+# define CRC_LE_BITS 1
+# define CRC_BE_BITS 1
+#endif
+
+/*
+ * How many bits at a time to use.  Valid values are 1, 2, 4, 8, 32 and 64.
+ * For less performance-sensitive, use 4 or 8 to save table size.
+ * For larger systems choose same as CPU architecture as default.
+ * This works well on X86_64, SPARC64 systems. This may require some
+ * elaboration after experiments with other architectures.
+ */
+#ifndef CRC_LE_BITS
+#  ifdef CONFIG_64BIT
+#  define CRC_LE_BITS 64
+#  else
+#  define CRC_LE_BITS 32
+#  endif
 #endif
 #ifndef CRC_BE_BITS
-# define CRC_BE_BITS 8
+#  ifdef CONFIG_64BIT
+#  define CRC_BE_BITS 64
+#  else
+#  define CRC_BE_BITS 32
+#  endif
 #endif
 
 /*
  * Little-endian CRC computation.  Used with serial bit streams sent
  * lsbit-first.  Be sure to use cpu_to_le32() to append the computed CRC.
  */
-#if CRC_LE_BITS > 8 || CRC_LE_BITS < 1 || CRC_LE_BITS & CRC_LE_BITS-1
-# error CRC_LE_BITS must be a power of 2 between 1 and 8
+#if CRC_LE_BITS > 64 || CRC_LE_BITS < 1 || CRC_LE_BITS == 16 || \
+        CRC_LE_BITS & CRC_LE_BITS-1
+# error "CRC_LE_BITS must be one of {1, 2, 4, 8, 32, 64}"
 #endif
 
 /*
  * Big-endian CRC computation.  Used with serial bit streams sent
  * msbit-first.  Be sure to use cpu_to_be32() to append the computed CRC.
  */
-#if CRC_BE_BITS > 8 || CRC_BE_BITS < 1 || CRC_BE_BITS & CRC_BE_BITS-1
-# error CRC_BE_BITS must be a power of 2 between 1 and 8
+#if CRC_BE_BITS > 64 || CRC_BE_BITS < 1 || CRC_BE_BITS == 16 || \
+        CRC_BE_BITS & CRC_BE_BITS-1
+# error "CRC_BE_BITS must be one of {1, 2, 4, 8, 32, 64}"
 #endif
diff --git a/lib/ctype.c b/lib/ctype.c
index 26baa620e95b..c646df91a2f7 100644
--- a/lib/ctype.c
+++ b/lib/ctype.c
@@ -5,7 +5,8 @@
  */
 
 #include <linux/ctype.h>
-#include <linux/module.h>
+#include <linux/compiler.h>
+#include <linux/export.h>
 
 const unsigned char _ctype[] = {
 _C,_C,_C,_C,_C,_C,_C,_C,                                /* 0-7 */
diff --git a/lib/debug_locks.c b/lib/debug_locks.c
index b1c177307677..f2fa60c59343 100644
--- a/lib/debug_locks.c
+++ b/lib/debug_locks.c
@@ -10,7 +10,7 @@
  */
 #include <linux/rwsem.h>
 #include <linux/mutex.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/spinlock.h>
 #include <linux/debug_locks.h>
 
diff --git a/lib/debugobjects.c b/lib/debugobjects.c
index a78b7c6e042c..d11808ca4bc4 100644
--- a/lib/debugobjects.c
+++ b/lib/debugobjects.c
@@ -79,30 +79,29 @@ static const char *obj_states[ODEBUG_STATE_MAX] = {
         [ODEBUG_STATE_NOTAVAILABLE]     = "not available",
 };
 
-static int fill_pool(void)
+static void fill_pool(void)
 {
         gfp_t gfp = GFP_ATOMIC | __GFP_NORETRY | __GFP_NOWARN;
         struct debug_obj *new;
         unsigned long flags;
 
         if (likely(obj_pool_free >= ODEBUG_POOL_MIN_LEVEL))
-                return obj_pool_free;
+                return;
 
         if (unlikely(!obj_cache))
-                return obj_pool_free;
+                return;
 
         while (obj_pool_free < ODEBUG_POOL_MIN_LEVEL) {
 
                 new = kmem_cache_zalloc(obj_cache, gfp);
                 if (!new)
-                        return obj_pool_free;
+                        return;
 
                 raw_spin_lock_irqsave(&pool_lock, flags);
                 hlist_add_head(&new->node, &obj_pool);
                 obj_pool_free++;
                 raw_spin_unlock_irqrestore(&pool_lock, flags);
         }
-        return obj_pool_free;
 }
 
 /*
@@ -268,12 +267,16 @@ static void debug_print_object(struct debug_obj *obj, char *msg)
  * Try to repair the damage, so we have a better chance to get useful
  * debug output.
  */
-static void
+static int
 debug_object_fixup(int (*fixup)(void *addr, enum debug_obj_state state),
                    void * addr, enum debug_obj_state state)
 {
+        int fixed = 0;
+
         if (fixup)
-                debug_objects_fixups += fixup(addr, state);
+                fixed = fixup(addr, state);
+        debug_objects_fixups += fixed;
+        return fixed;
 }
 
 static void debug_object_is_on_stack(void *addr, int onstack)
@@ -386,6 +389,9 @@ void debug_object_activate(void *addr, struct debug_obj_descr *descr)
         struct debug_bucket *db;
         struct debug_obj *obj;
         unsigned long flags;
+        struct debug_obj o = { .object = addr,
+                               .state = ODEBUG_STATE_NOTAVAILABLE,
+                               .descr = descr };
 
         if (!debug_objects_enabled)
                 return;
@@ -425,8 +431,9 @@ void debug_object_activate(void *addr, struct debug_obj_descr *descr)
          * let the type specific code decide whether this is
          * true or not.
          */
-        debug_object_fixup(descr->fixup_activate, addr,
-                           ODEBUG_STATE_NOTAVAILABLE);
+        if (debug_object_fixup(descr->fixup_activate, addr,
+                           ODEBUG_STATE_NOTAVAILABLE))
+                debug_print_object(&o, "activate");
 }
 
 /**
@@ -563,6 +570,44 @@ out_unlock:
 }
 
 /**
+ * debug_object_assert_init - debug checks when object should be init-ed
+ * @addr:       address of the object
+ * @descr:      pointer to an object specific debug description structure
+ */
+void debug_object_assert_init(void *addr, struct debug_obj_descr *descr)
+{
+        struct debug_bucket *db;
+        struct debug_obj *obj;
+        unsigned long flags;
+
+        if (!debug_objects_enabled)
+                return;
+
+        db = get_bucket((unsigned long) addr);
+
+        raw_spin_lock_irqsave(&db->lock, flags);
+
+        obj = lookup_object(addr, db);
+        if (!obj) {
+                struct debug_obj o = { .object = addr,
+                                       .state = ODEBUG_STATE_NOTAVAILABLE,
+                                       .descr = descr };
+
+                raw_spin_unlock_irqrestore(&db->lock, flags);
+                /*
+                 * Maybe the object is static.  Let the type specific
+                 * code decide what to do.
+                 */
+                if (debug_object_fixup(descr->fixup_assert_init, addr,
+                                       ODEBUG_STATE_NOTAVAILABLE))
+                        debug_print_object(&o, "assert_init");
+                return;
+        }
+
+        raw_spin_unlock_irqrestore(&db->lock, flags);
+}
+
+/**
  * debug_object_active_state - debug checks object usage state machine
  * @addr:       address of the object
  * @descr:      pointer to an object specific debug description structure
@@ -772,17 +817,9 @@ static int __init fixup_activate(void *addr, enum debug_obj_state state)
                 if (obj->static_init == 1) {
                         debug_object_init(obj, &descr_type_test);
                         debug_object_activate(obj, &descr_type_test);
-                        /*
-                         * Real code should return 0 here ! This is
-                         * not a fixup of some bad behaviour. We
-                         * merily call the debug_init function to keep
-                         * track of the object.
-                         */
-                        return 1;
-                } else {
-                        /* Real code needs to emit a warning here */
+                        return 0;
                 }
-                return 0;
+                return 1;
 
         case ODEBUG_STATE_ACTIVE:
                 debug_object_deactivate(obj, &descr_type_test);
@@ -921,7 +958,7 @@ static void __init debug_objects_selftest(void)
 
         obj.static_init = 1;
         debug_object_activate(&obj, &descr_type_test);
-        if (check_results(&obj, ODEBUG_STATE_ACTIVE, ++fixups, warnings))
+        if (check_results(&obj, ODEBUG_STATE_ACTIVE, fixups, warnings))
                 goto out;
         debug_object_init(&obj, &descr_type_test);
         if (check_results(&obj, ODEBUG_STATE_INIT, ++fixups, ++warnings))
@@ -1014,10 +1051,10 @@ static int __init debug_objects_replace_static_objects(void)
                         cnt++;
                 }
         }
+        local_irq_enable();
 
         printk(KERN_DEBUG "ODEBUG: %d of %d active objects replaced\n", cnt,
                obj_pool_used);
-        local_irq_enable();
         return 0;
 free:
         hlist_for_each_entry_safe(obj, node, tmp, &objects, node) {
diff --git a/lib/dec_and_lock.c b/lib/dec_and_lock.c
index b5257725daad..e26278576b31 100644
--- a/lib/dec_and_lock.c
+++ b/lib/dec_and_lock.c
@@ -1,4 +1,4 @@
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/spinlock.h>
 #include <linux/atomic.h>
 
diff --git a/lib/decompress.c b/lib/decompress.c
index 3d766b7f60ab..31a804277282 100644
--- a/lib/decompress.c
+++ b/lib/decompress.c
@@ -14,6 +14,7 @@
 
 #include <linux/types.h>
 #include <linux/string.h>
+#include <linux/init.h>
 
 #ifndef CONFIG_DECOMPRESS_GZIP
 # define gunzip NULL
@@ -31,11 +32,13 @@
 # define unlzo NULL
 #endif
 
-static const struct compress_format {
+struct compress_format {
         unsigned char magic[2];
         const char *name;
         decompress_fn decompressor;
-} compressed_formats[] = {
+};
+
+static const struct compress_format compressed_formats[] __initdata = {
         { {037, 0213}, "gzip", gunzip },
         { {037, 0236}, "gzip", gunzip },
         { {0x42, 0x5a}, "bzip2", bunzip2 },
@@ -45,7 +48,7 @@ static const struct compress_format {
         { {0, 0}, NULL, NULL }
 };
 
-decompress_fn decompress_method(const unsigned char *inbuf, int len,
+decompress_fn __init decompress_method(const unsigned char *inbuf, int len,
                                 const char **name)
 {
         const struct compress_format *cf;
diff --git a/lib/decompress_bunzip2.c b/lib/decompress_bunzip2.c
index a7b80c1d6a0d..31c5f7675fbf 100644
--- a/lib/decompress_bunzip2.c
+++ b/lib/decompress_bunzip2.c
@@ -1,4 +1,3 @@
-/* vi: set sw = 4 ts = 4: */
 /*      Small bzip2 deflate implementation, by Rob Landley (rob@landley.net).
 
         Based on bzip2 decompression code by Julian R Seward (jseward@acm.org),
@@ -691,7 +690,7 @@ STATIC int INIT bunzip2(unsigned char *buf, int len,
                 outbuf = malloc(BZIP2_IOBUF_SIZE);
 
         if (!outbuf) {
-                error("Could not allocate output bufer");
+                error("Could not allocate output buffer");
                 return RETVAL_OUT_OF_MEMORY;
         }
         if (buf)
@@ -699,7 +698,7 @@ STATIC int INIT bunzip2(unsigned char *buf, int len,
         else
                 inbuf = malloc(BZIP2_IOBUF_SIZE);
         if (!inbuf) {
-                error("Could not allocate input bufer");
+                error("Could not allocate input buffer");
                 i = RETVAL_OUT_OF_MEMORY;
                 goto exit_0;
         }
diff --git a/lib/decompress_unlzma.c b/lib/decompress_unlzma.c
index 476c65af9709..32adb73a9038 100644
--- a/lib/decompress_unlzma.c
+++ b/lib/decompress_unlzma.c
@@ -562,7 +562,7 @@ STATIC inline int INIT unlzma(unsigned char *buf, int in_len,
         else
                 inbuf = malloc(LZMA_IOBUF_SIZE);
         if (!inbuf) {
-                error("Could not allocate input bufer");
+                error("Could not allocate input buffer");
                 goto exit_0;
         }
 
diff --git a/lib/decompress_unlzo.c b/lib/decompress_unlzo.c
index 5a7a2adf4c4c..4531294fa62f 100644
--- a/lib/decompress_unlzo.c
+++ b/lib/decompress_unlzo.c
@@ -279,7 +279,7 @@ STATIC inline int INIT unlzo(u8 *input, int in_len,
         ret = 0;
 exit_2:
         if (!input)
-                free(in_buf);
+                free(in_buf_save);
 exit_1:
         if (!output)
                 free(out_buf);
diff --git a/lib/devres.c b/lib/devres.c
index 7c0e953a7486..80b9c76d436a 100644
--- a/lib/devres.c
+++ b/lib/devres.c
@@ -1,7 +1,7 @@
 #include <linux/pci.h>
 #include <linux/io.h>
 #include <linux/gfp.h>
-#include <linux/module.h>
+#include <linux/export.h>
 
 void devm_ioremap_release(struct device *dev, void *res)
 {
@@ -85,6 +85,57 @@ void devm_iounmap(struct device *dev, void __iomem *addr)
 }
 EXPORT_SYMBOL(devm_iounmap);
 
+/**
+ * devm_request_and_ioremap() - Check, request region, and ioremap resource
+ * @dev: Generic device to handle the resource for
+ * @res: resource to be handled
+ *
+ * Takes all necessary steps to ioremap a mem resource. Uses managed device, so
+ * everything is undone on driver detach. Checks arguments, so you can feed
+ * it the result from e.g. platform_get_resource() directly. Returns the
+ * remapped pointer or NULL on error. Usage example:
+ *
+ *      res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+ *      base = devm_request_and_ioremap(&pdev->dev, res);
+ *      if (!base)
+ *              return -EADDRNOTAVAIL;
+ */
+void __iomem *devm_request_and_ioremap(struct device *dev,
+                        struct resource *res)
+{
+        resource_size_t size;
+        const char *name;
+        void __iomem *dest_ptr;
+
+        BUG_ON(!dev);
+
+        if (!res || resource_type(res) != IORESOURCE_MEM) {
+                dev_err(dev, "invalid resource\n");
+                return NULL;
+        }
+
+        size = resource_size(res);
+        name = res->name ?: dev_name(dev);
+
+        if (!devm_request_mem_region(dev, res->start, size, name)) {
+                dev_err(dev, "can't request region for resource %pR\n", res);
+                return NULL;
+        }
+
+        if (res->flags & IORESOURCE_CACHEABLE)
+                dest_ptr = devm_ioremap(dev, res->start, size);
+        else
+                dest_ptr = devm_ioremap_nocache(dev, res->start, size);
+
+        if (!dest_ptr) {
+                dev_err(dev, "ioremap failed for resource %pR\n", res);
+                devm_release_mem_region(dev, res->start, size);
+        }
+
+        return dest_ptr;
+}
+EXPORT_SYMBOL(devm_request_and_ioremap);
+
 #ifdef CONFIG_HAS_IOPORT
 /*
  * Generic iomap devres
@@ -253,7 +304,7 @@ EXPORT_SYMBOL(pcim_iounmap);
  *
  * Request and iomap regions specified by @mask.
  */
-int pcim_iomap_regions(struct pci_dev *pdev, u16 mask, const char *name)
+int pcim_iomap_regions(struct pci_dev *pdev, int mask, const char *name)
 {
         void __iomem * const *iomap;
         int i, rc;
@@ -306,7 +357,7 @@ EXPORT_SYMBOL(pcim_iomap_regions);
  *
  * Request all PCI BARs and iomap regions specified by @mask.
  */
-int pcim_iomap_regions_request_all(struct pci_dev *pdev, u16 mask,
+int pcim_iomap_regions_request_all(struct pci_dev *pdev, int mask,
                                    const char *name)
 {
         int request_mask = ((1 << 6) - 1) & ~mask;
@@ -330,7 +381,7 @@ EXPORT_SYMBOL(pcim_iomap_regions_request_all);
  *
  * Unmap and release regions specified by @mask.
  */
-void pcim_iounmap_regions(struct pci_dev *pdev, u16 mask)
+void pcim_iounmap_regions(struct pci_dev *pdev, int mask)
 {
         void __iomem * const *iomap;
         int i;
@@ -348,5 +399,5 @@ void pcim_iounmap_regions(struct pci_dev *pdev, u16 mask)
         }
 }
 EXPORT_SYMBOL(pcim_iounmap_regions);
-#endif
-#endif
+#endif /* CONFIG_PCI */
+#endif /* CONFIG_HAS_IOPORT */
diff --git a/lib/digsig.c b/lib/digsig.c
new file mode 100644
index 000000000000..8c0e62975c88
--- /dev/null
+++ b/lib/digsig.c
@@ -0,0 +1,280 @@
+/*
+ * Copyright (C) 2011 Nokia Corporation
+ * Copyright (C) 2011 Intel Corporation
+ *
+ * Author:
+ * Dmitry Kasatkin <dmitry.kasatkin@nokia.com>
+ *                 <dmitry.kasatkin@intel.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation, version 2 of the License.
+ *
+ * File: sign.c
+ *      implements signature (RSA) verification
+ *      pkcs decoding is based on LibTomCrypt code
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/err.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/key.h>
+#include <linux/crypto.h>
+#include <crypto/hash.h>
+#include <crypto/sha.h>
+#include <keys/user-type.h>
+#include <linux/mpi.h>
+#include <linux/digsig.h>
+
+static struct crypto_shash *shash;
+
+static int pkcs_1_v1_5_decode_emsa(const unsigned char *msg,
+                        unsigned long  msglen,
+                        unsigned long  modulus_bitlen,
+                        unsigned char *out,
+                        unsigned long *outlen)
+{
+        unsigned long modulus_len, ps_len, i;
+
+        modulus_len = (modulus_bitlen >> 3) + (modulus_bitlen & 7 ? 1 : 0);
+
+        /* test message size */
+        if ((msglen > modulus_len) || (modulus_len < 11))
+                return -EINVAL;
+
+        /* separate encoded message */
+        if ((msg[0] != 0x00) || (msg[1] != (unsigned char)1))
+                return -EINVAL;
+
+        for (i = 2; i < modulus_len - 1; i++)
+                if (msg[i] != 0xFF)
+                        break;
+
+        /* separator check */
+        if (msg[i] != 0)
+                /* There was no octet with hexadecimal value 0x00
+                to separate ps from m. */
+                return -EINVAL;
+
+        ps_len = i - 2;
+
+        if (*outlen < (msglen - (2 + ps_len + 1))) {
+                *outlen = msglen - (2 + ps_len + 1);
+                return -EOVERFLOW;
+        }
+
+        *outlen = (msglen - (2 + ps_len + 1));
+        memcpy(out, &msg[2 + ps_len + 1], *outlen);
+
+        return 0;
+}
+
+/*
+ * RSA Signature verification with public key
+ */
+static int digsig_verify_rsa(struct key *key,
+                    const char *sig, int siglen,
+                       const char *h, int hlen)
+{
+        int err = -EINVAL;
+        unsigned long len;
+        unsigned long mlen, mblen;
+        unsigned nret, l;
+        int head, i;
+        unsigned char *out1 = NULL, *out2 = NULL;
+        MPI in = NULL, res = NULL, pkey[2];
+        uint8_t *p, *datap, *endp;
+        struct user_key_payload *ukp;
+        struct pubkey_hdr *pkh;
+
+        down_read(&key->sem);
+        ukp = key->payload.data;
+
+        if (ukp->datalen < sizeof(*pkh))
+                goto err1;
+
+        pkh = (struct pubkey_hdr *)ukp->data;
+
+        if (pkh->version != 1)
+                goto err1;
+
+        if (pkh->algo != PUBKEY_ALGO_RSA)
+                goto err1;
+
+        if (pkh->nmpi != 2)
+                goto err1;
+
+        datap = pkh->mpi;
+        endp = ukp->data + ukp->datalen;
+
+        err = -ENOMEM;
+
+        for (i = 0; i < pkh->nmpi; i++) {
+                unsigned int remaining = endp - datap;
+                pkey[i] = mpi_read_from_buffer(datap, &remaining);
+                if (!pkey[i])
+                        goto err;
+                datap += remaining;
+        }
+
+        mblen = mpi_get_nbits(pkey[0]);
+        mlen = (mblen + 7)/8;
+
+        if (mlen == 0)
+                goto err;
+
+        out1 = kzalloc(mlen, GFP_KERNEL);
+        if (!out1)
+                goto err;
+
+        out2 = kzalloc(mlen, GFP_KERNEL);
+        if (!out2)
+                goto err;
+
+        nret = siglen;
+        in = mpi_read_from_buffer(sig, &nret);
+        if (!in)
+                goto err;
+
+        res = mpi_alloc(mpi_get_nlimbs(in) * 2);
+        if (!res)
+                goto err;
+
+        err = mpi_powm(res, in, pkey[1], pkey[0]);
+        if (err)
+                goto err;
+
+        if (mpi_get_nlimbs(res) * BYTES_PER_MPI_LIMB > mlen) {
+                err = -EINVAL;
+                goto err;
+        }
+
+        p = mpi_get_buffer(res, &l, NULL);
+        if (!p) {
+                err = -EINVAL;
+                goto err;
+        }
+
+        len = mlen;
+        head = len - l;
+        memset(out1, 0, head);
+        memcpy(out1 + head, p, l);
+
+        err = pkcs_1_v1_5_decode_emsa(out1, len, mblen, out2, &len);
+        if (err)
+                goto err;
+
+        if (len != hlen || memcmp(out2, h, hlen))
+                err = -EINVAL;
+
+err:
+        mpi_free(in);
+        mpi_free(res);
+        kfree(out1);
+        kfree(out2);
+        while (--i >= 0)
+                mpi_free(pkey[i]);
+err1:
+        up_read(&key->sem);
+
+        return err;
+}
+
+/**
+ * digsig_verify() - digital signature verification with public key
+ * @keyring:    keyring to search key in
+ * @sig:        digital signature
+ * @sigen:      length of the signature
+ * @data:       data
+ * @datalen:    length of the data
+ * @return:     0 on success, -EINVAL otherwise
+ *
+ * Verifies data integrity against digital signature.
+ * Currently only RSA is supported.
+ * Normally hash of the content is used as a data for this function.
+ *
+ */
+int digsig_verify(struct key *keyring, const char *sig, int siglen,
+                                                const char *data, int datalen)
+{
+        int err = -ENOMEM;
+        struct signature_hdr *sh = (struct signature_hdr *)sig;
+        struct shash_desc *desc = NULL;
+        unsigned char hash[SHA1_DIGEST_SIZE];
+        struct key *key;
+        char name[20];
+
+        if (siglen < sizeof(*sh) + 2)
+                return -EINVAL;
+
+        if (sh->algo != PUBKEY_ALGO_RSA)
+                return -ENOTSUPP;
+
+        sprintf(name, "%llX", __be64_to_cpup((uint64_t *)sh->keyid));
+
+        if (keyring) {
+                /* search in specific keyring */
+                key_ref_t kref;
+                kref = keyring_search(make_key_ref(keyring, 1UL),
+                                                &key_type_user, name);
+                if (IS_ERR(kref))
+                        key = ERR_PTR(PTR_ERR(kref));
+                else
+                        key = key_ref_to_ptr(kref);
+        } else {
+                key = request_key(&key_type_user, name, NULL);
+        }
+        if (IS_ERR(key)) {
+                pr_err("key not found, id: %s\n", name);
+                return PTR_ERR(key);
+        }
+
+        desc = kzalloc(sizeof(*desc) + crypto_shash_descsize(shash),
+                       GFP_KERNEL);
+        if (!desc)
+                goto err;
+
+        desc->tfm = shash;
+        desc->flags = CRYPTO_TFM_REQ_MAY_SLEEP;
+
+        crypto_shash_init(desc);
+        crypto_shash_update(desc, data, datalen);
+        crypto_shash_update(desc, sig, sizeof(*sh));
+        crypto_shash_final(desc, hash);
+
+        kfree(desc);
+
+        /* pass signature mpis address */
+        err = digsig_verify_rsa(key, sig + sizeof(*sh), siglen - sizeof(*sh),
+                             hash, sizeof(hash));
+
+err:
+        key_put(key);
+
+        return err ? -EINVAL : 0;
+}
+EXPORT_SYMBOL_GPL(digsig_verify);
+
+static int __init digsig_init(void)
+{
+        shash = crypto_alloc_shash("sha1", 0, 0);
+        if (IS_ERR(shash)) {
+                pr_err("shash allocation failed\n");
+                return  PTR_ERR(shash);
+        }
+
+        return 0;
+
+}
+
+static void __exit digsig_cleanup(void)
+{
+        crypto_free_shash(shash);
+}
+
+module_init(digsig_init);
+module_exit(digsig_cleanup);
+
+MODULE_LICENSE("GPL");
diff --git a/lib/div64.c b/lib/div64.c
index 5b4919191778..a163b6caef73 100644
--- a/lib/div64.c
+++ b/lib/div64.c
@@ -16,7 +16,8 @@
  * assembly versions such as arch/ppc/lib/div64.S and arch/sh/lib/div64.S.
  */
 
-#include <linux/module.h>
+#include <linux/export.h>
+#include <linux/kernel.h>
 #include <linux/math64.h>
 
 /* Not needed on 64bit architectures */
@@ -86,7 +87,7 @@ EXPORT_SYMBOL(div_s64_rem);
  * by the book 'Hacker's Delight'.  The original source and full proof
  * can be found here and is available for use without restriction.
  *
- * 'http://www.hackersdelight.org/HDcode/newCode/divDouble.c'
+ * 'http://www.hackersdelight.org/HDcode/newCode/divDouble.c.txt'
  */
 #ifndef div64_u64
 u64 div64_u64(u64 dividend, u64 divisor)
diff --git a/lib/dma-debug.c b/lib/dma-debug.c
index db07bfd9298e..d84beb994f36 100644
--- a/lib/dma-debug.c
+++ b/lib/dma-debug.c
@@ -24,6 +24,7 @@
 #include <linux/spinlock.h>
 #include <linux/debugfs.h>
 #include <linux/uaccess.h>
+#include <linux/export.h>
 #include <linux/device.h>
 #include <linux/types.h>
 #include <linux/sched.h>
@@ -62,6 +63,8 @@ struct dma_debug_entry {
 #endif
 };
 
+typedef bool (*match_fn)(struct dma_debug_entry *, struct dma_debug_entry *);
+
 struct hash_bucket {
         struct list_head list;
         spinlock_t lock;
@@ -75,7 +78,7 @@ static LIST_HEAD(free_entries);
 static DEFINE_SPINLOCK(free_entries_lock);
 
 /* Global disable flag - will be set in case of an error */
-static bool global_disable __read_mostly;
+static u32 global_disable __read_mostly;
 
 /* Global error count */
 static u32 error_count;
@@ -117,11 +120,6 @@ static const char *type2name[4] = { "single", "page",
 static const char *dir2name[4] = { "DMA_BIDIRECTIONAL", "DMA_TO_DEVICE",
                                    "DMA_FROM_DEVICE", "DMA_NONE" };
 
-/* little merge helper - remove it after the merge window */
-#ifndef BUS_NOTIFY_UNBOUND_DRIVER
-#define BUS_NOTIFY_UNBOUND_DRIVER 0x0005
-#endif
-
 /*
  * The access to some variables in this macro is racy. We can't use atomic_t
  * here because all these variables are exported to debugfs. Some of them even
@@ -167,7 +165,7 @@ static bool driver_filter(struct device *dev)
                 return false;
 
         /* driver filter on but not yet initialized */
-        drv = get_driver(dev->driver);
+        drv = dev->driver;
         if (!drv)
                 return false;
 
@@ -182,7 +180,6 @@ static bool driver_filter(struct device *dev)
         }
 
         read_unlock_irqrestore(&driver_name_lock, flags);
-        put_driver(drv);
 
         return ret;
 }
@@ -240,18 +237,37 @@ static void put_hash_bucket(struct hash_bucket *bucket,
         spin_unlock_irqrestore(&bucket->lock, __flags);
 }
 
+static bool exact_match(struct dma_debug_entry *a, struct dma_debug_entry *b)
+{
+        return ((a->dev_addr == b->dev_addr) &&
+                (a->dev == b->dev)) ? true : false;
+}
+
+static bool containing_match(struct dma_debug_entry *a,
+                             struct dma_debug_entry *b)
+{
+        if (a->dev != b->dev)
+                return false;
+
+        if ((b->dev_addr <= a->dev_addr) &&
+            ((b->dev_addr + b->size) >= (a->dev_addr + a->size)))
+                return true;
+
+        return false;
+}
+
 /*
  * Search a given entry in the hash bucket list
  */
-static struct dma_debug_entry *hash_bucket_find(struct hash_bucket *bucket,
-                                                struct dma_debug_entry *ref)
+static struct dma_debug_entry *__hash_bucket_find(struct hash_bucket *bucket,
+                                                  struct dma_debug_entry *ref,
+                                                  match_fn match)
 {
         struct dma_debug_entry *entry, *ret = NULL;
-        int matches = 0, match_lvl, last_lvl = 0;
+        int matches = 0, match_lvl, last_lvl = -1;
 
         list_for_each_entry(entry, &bucket->list, list) {
-                if ((entry->dev_addr != ref->dev_addr) ||
-                    (entry->dev != ref->dev))
+                if (!match(ref, entry))
                         continue;
 
                 /*
@@ -277,7 +293,7 @@ static struct dma_debug_entry *hash_bucket_find(struct hash_bucket *bucket,
                 } else if (match_lvl > last_lvl) {
                         /*
                          * We found an entry that fits better then the
-                         * previous one
+                         * previous one or it is the 1st match.
                          */
                         last_lvl = match_lvl;
                         ret      = entry;
@@ -293,6 +309,39 @@ static struct dma_debug_entry *hash_bucket_find(struct hash_bucket *bucket,
         return ret;
 }
 
+static struct dma_debug_entry *bucket_find_exact(struct hash_bucket *bucket,
+                                                 struct dma_debug_entry *ref)
+{
+        return __hash_bucket_find(bucket, ref, exact_match);
+}
+
+static struct dma_debug_entry *bucket_find_contain(struct hash_bucket **bucket,
+                                                   struct dma_debug_entry *ref,
+                                                   unsigned long *flags)
+{
+
+        unsigned int max_range = dma_get_max_seg_size(ref->dev);
+        struct dma_debug_entry *entry, index = *ref;
+        unsigned int range = 0;
+
+        while (range <= max_range) {
+                entry = __hash_bucket_find(*bucket, &index, containing_match);
+
+                if (entry)
+                        return entry;
+
+                /*
+                 * Nothing found, go back a hash bucket
+                 */
+                put_hash_bucket(*bucket, flags);
+                range          += (1 << HASH_FN_SHIFT);
+                index.dev_addr -= (1 << HASH_FN_SHIFT);
+                *bucket = get_hash_bucket(&index, flags);
+        }
+
+        return NULL;
+}
+
 /*
  * Add an entry to a hash bucket
  */
@@ -376,7 +425,7 @@ static struct dma_debug_entry *__dma_entry_alloc(void)
  */
 static struct dma_debug_entry *dma_entry_alloc(void)
 {
-        struct dma_debug_entry *entry = NULL;
+        struct dma_debug_entry *entry;
         unsigned long flags;
 
         spin_lock_irqsave(&free_entries_lock, flags);
@@ -384,11 +433,14 @@ static struct dma_debug_entry *dma_entry_alloc(void)
         if (list_empty(&free_entries)) {
                 pr_err("DMA-API: debugging out of memory - disabling\n");
                 global_disable = true;
-                goto out;
+                spin_unlock_irqrestore(&free_entries_lock, flags);
+                return NULL;
         }
 
         entry = __dma_entry_alloc();
 
+        spin_unlock_irqrestore(&free_entries_lock, flags);
+
 #ifdef CONFIG_STACKTRACE
         entry->stacktrace.max_entries = DMA_DEBUG_STACKTRACE_ENTRIES;
         entry->stacktrace.entries = entry->st_entries;
@@ -396,9 +448,6 @@ static struct dma_debug_entry *dma_entry_alloc(void)
         save_stack_trace(&entry->stacktrace);
 #endif
 
-out:
-        spin_unlock_irqrestore(&free_entries_lock, flags);
-
         return entry;
 }
 
@@ -603,7 +652,7 @@ static int dma_debug_fs_init(void)
 
         global_disable_dent = debugfs_create_bool("disabled", 0444,
                         dma_debug_dent,
-                        (u32 *)&global_disable);
+                        &global_disable);
         if (!global_disable_dent)
                 goto out_err;
 
@@ -802,7 +851,7 @@ static void check_unmap(struct dma_debug_entry *ref)
         }
 
         bucket = get_hash_bucket(ref, &flags);
-        entry = hash_bucket_find(bucket, ref);
+        entry = bucket_find_exact(bucket, ref);
 
         if (!entry) {
                 err_printk(ref->dev, NULL, "DMA-API: device driver tries "
@@ -902,7 +951,7 @@ static void check_sync(struct device *dev,
 
         bucket = get_hash_bucket(ref, &flags);
 
-        entry = hash_bucket_find(bucket, ref);
+        entry = bucket_find_contain(&bucket, ref, &flags);
 
         if (!entry) {
                 err_printk(dev, NULL, "DMA-API: device driver tries "
@@ -1060,7 +1109,7 @@ static int get_nr_mapped_entries(struct device *dev,
         int mapped_ents;
 
         bucket       = get_hash_bucket(ref, &flags);
-        entry        = hash_bucket_find(bucket, ref);
+        entry        = bucket_find_exact(bucket, ref);
         mapped_ents  = 0;
 
         if (entry)
diff --git a/lib/dump_stack.c b/lib/dump_stack.c
index 53bff4c8452b..42f4f55c9458 100644
--- a/lib/dump_stack.c
+++ b/lib/dump_stack.c
@@ -4,7 +4,7 @@
  */
 
 #include <linux/kernel.h>
-#include <linux/module.h>
+#include <linux/export.h>
 
 void dump_stack(void)
 {
diff --git a/lib/dynamic_debug.c b/lib/dynamic_debug.c
index 75ca78f3a8c9..e7f7d993357a 100644
--- a/lib/dynamic_debug.c
+++ b/lib/dynamic_debug.c
@@ -10,11 +10,12 @@
  * Copyright (C) 2011 Bart Van Assche.  All Rights Reserved.
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ":%s: " fmt, __func__
+
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/moduleparam.h>
 #include <linux/kallsyms.h>
-#include <linux/version.h>
 #include <linux/types.h>
 #include <linux/mutex.h>
 #include <linux/proc_fs.h>
@@ -30,6 +31,8 @@
 #include <linux/jump_label.h>
 #include <linux/hardirq.h>
 #include <linux/sched.h>
+#include <linux/device.h>
+#include <linux/netdevice.h>
 
 extern struct _ddebug __start___verbose[];
 extern struct _ddebug __stop___verbose[];
@@ -38,7 +41,6 @@ struct ddebug_table {
         struct list_head link;
         char *mod_name;
         unsigned int num_ddebugs;
-        unsigned int num_enabled;
         struct _ddebug *ddebugs;
 };
 
@@ -58,6 +60,7 @@ struct ddebug_iter {
 static DEFINE_MUTEX(ddebug_lock);
 static LIST_HEAD(ddebug_tables);
 static int verbose = 0;
+module_param(verbose, int, 0644);
 
 /* Return the last part of a pathname */
 static inline const char *basename(const char *path)
@@ -66,12 +69,24 @@ static inline const char *basename(const char *path)
         return tail ? tail+1 : path;
 }
 
+/* Return the path relative to source root */
+static inline const char *trim_prefix(const char *path)
+{
+        int skip = strlen(__FILE__) - strlen("lib/dynamic_debug.c");
+
+        if (strncmp(path, __FILE__, skip))
+                skip = 0; /* prefix mismatch, don't skip */
+
+        return path + skip;
+}
+
 static struct { unsigned flag:8; char opt_char; } opt_array[] = {
         { _DPRINTK_FLAGS_PRINT, 'p' },
         { _DPRINTK_FLAGS_INCL_MODNAME, 'm' },
         { _DPRINTK_FLAGS_INCL_FUNCNAME, 'f' },
         { _DPRINTK_FLAGS_INCL_LINENO, 'l' },
         { _DPRINTK_FLAGS_INCL_TID, 't' },
+        { _DPRINTK_FLAGS_NONE, '_' },
 };
 
 /* format a string into buf[] which describes the _ddebug's flags */
@@ -81,58 +96,76 @@ static char *ddebug_describe_flags(struct _ddebug *dp, char *buf,
         char *p = buf;
         int i;
 
-        BUG_ON(maxlen < 4);
+        BUG_ON(maxlen < 6);
         for (i = 0; i < ARRAY_SIZE(opt_array); ++i)
                 if (dp->flags & opt_array[i].flag)
                         *p++ = opt_array[i].opt_char;
         if (p == buf)
-                *p++ = '-';
+                *p++ = '_';
         *p = '\0';
 
         return buf;
 }
 
+#define vpr_info(fmt, ...) \
+        if (verbose) do { pr_info(fmt, ##__VA_ARGS__); } while (0)
+
+#define vpr_info_dq(q, msg)                                     \
+do {                                                            \
+        /* trim last char off format print */                   \
+        vpr_info("%s: func=\"%s\" file=\"%s\" "                 \
+                "module=\"%s\" format=\"%.*s\" "                \
+                "lineno=%u-%u",                                 \
+                msg,                                            \
+                q->function ? q->function : "",                 \
+                q->filename ? q->filename : "",                 \
+                q->module ? q->module : "",                     \
+                (int)(q->format ? strlen(q->format) - 1 : 0),   \
+                q->format ? q->format : "",                     \
+                q->first_lineno, q->last_lineno);               \
+} while (0)
+
 /*
- * Search the tables for _ddebug's which match the given
- * `query' and apply the `flags' and `mask' to them.  Tells
- * the user which ddebug's were changed, or whether none
- * were matched.
+ * Search the tables for _ddebug's which match the given `query' and
+ * apply the `flags' and `mask' to them.  Returns number of matching
+ * callsites, normally the same as number of changes.  If verbose,
+ * logs the changes.  Takes ddebug_lock.
  */
-static void ddebug_change(const struct ddebug_query *query,
-                           unsigned int flags, unsigned int mask)
+static int ddebug_change(const struct ddebug_query *query,
+                        unsigned int flags, unsigned int mask)
 {
         int i;
         struct ddebug_table *dt;
         unsigned int newflags;
         unsigned int nfound = 0;
-        char flagbuf[8];
+        char flagbuf[10];
 
         /* search for matching ddebugs */
         mutex_lock(&ddebug_lock);
         list_for_each_entry(dt, &ddebug_tables, link) {
 
                 /* match against the module name */
-                if (query->module != NULL &&
-                    strcmp(query->module, dt->mod_name))
+                if (query->module && strcmp(query->module, dt->mod_name))
                         continue;
 
                 for (i = 0 ; i < dt->num_ddebugs ; i++) {
                         struct _ddebug *dp = &dt->ddebugs[i];
 
                         /* match against the source filename */
-                        if (query->filename != NULL &&
+                        if (query->filename &&
                             strcmp(query->filename, dp->filename) &&
-                            strcmp(query->filename, basename(dp->filename)))
+                            strcmp(query->filename, basename(dp->filename)) &&
+                            strcmp(query->filename, trim_prefix(dp->filename)))
                                 continue;
 
                         /* match against the function */
-                        if (query->function != NULL &&
+                        if (query->function &&
                             strcmp(query->function, dp->function))
                                 continue;
 
                         /* match against the format */
-                        if (query->format != NULL &&
-                            strstr(dp->format, query->format) == NULL)
+                        if (query->format &&
+                            !strstr(dp->format, query->format))
                                 continue;
 
                         /* match against the line number range */
@@ -148,29 +181,20 @@ static void ddebug_change(const struct ddebug_query *query,
                         newflags = (dp->flags & mask) | flags;
                         if (newflags == dp->flags)
                                 continue;
-
-                        if (!newflags)
-                                dt->num_enabled--;
-                        else if (!dp->flags)
-                                dt->num_enabled++;
                         dp->flags = newflags;
-                        if (newflags)
-                                dp->enabled = 1;
-                        else
-                                dp->enabled = 0;
-                        if (verbose)
-                                printk(KERN_INFO
-                                        "ddebug: changed %s:%d [%s]%s %s\n",
-                                        dp->filename, dp->lineno,
-                                        dt->mod_name, dp->function,
-                                        ddebug_describe_flags(dp, flagbuf,
-                                                        sizeof(flagbuf)));
+                        vpr_info("changed %s:%d [%s]%s =%s\n",
+                                trim_prefix(dp->filename), dp->lineno,
+                                dt->mod_name, dp->function,
+                                ddebug_describe_flags(dp, flagbuf,
+                                                sizeof(flagbuf)));
                 }
         }
         mutex_unlock(&ddebug_lock);
 
         if (!nfound && verbose)
-                printk(KERN_INFO "ddebug: no matches for query\n");
+                pr_info("no matches for query\n");
+
+        return nfound;
 }
 
 /*
@@ -190,8 +214,10 @@ static int ddebug_tokenize(char *buf, char *words[], int maxwords)
                 buf = skip_spaces(buf);
                 if (!*buf)
                         break;  /* oh, it was trailing whitespace */
+                if (*buf == '#')
+                        break;  /* token starts comment, skip rest of line */
 
-                /* Run `end' over a word, either whitespace separated or quoted */
+                /* find `end' of word, whitespace separated or quoted */
                 if (*buf == '"' || *buf == '\'') {
                         int quote = *buf++;
                         for (end = buf ; *end && *end != quote ; end++)
@@ -203,8 +229,8 @@ static int ddebug_tokenize(char *buf, char *words[], int maxwords)
                                 ;
                         BUG_ON(end == buf);
                 }
-                /* Here `buf' is the start of the word, `end' is one past the end */
 
+                /* `buf' is start of word, `end' is one past its end */
                 if (nwords == maxwords)
                         return -EINVAL; /* ran out of words[] before bytes */
                 if (*end)
@@ -215,10 +241,10 @@ static int ddebug_tokenize(char *buf, char *words[], int maxwords)
 
         if (verbose) {
                 int i;
-                printk(KERN_INFO "%s: split into words:", __func__);
+                pr_info("split into words:");
                 for (i = 0 ; i < nwords ; i++)
-                        printk(" \"%s\"", words[i]);
-                printk("\n");
+                        pr_cont(" \"%s\"", words[i]);
+                pr_cont("\n");
         }
 
         return nwords;
@@ -283,6 +309,19 @@ static char *unescape(char *str)
         return str;
 }
 
+static int check_set(const char **dest, char *src, char *name)
+{
+        int rc = 0;
+
+        if (*dest) {
+                rc = -EINVAL;
+                pr_err("match-spec:%s val:%s overridden by %s",
+                        name, *dest, src);
+        }
+        *dest = src;
+        return rc;
+}
+
 /*
  * Parse words[] as a ddebug query specification, which is a series
  * of (keyword, value) pairs chosen from these possibilities:
@@ -294,55 +333,64 @@ static char *unescape(char *str)
  * format <escaped-string-to-find-in-format>
  * line <lineno>
  * line <first-lineno>-<last-lineno> // where either may be empty
+ *
+ * Only 1 of each type is allowed.
+ * Returns 0 on success, <0 on error.
  */
 static int ddebug_parse_query(char *words[], int nwords,
-                               struct ddebug_query *query)
+                        struct ddebug_query *query, const char *modname)
 {
         unsigned int i;
+        int rc;
 
         /* check we have an even number of words */
         if (nwords % 2 != 0)
                 return -EINVAL;
         memset(query, 0, sizeof(*query));
 
+        if (modname)
+                /* support $modname.dyndbg=<multiple queries> */
+                query->module = modname;
+
         for (i = 0 ; i < nwords ; i += 2) {
                 if (!strcmp(words[i], "func"))
-                        query->function = words[i+1];
+                        rc = check_set(&query->function, words[i+1], "func");
                 else if (!strcmp(words[i], "file"))
-                        query->filename = words[i+1];
+                        rc = check_set(&query->filename, words[i+1], "file");
                 else if (!strcmp(words[i], "module"))
-                        query->module = words[i+1];
+                        rc = check_set(&query->module, words[i+1], "module");
                 else if (!strcmp(words[i], "format"))
-                        query->format = unescape(words[i+1]);
+                        rc = check_set(&query->format, unescape(words[i+1]),
+                                "format");
                 else if (!strcmp(words[i], "line")) {
                         char *first = words[i+1];
                         char *last = strchr(first, '-');
+                        if (query->first_lineno || query->last_lineno) {
+                                pr_err("match-spec:line given 2 times\n");
+                                return -EINVAL;
+                        }
                         if (last)
                                 *last++ = '\0';
                         if (parse_lineno(first, &query->first_lineno) < 0)
                                 return -EINVAL;
-                        if (last != NULL) {
+                        if (last) {
                                 /* range <first>-<last> */
-                                if (parse_lineno(last, &query->last_lineno) < 0)
+                                if (parse_lineno(last, &query->last_lineno)
+                                    < query->first_lineno) {
+                                        pr_err("last-line < 1st-line\n");
                                         return -EINVAL;
+                                }
                         } else {
                                 query->last_lineno = query->first_lineno;
                         }
                 } else {
-                        if (verbose)
-                                printk(KERN_ERR "%s: unknown keyword \"%s\"\n",
-                                        __func__, words[i]);
+                        pr_err("unknown keyword \"%s\"\n", words[i]);
                         return -EINVAL;
                 }
+                if (rc)
+                        return rc;
         }
-
-        if (verbose)
-                printk(KERN_INFO "%s: q->function=\"%s\" q->filename=\"%s\" "
-                       "q->module=\"%s\" q->format=\"%s\" q->lineno=%u-%u\n",
-                        __func__, query->function, query->filename,
-                        query->module, query->format, query->first_lineno,
-                        query->last_lineno);
-
+        vpr_info_dq(query, "parsed");
         return 0;
 }
 
@@ -367,8 +415,7 @@ static int ddebug_parse_flags(const char *str, unsigned int *flagsp,
         default:
                 return -EINVAL;
         }
-        if (verbose)
-                printk(KERN_INFO "%s: op='%c'\n", __func__, op);
+        vpr_info("op='%c'\n", op);
 
         for ( ; *str ; ++str) {
                 for (i = ARRAY_SIZE(opt_array) - 1; i >= 0; i--) {
@@ -380,10 +427,7 @@ static int ddebug_parse_flags(const char *str, unsigned int *flagsp,
                 if (i < 0)
                         return -EINVAL;
         }
-        if (flags == 0)
-                return -EINVAL;
-        if (verbose)
-                printk(KERN_INFO "%s: flags=0x%x\n", __func__, flags);
+        vpr_info("flags=0x%x\n", flags);
 
         /* calculate final *flagsp, *maskp according to mask and op */
         switch (op) {
@@ -400,70 +444,216 @@ static int ddebug_parse_flags(const char *str, unsigned int *flagsp,
                 *flagsp = 0;
                 break;
         }
-        if (verbose)
-                printk(KERN_INFO "%s: *flagsp=0x%x *maskp=0x%x\n",
-                        __func__, *flagsp, *maskp);
+        vpr_info("*flagsp=0x%x *maskp=0x%x\n", *flagsp, *maskp);
         return 0;
 }
 
-static int ddebug_exec_query(char *query_string)
+static int ddebug_exec_query(char *query_string, const char *modname)
 {
         unsigned int flags = 0, mask = 0;
         struct ddebug_query query;
 #define MAXWORDS 9
-        int nwords;
+        int nwords, nfound;
         char *words[MAXWORDS];
 
         nwords = ddebug_tokenize(query_string, words, MAXWORDS);
         if (nwords <= 0)
                 return -EINVAL;
-        if (ddebug_parse_query(words, nwords-1, &query))
+        if (ddebug_parse_query(words, nwords-1, &query, modname))
                 return -EINVAL;
         if (ddebug_parse_flags(words[nwords-1], &flags, &mask))
                 return -EINVAL;
 
         /* actually go and implement the change */
-        ddebug_change(&query, flags, mask);
+        nfound = ddebug_change(&query, flags, mask);
+        vpr_info_dq((&query), (nfound) ? "applied" : "no-match");
+
+        return nfound;
+}
+
+/* handle multiple queries in query string, continue on error, return
+   last error or number of matching callsites.  Module name is either
+   in param (for boot arg) or perhaps in query string.
+*/
+static int ddebug_exec_queries(char *query, const char *modname)
+{
+        char *split;
+        int i, errs = 0, exitcode = 0, rc, nfound = 0;
+
+        for (i = 0; query; query = split) {
+                split = strpbrk(query, ";\n");
+                if (split)
+                        *split++ = '\0';
+
+                query = skip_spaces(query);
+                if (!query || !*query || *query == '#')
+                        continue;
+
+                vpr_info("query %d: \"%s\"\n", i, query);
+
+                rc = ddebug_exec_query(query, modname);
+                if (rc < 0) {
+                        errs++;
+                        exitcode = rc;
+                } else
+                        nfound += rc;
+                i++;
+        }
+        vpr_info("processed %d queries, with %d matches, %d errs\n",
+                 i, nfound, errs);
+
+        if (exitcode)
+                return exitcode;
+        return nfound;
+}
+
+#define PREFIX_SIZE 64
+
+static int remaining(int wrote)
+{
+        if (PREFIX_SIZE - wrote > 0)
+                return PREFIX_SIZE - wrote;
         return 0;
 }
 
+static char *dynamic_emit_prefix(const struct _ddebug *desc, char *buf)
+{
+        int pos_after_tid;
+        int pos = 0;
+
+        *buf = '\0';
+
+        if (desc->flags & _DPRINTK_FLAGS_INCL_TID) {
+                if (in_interrupt())
+                        pos += snprintf(buf + pos, remaining(pos), "<intr> ");
+                else
+                        pos += snprintf(buf + pos, remaining(pos), "[%d] ",
+                                        task_pid_vnr(current));
+        }
+        pos_after_tid = pos;
+        if (desc->flags & _DPRINTK_FLAGS_INCL_MODNAME)
+                pos += snprintf(buf + pos, remaining(pos), "%s:",
+                                desc->modname);
+        if (desc->flags & _DPRINTK_FLAGS_INCL_FUNCNAME)
+                pos += snprintf(buf + pos, remaining(pos), "%s:",
+                                desc->function);
+        if (desc->flags & _DPRINTK_FLAGS_INCL_LINENO)
+                pos += snprintf(buf + pos, remaining(pos), "%d:",
+                                desc->lineno);
+        if (pos - pos_after_tid)
+                pos += snprintf(buf + pos, remaining(pos), " ");
+        if (pos >= PREFIX_SIZE)
+                buf[PREFIX_SIZE - 1] = '\0';
+
+        return buf;
+}
+
 int __dynamic_pr_debug(struct _ddebug *descriptor, const char *fmt, ...)
 {
         va_list args;
         int res;
+        struct va_format vaf;
+        char buf[PREFIX_SIZE];
 
         BUG_ON(!descriptor);
         BUG_ON(!fmt);
 
         va_start(args, fmt);
-        res = printk(KERN_DEBUG);
-        if (descriptor->flags & _DPRINTK_FLAGS_INCL_TID) {
-                if (in_interrupt())
-                        res += printk(KERN_CONT "<intr> ");
-                else
-                        res += printk(KERN_CONT "[%d] ", task_pid_vnr(current));
-        }
-        if (descriptor->flags & _DPRINTK_FLAGS_INCL_MODNAME)
-                res += printk(KERN_CONT "%s:", descriptor->modname);
-        if (descriptor->flags & _DPRINTK_FLAGS_INCL_FUNCNAME)
-                res += printk(KERN_CONT "%s:", descriptor->function);
-        if (descriptor->flags & _DPRINTK_FLAGS_INCL_LINENO)
-                res += printk(KERN_CONT "%d ", descriptor->lineno);
-        res += vprintk(fmt, args);
+
+        vaf.fmt = fmt;
+        vaf.va = &args;
+
+        res = printk(KERN_DEBUG "%s%pV",
+                     dynamic_emit_prefix(descriptor, buf), &vaf);
+
         va_end(args);
 
         return res;
 }
 EXPORT_SYMBOL(__dynamic_pr_debug);
 
-static __initdata char ddebug_setup_string[1024];
+int __dynamic_dev_dbg(struct _ddebug *descriptor,
+                      const struct device *dev, const char *fmt, ...)
+{
+        struct va_format vaf;
+        va_list args;
+        int res;
+
+        BUG_ON(!descriptor);
+        BUG_ON(!fmt);
+
+        va_start(args, fmt);
+
+        vaf.fmt = fmt;
+        vaf.va = &args;
+
+        if (!dev) {
+                res = printk(KERN_DEBUG "(NULL device *): %pV", &vaf);
+        } else {
+                char buf[PREFIX_SIZE];
+
+                res = dev_printk_emit(7, dev, "%s%s %s: %pV",
+                                      dynamic_emit_prefix(descriptor, buf),
+                                      dev_driver_string(dev), dev_name(dev),
+                                      &vaf);
+        }
+
+        va_end(args);
+
+        return res;
+}
+EXPORT_SYMBOL(__dynamic_dev_dbg);
+
+#ifdef CONFIG_NET
+
+int __dynamic_netdev_dbg(struct _ddebug *descriptor,
+                         const struct net_device *dev, const char *fmt, ...)
+{
+        struct va_format vaf;
+        va_list args;
+        int res;
+
+        BUG_ON(!descriptor);
+        BUG_ON(!fmt);
+
+        va_start(args, fmt);
+
+        vaf.fmt = fmt;
+        vaf.va = &args;
+
+        if (dev && dev->dev.parent) {
+                char buf[PREFIX_SIZE];
+
+                res = dev_printk_emit(7, dev->dev.parent,
+                                      "%s%s %s %s: %pV",
+                                      dynamic_emit_prefix(descriptor, buf),
+                                      dev_driver_string(dev->dev.parent),
+                                      dev_name(dev->dev.parent),
+                                      netdev_name(dev), &vaf);
+        } else if (dev) {
+                res = printk(KERN_DEBUG "%s: %pV", netdev_name(dev), &vaf);
+        } else {
+                res = printk(KERN_DEBUG "(NULL net_device): %pV", &vaf);
+        }
+
+        va_end(args);
+
+        return res;
+}
+EXPORT_SYMBOL(__dynamic_netdev_dbg);
+
+#endif
+
+#define DDEBUG_STRING_SIZE 1024
+static __initdata char ddebug_setup_string[DDEBUG_STRING_SIZE];
+
 static __init int ddebug_setup_query(char *str)
 {
-        if (strlen(str) >= 1024) {
-                pr_warning("ddebug boot param string too large\n");
+        if (strlen(str) >= DDEBUG_STRING_SIZE) {
+                pr_warn("ddebug boot param string too large\n");
                 return 0;
         }
-        strcpy(ddebug_setup_string, str);
+        strlcpy(ddebug_setup_string, str, DDEBUG_STRING_SIZE);
         return 1;
 }
 
@@ -473,26 +663,32 @@ __setup("ddebug_query=", ddebug_setup_query);
  * File_ops->write method for <debugfs>/dynamic_debug/conrol.  Gathers the
  * command text from userspace, parses and executes it.
  */
+#define USER_BUF_PAGE 4096
 static ssize_t ddebug_proc_write(struct file *file, const char __user *ubuf,
                                   size_t len, loff_t *offp)
 {
-        char tmpbuf[256];
+        char *tmpbuf;
         int ret;
 
         if (len == 0)
                 return 0;
-        /* we don't check *offp -- multiple writes() are allowed */
-        if (len > sizeof(tmpbuf)-1)
+        if (len > USER_BUF_PAGE - 1) {
+                pr_warn("expected <%d bytes into control\n", USER_BUF_PAGE);
                 return -E2BIG;
-        if (copy_from_user(tmpbuf, ubuf, len))
+        }
+        tmpbuf = kmalloc(len + 1, GFP_KERNEL);
+        if (!tmpbuf)
+                return -ENOMEM;
+        if (copy_from_user(tmpbuf, ubuf, len)) {
+                kfree(tmpbuf);
                 return -EFAULT;
+        }
         tmpbuf[len] = '\0';
-        if (verbose)
-                printk(KERN_INFO "%s: read %d bytes from userspace\n",
-                        __func__, (int)len);
+        vpr_info("read %d bytes from userspace\n", (int)len);
 
-        ret = ddebug_exec_query(tmpbuf);
-        if (ret)
+        ret = ddebug_exec_queries(tmpbuf, NULL);
+        kfree(tmpbuf);
+        if (ret < 0)
                 return ret;
 
         *offp += len;
@@ -551,9 +747,7 @@ static void *ddebug_proc_start(struct seq_file *m, loff_t *pos)
         struct _ddebug *dp;
         int n = *pos;
 
-        if (verbose)
-                printk(KERN_INFO "%s: called m=%p *pos=%lld\n",
-                        __func__, m, (unsigned long long)*pos);
+        vpr_info("called m=%p *pos=%lld\n", m, (unsigned long long)*pos);
 
         mutex_lock(&ddebug_lock);
 
@@ -577,9 +771,8 @@ static void *ddebug_proc_next(struct seq_file *m, void *p, loff_t *pos)
         struct ddebug_iter *iter = m->private;
         struct _ddebug *dp;
 
-        if (verbose)
-                printk(KERN_INFO "%s: called m=%p p=%p *pos=%lld\n",
-                        __func__, m, p, (unsigned long long)*pos);
+        vpr_info("called m=%p p=%p *pos=%lld\n",
+                m, p, (unsigned long long)*pos);
 
         if (p == SEQ_START_TOKEN)
                 dp = ddebug_iter_first(iter);
@@ -599,11 +792,9 @@ static int ddebug_proc_show(struct seq_file *m, void *p)
 {
         struct ddebug_iter *iter = m->private;
         struct _ddebug *dp = p;
-        char flagsbuf[8];
+        char flagsbuf[10];
 
-        if (verbose)
-                printk(KERN_INFO "%s: called m=%p p=%p\n",
-                        __func__, m, p);
+        vpr_info("called m=%p p=%p\n", m, p);
 
         if (p == SEQ_START_TOKEN) {
                 seq_puts(m,
@@ -611,10 +802,10 @@ static int ddebug_proc_show(struct seq_file *m, void *p)
                 return 0;
         }
 
-        seq_printf(m, "%s:%u [%s]%s %s \"",
-                   dp->filename, dp->lineno,
-                   iter->table->mod_name, dp->function,
-                   ddebug_describe_flags(dp, flagsbuf, sizeof(flagsbuf)));
+        seq_printf(m, "%s:%u [%s]%s =%s \"",
+                trim_prefix(dp->filename), dp->lineno,
+                iter->table->mod_name, dp->function,
+                ddebug_describe_flags(dp, flagsbuf, sizeof(flagsbuf)));
         seq_escape(m, dp->format, "\t\r\n\"");
         seq_puts(m, "\"\n");
 
@@ -627,9 +818,7 @@ static int ddebug_proc_show(struct seq_file *m, void *p)
  */
 static void ddebug_proc_stop(struct seq_file *m, void *p)
 {
-        if (verbose)
-                printk(KERN_INFO "%s: called m=%p p=%p\n",
-                        __func__, m, p);
+        vpr_info("called m=%p p=%p\n", m, p);
         mutex_unlock(&ddebug_lock);
 }
 
@@ -641,18 +830,18 @@ static const struct seq_operations ddebug_proc_seqops = {
 };
 
 /*
- * File_ops->open method for <debugfs>/dynamic_debug/control.  Does the seq_file
- * setup dance, and also creates an iterator to walk the _ddebugs.
- * Note that we create a seq_file always, even for O_WRONLY files
- * where it's not needed, as doing so simplifies the ->release method.
+ * File_ops->open method for <debugfs>/dynamic_debug/control.  Does
+ * the seq_file setup dance, and also creates an iterator to walk the
+ * _ddebugs.  Note that we create a seq_file always, even for O_WRONLY
+ * files where it's not needed, as doing so simplifies the ->release
+ * method.
  */
 static int ddebug_proc_open(struct inode *inode, struct file *file)
 {
         struct ddebug_iter *iter;
         int err;
 
-        if (verbose)
-                printk(KERN_INFO "%s: called\n", __func__);
+        vpr_info("called\n");
 
         iter = kzalloc(sizeof(*iter), GFP_KERNEL);
         if (iter == NULL)
@@ -696,20 +885,57 @@ int ddebug_add_module(struct _ddebug *tab, unsigned int n,
         }
         dt->mod_name = new_name;
         dt->num_ddebugs = n;
-        dt->num_enabled = 0;
         dt->ddebugs = tab;
 
         mutex_lock(&ddebug_lock);
         list_add_tail(&dt->link, &ddebug_tables);
         mutex_unlock(&ddebug_lock);
 
-        if (verbose)
-                printk(KERN_INFO "%u debug prints in module %s\n",
-                                 n, dt->mod_name);
+        vpr_info("%u debug prints in module %s\n", n, dt->mod_name);
         return 0;
 }
 EXPORT_SYMBOL_GPL(ddebug_add_module);
 
+/* helper for ddebug_dyndbg_(boot|module)_param_cb */
+static int ddebug_dyndbg_param_cb(char *param, char *val,
+                                const char *modname, int on_err)
+{
+        char *sep;
+
+        sep = strchr(param, '.');
+        if (sep) {
+                /* needed only for ddebug_dyndbg_boot_param_cb */
+                *sep = '\0';
+                modname = param;
+                param = sep + 1;
+        }
+        if (strcmp(param, "dyndbg"))
+                return on_err; /* determined by caller */
+
+        ddebug_exec_queries((val ? val : "+p"), modname);
+
+        return 0; /* query failure shouldnt stop module load */
+}
+
+/* handle both dyndbg and $module.dyndbg params at boot */
+static int ddebug_dyndbg_boot_param_cb(char *param, char *val,
+                                const char *unused)
+{
+        vpr_info("%s=\"%s\"\n", param, val);
+        return ddebug_dyndbg_param_cb(param, val, NULL, 0);
+}
+
+/*
+ * modprobe foo finds foo.params in boot-args, strips "foo.", and
+ * passes them to load_module().  This callback gets unknown params,
+ * processes dyndbg params, rejects others.
+ */
+int ddebug_dyndbg_module_param_cb(char *param, char *val, const char *module)
+{
+        vpr_info("module: %s %s=\"%s\"\n", module, param, val);
+        return ddebug_dyndbg_param_cb(param, val, module, -ENOENT);
+}
+
 static void ddebug_table_free(struct ddebug_table *dt)
 {
         list_del_init(&dt->link);
@@ -726,9 +952,7 @@ int ddebug_remove_module(const char *mod_name)
         struct ddebug_table *dt, *nextdt;
         int ret = -ENOENT;
 
-        if (verbose)
-                printk(KERN_INFO "%s: removing module \"%s\"\n",
-                                __func__, mod_name);
+        vpr_info("removing module \"%s\"\n", mod_name);
 
         mutex_lock(&ddebug_lock);
         list_for_each_entry_safe(dt, nextdt, &ddebug_tables, link) {
@@ -779,46 +1003,76 @@ static int __init dynamic_debug_init(void)
 {
         struct _ddebug *iter, *iter_start;
         const char *modname = NULL;
+        char *cmdline;
         int ret = 0;
-        int n = 0;
-
-        if (__start___verbose != __stop___verbose) {
-                iter = __start___verbose;
-                modname = iter->modname;
-                iter_start = iter;
-                for (; iter < __stop___verbose; iter++) {
-                        if (strcmp(modname, iter->modname)) {
-                                ret = ddebug_add_module(iter_start, n, modname);
-                                if (ret)
-                                        goto out_free;
-                                n = 0;
-                                modname = iter->modname;
-                                iter_start = iter;
-                        }
-                        n++;
+        int n = 0, entries = 0, modct = 0;
+        int verbose_bytes = 0;
+
+        if (__start___verbose == __stop___verbose) {
+                pr_warn("_ddebug table is empty in a "
+                        "CONFIG_DYNAMIC_DEBUG build");
+                return 1;
+        }
+        iter = __start___verbose;
+        modname = iter->modname;
+        iter_start = iter;
+        for (; iter < __stop___verbose; iter++) {
+                entries++;
+                verbose_bytes += strlen(iter->modname) + strlen(iter->function)
+                        + strlen(iter->filename) + strlen(iter->format);
+
+                if (strcmp(modname, iter->modname)) {
+                        modct++;
+                        ret = ddebug_add_module(iter_start, n, modname);
+                        if (ret)
+                                goto out_err;
+                        n = 0;
+                        modname = iter->modname;
+                        iter_start = iter;
                 }
-                ret = ddebug_add_module(iter_start, n, modname);
+                n++;
         }
+        ret = ddebug_add_module(iter_start, n, modname);
+        if (ret)
+                goto out_err;
 
-        /* ddebug_query boot param got passed -> set it up */
+        ddebug_init_success = 1;
+        vpr_info("%d modules, %d entries and %d bytes in ddebug tables,"
+                " %d bytes in (readonly) verbose section\n",
+                modct, entries, (int)( modct * sizeof(struct ddebug_table)),
+                verbose_bytes + (int)(__stop___verbose - __start___verbose));
+
+        /* apply ddebug_query boot param, dont unload tables on err */
         if (ddebug_setup_string[0] != '\0') {
-                ret = ddebug_exec_query(ddebug_setup_string);
-                if (ret)
-                        pr_warning("Invalid ddebug boot param %s",
-                                   ddebug_setup_string);
-                else
-                        pr_info("ddebug initialized with string %s",
+                pr_warn("ddebug_query param name is deprecated,"
+                        " change it to dyndbg\n");
+                ret = ddebug_exec_queries(ddebug_setup_string, NULL);
+                if (ret < 0)
+                        pr_warn("Invalid ddebug boot param %s",
                                 ddebug_setup_string);
+                else
+                        pr_info("%d changes by ddebug_query\n", ret);
         }
+        /* now that ddebug tables are loaded, process all boot args
+         * again to find and activate queries given in dyndbg params.
+         * While this has already been done for known boot params, it
+         * ignored the unknown ones (dyndbg in particular).  Reusing
+         * parse_args avoids ad-hoc parsing.  This will also attempt
+         * to activate queries for not-yet-loaded modules, which is
+         * slightly noisy if verbose, but harmless.
+         */
+        cmdline = kstrdup(saved_command_line, GFP_KERNEL);
+        parse_args("dyndbg params", cmdline, NULL,
+                   0, 0, 0, &ddebug_dyndbg_boot_param_cb);
+        kfree(cmdline);
+        return 0;
 
-out_free:
-        if (ret)
-                ddebug_remove_all_tables();
-        else
-                ddebug_init_success = 1;
+out_err:
+        ddebug_remove_all_tables();
         return 0;
 }
 /* Allow early initialization for boot messages via boot param */
-arch_initcall(dynamic_debug_init);
+early_initcall(dynamic_debug_init);
+
 /* Debugfs setup must be done later */
-module_init(dynamic_debug_init_debugfs);
+fs_initcall(dynamic_debug_init_debugfs);
diff --git a/lib/dynamic_queue_limits.c b/lib/dynamic_queue_limits.c
new file mode 100644
index 000000000000..0777c5a45fa0
--- /dev/null
+++ b/lib/dynamic_queue_limits.c
@@ -0,0 +1,138 @@
+/*
+ * Dynamic byte queue limits.  See include/linux/dynamic_queue_limits.h
+ *
+ * Copyright (c) 2011, Tom Herbert <therbert@google.com>
+ */
+#include <linux/module.h>
+#include <linux/types.h>
+#include <linux/ctype.h>
+#include <linux/kernel.h>
+#include <linux/jiffies.h>
+#include <linux/dynamic_queue_limits.h>
+
+#define POSDIFF(A, B) ((int)((A) - (B)) > 0 ? (A) - (B) : 0)
+#define AFTER_EQ(A, B) ((int)((A) - (B)) >= 0)
+
+/* Records completed count and recalculates the queue limit */
+void dql_completed(struct dql *dql, unsigned int count)
+{
+        unsigned int inprogress, prev_inprogress, limit;
+        unsigned int ovlimit, completed, num_queued;
+        bool all_prev_completed;
+
+        num_queued = ACCESS_ONCE(dql->num_queued);
+
+        /* Can't complete more than what's in queue */
+        BUG_ON(count > num_queued - dql->num_completed);
+
+        completed = dql->num_completed + count;
+        limit = dql->limit;
+        ovlimit = POSDIFF(num_queued - dql->num_completed, limit);
+        inprogress = num_queued - completed;
+        prev_inprogress = dql->prev_num_queued - dql->num_completed;
+        all_prev_completed = AFTER_EQ(completed, dql->prev_num_queued);
+
+        if ((ovlimit && !inprogress) ||
+            (dql->prev_ovlimit && all_prev_completed)) {
+                /*
+                 * Queue considered starved if:
+                 *   - The queue was over-limit in the last interval,
+                 *     and there is no more data in the queue.
+                 *  OR
+                 *   - The queue was over-limit in the previous interval and
+                 *     when enqueuing it was possible that all queued data
+                 *     had been consumed.  This covers the case when queue
+                 *     may have becomes starved between completion processing
+                 *     running and next time enqueue was scheduled.
+                 *
+                 *     When queue is starved increase the limit by the amount
+                 *     of bytes both sent and completed in the last interval,
+                 *     plus any previous over-limit.
+                 */
+                limit += POSDIFF(completed, dql->prev_num_queued) +
+                     dql->prev_ovlimit;
+                dql->slack_start_time = jiffies;
+                dql->lowest_slack = UINT_MAX;
+        } else if (inprogress && prev_inprogress && !all_prev_completed) {
+                /*
+                 * Queue was not starved, check if the limit can be decreased.
+                 * A decrease is only considered if the queue has been busy in
+                 * the whole interval (the check above).
+                 *
+                 * If there is slack, the amount of execess data queued above
+                 * the the amount needed to prevent starvation, the queue limit
+                 * can be decreased.  To avoid hysteresis we consider the
+                 * minimum amount of slack found over several iterations of the
+                 * completion routine.
+                 */
+                unsigned int slack, slack_last_objs;
+
+                /*
+                 * Slack is the maximum of
+                 *   - The queue limit plus previous over-limit minus twice
+                 *     the number of objects completed.  Note that two times
+                 *     number of completed bytes is a basis for an upper bound
+                 *     of the limit.
+                 *   - Portion of objects in the last queuing operation that
+                 *     was not part of non-zero previous over-limit.  That is
+                 *     "round down" by non-overlimit portion of the last
+                 *     queueing operation.
+                 */
+                slack = POSDIFF(limit + dql->prev_ovlimit,
+                    2 * (completed - dql->num_completed));
+                slack_last_objs = dql->prev_ovlimit ?
+                    POSDIFF(dql->prev_last_obj_cnt, dql->prev_ovlimit) : 0;
+
+                slack = max(slack, slack_last_objs);
+
+                if (slack < dql->lowest_slack)
+                        dql->lowest_slack = slack;
+
+                if (time_after(jiffies,
+                               dql->slack_start_time + dql->slack_hold_time)) {
+                        limit = POSDIFF(limit, dql->lowest_slack);
+                        dql->slack_start_time = jiffies;
+                        dql->lowest_slack = UINT_MAX;
+                }
+        }
+
+        /* Enforce bounds on limit */
+        limit = clamp(limit, dql->min_limit, dql->max_limit);
+
+        if (limit != dql->limit) {
+                dql->limit = limit;
+                ovlimit = 0;
+        }
+
+        dql->adj_limit = limit + completed;
+        dql->prev_ovlimit = ovlimit;
+        dql->prev_last_obj_cnt = dql->last_obj_cnt;
+        dql->num_completed = completed;
+        dql->prev_num_queued = num_queued;
+}
+EXPORT_SYMBOL(dql_completed);
+
+void dql_reset(struct dql *dql)
+{
+        /* Reset all dynamic values */
+        dql->limit = 0;
+        dql->num_queued = 0;
+        dql->num_completed = 0;
+        dql->last_obj_cnt = 0;
+        dql->prev_num_queued = 0;
+        dql->prev_last_obj_cnt = 0;
+        dql->prev_ovlimit = 0;
+        dql->lowest_slack = UINT_MAX;
+        dql->slack_start_time = jiffies;
+}
+EXPORT_SYMBOL(dql_reset);
+
+int dql_init(struct dql *dql, unsigned hold_time)
+{
+        dql->max_limit = DQL_MAX_LIMIT;
+        dql->min_limit = 0;
+        dql->slack_hold_time = hold_time;
+        dql_reset(dql);
+        return 0;
+}
+EXPORT_SYMBOL(dql_init);
diff --git a/lib/fault-inject.c b/lib/fault-inject.c
index f193b7796449..f7210ad6cffd 100644
--- a/lib/fault-inject.c
+++ b/lib/fault-inject.c
@@ -5,7 +5,7 @@
 #include <linux/stat.h>
 #include <linux/types.h>
 #include <linux/fs.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/interrupt.h>
 #include <linux/stacktrace.h>
 #include <linux/fault-inject.h>
@@ -14,7 +14,7 @@
  * setup_fault_attr() is a helper function for various __setup handlers, so it
  * returns 0 on error, because that is what __setup handlers do.
  */
-int __init setup_fault_attr(struct fault_attr *attr, char *str)
+int setup_fault_attr(struct fault_attr *attr, char *str)
 {
         unsigned long probability;
         unsigned long interval;
@@ -36,6 +36,7 @@ int __init setup_fault_attr(struct fault_attr *attr, char *str)
 
         return 1;
 }
+EXPORT_SYMBOL_GPL(setup_fault_attr);
 
 static void fail_dump(struct fault_attr *attr)
 {
@@ -100,6 +101,10 @@ static inline bool fail_stacktrace(struct fault_attr *attr)
 
 bool should_fail(struct fault_attr *attr, ssize_t size)
 {
+        /* No need to check any other properties if the probability is 0 */
+        if (attr->probability == 0)
+                return false;
+
         if (attr->task_filter && !fail_task(attr, current))
                 return false;
 
@@ -130,6 +135,7 @@ bool should_fail(struct fault_attr *attr, ssize_t size)
 
         return true;
 }
+EXPORT_SYMBOL_GPL(should_fail);
 
 #ifdef CONFIG_FAULT_INJECTION_DEBUG_FS
 
@@ -147,7 +153,7 @@ static int debugfs_ul_get(void *data, u64 *val)
 
 DEFINE_SIMPLE_ATTRIBUTE(fops_ul, debugfs_ul_get, debugfs_ul_set, "%llu\n");
 
-static struct dentry *debugfs_create_ul(const char *name, mode_t mode,
+static struct dentry *debugfs_create_ul(const char *name, umode_t mode,
                                 struct dentry *parent, unsigned long *value)
 {
         return debugfs_create_file(name, mode, parent, value, &fops_ul);
@@ -167,7 +173,7 @@ DEFINE_SIMPLE_ATTRIBUTE(fops_stacktrace_depth, debugfs_ul_get,
                         debugfs_stacktrace_depth_set, "%llu\n");
 
 static struct dentry *debugfs_create_stacktrace_depth(
-        const char *name, mode_t mode,
+        const char *name, umode_t mode,
         struct dentry *parent, unsigned long *value)
 {
         return debugfs_create_file(name, mode, parent, value,
@@ -191,7 +197,7 @@ static int debugfs_atomic_t_get(void *data, u64 *val)
 DEFINE_SIMPLE_ATTRIBUTE(fops_atomic_t, debugfs_atomic_t_get,
                         debugfs_atomic_t_set, "%lld\n");
 
-static struct dentry *debugfs_create_atomic_t(const char *name, mode_t mode,
+static struct dentry *debugfs_create_atomic_t(const char *name, umode_t mode,
                                 struct dentry *parent, atomic_t *value)
 {
         return debugfs_create_file(name, mode, parent, value, &fops_atomic_t);
@@ -200,7 +206,7 @@ static struct dentry *debugfs_create_atomic_t(const char *name, mode_t mode,
 struct dentry *fault_create_debugfs_attr(const char *name,
                         struct dentry *parent, struct fault_attr *attr)
 {
-        mode_t mode = S_IFREG | S_IRUSR | S_IWUSR;
+        umode_t mode = S_IFREG | S_IRUSR | S_IWUSR;
         struct dentry *dir;
 
         dir = debugfs_create_dir(name, parent);
@@ -243,5 +249,6 @@ fail:
 
         return ERR_PTR(-ENOMEM);
 }
+EXPORT_SYMBOL_GPL(fault_create_debugfs_attr);
 
 #endif /* CONFIG_FAULT_INJECTION_DEBUG_FS */
diff --git a/lib/fdt.c b/lib/fdt.c
new file mode 100644
index 000000000000..97f20069fc37
--- /dev/null
+++ b/lib/fdt.c
@@ -0,0 +1,2 @@
+#include <linux/libfdt_env.h>
+#include "../scripts/dtc/libfdt/fdt.c"
diff --git a/lib/fdt_ro.c b/lib/fdt_ro.c
new file mode 100644
index 000000000000..f73c04ea7be4
--- /dev/null
+++ b/lib/fdt_ro.c
@@ -0,0 +1,2 @@
+#include <linux/libfdt_env.h>
+#include "../scripts/dtc/libfdt/fdt_ro.c"
diff --git a/lib/fdt_rw.c b/lib/fdt_rw.c
new file mode 100644
index 000000000000..0c1f0f4a4b13
--- /dev/null
+++ b/lib/fdt_rw.c
@@ -0,0 +1,2 @@
+#include <linux/libfdt_env.h>
+#include "../scripts/dtc/libfdt/fdt_rw.c"
diff --git a/lib/fdt_strerror.c b/lib/fdt_strerror.c
new file mode 100644
index 000000000000..8713e3ff4707
--- /dev/null
+++ b/lib/fdt_strerror.c
@@ -0,0 +1,2 @@
+#include <linux/libfdt_env.h>
+#include "../scripts/dtc/libfdt/fdt_strerror.c"
diff --git a/lib/fdt_sw.c b/lib/fdt_sw.c
new file mode 100644
index 000000000000..9ac7e50c76ce
--- /dev/null
+++ b/lib/fdt_sw.c
@@ -0,0 +1,2 @@
+#include <linux/libfdt_env.h>
+#include "../scripts/dtc/libfdt/fdt_sw.c"
diff --git a/lib/fdt_wip.c b/lib/fdt_wip.c
new file mode 100644
index 000000000000..45b3fc3d3ba1
--- /dev/null
+++ b/lib/fdt_wip.c
@@ -0,0 +1,2 @@
+#include <linux/libfdt_env.h>
+#include "../scripts/dtc/libfdt/fdt_wip.c"
diff --git a/lib/find_last_bit.c b/lib/find_last_bit.c
index d903959ad695..91ca09fbf6f9 100644
--- a/lib/find_last_bit.c
+++ b/lib/find_last_bit.c
@@ -11,7 +11,7 @@
  */
 
 #include <linux/bitops.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <asm/types.h>
 #include <asm/byteorder.h>
 
diff --git a/lib/find_next_bit.c b/lib/find_next_bit.c
index 4bd75a73ba00..0cbfc0b4398f 100644
--- a/lib/find_next_bit.c
+++ b/lib/find_next_bit.c
@@ -10,7 +10,7 @@
  */
 
 #include <linux/bitops.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <asm/types.h>
 #include <asm/byteorder.h>
 
diff --git a/lib/flex_array.c b/lib/flex_array.c
index 9b8b89458c4c..6948a6692fc4 100644
--- a/lib/flex_array.c
+++ b/lib/flex_array.c
@@ -23,7 +23,7 @@
 #include <linux/flex_array.h>
 #include <linux/slab.h>
 #include <linux/stddef.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/reciprocal_div.h>
 
 struct flex_array_part {
diff --git a/lib/flex_proportions.c b/lib/flex_proportions.c
new file mode 100644
index 000000000000..ebf3bac460b0
--- /dev/null
+++ b/lib/flex_proportions.c
@@ -0,0 +1,272 @@
+/*
+ *  Floating proportions with flexible aging period
+ *
+ *   Copyright (C) 2011, SUSE, Jan Kara <jack@suse.cz>
+ *
+ * The goal of this code is: Given different types of event, measure proportion
+ * of each type of event over time. The proportions are measured with
+ * exponentially decaying history to give smooth transitions. A formula
+ * expressing proportion of event of type 'j' is:
+ *
+ *   p_{j} = (\Sum_{i>=0} x_{i,j}/2^{i+1})/(\Sum_{i>=0} x_i/2^{i+1})
+ *
+ * Where x_{i,j} is j's number of events in i-th last time period and x_i is
+ * total number of events in i-th last time period.
+ *
+ * Note that p_{j}'s are normalised, i.e.
+ *
+ *   \Sum_{j} p_{j} = 1,
+ *
+ * This formula can be straightforwardly computed by maintaing denominator
+ * (let's call it 'd') and for each event type its numerator (let's call it
+ * 'n_j'). When an event of type 'j' happens, we simply need to do:
+ *   n_j++; d++;
+ *
+ * When a new period is declared, we could do:
+ *   d /= 2
+ *   for each j
+ *     n_j /= 2
+ *
+ * To avoid iteration over all event types, we instead shift numerator of event
+ * j lazily when someone asks for a proportion of event j or when event j
+ * occurs. This can bit trivially implemented by remembering last period in
+ * which something happened with proportion of type j.
+ */
+#include <linux/flex_proportions.h>
+
+int fprop_global_init(struct fprop_global *p)
+{
+        int err;
+
+        p->period = 0;
+        /* Use 1 to avoid dealing with periods with 0 events... */
+        err = percpu_counter_init(&p->events, 1);
+        if (err)
+                return err;
+        seqcount_init(&p->sequence);
+        return 0;
+}
+
+void fprop_global_destroy(struct fprop_global *p)
+{
+        percpu_counter_destroy(&p->events);
+}
+
+/*
+ * Declare @periods new periods. It is upto the caller to make sure period
+ * transitions cannot happen in parallel.
+ *
+ * The function returns true if the proportions are still defined and false
+ * if aging zeroed out all events. This can be used to detect whether declaring
+ * further periods has any effect.
+ */
+bool fprop_new_period(struct fprop_global *p, int periods)
+{
+        s64 events;
+        unsigned long flags;
+
+        local_irq_save(flags);
+        events = percpu_counter_sum(&p->events);
+        /*
+         * Don't do anything if there are no events.
+         */
+        if (events <= 1) {
+                local_irq_restore(flags);
+                return false;
+        }
+        write_seqcount_begin(&p->sequence);
+        if (periods < 64)
+                events -= events >> periods;
+        /* Use addition to avoid losing events happening between sum and set */
+        percpu_counter_add(&p->events, -events);
+        p->period += periods;
+        write_seqcount_end(&p->sequence);
+        local_irq_restore(flags);
+
+        return true;
+}
+
+/*
+ * ---- SINGLE ----
+ */
+
+int fprop_local_init_single(struct fprop_local_single *pl)
+{
+        pl->events = 0;
+        pl->period = 0;
+        raw_spin_lock_init(&pl->lock);
+        return 0;
+}
+
+void fprop_local_destroy_single(struct fprop_local_single *pl)
+{
+}
+
+static void fprop_reflect_period_single(struct fprop_global *p,
+                                        struct fprop_local_single *pl)
+{
+        unsigned int period = p->period;
+        unsigned long flags;
+
+        /* Fast path - period didn't change */
+        if (pl->period == period)
+                return;
+        raw_spin_lock_irqsave(&pl->lock, flags);
+        /* Someone updated pl->period while we were spinning? */
+        if (pl->period >= period) {
+                raw_spin_unlock_irqrestore(&pl->lock, flags);
+                return;
+        }
+        /* Aging zeroed our fraction? */
+        if (period - pl->period < BITS_PER_LONG)
+                pl->events >>= period - pl->period;
+        else
+                pl->events = 0;
+        pl->period = period;
+        raw_spin_unlock_irqrestore(&pl->lock, flags);
+}
+
+/* Event of type pl happened */
+void __fprop_inc_single(struct fprop_global *p, struct fprop_local_single *pl)
+{
+        fprop_reflect_period_single(p, pl);
+        pl->events++;
+        percpu_counter_add(&p->events, 1);
+}
+
+/* Return fraction of events of type pl */
+void fprop_fraction_single(struct fprop_global *p,
+                           struct fprop_local_single *pl,
+                           unsigned long *numerator, unsigned long *denominator)
+{
+        unsigned int seq;
+        s64 num, den;
+
+        do {
+                seq = read_seqcount_begin(&p->sequence);
+                fprop_reflect_period_single(p, pl);
+                num = pl->events;
+                den = percpu_counter_read_positive(&p->events);
+        } while (read_seqcount_retry(&p->sequence, seq));
+
+        /*
+         * Make fraction <= 1 and denominator > 0 even in presence of percpu
+         * counter errors
+         */
+        if (den <= num) {
+                if (num)
+                        den = num;
+                else
+                        den = 1;
+        }
+        *denominator = den;
+        *numerator = num;
+}
+
+/*
+ * ---- PERCPU ----
+ */
+#define PROP_BATCH (8*(1+ilog2(nr_cpu_ids)))
+
+int fprop_local_init_percpu(struct fprop_local_percpu *pl)
+{
+        int err;
+
+        err = percpu_counter_init(&pl->events, 0);
+        if (err)
+                return err;
+        pl->period = 0;
+        raw_spin_lock_init(&pl->lock);
+        return 0;
+}
+
+void fprop_local_destroy_percpu(struct fprop_local_percpu *pl)
+{
+        percpu_counter_destroy(&pl->events);
+}
+
+static void fprop_reflect_period_percpu(struct fprop_global *p,
+                                        struct fprop_local_percpu *pl)
+{
+        unsigned int period = p->period;
+        unsigned long flags;
+
+        /* Fast path - period didn't change */
+        if (pl->period == period)
+                return;
+        raw_spin_lock_irqsave(&pl->lock, flags);
+        /* Someone updated pl->period while we were spinning? */
+        if (pl->period >= period) {
+                raw_spin_unlock_irqrestore(&pl->lock, flags);
+                return;
+        }
+        /* Aging zeroed our fraction? */
+        if (period - pl->period < BITS_PER_LONG) {
+                s64 val = percpu_counter_read(&pl->events);
+
+                if (val < (nr_cpu_ids * PROP_BATCH))
+                        val = percpu_counter_sum(&pl->events);
+
+                __percpu_counter_add(&pl->events,
+                        -val + (val >> (period-pl->period)), PROP_BATCH);
+        } else
+                percpu_counter_set(&pl->events, 0);
+        pl->period = period;
+        raw_spin_unlock_irqrestore(&pl->lock, flags);
+}
+
+/* Event of type pl happened */
+void __fprop_inc_percpu(struct fprop_global *p, struct fprop_local_percpu *pl)
+{
+        fprop_reflect_period_percpu(p, pl);
+        __percpu_counter_add(&pl->events, 1, PROP_BATCH);
+        percpu_counter_add(&p->events, 1);
+}
+
+void fprop_fraction_percpu(struct fprop_global *p,
+                           struct fprop_local_percpu *pl,
+                           unsigned long *numerator, unsigned long *denominator)
+{
+        unsigned int seq;
+        s64 num, den;
+
+        do {
+                seq = read_seqcount_begin(&p->sequence);
+                fprop_reflect_period_percpu(p, pl);
+                num = percpu_counter_read_positive(&pl->events);
+                den = percpu_counter_read_positive(&p->events);
+        } while (read_seqcount_retry(&p->sequence, seq));
+
+        /*
+         * Make fraction <= 1 and denominator > 0 even in presence of percpu
+         * counter errors
+         */
+        if (den <= num) {
+                if (num)
+                        den = num;
+                else
+                        den = 1;
+        }
+        *denominator = den;
+        *numerator = num;
+}
+
+/*
+ * Like __fprop_inc_percpu() except that event is counted only if the given
+ * type has fraction smaller than @max_frac/FPROP_FRAC_BASE
+ */
+void __fprop_inc_percpu_max(struct fprop_global *p,
+                            struct fprop_local_percpu *pl, int max_frac)
+{
+        if (unlikely(max_frac < FPROP_FRAC_BASE)) {
+                unsigned long numerator, denominator;
+
+                fprop_fraction_percpu(p, pl, &numerator, &denominator);
+                if (numerator >
+                    (((u64)denominator) * max_frac) >> FPROP_FRAC_SHIFT)
+                        return;
+        } else
+                fprop_reflect_period_percpu(p, pl);
+        __percpu_counter_add(&pl->events, 1, PROP_BATCH);
+        percpu_counter_add(&p->events, 1);
+}
diff --git a/lib/gcd.c b/lib/gcd.c
index f879033d9822..3657f129d7b8 100644
--- a/lib/gcd.c
+++ b/lib/gcd.c
@@ -1,6 +1,6 @@
 #include <linux/kernel.h>
 #include <linux/gcd.h>
-#include <linux/module.h>
+#include <linux/export.h>
 
 /* Greatest common divisor */
 unsigned long gcd(unsigned long a, unsigned long b)
@@ -9,6 +9,9 @@ unsigned long gcd(unsigned long a, unsigned long b)
 
         if (a < b)
                 swap(a, b);
+
+        if (!b)
+                return a;
         while ((r = a % b) != 0) {
                 a = b;
                 b = r;
diff --git a/lib/gen_crc32table.c b/lib/gen_crc32table.c
index 85d0e412a04f..71fcfcd96410 100644
--- a/lib/gen_crc32table.c
+++ b/lib/gen_crc32table.c
@@ -1,14 +1,29 @@
 #include <stdio.h>
+#include "../include/generated/autoconf.h"
 #include "crc32defs.h"
 #include <inttypes.h>
 
 #define ENTRIES_PER_LINE 4
 
-#define LE_TABLE_SIZE (1 << CRC_LE_BITS)
-#define BE_TABLE_SIZE (1 << CRC_BE_BITS)
+#if CRC_LE_BITS > 8
+# define LE_TABLE_ROWS (CRC_LE_BITS/8)
+# define LE_TABLE_SIZE 256
+#else
+# define LE_TABLE_ROWS 1
+# define LE_TABLE_SIZE (1 << CRC_LE_BITS)
+#endif
 
-static uint32_t crc32table_le[4][LE_TABLE_SIZE];
-static uint32_t crc32table_be[4][BE_TABLE_SIZE];
+#if CRC_BE_BITS > 8
+# define BE_TABLE_ROWS (CRC_BE_BITS/8)
+# define BE_TABLE_SIZE 256
+#else
+# define BE_TABLE_ROWS 1
+# define BE_TABLE_SIZE (1 << CRC_BE_BITS)
+#endif
+
+static uint32_t crc32table_le[LE_TABLE_ROWS][256];
+static uint32_t crc32table_be[BE_TABLE_ROWS][256];
+static uint32_t crc32ctable_le[LE_TABLE_ROWS][256];
 
 /**
  * crc32init_le() - allocate and initialize LE table data
@@ -17,27 +32,38 @@ static uint32_t crc32table_be[4][BE_TABLE_SIZE];
  * fact that crctable[i^j] = crctable[i] ^ crctable[j].
  *
  */
-static void crc32init_le(void)
+static void crc32init_le_generic(const uint32_t polynomial,
+                                 uint32_t (*tab)[256])
 {
         unsigned i, j;
         uint32_t crc = 1;
 
-        crc32table_le[0][0] = 0;
+        tab[0][0] = 0;
 
-        for (i = 1 << (CRC_LE_BITS - 1); i; i >>= 1) {
-                crc = (crc >> 1) ^ ((crc & 1) ? CRCPOLY_LE : 0);
+        for (i = LE_TABLE_SIZE >> 1; i; i >>= 1) {
+                crc = (crc >> 1) ^ ((crc & 1) ? polynomial : 0);
                 for (j = 0; j < LE_TABLE_SIZE; j += 2 * i)
-                        crc32table_le[0][i + j] = crc ^ crc32table_le[0][j];
+                        tab[0][i + j] = crc ^ tab[0][j];
         }
         for (i = 0; i < LE_TABLE_SIZE; i++) {
-                crc = crc32table_le[0][i];
-                for (j = 1; j < 4; j++) {
-                        crc = crc32table_le[0][crc & 0xff] ^ (crc >> 8);
-                        crc32table_le[j][i] = crc;
+                crc = tab[0][i];
+                for (j = 1; j < LE_TABLE_ROWS; j++) {
+                        crc = tab[0][crc & 0xff] ^ (crc >> 8);
+                        tab[j][i] = crc;
                 }
         }
 }
 
+static void crc32init_le(void)
+{
+        crc32init_le_generic(CRCPOLY_LE, crc32table_le);
+}
+
+static void crc32cinit_le(void)
+{
+        crc32init_le_generic(CRC32C_POLY_LE, crc32ctable_le);
+}
+
 /**
  * crc32init_be() - allocate and initialize BE table data
  */
@@ -55,18 +81,18 @@ static void crc32init_be(void)
         }
         for (i = 0; i < BE_TABLE_SIZE; i++) {
                 crc = crc32table_be[0][i];
-                for (j = 1; j < 4; j++) {
+                for (j = 1; j < BE_TABLE_ROWS; j++) {
                         crc = crc32table_be[0][(crc >> 24) & 0xff] ^ (crc << 8);
                         crc32table_be[j][i] = crc;
                 }
         }
 }
 
-static void output_table(uint32_t table[4][256], int len, char *trans)
+static void output_table(uint32_t (*table)[256], int rows, int len, char *trans)
 {
         int i, j;
 
-        for (j = 0 ; j < 4; j++) {
+        for (j = 0 ; j < rows; j++) {
                 printf("{");
                 for (i = 0; i < len - 1; i++) {
                         if (i % ENTRIES_PER_LINE == 0)
@@ -83,15 +109,30 @@ int main(int argc, char** argv)
 
         if (CRC_LE_BITS > 1) {
                 crc32init_le();
-                printf("static const u32 crc32table_le[4][256] = {");
-                output_table(crc32table_le, LE_TABLE_SIZE, "tole");
+                printf("static u32 __cacheline_aligned "
+                       "crc32table_le[%d][%d] = {",
+                       LE_TABLE_ROWS, LE_TABLE_SIZE);
+                output_table(crc32table_le, LE_TABLE_ROWS,
+                             LE_TABLE_SIZE, "tole");
                 printf("};\n");
         }
 
         if (CRC_BE_BITS > 1) {
                 crc32init_be();
-                printf("static const u32 crc32table_be[4][256] = {");
-                output_table(crc32table_be, BE_TABLE_SIZE, "tobe");
+                printf("static u32 __cacheline_aligned "
+                       "crc32table_be[%d][%d] = {",
+                       BE_TABLE_ROWS, BE_TABLE_SIZE);
+                output_table(crc32table_be, LE_TABLE_ROWS,
+                             BE_TABLE_SIZE, "tobe");
+                printf("};\n");
+        }
+        if (CRC_LE_BITS > 1) {
+                crc32cinit_le();
+                printf("static u32 __cacheline_aligned "
+                       "crc32ctable_le[%d][%d] = {",
+                       LE_TABLE_ROWS, LE_TABLE_SIZE);
+                output_table(crc32ctable_le, LE_TABLE_ROWS,
+                             LE_TABLE_SIZE, "tole");
                 printf("};\n");
         }
 
diff --git a/lib/genalloc.c b/lib/genalloc.c
index f352cc42f4f8..54920433705a 100644
--- a/lib/genalloc.c
+++ b/lib/genalloc.c
@@ -29,7 +29,7 @@
  */
 
 #include <linux/slab.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/bitmap.h>
 #include <linux/rculist.h>
 #include <linux/interrupt.h>
@@ -152,6 +152,8 @@ struct gen_pool *gen_pool_create(int min_alloc_order, int nid)
                 spin_lock_init(&pool->lock);
                 INIT_LIST_HEAD(&pool->chunks);
                 pool->min_alloc_order = min_alloc_order;
+                pool->algo = gen_pool_first_fit;
+                pool->data = NULL;
         }
         return pool;
 }
@@ -176,7 +178,7 @@ int gen_pool_add_virt(struct gen_pool *pool, unsigned long virt, phys_addr_t phy
         struct gen_pool_chunk *chunk;
         int nbits = size >> pool->min_alloc_order;
         int nbytes = sizeof(struct gen_pool_chunk) +
-                                (nbits + BITS_PER_BYTE - 1) / BITS_PER_BYTE;
+                                BITS_TO_LONGS(nbits) * sizeof(long);
 
         chunk = kmalloc_node(nbytes, GFP_KERNEL | __GFP_ZERO, nid);
         if (unlikely(chunk == NULL))
@@ -255,8 +257,9 @@ EXPORT_SYMBOL(gen_pool_destroy);
  * @size: number of bytes to allocate from the pool
  *
  * Allocate the requested number of bytes from the specified pool.
- * Uses a first-fit algorithm. Can not be used in NMI handler on
- * architectures without NMI-safe cmpxchg implementation.
+ * Uses the pool allocation function (with first-fit algorithm by default).
+ * Can not be used in NMI handler on architectures without
+ * NMI-safe cmpxchg implementation.
  */
 unsigned long gen_pool_alloc(struct gen_pool *pool, size_t size)
 {
@@ -280,8 +283,8 @@ unsigned long gen_pool_alloc(struct gen_pool *pool, size_t size)
 
                 end_bit = (chunk->end_addr - chunk->start_addr) >> order;
 retry:
-                start_bit = bitmap_find_next_zero_area(chunk->bits, end_bit,
-                                                       start_bit, nbits, 0);
+                start_bit = pool->algo(chunk->bits, end_bit, start_bit, nbits,
+                                pool->data);
                 if (start_bit >= end_bit)
                         continue;
                 remain = bitmap_set_ll(chunk->bits, start_bit, nbits);
@@ -400,3 +403,80 @@ size_t gen_pool_size(struct gen_pool *pool)
         return size;
 }
 EXPORT_SYMBOL_GPL(gen_pool_size);
+
+/**
+ * gen_pool_set_algo - set the allocation algorithm
+ * @pool: pool to change allocation algorithm
+ * @algo: custom algorithm function
+ * @data: additional data used by @algo
+ *
+ * Call @algo for each memory allocation in the pool.
+ * If @algo is NULL use gen_pool_first_fit as default
+ * memory allocation function.
+ */
+void gen_pool_set_algo(struct gen_pool *pool, genpool_algo_t algo, void *data)
+{
+        rcu_read_lock();
+
+        pool->algo = algo;
+        if (!pool->algo)
+                pool->algo = gen_pool_first_fit;
+
+        pool->data = data;
+
+        rcu_read_unlock();
+}
+EXPORT_SYMBOL(gen_pool_set_algo);
+
+/**
+ * gen_pool_first_fit - find the first available region
+ * of memory matching the size requirement (no alignment constraint)
+ * @map: The address to base the search on
+ * @size: The bitmap size in bits
+ * @start: The bitnumber to start searching at
+ * @nr: The number of zeroed bits we're looking for
+ * @data: additional data - unused
+ */
+unsigned long gen_pool_first_fit(unsigned long *map, unsigned long size,
+                unsigned long start, unsigned int nr, void *data)
+{
+        return bitmap_find_next_zero_area(map, size, start, nr, 0);
+}
+EXPORT_SYMBOL(gen_pool_first_fit);
+
+/**
+ * gen_pool_best_fit - find the best fitting region of memory
+ * macthing the size requirement (no alignment constraint)
+ * @map: The address to base the search on
+ * @size: The bitmap size in bits
+ * @start: The bitnumber to start searching at
+ * @nr: The number of zeroed bits we're looking for
+ * @data: additional data - unused
+ *
+ * Iterate over the bitmap to find the smallest free region
+ * which we can allocate the memory.
+ */
+unsigned long gen_pool_best_fit(unsigned long *map, unsigned long size,
+                unsigned long start, unsigned int nr, void *data)
+{
+        unsigned long start_bit = size;
+        unsigned long len = size + 1;
+        unsigned long index;
+
+        index = bitmap_find_next_zero_area(map, size, start, nr, 0);
+
+        while (index < size) {
+                int next_bit = find_next_bit(map, size, index + nr);
+                if ((next_bit - index) < len) {
+                        len = next_bit - index;
+                        start_bit = index;
+                        if (len == nr)
+                                return start_bit;
+                }
+                index = bitmap_find_next_zero_area(map, size,
+                                                   next_bit + 1, nr, 0);
+        }
+
+        return start_bit;
+}
+EXPORT_SYMBOL(gen_pool_best_fit);
diff --git a/lib/halfmd4.c b/lib/halfmd4.c
index e11db26f8ae5..66d0ee8b7776 100644
--- a/lib/halfmd4.c
+++ b/lib/halfmd4.c
@@ -1,5 +1,5 @@
 #include <linux/kernel.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/cryptohash.h>
 
 /* F, G and H are basic MD4 functions: selection, majority, parity */
diff --git a/lib/hexdump.c b/lib/hexdump.c
index f5fe6ba7a3ab..6540d657dca4 100644
--- a/lib/hexdump.c
+++ b/lib/hexdump.c
@@ -10,7 +10,7 @@
 #include <linux/types.h>
 #include <linux/ctype.h>
 #include <linux/kernel.h>
-#include <linux/module.h>
+#include <linux/export.h>
 
 const char hex_asc[] = "0123456789abcdef";
 EXPORT_SYMBOL(hex_asc);
@@ -38,14 +38,21 @@ EXPORT_SYMBOL(hex_to_bin);
  * @dst: binary result
  * @src: ascii hexadecimal string
  * @count: result length
+ *
+ * Return 0 on success, -1 in case of bad input.
  */
-void hex2bin(u8 *dst, const char *src, size_t count)
+int hex2bin(u8 *dst, const char *src, size_t count)
 {
         while (count--) {
-                *dst = hex_to_bin(*src++) << 4;
-                *dst += hex_to_bin(*src++);
-                dst++;
+                int hi = hex_to_bin(*src++);
+                int lo = hex_to_bin(*src++);
+
+                if ((hi < 0) || (lo < 0))
+                        return -1;
+
+                *dst++ = (hi << 4) | lo;
         }
+        return 0;
 }
 EXPORT_SYMBOL(hex2bin);
 
diff --git a/lib/hweight.c b/lib/hweight.c
index 3c79d50814cf..b7d81ba143d1 100644
--- a/lib/hweight.c
+++ b/lib/hweight.c
@@ -1,4 +1,4 @@
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/bitops.h>
 #include <asm/types.h>
 
diff --git a/lib/idr.c b/lib/idr.c
index db040ce3fa73..648239079dd2 100644
--- a/lib/idr.c
+++ b/lib/idr.c
@@ -20,7 +20,7 @@
  * that id to this code and it returns your pointer.
 
  * You can release ids at any time. When all ids are released, most of
- * the memory is returned (we keep IDR_FREE_MAX) in a local pool so we
+ * the memory is returned (we keep MAX_IDR_FREE) in a local pool so we
  * don't need to go to the memory "store" during an id allocate, just
  * so you don't need to be too concerned about locking and conflicts
  * with the slab allocator.
@@ -29,7 +29,7 @@
 #ifndef TEST                        // to test in user space...
 #include <linux/slab.h>
 #include <linux/init.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #endif
 #include <linux/err.h>
 #include <linux/string.h>
@@ -122,7 +122,7 @@ static void idr_mark_full(struct idr_layer **pa, int id)
  */
 int idr_pre_get(struct idr *idp, gfp_t gfp_mask)
 {
-        while (idp->id_free_cnt < IDR_FREE_MAX) {
+        while (idp->id_free_cnt < MAX_IDR_FREE) {
                 struct idr_layer *new;
                 new = kmem_cache_zalloc(idr_layer_cache, gfp_mask);
                 if (new == NULL)
@@ -179,7 +179,7 @@ static int sub_alloc(struct idr *idp, int *starting_id, struct idr_layer **pa)
                         sh = IDR_BITS*l;
                         id = ((id >> sh) ^ n ^ m) << sh;
                 }
-                if ((id >= MAX_ID_BIT) || (id < 0))
+                if ((id >= MAX_IDR_BIT) || (id < 0))
                         return IDR_NOMORE_SPACE;
                 if (l == 0)
                         break;
@@ -223,7 +223,7 @@ build_up:
          * Add a new layer to the top of the tree if the requested
          * id is larger than the currently allocated space.
          */
-        while ((layers < (MAX_LEVEL - 1)) && (id >= (1 << (layers*IDR_BITS)))) {
+        while ((layers < (MAX_IDR_LEVEL - 1)) && (id >= (1 << (layers*IDR_BITS)))) {
                 layers++;
                 if (!p->count) {
                         /* special case: if the tree is currently empty,
@@ -265,7 +265,7 @@ build_up:
 
 static int idr_get_new_above_int(struct idr *idp, void *ptr, int starting_id)
 {
-        struct idr_layer *pa[MAX_LEVEL];
+        struct idr_layer *pa[MAX_IDR_LEVEL];
         int id;
 
         id = idr_get_empty_slot(idp, starting_id, pa);
@@ -357,7 +357,7 @@ static void idr_remove_warning(int id)
 static void sub_remove(struct idr *idp, int shift, int id)
 {
         struct idr_layer *p = idp->top;
-        struct idr_layer **pa[MAX_LEVEL];
+        struct idr_layer **pa[MAX_IDR_LEVEL];
         struct idr_layer ***paa = &pa[0];
         struct idr_layer *to_free;
         int n;
@@ -402,7 +402,7 @@ void idr_remove(struct idr *idp, int id)
         struct idr_layer *to_free;
 
         /* Mask off upper bits we don't use for the search. */
-        id &= MAX_ID_MASK;
+        id &= MAX_IDR_MASK;
 
         sub_remove(idp, (idp->layers - 1) * IDR_BITS, id);
         if (idp->top && idp->top->count == 1 && (idp->layers > 1) &&
@@ -420,7 +420,7 @@ void idr_remove(struct idr *idp, int id)
                 to_free->bitmap = to_free->count = 0;
                 free_layer(to_free);
         }
-        while (idp->id_free_cnt >= IDR_FREE_MAX) {
+        while (idp->id_free_cnt >= MAX_IDR_FREE) {
                 p = get_from_free_list(idp);
                 /*
                  * Note: we don't call the rcu callback here, since the only
@@ -451,7 +451,7 @@ void idr_remove_all(struct idr *idp)
         int n, id, max;
         int bt_mask;
         struct idr_layer *p;
-        struct idr_layer *pa[MAX_LEVEL];
+        struct idr_layer *pa[MAX_IDR_LEVEL];
         struct idr_layer **paa = &pa[0];
 
         n = idp->layers * IDR_BITS;
@@ -517,7 +517,7 @@ void *idr_find(struct idr *idp, int id)
         n = (p->layer+1) * IDR_BITS;
 
         /* Mask off upper bits we don't use for the search. */
-        id &= MAX_ID_MASK;
+        id &= MAX_IDR_MASK;
 
         if (id >= (1 << n))
                 return NULL;
@@ -555,7 +555,7 @@ int idr_for_each(struct idr *idp,
 {
         int n, id, max, error = 0;
         struct idr_layer *p;
-        struct idr_layer *pa[MAX_LEVEL];
+        struct idr_layer *pa[MAX_IDR_LEVEL];
         struct idr_layer **paa = &pa[0];
 
         n = idp->layers * IDR_BITS;
@@ -595,21 +595,23 @@ EXPORT_SYMBOL(idr_for_each);
  * Returns pointer to registered object with id, which is next number to
  * given id. After being looked up, *@nextidp will be updated for the next
  * iteration.
+ *
+ * This function can be called under rcu_read_lock(), given that the leaf
+ * pointers lifetimes are correctly managed.
  */
-
 void *idr_get_next(struct idr *idp, int *nextidp)
 {
-        struct idr_layer *p, *pa[MAX_LEVEL];
+        struct idr_layer *p, *pa[MAX_IDR_LEVEL];
         struct idr_layer **paa = &pa[0];
         int id = *nextidp;
         int n, max;
 
         /* find first ent */
-        n = idp->layers * IDR_BITS;
-        max = 1 << n;
         p = rcu_dereference_raw(idp->top);
         if (!p)
                 return NULL;
+        n = (p->layer + 1) * IDR_BITS;
+        max = 1 << n;
 
         while (id < max) {
                 while (n > 0 && p) {
@@ -657,7 +659,7 @@ void *idr_replace(struct idr *idp, void *ptr, int id)
 
         n = (p->layer+1) * IDR_BITS;
 
-        id &= MAX_ID_MASK;
+        id &= MAX_IDR_MASK;
 
         if (id >= (1 << n))
                 return ERR_PTR(-EINVAL);
@@ -767,8 +769,8 @@ EXPORT_SYMBOL(ida_pre_get);
  * @starting_id: id to start search at
  * @p_id:       pointer to the allocated handle
  *
- * Allocate new ID above or equal to @ida.  It should be called with
- * any required locks.
+ * Allocate new ID above or equal to @starting_id.  It should be called
+ * with any required locks.
  *
  * If memory is required, it will return %-EAGAIN, you should unlock
  * and go back to the ida_pre_get() call.  If the ida is full, it will
@@ -778,7 +780,7 @@ EXPORT_SYMBOL(ida_pre_get);
  */
 int ida_get_new_above(struct ida *ida, int starting_id, int *p_id)
 {
-        struct idr_layer *pa[MAX_LEVEL];
+        struct idr_layer *pa[MAX_IDR_LEVEL];
         struct ida_bitmap *bitmap;
         unsigned long flags;
         int idr_id = starting_id / IDA_BITMAP_BITS;
@@ -791,7 +793,7 @@ int ida_get_new_above(struct ida *ida, int starting_id, int *p_id)
         if (t < 0)
                 return _idr_rc_to_errno(t);
 
-        if (t * IDA_BITMAP_BITS >= MAX_ID_BIT)
+        if (t * IDA_BITMAP_BITS >= MAX_IDR_BIT)
                 return -ENOSPC;
 
         if (t != idr_id)
@@ -825,7 +827,7 @@ int ida_get_new_above(struct ida *ida, int starting_id, int *p_id)
         }
 
         id = idr_id * IDA_BITMAP_BITS + t;
-        if (id >= MAX_ID_BIT)
+        if (id >= MAX_IDR_BIT)
                 return -ENOSPC;
 
         __set_bit(t, bitmap->bitmap);
@@ -860,7 +862,7 @@ EXPORT_SYMBOL(ida_get_new_above);
  * and go back to the idr_pre_get() call.  If the idr is full, it will
  * return %-ENOSPC.
  *
- * @id returns a value in the range %0 ... %0x7fffffff.
+ * @p_id returns a value in the range %0 ... %0x7fffffff.
  */
 int ida_get_new(struct ida *ida, int *p_id)
 {
@@ -944,6 +946,7 @@ int ida_simple_get(struct ida *ida, unsigned int start, unsigned int end,
 {
         int ret, id;
         unsigned int max;
+        unsigned long flags;
 
         BUG_ON((int)start < 0);
         BUG_ON((int)end < 0);
@@ -959,7 +962,7 @@ again:
         if (!ida_pre_get(ida, gfp_mask))
                 return -ENOMEM;
 
-        spin_lock(&simple_ida_lock);
+        spin_lock_irqsave(&simple_ida_lock, flags);
         ret = ida_get_new_above(ida, start, &id);
         if (!ret) {
                 if (id > max) {
@@ -969,7 +972,7 @@ again:
                         ret = id;
                 }
         }
-        spin_unlock(&simple_ida_lock);
+        spin_unlock_irqrestore(&simple_ida_lock, flags);
 
         if (unlikely(ret == -EAGAIN))
                 goto again;
@@ -985,10 +988,12 @@ EXPORT_SYMBOL(ida_simple_get);
  */
 void ida_simple_remove(struct ida *ida, unsigned int id)
 {
+        unsigned long flags;
+
         BUG_ON((int)id < 0);
-        spin_lock(&simple_ida_lock);
+        spin_lock_irqsave(&simple_ida_lock, flags);
         ida_remove(ida, id);
-        spin_unlock(&simple_ida_lock);
+        spin_unlock_irqrestore(&simple_ida_lock, flags);
 }
 EXPORT_SYMBOL(ida_simple_remove);
 
diff --git a/lib/int_sqrt.c b/lib/int_sqrt.c
index fd355a99327c..fc2eeb7cb2ea 100644
--- a/lib/int_sqrt.c
+++ b/lib/int_sqrt.c
@@ -1,6 +1,6 @@
 
 #include <linux/kernel.h>
-#include <linux/module.h>
+#include <linux/export.h>
 
 /**
  * int_sqrt - rough approximation to sqrt
diff --git a/lib/interval_tree.c b/lib/interval_tree.c
new file mode 100644
index 000000000000..e6eb406f2d65
--- /dev/null
+++ b/lib/interval_tree.c
@@ -0,0 +1,10 @@
+#include <linux/init.h>
+#include <linux/interval_tree.h>
+#include <linux/interval_tree_generic.h>
+
+#define START(node) ((node)->start)
+#define LAST(node)  ((node)->last)
+
+INTERVAL_TREE_DEFINE(struct interval_tree_node, rb,
+                     unsigned long, __subtree_last,
+                     START, LAST,, interval_tree)
diff --git a/lib/interval_tree_test_main.c b/lib/interval_tree_test_main.c
new file mode 100644
index 000000000000..b25903987f7a
--- /dev/null
+++ b/lib/interval_tree_test_main.c
@@ -0,0 +1,105 @@
+#include <linux/module.h>
+#include <linux/interval_tree.h>
+#include <linux/random.h>
+#include <asm/timex.h>
+
+#define NODES        100
+#define PERF_LOOPS   100000
+#define SEARCHES     100
+#define SEARCH_LOOPS 10000
+
+static struct rb_root root = RB_ROOT;
+static struct interval_tree_node nodes[NODES];
+static u32 queries[SEARCHES];
+
+static struct rnd_state rnd;
+
+static inline unsigned long
+search(unsigned long query, struct rb_root *root)
+{
+        struct interval_tree_node *node;
+        unsigned long results = 0;
+
+        for (node = interval_tree_iter_first(root, query, query); node;
+             node = interval_tree_iter_next(node, query, query))
+                results++;
+        return results;
+}
+
+static void init(void)
+{
+        int i;
+        for (i = 0; i < NODES; i++) {
+                u32 a = prandom32(&rnd), b = prandom32(&rnd);
+                if (a <= b) {
+                        nodes[i].start = a;
+                        nodes[i].last = b;
+                } else {
+                        nodes[i].start = b;
+                        nodes[i].last = a;
+                }
+        }
+        for (i = 0; i < SEARCHES; i++)
+                queries[i] = prandom32(&rnd);
+}
+
+static int interval_tree_test_init(void)
+{
+        int i, j;
+        unsigned long results;
+        cycles_t time1, time2, time;
+
+        printk(KERN_ALERT "interval tree insert/remove");
+
+        prandom32_seed(&rnd, 3141592653589793238ULL);
+        init();
+
+        time1 = get_cycles();
+
+        for (i = 0; i < PERF_LOOPS; i++) {
+                for (j = 0; j < NODES; j++)
+                        interval_tree_insert(nodes + j, &root);
+                for (j = 0; j < NODES; j++)
+                        interval_tree_remove(nodes + j, &root);
+        }
+
+        time2 = get_cycles();
+        time = time2 - time1;
+
+        time = div_u64(time, PERF_LOOPS);
+        printk(" -> %llu cycles\n", (unsigned long long)time);
+
+        printk(KERN_ALERT "interval tree search");
+
+        for (j = 0; j < NODES; j++)
+                interval_tree_insert(nodes + j, &root);
+
+        time1 = get_cycles();
+
+        results = 0;
+        for (i = 0; i < SEARCH_LOOPS; i++)
+                for (j = 0; j < SEARCHES; j++)
+                        results += search(queries[j], &root);
+
+        time2 = get_cycles();
+        time = time2 - time1;
+
+        time = div_u64(time, SEARCH_LOOPS);
+        results = div_u64(results, SEARCH_LOOPS);
+        printk(" -> %llu cycles (%lu results)\n",
+               (unsigned long long)time, results);
+
+        return -EAGAIN; /* Fail will directly unload the module */
+}
+
+static void interval_tree_test_exit(void)
+{
+        printk(KERN_ALERT "test exit\n");
+}
+
+module_init(interval_tree_test_init)
+module_exit(interval_tree_test_exit)
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Michel Lespinasse");
+MODULE_DESCRIPTION("Interval Tree test");
diff --git a/lib/iomap.c b/lib/iomap.c
index 5dbcb4b2d864..2c08f36862eb 100644
--- a/lib/iomap.c
+++ b/lib/iomap.c
@@ -6,7 +6,7 @@
 #include <linux/pci.h>
 #include <linux/io.h>
 
-#include <linux/module.h>
+#include <linux/export.h>
 
 /*
  * Read/write from/to an (offsettable) iomem cookie. It might be a PIO
@@ -242,45 +242,11 @@ EXPORT_SYMBOL(ioport_unmap);
 #endif /* CONFIG_HAS_IOPORT */
 
 #ifdef CONFIG_PCI
-/**
- * pci_iomap - create a virtual mapping cookie for a PCI BAR
- * @dev: PCI device that owns the BAR
- * @bar: BAR number
- * @maxlen: length of the memory to map
- *
- * Using this function you will get a __iomem address to your device BAR.
- * You can access it using ioread*() and iowrite*(). These functions hide
- * the details if this is a MMIO or PIO address space and will just do what
- * you expect from them in the correct way.
- *
- * @maxlen specifies the maximum length to map. If you want to get access to
- * the complete BAR without checking for its length first, pass %0 here.
- * */
-void __iomem *pci_iomap(struct pci_dev *dev, int bar, unsigned long maxlen)
-{
-        resource_size_t start = pci_resource_start(dev, bar);
-        resource_size_t len = pci_resource_len(dev, bar);
-        unsigned long flags = pci_resource_flags(dev, bar);
-
-        if (!len || !start)
-                return NULL;
-        if (maxlen && len > maxlen)
-                len = maxlen;
-        if (flags & IORESOURCE_IO)
-                return ioport_map(start, len);
-        if (flags & IORESOURCE_MEM) {
-                if (flags & IORESOURCE_CACHEABLE)
-                        return ioremap(start, len);
-                return ioremap_nocache(start, len);
-        }
-        /* What? */
-        return NULL;
-}
-
+/* Hide the details if this is a MMIO or PIO address space and just do what
+ * you expect in the correct way. */
 void pci_iounmap(struct pci_dev *dev, void __iomem * addr)
 {
         IO_COND(addr, /* nothing */, iounmap(addr));
 }
-EXPORT_SYMBOL(pci_iomap);
 EXPORT_SYMBOL(pci_iounmap);
 #endif /* CONFIG_PCI */
diff --git a/lib/iomap_copy.c b/lib/iomap_copy.c
index 864fc5ea398c..4527e751b5e0 100644
--- a/lib/iomap_copy.c
+++ b/lib/iomap_copy.c
@@ -15,7 +15,7 @@
  * Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301, USA.
  */
 
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/io.h>
 
 /**
diff --git a/lib/iommu-helper.c b/lib/iommu-helper.c
index da053313ee5c..c27e269210c4 100644
--- a/lib/iommu-helper.c
+++ b/lib/iommu-helper.c
@@ -2,8 +2,9 @@
  * IOMMU helper functions for the free area management
  */
 
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/bitmap.h>
+#include <linux/bug.h>
 
 int iommu_is_span_boundary(unsigned int index, unsigned int nr,
                            unsigned long shift,
diff --git a/lib/ioremap.c b/lib/ioremap.c
index da4e2ad74b68..0c9216c48762 100644
--- a/lib/ioremap.c
+++ b/lib/ioremap.c
@@ -9,7 +9,7 @@
 #include <linux/mm.h>
 #include <linux/sched.h>
 #include <linux/io.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <asm/cacheflush.h>
 #include <asm/pgtable.h>
 
diff --git a/lib/irq_regs.c b/lib/irq_regs.c
index 753880a5440c..9c0a1d70fbe8 100644
--- a/lib/irq_regs.c
+++ b/lib/irq_regs.c
@@ -8,7 +8,8 @@
  * as published by the Free Software Foundation; either version
  * 2 of the License, or (at your option) any later version.
  */
-#include <linux/module.h>
+#include <linux/export.h>
+#include <linux/percpu.h>
 #include <asm/irq_regs.h>
 
 #ifndef ARCH_HAS_OWN_IRQ_REGS
diff --git a/lib/jedec_ddr_data.c b/lib/jedec_ddr_data.c
new file mode 100644
index 000000000000..6d2cbf1d567f
--- /dev/null
+++ b/lib/jedec_ddr_data.c
@@ -0,0 +1,135 @@
+/*
+ * DDR addressing details and AC timing parameters from JEDEC specs
+ *
+ * Copyright (C) 2012 Texas Instruments, Inc.
+ *
+ * Aneesh V <aneesh@ti.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <memory/jedec_ddr.h>
+#include <linux/module.h>
+
+/* LPDDR2 addressing details from JESD209-2 section 2.4 */
+const struct lpddr2_addressing
+        lpddr2_jedec_addressing_table[NUM_DDR_ADDR_TABLE_ENTRIES] = {
+        {B4, T_REFI_15_6, T_RFC_90}, /* 64M */
+        {B4, T_REFI_15_6, T_RFC_90}, /* 128M */
+        {B4, T_REFI_7_8,  T_RFC_90}, /* 256M */
+        {B4, T_REFI_7_8,  T_RFC_90}, /* 512M */
+        {B8, T_REFI_7_8, T_RFC_130}, /* 1GS4 */
+        {B8, T_REFI_3_9, T_RFC_130}, /* 2GS4 */
+        {B8, T_REFI_3_9, T_RFC_130}, /* 4G */
+        {B8, T_REFI_3_9, T_RFC_210}, /* 8G */
+        {B4, T_REFI_7_8, T_RFC_130}, /* 1GS2 */
+        {B4, T_REFI_3_9, T_RFC_130}, /* 2GS2 */
+};
+EXPORT_SYMBOL_GPL(lpddr2_jedec_addressing_table);
+
+/* LPDDR2 AC timing parameters from JESD209-2 section 12 */
+const struct lpddr2_timings
+        lpddr2_jedec_timings[NUM_DDR_TIMING_TABLE_ENTRIES] = {
+        /* Speed bin 400(200 MHz) */
+        [0] = {
+                .max_freq       = 200000000,
+                .min_freq       = 10000000,
+                .tRPab          = 21000,
+                .tRCD           = 18000,
+                .tWR            = 15000,
+                .tRAS_min       = 42000,
+                .tRRD           = 10000,
+                .tWTR           = 10000,
+                .tXP            = 7500,
+                .tRTP           = 7500,
+                .tCKESR         = 15000,
+                .tDQSCK_max     = 5500,
+                .tFAW           = 50000,
+                .tZQCS          = 90000,
+                .tZQCL          = 360000,
+                .tZQinit        = 1000000,
+                .tRAS_max_ns    = 70000,
+                .tDQSCK_max_derated = 6000,
+        },
+        /* Speed bin 533(266 MHz) */
+        [1] = {
+                .max_freq       = 266666666,
+                .min_freq       = 10000000,
+                .tRPab          = 21000,
+                .tRCD           = 18000,
+                .tWR            = 15000,
+                .tRAS_min       = 42000,
+                .tRRD           = 10000,
+                .tWTR           = 7500,
+                .tXP            = 7500,
+                .tRTP           = 7500,
+                .tCKESR         = 15000,
+                .tDQSCK_max     = 5500,
+                .tFAW           = 50000,
+                .tZQCS          = 90000,
+                .tZQCL          = 360000,
+                .tZQinit        = 1000000,
+                .tRAS_max_ns    = 70000,
+                .tDQSCK_max_derated = 6000,
+        },
+        /* Speed bin 800(400 MHz) */
+        [2] = {
+                .max_freq       = 400000000,
+                .min_freq       = 10000000,
+                .tRPab          = 21000,
+                .tRCD           = 18000,
+                .tWR            = 15000,
+                .tRAS_min       = 42000,
+                .tRRD           = 10000,
+                .tWTR           = 7500,
+                .tXP            = 7500,
+                .tRTP           = 7500,
+                .tCKESR         = 15000,
+                .tDQSCK_max     = 5500,
+                .tFAW           = 50000,
+                .tZQCS          = 90000,
+                .tZQCL          = 360000,
+                .tZQinit        = 1000000,
+                .tRAS_max_ns    = 70000,
+                .tDQSCK_max_derated = 6000,
+        },
+        /* Speed bin 1066(533 MHz) */
+        [3] = {
+                .max_freq       = 533333333,
+                .min_freq       = 10000000,
+                .tRPab          = 21000,
+                .tRCD           = 18000,
+                .tWR            = 15000,
+                .tRAS_min       = 42000,
+                .tRRD           = 10000,
+                .tWTR           = 7500,
+                .tXP            = 7500,
+                .tRTP           = 7500,
+                .tCKESR         = 15000,
+                .tDQSCK_max     = 5500,
+                .tFAW           = 50000,
+                .tZQCS          = 90000,
+                .tZQCL          = 360000,
+                .tZQinit        = 1000000,
+                .tRAS_max_ns    = 70000,
+                .tDQSCK_max_derated = 5620,
+        },
+};
+EXPORT_SYMBOL_GPL(lpddr2_jedec_timings);
+
+const struct lpddr2_min_tck lpddr2_jedec_min_tck = {
+        .tRPab          = 3,
+        .tRCD           = 3,
+        .tWR            = 3,
+        .tRASmin        = 3,
+        .tRRD           = 2,
+        .tWTR           = 2,
+        .tXP            = 2,
+        .tRTP           = 2,
+        .tCKE           = 3,
+        .tCKESR         = 3,
+        .tFAW           = 8
+};
+EXPORT_SYMBOL_GPL(lpddr2_jedec_min_tck);
diff --git a/lib/kasprintf.c b/lib/kasprintf.c
index 9c4233b23783..32f12150fc4f 100644
--- a/lib/kasprintf.c
+++ b/lib/kasprintf.c
@@ -5,7 +5,7 @@
  */
 
 #include <stdarg.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/slab.h>
 #include <linux/types.h>
 #include <linux/string.h>
@@ -21,7 +21,7 @@ char *kvasprintf(gfp_t gfp, const char *fmt, va_list ap)
         len = vsnprintf(NULL, 0, fmt, aq);
         va_end(aq);
 
-        p = kmalloc(len+1, gfp);
+        p = kmalloc_track_caller(len+1, gfp);
         if (!p)
                 return NULL;
 
diff --git a/lib/klist.c b/lib/klist.c
index 573d6068a42e..0874e41609a6 100644
--- a/lib/klist.c
+++ b/lib/klist.c
@@ -35,7 +35,7 @@
  */
 
 #include <linux/klist.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/sched.h>
 
 /*
diff --git a/lib/kobject.c b/lib/kobject.c
index 640bd98a4c8a..e07ee1fcd6f1 100644
--- a/lib/kobject.c
+++ b/lib/kobject.c
@@ -14,7 +14,7 @@
 
 #include <linux/kobject.h>
 #include <linux/string.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/stat.h>
 #include <linux/slab.h>
 
@@ -47,13 +47,11 @@ static int populate_dir(struct kobject *kobj)
 static int create_dir(struct kobject *kobj)
 {
         int error = 0;
-        if (kobject_name(kobj)) {
-                error = sysfs_create_dir(kobj);
-                if (!error) {
-                        error = populate_dir(kobj);
-                        if (error)
-                                sysfs_remove_dir(kobj);
-                }
+        error = sysfs_create_dir(kobj);
+        if (!error) {
+                error = populate_dir(kobj);
+                if (error)
+                        sysfs_remove_dir(kobj);
         }
         return error;
 }
@@ -192,14 +190,14 @@ static int kobject_add_internal(struct kobject *kobj)
 
                 /* be noisy on error issues */
                 if (error == -EEXIST)
-                        printk(KERN_ERR "%s failed for %s with "
-                               "-EEXIST, don't try to register things with "
-                               "the same name in the same directory.\n",
-                               __func__, kobject_name(kobj));
+                        WARN(1, "%s failed for %s with "
+                             "-EEXIST, don't try to register things with "
+                             "the same name in the same directory.\n",
+                             __func__, kobject_name(kobj));
                 else
-                        printk(KERN_ERR "%s failed for %s (%d)\n",
-                               __func__, kobject_name(kobj), error);
-                dump_stack();
+                        WARN(1, "%s failed for %s (error: %d parent: %s)\n",
+                             __func__, kobject_name(kobj), error,
+                             parent ? kobject_name(parent) : "'none'");
         } else
                 kobj->state_in_sysfs = 1;
 
@@ -634,7 +632,7 @@ struct kobject *kobject_create(void)
 /**
  * kobject_create_and_add - create a struct kobject dynamically and register it with sysfs
  *
- * @name: the name for the kset
+ * @name: the name for the kobject
  * @parent: the parent kobject of this kobject, if any.
  *
  * This function creates a kobject structure dynamically and registers it
@@ -746,43 +744,11 @@ void kset_unregister(struct kset *k)
  */
 struct kobject *kset_find_obj(struct kset *kset, const char *name)
 {
-        return kset_find_obj_hinted(kset, name, NULL);
-}
-
-/**
- * kset_find_obj_hinted - search for object in kset given a predecessor hint.
- * @kset: kset we're looking in.
- * @name: object's name.
- * @hint: hint to possible object's predecessor.
- *
- * Check the hint's next object and if it is a match return it directly,
- * otherwise, fall back to the behavior of kset_find_obj().  Either way
- * a reference for the returned object is held and the reference on the
- * hinted object is released.
- */
-struct kobject *kset_find_obj_hinted(struct kset *kset, const char *name,
-                                     struct kobject *hint)
-{
         struct kobject *k;
         struct kobject *ret = NULL;
 
         spin_lock(&kset->list_lock);
 
-        if (!hint)
-                goto slow_search;
-
-        /* end of list detection */
-        if (hint->entry.next == kset->list.next)
-                goto slow_search;
-
-        k = container_of(hint->entry.next, struct kobject, entry);
-        if (!kobject_name(k) || strcmp(kobject_name(k), name))
-                goto slow_search;
-
-        ret = kobject_get(k);
-        goto unlock_exit;
-
-slow_search:
         list_for_each_entry(k, &kset->list, entry) {
                 if (kobject_name(k) && !strcmp(kobject_name(k), name)) {
                         ret = kobject_get(k);
@@ -790,12 +756,7 @@ slow_search:
                 }
         }
 
-unlock_exit:
         spin_unlock(&kset->list_lock);
-
-        if (hint)
-                kobject_put(hint);
-
         return ret;
 }
 
diff --git a/lib/kobject_uevent.c b/lib/kobject_uevent.c
index 70af0a7f97c0..52e5abbc41db 100644
--- a/lib/kobject_uevent.c
+++ b/lib/kobject_uevent.c
@@ -17,7 +17,8 @@
 #include <linux/spinlock.h>
 #include <linux/string.h>
 #include <linux/kobject.h>
-#include <linux/module.h>
+#include <linux/export.h>
+#include <linux/kmod.h>
 #include <linux/slab.h>
 #include <linux/user_namespace.h>
 #include <linux/socket.h>
@@ -29,16 +30,17 @@
 
 u64 uevent_seqnum;
 char uevent_helper[UEVENT_HELPER_PATH_LEN] = CONFIG_UEVENT_HELPER_PATH;
-static DEFINE_SPINLOCK(sequence_lock);
 #ifdef CONFIG_NET
 struct uevent_sock {
         struct list_head list;
         struct sock *sk;
 };
 static LIST_HEAD(uevent_sock_list);
-static DEFINE_MUTEX(uevent_sock_mutex);
 #endif
 
+/* This lock protects uevent_seqnum and uevent_sock_list */
+static DEFINE_MUTEX(uevent_sock_mutex);
+
 /* the strings here must match the enum in include/linux/kobject.h */
 static const char *kobject_actions[] = {
         [KOBJ_ADD] =            "add",
@@ -136,7 +138,6 @@ int kobject_uevent_env(struct kobject *kobj, enum kobject_action action,
         struct kobject *top_kobj;
         struct kset *kset;
         const struct kset_uevent_ops *uevent_ops;
-        u64 seq;
         int i = 0;
         int retval = 0;
 #ifdef CONFIG_NET
@@ -243,22 +244,24 @@ int kobject_uevent_env(struct kobject *kobj, enum kobject_action action,
         else if (action == KOBJ_REMOVE)
                 kobj->state_remove_uevent_sent = 1;
 
+        mutex_lock(&uevent_sock_mutex);
         /* we will send an event, so request a new sequence number */
-        spin_lock(&sequence_lock);
-        seq = ++uevent_seqnum;
-        spin_unlock(&sequence_lock);
-        retval = add_uevent_var(env, "SEQNUM=%llu", (unsigned long long)seq);
-        if (retval)
+        retval = add_uevent_var(env, "SEQNUM=%llu", (unsigned long long)++uevent_seqnum);
+        if (retval) {
+                mutex_unlock(&uevent_sock_mutex);
                 goto exit;
+        }
 
 #if defined(CONFIG_NET)
         /* send netlink message */
-        mutex_lock(&uevent_sock_mutex);
         list_for_each_entry(ue_sk, &uevent_sock_list, list) {
                 struct sock *uevent_sock = ue_sk->sk;
                 struct sk_buff *skb;
                 size_t len;
 
+                if (!netlink_has_listeners(uevent_sock, 1))
+                        continue;
+
                 /* allocate message with the maximum possible size */
                 len = strlen(action_string) + strlen(devpath) + 2;
                 skb = alloc_skb(len + env->buflen, GFP_KERNEL);
@@ -282,13 +285,13 @@ int kobject_uevent_env(struct kobject *kobj, enum kobject_action action,
                                                             kobj_bcast_filter,
                                                             kobj);
                         /* ENOBUFS should be handled in userspace */
-                        if (retval == -ENOBUFS)
+                        if (retval == -ENOBUFS || retval == -ESRCH)
                                 retval = 0;
                 } else
                         retval = -ENOMEM;
         }
-        mutex_unlock(&uevent_sock_mutex);
 #endif
+        mutex_unlock(&uevent_sock_mutex);
 
         /* call uevent_helper, usually only enabled during early boot */
         if (uevent_helper[0] && !kobj_usermode_filter(kobj)) {
@@ -370,13 +373,16 @@ EXPORT_SYMBOL_GPL(add_uevent_var);
 static int uevent_net_init(struct net *net)
 {
         struct uevent_sock *ue_sk;
+        struct netlink_kernel_cfg cfg = {
+                .groups = 1,
+                .flags  = NL_CFG_F_NONROOT_RECV,
+        };
 
         ue_sk = kzalloc(sizeof(*ue_sk), GFP_KERNEL);
         if (!ue_sk)
                 return -ENOMEM;
 
-        ue_sk->sk = netlink_kernel_create(net, NETLINK_KOBJECT_UEVENT,
-                                          1, NULL, NULL, THIS_MODULE);
+        ue_sk->sk = netlink_kernel_create(net, NETLINK_KOBJECT_UEVENT, &cfg);
         if (!ue_sk->sk) {
                 printk(KERN_ERR
                        "kobject_uevent: unable to create netlink socket!\n");
@@ -416,7 +422,6 @@ static struct pernet_operations uevent_net_ops = {
 
 static int __init kobject_uevent_init(void)
 {
-        netlink_set_nonroot(NETLINK_KOBJECT_UEVENT, NL_NONROOT_RECV);
         return register_pernet_subsys(&uevent_net_ops);
 }
 
diff --git a/lib/kref.c b/lib/kref.c
deleted file mode 100644
index 3efb882b11db..000000000000
--- a/lib/kref.c
+++ /dev/null
@@ -1,97 +0,0 @@
-/*
- * kref.c - library routines for handling generic reference counted objects
- *
- * Copyright (C) 2004 Greg Kroah-Hartman <greg@kroah.com>
- * Copyright (C) 2004 IBM Corp.
- *
- * based on lib/kobject.c which was:
- * Copyright (C) 2002-2003 Patrick Mochel <mochel@osdl.org>
- *
- * This file is released under the GPLv2.
- *
- */
-
-#include <linux/kref.h>
-#include <linux/module.h>
-#include <linux/slab.h>
-
-/**
- * kref_init - initialize object.
- * @kref: object in question.
- */
-void kref_init(struct kref *kref)
-{
-        atomic_set(&kref->refcount, 1);
-        smp_mb();
-}
-
-/**
- * kref_get - increment refcount for object.
- * @kref: object.
- */
-void kref_get(struct kref *kref)
-{
-        WARN_ON(!atomic_read(&kref->refcount));
-        atomic_inc(&kref->refcount);
-        smp_mb__after_atomic_inc();
-}
-
-/**
- * kref_put - decrement refcount for object.
- * @kref: object.
- * @release: pointer to the function that will clean up the object when the
- *           last reference to the object is released.
- *           This pointer is required, and it is not acceptable to pass kfree
- *           in as this function.
- *
- * Decrement the refcount, and if 0, call release().
- * Return 1 if the object was removed, otherwise return 0.  Beware, if this
- * function returns 0, you still can not count on the kref from remaining in
- * memory.  Only use the return value if you want to see if the kref is now
- * gone, not present.
- */
-int kref_put(struct kref *kref, void (*release)(struct kref *kref))
-{
-        WARN_ON(release == NULL);
-        WARN_ON(release == (void (*)(struct kref *))kfree);
-
-        if (atomic_dec_and_test(&kref->refcount)) {
-                release(kref);
-                return 1;
-        }
-        return 0;
-}
-
-
-/**
- * kref_sub - subtract a number of refcounts for object.
- * @kref: object.
- * @count: Number of recounts to subtract.
- * @release: pointer to the function that will clean up the object when the
- *           last reference to the object is released.
- *           This pointer is required, and it is not acceptable to pass kfree
- *           in as this function.
- *
- * Subtract @count from the refcount, and if 0, call release().
- * Return 1 if the object was removed, otherwise return 0.  Beware, if this
- * function returns 0, you still can not count on the kref from remaining in
- * memory.  Only use the return value if you want to see if the kref is now
- * gone, not present.
- */
-int kref_sub(struct kref *kref, unsigned int count,
-             void (*release)(struct kref *kref))
-{
-        WARN_ON(release == NULL);
-        WARN_ON(release == (void (*)(struct kref *))kfree);
-
-        if (atomic_sub_and_test((int) count, &kref->refcount)) {
-                release(kref);
-                return 1;
-        }
-        return 0;
-}
-
-EXPORT_SYMBOL(kref_init);
-EXPORT_SYMBOL(kref_get);
-EXPORT_SYMBOL(kref_put);
-EXPORT_SYMBOL(kref_sub);
diff --git a/lib/kstrtox.c b/lib/kstrtox.c
index 5e066759f551..c3615eab0cc3 100644
--- a/lib/kstrtox.c
+++ b/lib/kstrtox.c
@@ -15,29 +15,44 @@
 #include <linux/errno.h>
 #include <linux/kernel.h>
 #include <linux/math64.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/types.h>
 #include <asm/uaccess.h>
+#include "kstrtox.h"
 
-static int _kstrtoull(const char *s, unsigned int base, unsigned long long *res)
+const char *_parse_integer_fixup_radix(const char *s, unsigned int *base)
 {
-        unsigned long long acc;
-        int ok;
-
-        if (base == 0) {
+        if (*base == 0) {
                 if (s[0] == '0') {
                         if (_tolower(s[1]) == 'x' && isxdigit(s[2]))
-                                base = 16;
+                                *base = 16;
                         else
-                                base = 8;
+                                *base = 8;
                 } else
-                        base = 10;
+                        *base = 10;
         }
-        if (base == 16 && s[0] == '0' && _tolower(s[1]) == 'x')
+        if (*base == 16 && s[0] == '0' && _tolower(s[1]) == 'x')
                 s += 2;
+        return s;
+}
 
-        acc = 0;
-        ok = 0;
+/*
+ * Convert non-negative integer string representation in explicitly given radix
+ * to an integer.
+ * Return number of characters consumed maybe or-ed with overflow bit.
+ * If overflow occurs, result integer (incorrect) is still returned.
+ *
+ * Don't you dare use this function.
+ */
+unsigned int _parse_integer(const char *s, unsigned int base, unsigned long long *p)
+{
+        unsigned long long res;
+        unsigned int rv;
+        int overflow;
+
+        res = 0;
+        rv = 0;
+        overflow = 0;
         while (*s) {
                 unsigned int val;
 
@@ -45,23 +60,47 @@ static int _kstrtoull(const char *s, unsigned int base, unsigned long long *res)
                         val = *s - '0';
                 else if ('a' <= _tolower(*s) && _tolower(*s) <= 'f')
                         val = _tolower(*s) - 'a' + 10;
-                else if (*s == '\n' && *(s + 1) == '\0')
-                        break;
                 else
-                        return -EINVAL;
+                        break;
 
                 if (val >= base)
-                        return -EINVAL;
-                if (acc > div_u64(ULLONG_MAX - val, base))
-                        return -ERANGE;
-                acc = acc * base + val;
-                ok = 1;
-
+                        break;
+                /*
+                 * Check for overflow only if we are within range of
+                 * it in the max base we support (16)
+                 */
+                if (unlikely(res & (~0ull << 60))) {
+                        if (res > div_u64(ULLONG_MAX - val, base))
+                                overflow = 1;
+                }
+                res = res * base + val;
+                rv++;
                 s++;
         }
-        if (!ok)
+        *p = res;
+        if (overflow)
+                rv |= KSTRTOX_OVERFLOW;
+        return rv;
+}
+
+static int _kstrtoull(const char *s, unsigned int base, unsigned long long *res)
+{
+        unsigned long long _res;
+        unsigned int rv;
+
+        s = _parse_integer_fixup_radix(s, &base);
+        rv = _parse_integer(s, base, &_res);
+        if (rv & KSTRTOX_OVERFLOW)
+                return -ERANGE;
+        rv &= ~KSTRTOX_OVERFLOW;
+        if (rv == 0)
+                return -EINVAL;
+        s += rv;
+        if (*s == '\n')
+                s++;
+        if (*s)
                 return -EINVAL;
-        *res = acc;
+        *res = _res;
         return 0;
 }
 
diff --git a/lib/kstrtox.h b/lib/kstrtox.h
new file mode 100644
index 000000000000..f13eeeaf441d
--- /dev/null
+++ b/lib/kstrtox.h
@@ -0,0 +1,8 @@
+#ifndef _LIB_KSTRTOX_H
+#define _LIB_KSTRTOX_H
+
+#define KSTRTOX_OVERFLOW        (1U << 31)
+const char *_parse_integer_fixup_radix(const char *s, unsigned int *base);
+unsigned int _parse_integer(const char *s, unsigned int base, unsigned long long *res);
+
+#endif
diff --git a/lib/lcm.c b/lib/lcm.c
index 10b5cfcacf6b..b9c8de461e9e 100644
--- a/lib/lcm.c
+++ b/lib/lcm.c
@@ -1,6 +1,6 @@
 #include <linux/kernel.h>
 #include <linux/gcd.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/lcm.h>
 
 /* Lowest common multiple */
diff --git a/lib/list_debug.c b/lib/list_debug.c
index b8029a5583ff..c24c2f7e296f 100644
--- a/lib/list_debug.c
+++ b/lib/list_debug.c
@@ -6,8 +6,11 @@
  * DEBUG_LIST.
  */
 
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/list.h>
+#include <linux/bug.h>
+#include <linux/kernel.h>
+#include <linux/rculist.h>
 
 /*
  * Insert a new entry between two known consecutive entries.
@@ -28,6 +31,9 @@ void __list_add(struct list_head *new,
                 "list_add corruption. prev->next should be "
                 "next (%p), but was %p. (prev=%p).\n",
                 next, prev->next, prev);
+        WARN(new == prev || new == next,
+             "list_add double add: new=%p, prev=%p, next=%p.\n",
+             new, prev, next);
         next->prev = new;
         new->next = next;
         new->prev = prev;
@@ -73,3 +79,22 @@ void list_del(struct list_head *entry)
         entry->prev = LIST_POISON2;
 }
 EXPORT_SYMBOL(list_del);
+
+/*
+ * RCU variants.
+ */
+void __list_add_rcu(struct list_head *new,
+                    struct list_head *prev, struct list_head *next)
+{
+        WARN(next->prev != prev,
+                "list_add_rcu corruption. next->prev should be prev (%p), but was %p. (next=%p).\n",
+                prev, next->prev, next);
+        WARN(prev->next != next,
+                "list_add_rcu corruption. prev->next should be next (%p), but was %p. (prev=%p).\n",
+                next, prev->next, prev);
+        new->next = next;
+        new->prev = prev;
+        rcu_assign_pointer(list_next_rcu(prev), new);
+        next->prev = new;
+}
+EXPORT_SYMBOL(__list_add_rcu);
diff --git a/lib/llist.c b/lib/llist.c
index da445724fa1f..4a15115e90f8 100644
--- a/lib/llist.c
+++ b/lib/llist.c
@@ -3,8 +3,8 @@
  *
  * The basic atomic operation of this list is cmpxchg on long.  On
  * architectures that don't have NMI-safe cmpxchg implementation, the
- * list can NOT be used in NMI handler.  So code uses the list in NMI
- * handler should depend on CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG.
+ * list can NOT be used in NMI handlers.  So code that uses the list in
+ * an NMI handler should depend on CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG.
  *
  * Copyright 2010,2011 Intel Corp.
  *   Author: Huang Ying <ying.huang@intel.com>
@@ -23,55 +23,34 @@
  * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
  */
 #include <linux/kernel.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/interrupt.h>
 #include <linux/llist.h>
 
-#include <asm/system.h>
-
-/**
- * llist_add - add a new entry
- * @new:        new entry to be added
- * @head:       the head for your lock-less list
- */
-void llist_add(struct llist_node *new, struct llist_head *head)
-{
-        struct llist_node *entry, *old_entry;
-
-#ifndef CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG
-        BUG_ON(in_nmi());
-#endif
-
-        entry = head->first;
-        do {
-                old_entry = entry;
-                new->next = entry;
-                cpu_relax();
-        } while ((entry = cmpxchg(&head->first, old_entry, new)) != old_entry);
-}
-EXPORT_SYMBOL_GPL(llist_add);
 
 /**
  * llist_add_batch - add several linked entries in batch
  * @new_first:  first entry in batch to be added
  * @new_last:   last entry in batch to be added
  * @head:       the head for your lock-less list
+ *
+ * Return whether list is empty before adding.
  */
-void llist_add_batch(struct llist_node *new_first, struct llist_node *new_last,
+bool llist_add_batch(struct llist_node *new_first, struct llist_node *new_last,
                      struct llist_head *head)
 {
         struct llist_node *entry, *old_entry;
 
-#ifndef CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG
-        BUG_ON(in_nmi());
-#endif
-
         entry = head->first;
-        do {
+        for (;;) {
                 old_entry = entry;
                 new_last->next = entry;
-                cpu_relax();
-        } while ((entry = cmpxchg(&head->first, old_entry, new_first)) != old_entry);
+                entry = cmpxchg(&head->first, old_entry, new_first);
+                if (entry == old_entry)
+                        break;
+        }
+
+        return old_entry == NULL;
 }
 EXPORT_SYMBOL_GPL(llist_add_batch);
 
@@ -93,37 +72,17 @@ struct llist_node *llist_del_first(struct llist_head *head)
 {
         struct llist_node *entry, *old_entry, *next;
 
-#ifndef CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG
-        BUG_ON(in_nmi());
-#endif
-
         entry = head->first;
-        do {
+        for (;;) {
                 if (entry == NULL)
                         return NULL;
                 old_entry = entry;
                 next = entry->next;
-                cpu_relax();
-        } while ((entry = cmpxchg(&head->first, old_entry, next)) != old_entry);
+                entry = cmpxchg(&head->first, old_entry, next);
+                if (entry == old_entry)
+                        break;
+        }
 
         return entry;
 }
 EXPORT_SYMBOL_GPL(llist_del_first);
-
-/**
- * llist_del_all - delete all entries from lock-less list
- * @head:       the head of lock-less list to delete all entries
- *
- * If list is empty, return NULL, otherwise, delete all entries and
- * return the pointer to the first entry.  The order of entries
- * deleted is from the newest to the oldest added one.
- */
-struct llist_node *llist_del_all(struct llist_head *head)
-{
-#ifndef CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG
-        BUG_ON(in_nmi());
-#endif
-
-        return xchg(&head->first, NULL);
-}
-EXPORT_SYMBOL_GPL(llist_del_all);
diff --git a/lib/locking-selftest.c b/lib/locking-selftest.c
index 507a22fab738..7aae0f2a5e0a 100644
--- a/lib/locking-selftest.c
+++ b/lib/locking-selftest.c
@@ -14,7 +14,6 @@
 #include <linux/mutex.h>
 #include <linux/sched.h>
 #include <linux/delay.h>
-#include <linux/module.h>
 #include <linux/lockdep.h>
 #include <linux/spinlock.h>
 #include <linux/kallsyms.h>
diff --git a/lib/md5.c b/lib/md5.c
index c777180e1f2f..958a3c15923c 100644
--- a/lib/md5.c
+++ b/lib/md5.c
@@ -1,5 +1,5 @@
 #include <linux/kernel.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/cryptohash.h>
 
 #define F1(x, y, z)     (z ^ (x & (y ^ z)))
diff --git a/lib/memory-notifier-error-inject.c b/lib/memory-notifier-error-inject.c
new file mode 100644
index 000000000000..e6239bf0b0df
--- /dev/null
+++ b/lib/memory-notifier-error-inject.c
@@ -0,0 +1,48 @@
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/memory.h>
+
+#include "notifier-error-inject.h"
+
+static int priority;
+module_param(priority, int, 0);
+MODULE_PARM_DESC(priority, "specify memory notifier priority");
+
+static struct notifier_err_inject memory_notifier_err_inject = {
+        .actions = {
+                { NOTIFIER_ERR_INJECT_ACTION(MEM_GOING_ONLINE) },
+                { NOTIFIER_ERR_INJECT_ACTION(MEM_GOING_OFFLINE) },
+                {}
+        }
+};
+
+static struct dentry *dir;
+
+static int err_inject_init(void)
+{
+        int err;
+
+        dir = notifier_err_inject_init("memory", notifier_err_inject_dir,
+                                        &memory_notifier_err_inject, priority);
+        if (IS_ERR(dir))
+                return PTR_ERR(dir);
+
+        err = register_memory_notifier(&memory_notifier_err_inject.nb);
+        if (err)
+                debugfs_remove_recursive(dir);
+
+        return err;
+}
+
+static void err_inject_exit(void)
+{
+        unregister_memory_notifier(&memory_notifier_err_inject.nb);
+        debugfs_remove_recursive(dir);
+}
+
+module_init(err_inject_init);
+module_exit(err_inject_exit);
+
+MODULE_DESCRIPTION("memory notifier error injection module");
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Akinobu Mita <akinobu.mita@gmail.com>");
diff --git a/lib/memweight.c b/lib/memweight.c
new file mode 100644
index 000000000000..e35fc8771893
--- /dev/null
+++ b/lib/memweight.c
@@ -0,0 +1,38 @@
+#include <linux/export.h>
+#include <linux/bug.h>
+#include <linux/bitmap.h>
+
+/**
+ * memweight - count the total number of bits set in memory area
+ * @ptr: pointer to the start of the area
+ * @bytes: the size of the area
+ */
+size_t memweight(const void *ptr, size_t bytes)
+{
+        size_t ret = 0;
+        size_t longs;
+        const unsigned char *bitmap = ptr;
+
+        for (; bytes > 0 && ((unsigned long)bitmap) % sizeof(long);
+                        bytes--, bitmap++)
+                ret += hweight8(*bitmap);
+
+        longs = bytes / sizeof(long);
+        if (longs) {
+                BUG_ON(longs >= INT_MAX / BITS_PER_LONG);
+                ret += bitmap_weight((unsigned long *)bitmap,
+                                longs * BITS_PER_LONG);
+                bytes -= longs * sizeof(long);
+                bitmap += longs * sizeof(long);
+        }
+        /*
+         * The reason that this last loop is distinct from the preceding
+         * bitmap_weight() call is to compute 1-bits in the last region smaller
+         * than sizeof(long) properly on big-endian systems.
+         */
+        for (; bytes > 0; bytes--, bitmap++)
+                ret += hweight8(*bitmap);
+
+        return ret;
+}
+EXPORT_SYMBOL(memweight);
diff --git a/lib/mpi/Makefile b/lib/mpi/Makefile
new file mode 100644
index 000000000000..019a68c90144
--- /dev/null
+++ b/lib/mpi/Makefile
@@ -0,0 +1,22 @@
+#
+# MPI multiprecision maths library (from gpg)
+#
+
+obj-$(CONFIG_MPILIB) = mpi.o
+
+mpi-y = \
+        generic_mpih-lshift.o           \
+        generic_mpih-mul1.o             \
+        generic_mpih-mul2.o             \
+        generic_mpih-mul3.o             \
+        generic_mpih-rshift.o           \
+        generic_mpih-sub1.o             \
+        generic_mpih-add1.o             \
+        mpicoder.o                      \
+        mpi-bit.o                       \
+        mpi-cmp.o                       \
+        mpih-cmp.o                      \
+        mpih-div.o                      \
+        mpih-mul.o                      \
+        mpi-pow.o                       \
+        mpiutil.o
diff --git a/lib/mpi/generic_mpih-add1.c b/lib/mpi/generic_mpih-add1.c
new file mode 100644
index 000000000000..c94c7dd344b3
--- /dev/null
+++ b/lib/mpi/generic_mpih-add1.c
@@ -0,0 +1,61 @@
+/* mpihelp-add_1.c  -  MPI helper functions
+ * Copyright (C) 1994, 1996, 1997, 1998,
+ *               2000 Free Software Foundation, Inc.
+ *
+ * This file is part of GnuPG.
+ *
+ * GnuPG is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * GnuPG is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA
+ *
+ * Note: This code is heavily based on the GNU MP Library.
+ *       Actually it's the same code with only minor changes in the
+ *       way the data is stored; this is to support the abstraction
+ *       of an optional secure memory allocation which may be used
+ *       to avoid revealing of sensitive data due to paging etc.
+ *       The GNU MP Library itself is published under the LGPL;
+ *       however I decided to publish this code under the plain GPL.
+ */
+
+#include "mpi-internal.h"
+#include "longlong.h"
+
+mpi_limb_t
+mpihelp_add_n(mpi_ptr_t res_ptr, mpi_ptr_t s1_ptr,
+              mpi_ptr_t s2_ptr, mpi_size_t size)
+{
+        mpi_limb_t x, y, cy;
+        mpi_size_t j;
+
+        /* The loop counter and index J goes from -SIZE to -1.  This way
+           the loop becomes faster.  */
+        j = -size;
+
+        /* Offset the base pointers to compensate for the negative indices. */
+        s1_ptr -= j;
+        s2_ptr -= j;
+        res_ptr -= j;
+
+        cy = 0;
+        do {
+                y = s2_ptr[j];
+                x = s1_ptr[j];
+                y += cy;        /* add previous carry to one addend */
+                cy = y < cy;    /* get out carry from that addition */
+                y += x;         /* add other addend */
+                cy += y < x;    /* get out carry from that add, combine */
+                res_ptr[j] = y;
+        } while (++j);
+
+        return cy;
+}
diff --git a/lib/mpi/generic_mpih-lshift.c b/lib/mpi/generic_mpih-lshift.c
new file mode 100644
index 000000000000..86318927231a
--- /dev/null
+++ b/lib/mpi/generic_mpih-lshift.c
@@ -0,0 +1,63 @@
+/* mpihelp-lshift.c  -  MPI helper functions
+ * Copyright (C) 1994, 1996, 1998, 2001 Free Software Foundation, Inc.
+ *
+ * This file is part of GnuPG.
+ *
+ * GnuPG is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * GnuPG is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA
+ *
+ * Note: This code is heavily based on the GNU MP Library.
+ *       Actually it's the same code with only minor changes in the
+ *       way the data is stored; this is to support the abstraction
+ *       of an optional secure memory allocation which may be used
+ *       to avoid revealing of sensitive data due to paging etc.
+ *       The GNU MP Library itself is published under the LGPL;
+ *       however I decided to publish this code under the plain GPL.
+ */
+
+#include "mpi-internal.h"
+
+/* Shift U (pointed to by UP and USIZE digits long) CNT bits to the left
+ * and store the USIZE least significant digits of the result at WP.
+ * Return the bits shifted out from the most significant digit.
+ *
+ * Argument constraints:
+ * 1. 0 < CNT < BITS_PER_MP_LIMB
+ * 2. If the result is to be written over the input, WP must be >= UP.
+ */
+
+mpi_limb_t
+mpihelp_lshift(mpi_ptr_t wp, mpi_ptr_t up, mpi_size_t usize, unsigned int cnt)
+{
+        mpi_limb_t high_limb, low_limb;
+        unsigned sh_1, sh_2;
+        mpi_size_t i;
+        mpi_limb_t retval;
+
+        sh_1 = cnt;
+        wp += 1;
+        sh_2 = BITS_PER_MPI_LIMB - sh_1;
+        i = usize - 1;
+        low_limb = up[i];
+        retval = low_limb >> sh_2;
+        high_limb = low_limb;
+        while (--i >= 0) {
+                low_limb = up[i];
+                wp[i] = (high_limb << sh_1) | (low_limb >> sh_2);
+                high_limb = low_limb;
+        }
+        wp[i] = high_limb << sh_1;
+
+        return retval;
+}
diff --git a/lib/mpi/generic_mpih-mul1.c b/lib/mpi/generic_mpih-mul1.c
new file mode 100644
index 000000000000..1668dfd9092c
--- /dev/null
+++ b/lib/mpi/generic_mpih-mul1.c
@@ -0,0 +1,57 @@
+/* mpihelp-mul_1.c  -  MPI helper functions
+ * Copyright (C) 1994, 1996, 1997, 1998, 2001 Free Software Foundation, Inc.
+ *
+ * This file is part of GnuPG.
+ *
+ * GnuPG is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * GnuPG is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA
+ *
+ * Note: This code is heavily based on the GNU MP Library.
+ *       Actually it's the same code with only minor changes in the
+ *       way the data is stored; this is to support the abstraction
+ *       of an optional secure memory allocation which may be used
+ *       to avoid revealing of sensitive data due to paging etc.
+ *       The GNU MP Library itself is published under the LGPL;
+ *       however I decided to publish this code under the plain GPL.
+ */
+
+#include "mpi-internal.h"
+#include "longlong.h"
+
+mpi_limb_t
+mpihelp_mul_1(mpi_ptr_t res_ptr, mpi_ptr_t s1_ptr, mpi_size_t s1_size,
+              mpi_limb_t s2_limb)
+{
+        mpi_limb_t cy_limb;
+        mpi_size_t j;
+        mpi_limb_t prod_high, prod_low;
+
+        /* The loop counter and index J goes from -S1_SIZE to -1.  This way
+         * the loop becomes faster.  */
+        j = -s1_size;
+
+        /* Offset the base pointers to compensate for the negative indices.  */
+        s1_ptr -= j;
+        res_ptr -= j;
+
+        cy_limb = 0;
+        do {
+                umul_ppmm(prod_high, prod_low, s1_ptr[j], s2_limb);
+                prod_low += cy_limb;
+                cy_limb = (prod_low < cy_limb ? 1 : 0) + prod_high;
+                res_ptr[j] = prod_low;
+        } while (++j);
+
+        return cy_limb;
+}
diff --git a/lib/mpi/generic_mpih-mul2.c b/lib/mpi/generic_mpih-mul2.c
new file mode 100644
index 000000000000..8a7b29ee1740
--- /dev/null
+++ b/lib/mpi/generic_mpih-mul2.c
@@ -0,0 +1,60 @@
+/* mpihelp-mul_2.c  -  MPI helper functions
+ * Copyright (C) 1994, 1996, 1997, 1998, 2001 Free Software Foundation, Inc.
+ *
+ * This file is part of GnuPG.
+ *
+ * GnuPG is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * GnuPG is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA
+ *
+ * Note: This code is heavily based on the GNU MP Library.
+ *       Actually it's the same code with only minor changes in the
+ *       way the data is stored; this is to support the abstraction
+ *       of an optional secure memory allocation which may be used
+ *       to avoid revealing of sensitive data due to paging etc.
+ *       The GNU MP Library itself is published under the LGPL;
+ *       however I decided to publish this code under the plain GPL.
+ */
+
+#include "mpi-internal.h"
+#include "longlong.h"
+
+mpi_limb_t
+mpihelp_addmul_1(mpi_ptr_t res_ptr, mpi_ptr_t s1_ptr,
+                 mpi_size_t s1_size, mpi_limb_t s2_limb)
+{
+        mpi_limb_t cy_limb;
+        mpi_size_t j;
+        mpi_limb_t prod_high, prod_low;
+        mpi_limb_t x;
+
+        /* The loop counter and index J goes from -SIZE to -1.  This way
+         * the loop becomes faster.  */
+        j = -s1_size;
+        res_ptr -= j;
+        s1_ptr -= j;
+
+        cy_limb = 0;
+        do {
+                umul_ppmm(prod_high, prod_low, s1_ptr[j], s2_limb);
+
+                prod_low += cy_limb;
+                cy_limb = (prod_low < cy_limb ? 1 : 0) + prod_high;
+
+                x = res_ptr[j];
+                prod_low = x + prod_low;
+                cy_limb += prod_low < x ? 1 : 0;
+                res_ptr[j] = prod_low;
+        } while (++j);
+        return cy_limb;
+}
diff --git a/lib/mpi/generic_mpih-mul3.c b/lib/mpi/generic_mpih-mul3.c
new file mode 100644
index 000000000000..f96df327be63
--- /dev/null
+++ b/lib/mpi/generic_mpih-mul3.c
@@ -0,0 +1,61 @@
+/* mpihelp-mul_3.c  -  MPI helper functions
+ * Copyright (C) 1994, 1996, 1997, 1998, 2001 Free Software Foundation, Inc.
+ *
+ * This file is part of GnuPG.
+ *
+ * GnuPG is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * GnuPG is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA
+ *
+ * Note: This code is heavily based on the GNU MP Library.
+ *       Actually it's the same code with only minor changes in the
+ *       way the data is stored; this is to support the abstraction
+ *       of an optional secure memory allocation which may be used
+ *       to avoid revealing of sensitive data due to paging etc.
+ *       The GNU MP Library itself is published under the LGPL;
+ *       however I decided to publish this code under the plain GPL.
+ */
+
+#include "mpi-internal.h"
+#include "longlong.h"
+
+mpi_limb_t
+mpihelp_submul_1(mpi_ptr_t res_ptr, mpi_ptr_t s1_ptr,
+                 mpi_size_t s1_size, mpi_limb_t s2_limb)
+{
+        mpi_limb_t cy_limb;
+        mpi_size_t j;
+        mpi_limb_t prod_high, prod_low;
+        mpi_limb_t x;
+
+        /* The loop counter and index J goes from -SIZE to -1.  This way
+         * the loop becomes faster.  */
+        j = -s1_size;
+        res_ptr -= j;
+        s1_ptr -= j;
+
+        cy_limb = 0;
+        do {
+                umul_ppmm(prod_high, prod_low, s1_ptr[j], s2_limb);
+
+                prod_low += cy_limb;
+                cy_limb = (prod_low < cy_limb ? 1 : 0) + prod_high;
+
+                x = res_ptr[j];
+                prod_low = x - prod_low;
+                cy_limb += prod_low > x ? 1 : 0;
+                res_ptr[j] = prod_low;
+        } while (++j);
+
+        return cy_limb;
+}
diff --git a/lib/mpi/generic_mpih-rshift.c b/lib/mpi/generic_mpih-rshift.c
new file mode 100644
index 000000000000..ffa328818ca6
--- /dev/null
+++ b/lib/mpi/generic_mpih-rshift.c
@@ -0,0 +1,63 @@
+/* mpih-rshift.c  -  MPI helper functions
+ * Copyright (C) 1994, 1996, 1998, 1999,
+ *               2000, 2001 Free Software Foundation, Inc.
+ *
+ * This file is part of GNUPG
+ *
+ * GNUPG is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * GNUPG is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA
+ *
+ * Note: This code is heavily based on the GNU MP Library.
+ *       Actually it's the same code with only minor changes in the
+ *       way the data is stored; this is to support the abstraction
+ *       of an optional secure memory allocation which may be used
+ *       to avoid revealing of sensitive data due to paging etc.
+ *       The GNU MP Library itself is published under the LGPL;
+ *       however I decided to publish this code under the plain GPL.
+ */
+
+#include "mpi-internal.h"
+
+/* Shift U (pointed to by UP and USIZE limbs long) CNT bits to the right
+ * and store the USIZE least significant limbs of the result at WP.
+ * The bits shifted out to the right are returned.
+ *
+ * Argument constraints:
+ * 1. 0 < CNT < BITS_PER_MP_LIMB
+ * 2. If the result is to be written over the input, WP must be <= UP.
+ */
+
+mpi_limb_t
+mpihelp_rshift(mpi_ptr_t wp, mpi_ptr_t up, mpi_size_t usize, unsigned cnt)
+{
+        mpi_limb_t high_limb, low_limb;
+        unsigned sh_1, sh_2;
+        mpi_size_t i;
+        mpi_limb_t retval;
+
+        sh_1 = cnt;
+        wp -= 1;
+        sh_2 = BITS_PER_MPI_LIMB - sh_1;
+        high_limb = up[0];
+        retval = high_limb << sh_2;
+        low_limb = high_limb;
+        for (i = 1; i < usize; i++) {
+                high_limb = up[i];
+                wp[i] = (low_limb >> sh_1) | (high_limb << sh_2);
+                low_limb = high_limb;
+        }
+        wp[i] = low_limb >> sh_1;
+
+        return retval;
+}
diff --git a/lib/mpi/generic_mpih-sub1.c b/lib/mpi/generic_mpih-sub1.c
new file mode 100644
index 000000000000..5d98ab7d6853
--- /dev/null
+++ b/lib/mpi/generic_mpih-sub1.c
@@ -0,0 +1,60 @@
+/* mpihelp-add_2.c  -  MPI helper functions
+ * Copyright (C) 1994, 1996, 1997, 1998, 2001 Free Software Foundation, Inc.
+ *
+ * This file is part of GnuPG.
+ *
+ * GnuPG is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * GnuPG is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA
+ *
+ * Note: This code is heavily based on the GNU MP Library.
+ *       Actually it's the same code with only minor changes in the
+ *       way the data is stored; this is to support the abstraction
+ *       of an optional secure memory allocation which may be used
+ *       to avoid revealing of sensitive data due to paging etc.
+ *       The GNU MP Library itself is published under the LGPL;
+ *       however I decided to publish this code under the plain GPL.
+ */
+
+#include "mpi-internal.h"
+#include "longlong.h"
+
+mpi_limb_t
+mpihelp_sub_n(mpi_ptr_t res_ptr, mpi_ptr_t s1_ptr,
+              mpi_ptr_t s2_ptr, mpi_size_t size)
+{
+        mpi_limb_t x, y, cy;
+        mpi_size_t j;
+
+        /* The loop counter and index J goes from -SIZE to -1.  This way
+           the loop becomes faster.  */
+        j = -size;
+
+        /* Offset the base pointers to compensate for the negative indices.  */
+        s1_ptr -= j;
+        s2_ptr -= j;
+        res_ptr -= j;
+
+        cy = 0;
+        do {
+                y = s2_ptr[j];
+                x = s1_ptr[j];
+                y += cy;        /* add previous carry to subtrahend */
+                cy = y < cy;    /* get out carry from that addition */
+                y = x - y;      /* main subtract */
+                cy += y > x;    /* get out carry from the subtract, combine */
+                res_ptr[j] = y;
+        } while (++j);
+
+        return cy;
+}
diff --git a/lib/mpi/longlong.h b/lib/mpi/longlong.h
new file mode 100644
index 000000000000..678ce4f1e124
--- /dev/null
+++ b/lib/mpi/longlong.h
@@ -0,0 +1,1366 @@
+/* longlong.h -- definitions for mixed size 32/64 bit arithmetic.
+ * Note: I added some stuff for use with gnupg
+ *
+ * Copyright (C) 1991, 1992, 1993, 1994, 1996, 1998,
+ *      2000, 2001, 2002, 2003 Free Software Foundation, Inc.
+ *
+ * This file is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU Library General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or (at your
+ * option) any later version.
+ *
+ * This file is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY
+ * or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU Library General Public
+ * License for more details.
+ *
+ * You should have received a copy of the GNU Library General Public License
+ * along with this file; see the file COPYING.LIB.  If not, write to
+ * the Free Software Foundation, Inc., 59 Temple Place - Suite 330, Boston,
+ * MA 02111-1307, USA. */
+
+#include <asm-generic/bitops/count_zeros.h>
+
+/* You have to define the following before including this file:
+ *
+ * UWtype -- An unsigned type, default type for operations (typically a "word")
+ * UHWtype -- An unsigned type, at least half the size of UWtype.
+ * UDWtype -- An unsigned type, at least twice as large a UWtype
+ * W_TYPE_SIZE -- size in bits of UWtype
+ *
+ * SItype, USItype -- Signed and unsigned 32 bit types.
+ * DItype, UDItype -- Signed and unsigned 64 bit types.
+ *
+ * On a 32 bit machine UWtype should typically be USItype;
+ * on a 64 bit machine, UWtype should typically be UDItype.
+*/
+
+#define __BITS4 (W_TYPE_SIZE / 4)
+#define __ll_B ((UWtype) 1 << (W_TYPE_SIZE / 2))
+#define __ll_lowpart(t) ((UWtype) (t) & (__ll_B - 1))
+#define __ll_highpart(t) ((UWtype) (t) >> (W_TYPE_SIZE / 2))
+
+/* This is used to make sure no undesirable sharing between different libraries
+        that use this file takes place.  */
+#ifndef __MPN
+#define __MPN(x) __##x
+#endif
+
+/* Define auxiliary asm macros.
+ *
+ * 1) umul_ppmm(high_prod, low_prod, multipler, multiplicand) multiplies two
+ * UWtype integers MULTIPLER and MULTIPLICAND, and generates a two UWtype
+ * word product in HIGH_PROD and LOW_PROD.
+ *
+ * 2) __umulsidi3(a,b) multiplies two UWtype integers A and B, and returns a
+ * UDWtype product.  This is just a variant of umul_ppmm.
+
+ * 3) udiv_qrnnd(quotient, remainder, high_numerator, low_numerator,
+ * denominator) divides a UDWtype, composed by the UWtype integers
+ * HIGH_NUMERATOR and LOW_NUMERATOR, by DENOMINATOR and places the quotient
+ * in QUOTIENT and the remainder in REMAINDER.  HIGH_NUMERATOR must be less
+ * than DENOMINATOR for correct operation.  If, in addition, the most
+ * significant bit of DENOMINATOR must be 1, then the pre-processor symbol
+ * UDIV_NEEDS_NORMALIZATION is defined to 1.
+ * 4) sdiv_qrnnd(quotient, remainder, high_numerator, low_numerator,
+ * denominator).  Like udiv_qrnnd but the numbers are signed.  The quotient
+ * is rounded towards 0.
+ *
+ * 5) count_leading_zeros(count, x) counts the number of zero-bits from the
+ * msb to the first non-zero bit in the UWtype X.  This is the number of
+ * steps X needs to be shifted left to set the msb.  Undefined for X == 0,
+ * unless the symbol COUNT_LEADING_ZEROS_0 is defined to some value.
+ *
+ * 6) count_trailing_zeros(count, x) like count_leading_zeros, but counts
+ * from the least significant end.
+ *
+ * 7) add_ssaaaa(high_sum, low_sum, high_addend_1, low_addend_1,
+ * high_addend_2, low_addend_2) adds two UWtype integers, composed by
+ * HIGH_ADDEND_1 and LOW_ADDEND_1, and HIGH_ADDEND_2 and LOW_ADDEND_2
+ * respectively.  The result is placed in HIGH_SUM and LOW_SUM.  Overflow
+ * (i.e. carry out) is not stored anywhere, and is lost.
+ *
+ * 8) sub_ddmmss(high_difference, low_difference, high_minuend, low_minuend,
+ * high_subtrahend, low_subtrahend) subtracts two two-word UWtype integers,
+ * composed by HIGH_MINUEND_1 and LOW_MINUEND_1, and HIGH_SUBTRAHEND_2 and
+ * LOW_SUBTRAHEND_2 respectively.  The result is placed in HIGH_DIFFERENCE
+ * and LOW_DIFFERENCE.  Overflow (i.e. carry out) is not stored anywhere,
+ * and is lost.
+ *
+ * If any of these macros are left undefined for a particular CPU,
+ * C macros are used.  */
+
+/* The CPUs come in alphabetical order below.
+ *
+ * Please add support for more CPUs here, or improve the current support
+ * for the CPUs below!  */
+
+#if defined(__GNUC__) && !defined(NO_ASM)
+
+/* We sometimes need to clobber "cc" with gcc2, but that would not be
+        understood by gcc1.     Use cpp to avoid major code duplication.  */
+#if __GNUC__ < 2
+#define __CLOBBER_CC
+#define __AND_CLOBBER_CC
+#else /* __GNUC__ >= 2 */
+#define __CLOBBER_CC : "cc"
+#define __AND_CLOBBER_CC , "cc"
+#endif /* __GNUC__ < 2 */
+
+/***************************************
+        **************  A29K  *****************
+        ***************************************/
+#if (defined(__a29k__) || defined(_AM29K)) && W_TYPE_SIZE == 32
+#define add_ssaaaa(sh, sl, ah, al, bh, bl) \
+        __asm__ ("add %1,%4,%5\n" \
+                "addc %0,%2,%3" \
+        : "=r" ((USItype)(sh)), \
+                "=&r" ((USItype)(sl)) \
+        : "%r" ((USItype)(ah)), \
+                "rI" ((USItype)(bh)), \
+                "%r" ((USItype)(al)), \
+                "rI" ((USItype)(bl)))
+#define sub_ddmmss(sh, sl, ah, al, bh, bl) \
+        __asm__ ("sub %1,%4,%5\n" \
+                "subc %0,%2,%3" \
+        : "=r" ((USItype)(sh)), \
+                "=&r" ((USItype)(sl)) \
+        : "r" ((USItype)(ah)), \
+                "rI" ((USItype)(bh)), \
+                "r" ((USItype)(al)), \
+                "rI" ((USItype)(bl)))
+#define umul_ppmm(xh, xl, m0, m1) \
+do { \
+                USItype __m0 = (m0), __m1 = (m1); \
+                __asm__ ("multiplu %0,%1,%2" \
+                : "=r" ((USItype)(xl)) \
+                : "r" (__m0), \
+                        "r" (__m1)); \
+                __asm__ ("multmu %0,%1,%2" \
+                : "=r" ((USItype)(xh)) \
+                : "r" (__m0), \
+                        "r" (__m1)); \
+} while (0)
+#define udiv_qrnnd(q, r, n1, n0, d) \
+        __asm__ ("dividu %0,%3,%4" \
+        : "=r" ((USItype)(q)), \
+                "=q" ((USItype)(r)) \
+        : "1" ((USItype)(n1)), \
+                "r" ((USItype)(n0)), \
+                "r" ((USItype)(d)))
+#endif /* __a29k__ */
+
+#if defined(__alpha) && W_TYPE_SIZE == 64
+#define umul_ppmm(ph, pl, m0, m1) \
+do { \
+                UDItype __m0 = (m0), __m1 = (m1); \
+                __asm__ ("umulh %r1,%2,%0" \
+                : "=r" ((UDItype) ph) \
+                : "%rJ" (__m0), \
+                        "rI" (__m1)); \
+                (pl) = __m0 * __m1; \
+        } while (0)
+#define UMUL_TIME 46
+#ifndef LONGLONG_STANDALONE
+#define udiv_qrnnd(q, r, n1, n0, d) \
+do { UDItype __r; \
+        (q) = __udiv_qrnnd(&__r, (n1), (n0), (d)); \
+        (r) = __r; \
+} while (0)
+extern UDItype __udiv_qrnnd();
+#define UDIV_TIME 220
+#endif /* LONGLONG_STANDALONE */
+#endif /* __alpha */
+
+/***************************************
+        **************  ARM  ******************
+        ***************************************/
+#if defined(__arm__) && W_TYPE_SIZE == 32
+#define add_ssaaaa(sh, sl, ah, al, bh, bl) \
+        __asm__ ("adds %1, %4, %5\n" \
+                "adc  %0, %2, %3" \
+        : "=r" ((USItype)(sh)), \
+                "=&r" ((USItype)(sl)) \
+        : "%r" ((USItype)(ah)), \
+                "rI" ((USItype)(bh)), \
+                "%r" ((USItype)(al)), \
+                "rI" ((USItype)(bl)))
+#define sub_ddmmss(sh, sl, ah, al, bh, bl) \
+        __asm__ ("subs %1, %4, %5\n" \
+                "sbc  %0, %2, %3" \
+        : "=r" ((USItype)(sh)), \
+                "=&r" ((USItype)(sl)) \
+        : "r" ((USItype)(ah)), \
+                "rI" ((USItype)(bh)), \
+                "r" ((USItype)(al)), \
+                "rI" ((USItype)(bl)))
+#if defined __ARM_ARCH_2__ || defined __ARM_ARCH_3__
+#define umul_ppmm(xh, xl, a, b) \
+        __asm__ ("%@ Inlined umul_ppmm\n" \
+                "mov    %|r0, %2, lsr #16               @ AAAA\n" \
+                "mov    %|r2, %3, lsr #16               @ BBBB\n" \
+                "bic    %|r1, %2, %|r0, lsl #16         @ aaaa\n" \
+                "bic    %0, %3, %|r2, lsl #16           @ bbbb\n" \
+                "mul    %1, %|r1, %|r2                  @ aaaa * BBBB\n" \
+                "mul    %|r2, %|r0, %|r2                @ AAAA * BBBB\n" \
+                "mul    %|r1, %0, %|r1                  @ aaaa * bbbb\n" \
+                "mul    %0, %|r0, %0                    @ AAAA * bbbb\n" \
+                "adds   %|r0, %1, %0                    @ central sum\n" \
+                "addcs  %|r2, %|r2, #65536\n" \
+                "adds   %1, %|r1, %|r0, lsl #16\n" \
+                "adc    %0, %|r2, %|r0, lsr #16" \
+        : "=&r" ((USItype)(xh)), \
+                "=r" ((USItype)(xl)) \
+        : "r" ((USItype)(a)), \
+                "r" ((USItype)(b)) \
+        : "r0", "r1", "r2")
+#else
+#define umul_ppmm(xh, xl, a, b) \
+        __asm__ ("%@ Inlined umul_ppmm\n" \
+                "umull %r1, %r0, %r2, %r3" \
+        : "=&r" ((USItype)(xh)), \
+                        "=r" ((USItype)(xl)) \
+        : "r" ((USItype)(a)), \
+                        "r" ((USItype)(b)) \
+        : "r0", "r1")
+#endif
+#define UMUL_TIME 20
+#define UDIV_TIME 100
+#endif /* __arm__ */
+
+/***************************************
+        **************  CLIPPER  **************
+        ***************************************/
+#if defined(__clipper__) && W_TYPE_SIZE == 32
+#define umul_ppmm(w1, w0, u, v) \
+        ({union {UDItype __ll; \
+                struct {USItype __l, __h; } __i; \
+        } __xx; \
+        __asm__ ("mulwux %2,%0" \
+        : "=r" (__xx.__ll) \
+        : "%0" ((USItype)(u)), \
+                "r" ((USItype)(v))); \
+        (w1) = __xx.__i.__h; (w0) = __xx.__i.__l; })
+#define smul_ppmm(w1, w0, u, v) \
+        ({union {DItype __ll; \
+                struct {SItype __l, __h; } __i; \
+        } __xx; \
+        __asm__ ("mulwx %2,%0" \
+        : "=r" (__xx.__ll) \
+        : "%0" ((SItype)(u)), \
+                "r" ((SItype)(v))); \
+        (w1) = __xx.__i.__h; (w0) = __xx.__i.__l; })
+#define __umulsidi3(u, v) \
+        ({UDItype __w; \
+        __asm__ ("mulwux %2,%0" \
+        : "=r" (__w) \
+        : "%0" ((USItype)(u)), \
+                "r" ((USItype)(v))); \
+        __w; })
+#endif /* __clipper__ */
+
+/***************************************
+        **************  GMICRO  ***************
+        ***************************************/
+#if defined(__gmicro__) && W_TYPE_SIZE == 32
+#define add_ssaaaa(sh, sl, ah, al, bh, bl) \
+        __asm__ ("add.w %5,%1\n" \
+                "addx %3,%0" \
+        : "=g" ((USItype)(sh)), \
+                "=&g" ((USItype)(sl)) \
+        : "%0" ((USItype)(ah)), \
+                "g" ((USItype)(bh)), \
+                "%1" ((USItype)(al)), \
+                "g" ((USItype)(bl)))
+#define sub_ddmmss(sh, sl, ah, al, bh, bl) \
+        __asm__ ("sub.w %5,%1\n" \
+                "subx %3,%0" \
+        : "=g" ((USItype)(sh)), \
+                "=&g" ((USItype)(sl)) \
+        : "0" ((USItype)(ah)), \
+                "g" ((USItype)(bh)), \
+                "1" ((USItype)(al)), \
+                "g" ((USItype)(bl)))
+#define umul_ppmm(ph, pl, m0, m1) \
+        __asm__ ("mulx %3,%0,%1" \
+        : "=g" ((USItype)(ph)), \
+                "=r" ((USItype)(pl)) \
+        : "%0" ((USItype)(m0)), \
+                "g" ((USItype)(m1)))
+#define udiv_qrnnd(q, r, nh, nl, d) \
+        __asm__ ("divx %4,%0,%1" \
+        : "=g" ((USItype)(q)), \
+                "=r" ((USItype)(r)) \
+        : "1" ((USItype)(nh)), \
+                "0" ((USItype)(nl)), \
+                "g" ((USItype)(d)))
+#endif
+
+/***************************************
+        **************  HPPA  *****************
+        ***************************************/
+#if defined(__hppa) && W_TYPE_SIZE == 32
+#define add_ssaaaa(sh, sl, ah, al, bh, bl) \
+        __asm__ ("add %4,%5,%1\n" \
+                   "addc %2,%3,%0" \
+        : "=r" ((USItype)(sh)), \
+             "=&r" ((USItype)(sl)) \
+        : "%rM" ((USItype)(ah)), \
+             "rM" ((USItype)(bh)), \
+             "%rM" ((USItype)(al)), \
+             "rM" ((USItype)(bl)))
+#define sub_ddmmss(sh, sl, ah, al, bh, bl) \
+        __asm__ ("sub %4,%5,%1\n" \
+           "subb %2,%3,%0" \
+        : "=r" ((USItype)(sh)), \
+             "=&r" ((USItype)(sl)) \
+        : "rM" ((USItype)(ah)), \
+             "rM" ((USItype)(bh)), \
+             "rM" ((USItype)(al)), \
+             "rM" ((USItype)(bl)))
+#if defined(_PA_RISC1_1)
+#define umul_ppmm(wh, wl, u, v) \
+do { \
+        union {UDItype __ll; \
+        struct {USItype __h, __l; } __i; \
+        } __xx; \
+        __asm__ ("xmpyu %1,%2,%0" \
+        : "=*f" (__xx.__ll) \
+        : "*f" ((USItype)(u)), \
+               "*f" ((USItype)(v))); \
+        (wh) = __xx.__i.__h; \
+        (wl) = __xx.__i.__l; \
+} while (0)
+#define UMUL_TIME 8
+#define UDIV_TIME 60
+#else
+#define UMUL_TIME 40
+#define UDIV_TIME 80
+#endif
+#ifndef LONGLONG_STANDALONE
+#define udiv_qrnnd(q, r, n1, n0, d) \
+do { USItype __r; \
+        (q) = __udiv_qrnnd(&__r, (n1), (n0), (d)); \
+        (r) = __r; \
+} while (0)
+extern USItype __udiv_qrnnd();
+#endif /* LONGLONG_STANDALONE */
+#endif /* hppa */
+
+/***************************************
+        **************  I370  *****************
+        ***************************************/
+#if (defined(__i370__) || defined(__mvs__)) && W_TYPE_SIZE == 32
+#define umul_ppmm(xh, xl, m0, m1) \
+do { \
+        union {UDItype __ll; \
+           struct {USItype __h, __l; } __i; \
+        } __xx; \
+        USItype __m0 = (m0), __m1 = (m1); \
+        __asm__ ("mr %0,%3" \
+        : "=r" (__xx.__i.__h), \
+               "=r" (__xx.__i.__l) \
+        : "%1" (__m0), \
+               "r" (__m1)); \
+        (xh) = __xx.__i.__h; (xl) = __xx.__i.__l; \
+        (xh) += ((((SItype) __m0 >> 31) & __m1) \
+             + (((SItype) __m1 >> 31) & __m0)); \
+} while (0)
+#define smul_ppmm(xh, xl, m0, m1) \
+do { \
+        union {DItype __ll; \
+           struct {USItype __h, __l; } __i; \
+        } __xx; \
+        __asm__ ("mr %0,%3" \
+        : "=r" (__xx.__i.__h), \
+               "=r" (__xx.__i.__l) \
+        : "%1" (m0), \
+               "r" (m1)); \
+        (xh) = __xx.__i.__h; (xl) = __xx.__i.__l; \
+} while (0)
+#define sdiv_qrnnd(q, r, n1, n0, d) \
+do { \
+        union {DItype __ll; \
+           struct {USItype __h, __l; } __i; \
+        } __xx; \
+        __xx.__i.__h = n1; __xx.__i.__l = n0; \
+        __asm__ ("dr %0,%2" \
+        : "=r" (__xx.__ll) \
+        : "0" (__xx.__ll), "r" (d)); \
+        (q) = __xx.__i.__l; (r) = __xx.__i.__h; \
+} while (0)
+#endif
+
+/***************************************
+        **************  I386  *****************
+        ***************************************/
+#undef __i386__
+#if (defined(__i386__) || defined(__i486__)) && W_TYPE_SIZE == 32
+#define add_ssaaaa(sh, sl, ah, al, bh, bl) \
+        __asm__ ("addl %5,%1\n" \
+           "adcl %3,%0" \
+        : "=r" ((USItype)(sh)), \
+             "=&r" ((USItype)(sl)) \
+        : "%0" ((USItype)(ah)), \
+             "g" ((USItype)(bh)), \
+             "%1" ((USItype)(al)), \
+             "g" ((USItype)(bl)))
+#define sub_ddmmss(sh, sl, ah, al, bh, bl) \
+        __asm__ ("subl %5,%1\n" \
+           "sbbl %3,%0" \
+        : "=r" ((USItype)(sh)), \
+             "=&r" ((USItype)(sl)) \
+        : "0" ((USItype)(ah)), \
+             "g" ((USItype)(bh)), \
+             "1" ((USItype)(al)), \
+             "g" ((USItype)(bl)))
+#define umul_ppmm(w1, w0, u, v) \
+        __asm__ ("mull %3" \
+        : "=a" ((USItype)(w0)), \
+             "=d" ((USItype)(w1)) \
+        : "%0" ((USItype)(u)), \
+             "rm" ((USItype)(v)))
+#define udiv_qrnnd(q, r, n1, n0, d) \
+        __asm__ ("divl %4" \
+        : "=a" ((USItype)(q)), \
+             "=d" ((USItype)(r)) \
+        : "0" ((USItype)(n0)), \
+             "1" ((USItype)(n1)), \
+             "rm" ((USItype)(d)))
+#ifndef UMUL_TIME
+#define UMUL_TIME 40
+#endif
+#ifndef UDIV_TIME
+#define UDIV_TIME 40
+#endif
+#endif /* 80x86 */
+
+/***************************************
+        **************  I860  *****************
+        ***************************************/
+#if defined(__i860__) && W_TYPE_SIZE == 32
+#define rshift_rhlc(r, h, l, c) \
+        __asm__ ("shr %3,r0,r0\n" \
+        "shrd %1,%2,%0" \
+           "=r" (r) : "r" (h), "r" (l), "rn" (c))
+#endif /* i860 */
+
+/***************************************
+        **************  I960  *****************
+        ***************************************/
+#if defined(__i960__) && W_TYPE_SIZE == 32
+#define add_ssaaaa(sh, sl, ah, al, bh, bl) \
+        __asm__ ("cmpo 1,0\n" \
+        "addc %5,%4,%1\n" \
+        "addc %3,%2,%0" \
+        : "=r" ((USItype)(sh)), \
+             "=&r" ((USItype)(sl)) \
+        : "%dI" ((USItype)(ah)), \
+             "dI" ((USItype)(bh)), \
+             "%dI" ((USItype)(al)), \
+             "dI" ((USItype)(bl)))
+#define sub_ddmmss(sh, sl, ah, al, bh, bl) \
+        __asm__ ("cmpo 0,0\n" \
+        "subc %5,%4,%1\n" \
+        "subc %3,%2,%0" \
+        : "=r" ((USItype)(sh)), \
+             "=&r" ((USItype)(sl)) \
+        : "dI" ((USItype)(ah)), \
+             "dI" ((USItype)(bh)), \
+             "dI" ((USItype)(al)), \
+             "dI" ((USItype)(bl)))
+#define umul_ppmm(w1, w0, u, v) \
+        ({union {UDItype __ll; \
+           struct {USItype __l, __h; } __i; \
+        } __xx; \
+        __asm__ ("emul        %2,%1,%0" \
+        : "=d" (__xx.__ll) \
+        : "%dI" ((USItype)(u)), \
+             "dI" ((USItype)(v))); \
+        (w1) = __xx.__i.__h; (w0) = __xx.__i.__l; })
+#define __umulsidi3(u, v) \
+        ({UDItype __w; \
+        __asm__ ("emul      %2,%1,%0" \
+        : "=d" (__w) \
+        : "%dI" ((USItype)(u)), \
+               "dI" ((USItype)(v))); \
+        __w; })
+#define udiv_qrnnd(q, r, nh, nl, d) \
+do { \
+        union {UDItype __ll; \
+           struct {USItype __l, __h; } __i; \
+        } __nn; \
+        __nn.__i.__h = (nh); __nn.__i.__l = (nl); \
+        __asm__ ("ediv %d,%n,%0" \
+        : "=d" (__rq.__ll) \
+        : "dI" (__nn.__ll), \
+             "dI" ((USItype)(d))); \
+        (r) = __rq.__i.__l; (q) = __rq.__i.__h; \
+} while (0)
+#if defined(__i960mx)           /* what is the proper symbol to test??? */
+#define rshift_rhlc(r, h, l, c) \
+do { \
+        union {UDItype __ll; \
+           struct {USItype __l, __h; } __i; \
+        } __nn; \
+        __nn.__i.__h = (h); __nn.__i.__l = (l); \
+        __asm__ ("shre %2,%1,%0" \
+        : "=d" (r) : "dI" (__nn.__ll), "dI" (c)); \
+}
+#endif /* i960mx */
+#endif /* i960 */
+
+/***************************************
+        **************  68000   ****************
+        ***************************************/
+#if (defined(__mc68000__) || defined(__mc68020__) || defined(__NeXT__) || defined(mc68020)) && W_TYPE_SIZE == 32
+#define add_ssaaaa(sh, sl, ah, al, bh, bl) \
+        __asm__ ("add%.l %5,%1\n" \
+           "addx%.l %3,%0" \
+        : "=d" ((USItype)(sh)), \
+             "=&d" ((USItype)(sl)) \
+        : "%0" ((USItype)(ah)), \
+             "d" ((USItype)(bh)), \
+             "%1" ((USItype)(al)), \
+             "g" ((USItype)(bl)))
+#define sub_ddmmss(sh, sl, ah, al, bh, bl) \
+        __asm__ ("sub%.l %5,%1\n" \
+           "subx%.l %3,%0" \
+        : "=d" ((USItype)(sh)), \
+             "=&d" ((USItype)(sl)) \
+        : "0" ((USItype)(ah)), \
+             "d" ((USItype)(bh)), \
+             "1" ((USItype)(al)), \
+             "g" ((USItype)(bl)))
+#if (defined(__mc68020__) || defined(__NeXT__) || defined(mc68020))
+#define umul_ppmm(w1, w0, u, v) \
+        __asm__ ("mulu%.l %3,%1:%0" \
+        : "=d" ((USItype)(w0)), \
+             "=d" ((USItype)(w1)) \
+        : "%0" ((USItype)(u)), \
+             "dmi" ((USItype)(v)))
+#define UMUL_TIME 45
+#define udiv_qrnnd(q, r, n1, n0, d) \
+        __asm__ ("divu%.l %4,%1:%0" \
+        : "=d" ((USItype)(q)), \
+             "=d" ((USItype)(r)) \
+        : "0" ((USItype)(n0)), \
+             "1" ((USItype)(n1)), \
+             "dmi" ((USItype)(d)))
+#define UDIV_TIME 90
+#define sdiv_qrnnd(q, r, n1, n0, d) \
+        __asm__ ("divs%.l %4,%1:%0" \
+        : "=d" ((USItype)(q)), \
+             "=d" ((USItype)(r)) \
+        : "0" ((USItype)(n0)), \
+             "1" ((USItype)(n1)), \
+             "dmi" ((USItype)(d)))
+#else /* not mc68020 */
+#define umul_ppmm(xh, xl, a, b) \
+do { USItype __umul_tmp1, __umul_tmp2; \
+        __asm__ ("| Inlined umul_ppmm\n" \
+        "move%.l %5,%3\n" \
+        "move%.l %2,%0\n" \
+        "move%.w %3,%1\n" \
+        "swap   %3\n" \
+        "swap   %0\n" \
+        "mulu   %2,%1\n" \
+        "mulu   %3,%0\n" \
+        "mulu   %2,%3\n" \
+        "swap   %2\n" \
+        "mulu   %5,%2\n" \
+        "add%.l %3,%2\n" \
+        "jcc    1f\n" \
+        "add%.l %#0x10000,%0\n" \
+        "1:     move%.l %2,%3\n" \
+        "clr%.w %2\n" \
+        "swap   %2\n" \
+        "swap   %3\n" \
+        "clr%.w %3\n" \
+        "add%.l %3,%1\n" \
+        "addx%.l %2,%0\n" \
+        "| End inlined umul_ppmm" \
+        : "=&d" ((USItype)(xh)), "=&d" ((USItype)(xl)), \
+                "=d" (__umul_tmp1), "=&d" (__umul_tmp2) \
+        : "%2" ((USItype)(a)), "d" ((USItype)(b))); \
+} while (0)
+#define UMUL_TIME 100
+#define UDIV_TIME 400
+#endif /* not mc68020 */
+#endif /* mc68000 */
+
+/***************************************
+        **************  88000   ****************
+        ***************************************/
+#if defined(__m88000__) && W_TYPE_SIZE == 32
+#define add_ssaaaa(sh, sl, ah, al, bh, bl) \
+        __asm__ ("addu.co %1,%r4,%r5\n" \
+           "addu.ci %0,%r2,%r3" \
+        : "=r" ((USItype)(sh)), \
+             "=&r" ((USItype)(sl)) \
+        : "%rJ" ((USItype)(ah)), \
+             "rJ" ((USItype)(bh)), \
+             "%rJ" ((USItype)(al)), \
+             "rJ" ((USItype)(bl)))
+#define sub_ddmmss(sh, sl, ah, al, bh, bl) \
+        __asm__ ("subu.co %1,%r4,%r5\n" \
+           "subu.ci %0,%r2,%r3" \
+        : "=r" ((USItype)(sh)), \
+             "=&r" ((USItype)(sl)) \
+        : "rJ" ((USItype)(ah)), \
+             "rJ" ((USItype)(bh)), \
+             "rJ" ((USItype)(al)), \
+             "rJ" ((USItype)(bl)))
+#if defined(__m88110__)
+#define umul_ppmm(wh, wl, u, v) \
+do { \
+        union {UDItype __ll; \
+           struct {USItype __h, __l; } __i; \
+        } __x; \
+        __asm__ ("mulu.d %0,%1,%2" : "=r" (__x.__ll) : "r" (u), "r" (v)); \
+        (wh) = __x.__i.__h; \
+        (wl) = __x.__i.__l; \
+} while (0)
+#define udiv_qrnnd(q, r, n1, n0, d) \
+        ({union {UDItype __ll; \
+           struct {USItype __h, __l; } __i; \
+        } __x, __q; \
+        __x.__i.__h = (n1); __x.__i.__l = (n0); \
+        __asm__ ("divu.d %0,%1,%2" \
+        : "=r" (__q.__ll) : "r" (__x.__ll), "r" (d)); \
+        (r) = (n0) - __q.__l * (d); (q) = __q.__l; })
+#define UMUL_TIME 5
+#define UDIV_TIME 25
+#else
+#define UMUL_TIME 17
+#define UDIV_TIME 150
+#endif /* __m88110__ */
+#endif /* __m88000__ */
+
+/***************************************
+        **************  MIPS  *****************
+        ***************************************/
+#if defined(__mips__) && W_TYPE_SIZE == 32
+#if __GNUC__ > 2 || __GNUC_MINOR__ >= 7
+#define umul_ppmm(w1, w0, u, v) \
+        __asm__ ("multu %2,%3" \
+        : "=l" ((USItype)(w0)), \
+             "=h" ((USItype)(w1)) \
+        : "d" ((USItype)(u)), \
+             "d" ((USItype)(v)))
+#else
+#define umul_ppmm(w1, w0, u, v) \
+        __asm__ ("multu %2,%3\n" \
+           "mflo %0\n" \
+           "mfhi %1" \
+        : "=d" ((USItype)(w0)), \
+             "=d" ((USItype)(w1)) \
+        : "d" ((USItype)(u)), \
+             "d" ((USItype)(v)))
+#endif
+#define UMUL_TIME 10
+#define UDIV_TIME 100
+#endif /* __mips__ */
+
+/***************************************
+        **************  MIPS/64  **************
+        ***************************************/
+#if (defined(__mips) && __mips >= 3) && W_TYPE_SIZE == 64
+#if __GNUC__ > 2 || __GNUC_MINOR__ >= 7
+#define umul_ppmm(w1, w0, u, v) \
+        __asm__ ("dmultu %2,%3" \
+        : "=l" ((UDItype)(w0)), \
+             "=h" ((UDItype)(w1)) \
+        : "d" ((UDItype)(u)), \
+             "d" ((UDItype)(v)))
+#else
+#define umul_ppmm(w1, w0, u, v) \
+        __asm__ ("dmultu %2,%3\n" \
+           "mflo %0\n" \
+           "mfhi %1" \
+        : "=d" ((UDItype)(w0)), \
+             "=d" ((UDItype)(w1)) \
+        : "d" ((UDItype)(u)), \
+             "d" ((UDItype)(v)))
+#endif
+#define UMUL_TIME 20
+#define UDIV_TIME 140
+#endif /* __mips__ */
+
+/***************************************
+        **************  32000   ****************
+        ***************************************/
+#if defined(__ns32000__) && W_TYPE_SIZE == 32
+#define umul_ppmm(w1, w0, u, v) \
+        ({union {UDItype __ll; \
+           struct {USItype __l, __h; } __i; \
+        } __xx; \
+        __asm__ ("meid %2,%0" \
+        : "=g" (__xx.__ll) \
+        : "%0" ((USItype)(u)), \
+             "g" ((USItype)(v))); \
+        (w1) = __xx.__i.__h; (w0) = __xx.__i.__l; })
+#define __umulsidi3(u, v) \
+        ({UDItype __w; \
+        __asm__ ("meid %2,%0" \
+        : "=g" (__w) \
+        : "%0" ((USItype)(u)), \
+               "g" ((USItype)(v))); \
+        __w; })
+#define udiv_qrnnd(q, r, n1, n0, d) \
+        ({union {UDItype __ll; \
+           struct {USItype __l, __h; } __i; \
+        } __xx; \
+        __xx.__i.__h = (n1); __xx.__i.__l = (n0); \
+        __asm__ ("deid %2,%0" \
+        : "=g" (__xx.__ll) \
+        : "0" (__xx.__ll), \
+             "g" ((USItype)(d))); \
+        (r) = __xx.__i.__l; (q) = __xx.__i.__h; })
+#endif /* __ns32000__ */
+
+/***************************************
+        **************  PPC  ******************
+        ***************************************/
+#if (defined(_ARCH_PPC) || defined(_IBMR2)) && W_TYPE_SIZE == 32
+#define add_ssaaaa(sh, sl, ah, al, bh, bl) \
+do { \
+        if (__builtin_constant_p(bh) && (bh) == 0) \
+                __asm__ ("{a%I4|add%I4c} %1,%3,%4\n\t{aze|addze} %0,%2" \
+                : "=r" ((USItype)(sh)), \
+                "=&r" ((USItype)(sl)) \
+                : "%r" ((USItype)(ah)), \
+                "%r" ((USItype)(al)), \
+                "rI" ((USItype)(bl))); \
+        else if (__builtin_constant_p(bh) && (bh) == ~(USItype) 0) \
+                __asm__ ("{a%I4|add%I4c} %1,%3,%4\n\t{ame|addme} %0,%2" \
+                : "=r" ((USItype)(sh)), \
+                "=&r" ((USItype)(sl)) \
+                : "%r" ((USItype)(ah)), \
+                "%r" ((USItype)(al)), \
+                "rI" ((USItype)(bl))); \
+        else \
+                __asm__ ("{a%I5|add%I5c} %1,%4,%5\n\t{ae|adde} %0,%2,%3" \
+                : "=r" ((USItype)(sh)), \
+                "=&r" ((USItype)(sl)) \
+                : "%r" ((USItype)(ah)), \
+                "r" ((USItype)(bh)), \
+                "%r" ((USItype)(al)), \
+                "rI" ((USItype)(bl))); \
+} while (0)
+#define sub_ddmmss(sh, sl, ah, al, bh, bl) \
+do { \
+        if (__builtin_constant_p(ah) && (ah) == 0) \
+                __asm__ ("{sf%I3|subf%I3c} %1,%4,%3\n\t{sfze|subfze} %0,%2" \
+                : "=r" ((USItype)(sh)), \
+                "=&r" ((USItype)(sl)) \
+                : "r" ((USItype)(bh)), \
+                "rI" ((USItype)(al)), \
+                "r" ((USItype)(bl))); \
+        else if (__builtin_constant_p(ah) && (ah) == ~(USItype) 0) \
+                __asm__ ("{sf%I3|subf%I3c} %1,%4,%3\n\t{sfme|subfme} %0,%2" \
+                : "=r" ((USItype)(sh)), \
+                "=&r" ((USItype)(sl)) \
+                : "r" ((USItype)(bh)), \
+                "rI" ((USItype)(al)), \
+                "r" ((USItype)(bl))); \
+        else if (__builtin_constant_p(bh) && (bh) == 0) \
+                __asm__ ("{sf%I3|subf%I3c} %1,%4,%3\n\t{ame|addme} %0,%2" \
+                : "=r" ((USItype)(sh)), \
+                "=&r" ((USItype)(sl)) \
+                : "r" ((USItype)(ah)), \
+                "rI" ((USItype)(al)), \
+                "r" ((USItype)(bl))); \
+        else if (__builtin_constant_p(bh) && (bh) == ~(USItype) 0) \
+                __asm__ ("{sf%I3|subf%I3c} %1,%4,%3\n\t{aze|addze} %0,%2" \
+                : "=r" ((USItype)(sh)), \
+                "=&r" ((USItype)(sl)) \
+                : "r" ((USItype)(ah)), \
+                "rI" ((USItype)(al)), \
+                "r" ((USItype)(bl))); \
+        else \
+                __asm__ ("{sf%I4|subf%I4c} %1,%5,%4\n\t{sfe|subfe} %0,%3,%2" \
+                : "=r" ((USItype)(sh)), \
+                "=&r" ((USItype)(sl)) \
+                : "r" ((USItype)(ah)), \
+                "r" ((USItype)(bh)), \
+                "rI" ((USItype)(al)), \
+                "r" ((USItype)(bl))); \
+} while (0)
+#if defined(_ARCH_PPC)
+#define umul_ppmm(ph, pl, m0, m1) \
+do { \
+        USItype __m0 = (m0), __m1 = (m1); \
+        __asm__ ("mulhwu %0,%1,%2" \
+        : "=r" ((USItype) ph) \
+        : "%r" (__m0), \
+        "r" (__m1)); \
+        (pl) = __m0 * __m1; \
+} while (0)
+#define UMUL_TIME 15
+#define smul_ppmm(ph, pl, m0, m1) \
+do { \
+        SItype __m0 = (m0), __m1 = (m1); \
+        __asm__ ("mulhw %0,%1,%2" \
+        : "=r" ((SItype) ph) \
+        : "%r" (__m0), \
+        "r" (__m1)); \
+        (pl) = __m0 * __m1; \
+} while (0)
+#define SMUL_TIME 14
+#define UDIV_TIME 120
+#else
+#define umul_ppmm(xh, xl, m0, m1) \
+do { \
+        USItype __m0 = (m0), __m1 = (m1); \
+        __asm__ ("mul %0,%2,%3" \
+        : "=r" ((USItype)(xh)), \
+        "=q" ((USItype)(xl)) \
+        : "r" (__m0), \
+        "r" (__m1)); \
+        (xh) += ((((SItype) __m0 >> 31) & __m1) \
+        + (((SItype) __m1 >> 31) & __m0)); \
+} while (0)
+#define UMUL_TIME 8
+#define smul_ppmm(xh, xl, m0, m1) \
+        __asm__ ("mul %0,%2,%3" \
+        : "=r" ((SItype)(xh)), \
+        "=q" ((SItype)(xl)) \
+        : "r" (m0), \
+        "r" (m1))
+#define SMUL_TIME 4
+#define sdiv_qrnnd(q, r, nh, nl, d) \
+        __asm__ ("div %0,%2,%4" \
+        : "=r" ((SItype)(q)), "=q" ((SItype)(r)) \
+        : "r" ((SItype)(nh)), "1" ((SItype)(nl)), "r" ((SItype)(d)))
+#define UDIV_TIME 100
+#endif
+#endif /* Power architecture variants.  */
+
+/***************************************
+        **************  PYR  ******************
+        ***************************************/
+#if defined(__pyr__) && W_TYPE_SIZE == 32
+#define add_ssaaaa(sh, sl, ah, al, bh, bl) \
+        __asm__ ("addw        %5,%1\n" \
+        "addwc  %3,%0" \
+        : "=r" ((USItype)(sh)), \
+        "=&r" ((USItype)(sl)) \
+        : "%0" ((USItype)(ah)), \
+        "g" ((USItype)(bh)), \
+        "%1" ((USItype)(al)), \
+        "g" ((USItype)(bl)))
+#define sub_ddmmss(sh, sl, ah, al, bh, bl) \
+        __asm__ ("subw        %5,%1\n" \
+        "subwb  %3,%0" \
+        : "=r" ((USItype)(sh)), \
+        "=&r" ((USItype)(sl)) \
+        : "0" ((USItype)(ah)), \
+        "g" ((USItype)(bh)), \
+        "1" ((USItype)(al)), \
+        "g" ((USItype)(bl)))
+        /* This insn works on Pyramids with AP, XP, or MI CPUs, but not with SP.  */
+#define umul_ppmm(w1, w0, u, v) \
+        ({union {UDItype __ll; \
+        struct {USItype __h, __l; } __i; \
+        } __xx; \
+        __asm__ ("movw %1,%R0\n" \
+        "uemul %2,%0" \
+        : "=&r" (__xx.__ll) \
+        : "g" ((USItype) (u)), \
+        "g" ((USItype)(v))); \
+        (w1) = __xx.__i.__h; (w0) = __xx.__i.__l; })
+#endif /* __pyr__ */
+
+/***************************************
+        **************  RT/ROMP  **************
+        ***************************************/
+#if defined(__ibm032__) /* RT/ROMP */   && W_TYPE_SIZE == 32
+#define add_ssaaaa(sh, sl, ah, al, bh, bl) \
+        __asm__ ("a %1,%5\n" \
+        "ae %0,%3" \
+        : "=r" ((USItype)(sh)), \
+        "=&r" ((USItype)(sl)) \
+        : "%0" ((USItype)(ah)), \
+        "r" ((USItype)(bh)), \
+        "%1" ((USItype)(al)), \
+        "r" ((USItype)(bl)))
+#define sub_ddmmss(sh, sl, ah, al, bh, bl) \
+        __asm__ ("s %1,%5\n" \
+        "se %0,%3" \
+        : "=r" ((USItype)(sh)), \
+        "=&r" ((USItype)(sl)) \
+        : "0" ((USItype)(ah)), \
+        "r" ((USItype)(bh)), \
+        "1" ((USItype)(al)), \
+        "r" ((USItype)(bl)))
+#define umul_ppmm(ph, pl, m0, m1) \
+do { \
+        USItype __m0 = (m0), __m1 = (m1); \
+        __asm__ ( \
+        "s       r2,r2\n" \
+        "mts    r10,%2\n" \
+        "m      r2,%3\n" \
+        "m      r2,%3\n" \
+        "m      r2,%3\n" \
+        "m      r2,%3\n" \
+        "m      r2,%3\n" \
+        "m      r2,%3\n" \
+        "m      r2,%3\n" \
+        "m      r2,%3\n" \
+        "m      r2,%3\n" \
+        "m      r2,%3\n" \
+        "m      r2,%3\n" \
+        "m      r2,%3\n" \
+        "m      r2,%3\n" \
+        "m      r2,%3\n" \
+        "m      r2,%3\n" \
+        "m      r2,%3\n" \
+        "cas    %0,r2,r0\n" \
+        "mfs    r10,%1" \
+        : "=r" ((USItype)(ph)), \
+        "=r" ((USItype)(pl)) \
+        : "%r" (__m0), \
+        "r" (__m1) \
+        : "r2"); \
+        (ph) += ((((SItype) __m0 >> 31) & __m1) \
+        + (((SItype) __m1 >> 31) & __m0)); \
+} while (0)
+#define UMUL_TIME 20
+#define UDIV_TIME 200
+#endif /* RT/ROMP */
+
+/***************************************
+        **************  SH2  ******************
+        ***************************************/
+#if (defined(__sh2__) || defined(__sh3__) || defined(__SH4__)) \
+        && W_TYPE_SIZE == 32
+#define umul_ppmm(w1, w0, u, v) \
+        __asm__ ( \
+        "dmulu.l %2,%3\n" \
+        "sts    macl,%1\n" \
+        "sts    mach,%0" \
+        : "=r" ((USItype)(w1)), \
+        "=r" ((USItype)(w0)) \
+        : "r" ((USItype)(u)), \
+        "r" ((USItype)(v)) \
+        : "macl", "mach")
+#define UMUL_TIME 5
+#endif
+
+/***************************************
+        **************  SPARC   ****************
+        ***************************************/
+#if defined(__sparc__) && W_TYPE_SIZE == 32
+#define add_ssaaaa(sh, sl, ah, al, bh, bl) \
+        __asm__ ("addcc %r4,%5,%1\n" \
+        "addx %r2,%3,%0" \
+        : "=r" ((USItype)(sh)), \
+        "=&r" ((USItype)(sl)) \
+        : "%rJ" ((USItype)(ah)), \
+        "rI" ((USItype)(bh)), \
+        "%rJ" ((USItype)(al)), \
+        "rI" ((USItype)(bl)) \
+        __CLOBBER_CC)
+#define sub_ddmmss(sh, sl, ah, al, bh, bl) \
+        __asm__ ("subcc %r4,%5,%1\n" \
+        "subx %r2,%3,%0" \
+        : "=r" ((USItype)(sh)), \
+        "=&r" ((USItype)(sl)) \
+        : "rJ" ((USItype)(ah)), \
+        "rI" ((USItype)(bh)), \
+        "rJ" ((USItype)(al)), \
+        "rI" ((USItype)(bl)) \
+        __CLOBBER_CC)
+#if defined(__sparc_v8__)
+/* Don't match immediate range because, 1) it is not often useful,
+        2) the 'I' flag thinks of the range as a 13 bit signed interval,
+        while we want to match a 13 bit interval, sign extended to 32 bits,
+        but INTERPRETED AS UNSIGNED.  */
+#define umul_ppmm(w1, w0, u, v) \
+        __asm__ ("umul %2,%3,%1;rd %%y,%0" \
+        : "=r" ((USItype)(w1)), \
+        "=r" ((USItype)(w0)) \
+        : "r" ((USItype)(u)), \
+        "r" ((USItype)(v)))
+#define UMUL_TIME 5
+#ifndef SUPERSPARC              /* SuperSPARC's udiv only handles 53 bit dividends */
+#define udiv_qrnnd(q, r, n1, n0, d) \
+do { \
+        USItype __q; \
+        __asm__ ("mov %1,%%y;nop;nop;nop;udiv %2,%3,%0" \
+        : "=r" ((USItype)(__q)) \
+        : "r" ((USItype)(n1)), \
+        "r" ((USItype)(n0)), \
+        "r" ((USItype)(d))); \
+        (r) = (n0) - __q * (d); \
+        (q) = __q; \
+} while (0)
+#define UDIV_TIME 25
+#endif /* SUPERSPARC */
+#else /* ! __sparc_v8__ */
+#if defined(__sparclite__)
+/* This has hardware multiply but not divide.  It also has two additional
+        instructions scan (ffs from high bit) and divscc.  */
+#define umul_ppmm(w1, w0, u, v) \
+        __asm__ ("umul %2,%3,%1;rd %%y,%0" \
+        : "=r" ((USItype)(w1)), \
+        "=r" ((USItype)(w0)) \
+        : "r" ((USItype)(u)), \
+        "r" ((USItype)(v)))
+#define UMUL_TIME 5
+#define udiv_qrnnd(q, r, n1, n0, d) \
+        __asm__ ("! Inlined udiv_qrnnd\n" \
+        "wr     %%g0,%2,%%y     ! Not a delayed write for sparclite\n" \
+        "tst    %%g0\n" \
+        "divscc %3,%4,%%g1\n" \
+        "divscc %%g1,%4,%%g1\n" \
+        "divscc %%g1,%4,%%g1\n" \
+        "divscc %%g1,%4,%%g1\n" \
+        "divscc %%g1,%4,%%g1\n" \
+        "divscc %%g1,%4,%%g1\n" \
+        "divscc %%g1,%4,%%g1\n" \
+        "divscc %%g1,%4,%%g1\n" \
+        "divscc %%g1,%4,%%g1\n" \
+        "divscc %%g1,%4,%%g1\n" \
+        "divscc %%g1,%4,%%g1\n" \
+        "divscc %%g1,%4,%%g1\n" \
+        "divscc %%g1,%4,%%g1\n" \
+        "divscc %%g1,%4,%%g1\n" \
+        "divscc %%g1,%4,%%g1\n" \
+        "divscc %%g1,%4,%%g1\n" \
+        "divscc %%g1,%4,%%g1\n" \
+        "divscc %%g1,%4,%%g1\n" \
+        "divscc %%g1,%4,%%g1\n" \
+        "divscc %%g1,%4,%%g1\n" \
+        "divscc %%g1,%4,%%g1\n" \
+        "divscc %%g1,%4,%%g1\n" \
+        "divscc %%g1,%4,%%g1\n" \
+        "divscc %%g1,%4,%%g1\n" \
+        "divscc %%g1,%4,%%g1\n" \
+        "divscc %%g1,%4,%%g1\n" \
+        "divscc %%g1,%4,%%g1\n" \
+        "divscc %%g1,%4,%%g1\n" \
+        "divscc %%g1,%4,%%g1\n" \
+        "divscc %%g1,%4,%%g1\n" \
+        "divscc %%g1,%4,%%g1\n" \
+        "divscc %%g1,%4,%0\n" \
+        "rd     %%y,%1\n" \
+        "bl,a 1f\n" \
+        "add    %1,%4,%1\n" \
+        "1:     ! End of inline udiv_qrnnd" \
+        : "=r" ((USItype)(q)), \
+        "=r" ((USItype)(r)) \
+        : "r" ((USItype)(n1)), \
+        "r" ((USItype)(n0)), \
+        "rI" ((USItype)(d)) \
+        : "%g1" __AND_CLOBBER_CC)
+#define UDIV_TIME 37
+#endif /* __sparclite__ */
+#endif /* __sparc_v8__ */
+        /* Default to sparc v7 versions of umul_ppmm and udiv_qrnnd.  */
+#ifndef umul_ppmm
+#define umul_ppmm(w1, w0, u, v) \
+        __asm__ ("! Inlined umul_ppmm\n" \
+        "wr     %%g0,%2,%%y     ! SPARC has 0-3 delay insn after a wr\n" \
+        "sra    %3,31,%%g2      ! Don't move this insn\n" \
+        "and    %2,%%g2,%%g2    ! Don't move this insn\n" \
+        "andcc  %%g0,0,%%g1     ! Don't move this insn\n" \
+        "mulscc %%g1,%3,%%g1\n" \
+        "mulscc %%g1,%3,%%g1\n" \
+        "mulscc %%g1,%3,%%g1\n" \
+        "mulscc %%g1,%3,%%g1\n" \
+        "mulscc %%g1,%3,%%g1\n" \
+        "mulscc %%g1,%3,%%g1\n" \
+        "mulscc %%g1,%3,%%g1\n" \
+        "mulscc %%g1,%3,%%g1\n" \
+        "mulscc %%g1,%3,%%g1\n" \
+        "mulscc %%g1,%3,%%g1\n" \
+        "mulscc %%g1,%3,%%g1\n" \
+        "mulscc %%g1,%3,%%g1\n" \
+        "mulscc %%g1,%3,%%g1\n" \
+        "mulscc %%g1,%3,%%g1\n" \
+        "mulscc %%g1,%3,%%g1\n" \
+        "mulscc %%g1,%3,%%g1\n" \
+        "mulscc %%g1,%3,%%g1\n" \
+        "mulscc %%g1,%3,%%g1\n" \
+        "mulscc %%g1,%3,%%g1\n" \
+        "mulscc %%g1,%3,%%g1\n" \
+        "mulscc %%g1,%3,%%g1\n" \
+        "mulscc %%g1,%3,%%g1\n" \
+        "mulscc %%g1,%3,%%g1\n" \
+        "mulscc %%g1,%3,%%g1\n" \
+        "mulscc %%g1,%3,%%g1\n" \
+        "mulscc %%g1,%3,%%g1\n" \
+        "mulscc %%g1,%3,%%g1\n" \
+        "mulscc %%g1,%3,%%g1\n" \
+        "mulscc %%g1,%3,%%g1\n" \
+        "mulscc %%g1,%3,%%g1\n" \
+        "mulscc %%g1,%3,%%g1\n" \
+        "mulscc %%g1,%3,%%g1\n" \
+        "mulscc %%g1,0,%%g1\n" \
+        "add    %%g1,%%g2,%0\n" \
+        "rd     %%y,%1" \
+        : "=r" ((USItype)(w1)), \
+        "=r" ((USItype)(w0)) \
+        : "%rI" ((USItype)(u)), \
+        "r" ((USItype)(v)) \
+        : "%g1", "%g2" __AND_CLOBBER_CC)
+#define UMUL_TIME 39            /* 39 instructions */
+/* It's quite necessary to add this much assembler for the sparc.
+   The default udiv_qrnnd (in C) is more than 10 times slower!  */
+#define udiv_qrnnd(q, r, n1, n0, d) \
+  __asm__ ("! Inlined udiv_qrnnd\n\t"                                   \
+           "mov 32,%%g1\n\t"                                            \
+           "subcc       %1,%2,%%g0\n\t"                                 \
+           "1:  bcs     5f\n\t"                                         \
+           "addxcc %0,%0,%0     ! shift n1n0 and a q-bit in lsb\n\t"    \
+           "sub %1,%2,%1        ! this kills msb of n\n\t"              \
+           "addx        %1,%1,%1        ! so this can't give carry\n\t" \
+           "subcc       %%g1,1,%%g1\n\t"                                \
+           "2:  bne     1b\n\t"                                         \
+           "subcc       %1,%2,%%g0\n\t"                                 \
+           "bcs 3f\n\t"                                                 \
+           "addxcc %0,%0,%0     ! shift n1n0 and a q-bit in lsb\n\t"    \
+           "b           3f\n\t"                                         \
+           "sub %1,%2,%1        ! this kills msb of n\n\t"              \
+           "4:  sub     %1,%2,%1\n\t"                                   \
+           "5:  addxcc  %1,%1,%1\n\t"                                   \
+           "bcc 2b\n\t"                                                 \
+           "subcc       %%g1,1,%%g1\n\t"                                \
+           "! Got carry from n.  Subtract next step to cancel this carry.\n\t" \
+           "bne 4b\n\t"                                                 \
+           "addcc       %0,%0,%0        ! shift n1n0 and a 0-bit in lsb\n\t" \
+           "sub %1,%2,%1\n\t"                                           \
+           "3:  xnor    %0,0,%0\n\t"                                    \
+           "! End of inline udiv_qrnnd\n"                               \
+           : "=&r" ((USItype)(q)),                                      \
+             "=&r" ((USItype)(r))                                       \
+           : "r" ((USItype)(d)),                                        \
+             "1" ((USItype)(n1)),                                       \
+             "0" ((USItype)(n0)) : "%g1", "cc")
+#define UDIV_TIME (3+7*32)      /* 7 instructions/iteration. 32 iterations.  */
+#endif
+#endif /* __sparc__ */
+
+/***************************************
+        **************  VAX  ******************
+        ***************************************/
+#if defined(__vax__) && W_TYPE_SIZE == 32
+#define add_ssaaaa(sh, sl, ah, al, bh, bl) \
+        __asm__ ("addl2 %5,%1\n" \
+        "adwc %3,%0" \
+        : "=g" ((USItype)(sh)), \
+        "=&g" ((USItype)(sl)) \
+        : "%0" ((USItype)(ah)), \
+        "g" ((USItype)(bh)), \
+        "%1" ((USItype)(al)), \
+        "g" ((USItype)(bl)))
+#define sub_ddmmss(sh, sl, ah, al, bh, bl) \
+        __asm__ ("subl2 %5,%1\n" \
+        "sbwc %3,%0" \
+        : "=g" ((USItype)(sh)), \
+        "=&g" ((USItype)(sl)) \
+        : "0" ((USItype)(ah)), \
+        "g" ((USItype)(bh)), \
+        "1" ((USItype)(al)), \
+        "g" ((USItype)(bl)))
+#define umul_ppmm(xh, xl, m0, m1) \
+do { \
+        union {UDItype __ll; \
+        struct {USItype __l, __h; } __i; \
+        } __xx; \
+        USItype __m0 = (m0), __m1 = (m1); \
+        __asm__ ("emul %1,%2,$0,%0" \
+        : "=g" (__xx.__ll) \
+        : "g" (__m0), \
+        "g" (__m1)); \
+        (xh) = __xx.__i.__h; (xl) = __xx.__i.__l; \
+        (xh) += ((((SItype) __m0 >> 31) & __m1) \
+        + (((SItype) __m1 >> 31) & __m0)); \
+} while (0)
+#define sdiv_qrnnd(q, r, n1, n0, d) \
+do { \
+        union {DItype __ll; \
+        struct {SItype __l, __h; } __i; \
+        } __xx; \
+        __xx.__i.__h = n1; __xx.__i.__l = n0; \
+        __asm__ ("ediv %3,%2,%0,%1" \
+        : "=g" (q), "=g" (r) \
+        : "g" (__xx.__ll), "g" (d)); \
+} while (0)
+#endif /* __vax__ */
+
+/***************************************
+        **************  Z8000   ****************
+        ***************************************/
+#if defined(__z8000__) && W_TYPE_SIZE == 16
+#define add_ssaaaa(sh, sl, ah, al, bh, bl) \
+        __asm__ ("add %H1,%H5\n\tadc  %H0,%H3" \
+        : "=r" ((unsigned int)(sh)), \
+        "=&r" ((unsigned int)(sl)) \
+        : "%0" ((unsigned int)(ah)), \
+        "r" ((unsigned int)(bh)), \
+        "%1" ((unsigned int)(al)), \
+        "rQR" ((unsigned int)(bl)))
+#define sub_ddmmss(sh, sl, ah, al, bh, bl) \
+        __asm__ ("sub %H1,%H5\n\tsbc  %H0,%H3" \
+        : "=r" ((unsigned int)(sh)), \
+        "=&r" ((unsigned int)(sl)) \
+        : "0" ((unsigned int)(ah)), \
+        "r" ((unsigned int)(bh)), \
+        "1" ((unsigned int)(al)), \
+        "rQR" ((unsigned int)(bl)))
+#define umul_ppmm(xh, xl, m0, m1) \
+do { \
+        union {long int __ll; \
+        struct {unsigned int __h, __l; } __i; \
+        } __xx; \
+        unsigned int __m0 = (m0), __m1 = (m1); \
+        __asm__ ("mult      %S0,%H3" \
+        : "=r" (__xx.__i.__h), \
+        "=r" (__xx.__i.__l) \
+        : "%1" (__m0), \
+        "rQR" (__m1)); \
+        (xh) = __xx.__i.__h; (xl) = __xx.__i.__l; \
+        (xh) += ((((signed int) __m0 >> 15) & __m1) \
+        + (((signed int) __m1 >> 15) & __m0)); \
+} while (0)
+#endif /* __z8000__ */
+
+#endif /* __GNUC__ */
+
+/***************************************
+        ***********  Generic Versions   ********
+        ***************************************/
+#if !defined(umul_ppmm) && defined(__umulsidi3)
+#define umul_ppmm(ph, pl, m0, m1) \
+{ \
+        UDWtype __ll = __umulsidi3(m0, m1); \
+        ph = (UWtype) (__ll >> W_TYPE_SIZE); \
+        pl = (UWtype) __ll; \
+}
+#endif
+
+#if !defined(__umulsidi3)
+#define __umulsidi3(u, v) \
+        ({UWtype __hi, __lo; \
+        umul_ppmm(__hi, __lo, u, v); \
+        ((UDWtype) __hi << W_TYPE_SIZE) | __lo; })
+#endif
+
+        /* If this machine has no inline assembler, use C macros.  */
+
+#if !defined(add_ssaaaa)
+#define add_ssaaaa(sh, sl, ah, al, bh, bl) \
+do { \
+        UWtype __x; \
+        __x = (al) + (bl); \
+        (sh) = (ah) + (bh) + (__x < (al)); \
+        (sl) = __x; \
+} while (0)
+#endif
+
+#if !defined(sub_ddmmss)
+#define sub_ddmmss(sh, sl, ah, al, bh, bl) \
+do { \
+        UWtype __x; \
+        __x = (al) - (bl); \
+        (sh) = (ah) - (bh) - (__x > (al)); \
+        (sl) = __x; \
+} while (0)
+#endif
+
+#if !defined(umul_ppmm)
+#define umul_ppmm(w1, w0, u, v) \
+do { \
+        UWtype __x0, __x1, __x2, __x3; \
+        UHWtype __ul, __vl, __uh, __vh; \
+        UWtype __u = (u), __v = (v); \
+        \
+        __ul = __ll_lowpart(__u); \
+        __uh = __ll_highpart(__u); \
+        __vl = __ll_lowpart(__v); \
+        __vh = __ll_highpart(__v); \
+        \
+        __x0 = (UWtype) __ul * __vl; \
+        __x1 = (UWtype) __ul * __vh; \
+        __x2 = (UWtype) __uh * __vl; \
+        __x3 = (UWtype) __uh * __vh; \
+        \
+        __x1 += __ll_highpart(__x0);/* this can't give carry */ \
+        __x1 += __x2;           /* but this indeed can */ \
+        if (__x1 < __x2)                /* did we get it? */ \
+        __x3 += __ll_B;         /* yes, add it in the proper pos. */ \
+        \
+        (w1) = __x3 + __ll_highpart(__x1); \
+        (w0) = (__ll_lowpart(__x1) << W_TYPE_SIZE/2) + __ll_lowpart(__x0); \
+} while (0)
+#endif
+
+#if !defined(umul_ppmm)
+#define smul_ppmm(w1, w0, u, v) \
+do { \
+        UWtype __w1; \
+        UWtype __m0 = (u), __m1 = (v); \
+        umul_ppmm(__w1, w0, __m0, __m1); \
+        (w1) = __w1 - (-(__m0 >> (W_TYPE_SIZE - 1)) & __m1) \
+        - (-(__m1 >> (W_TYPE_SIZE - 1)) & __m0); \
+} while (0)
+#endif
+
+        /* Define this unconditionally, so it can be used for debugging.  */
+#define __udiv_qrnnd_c(q, r, n1, n0, d) \
+do { \
+        UWtype __d1, __d0, __q1, __q0, __r1, __r0, __m; \
+        __d1 = __ll_highpart(d); \
+        __d0 = __ll_lowpart(d); \
+        \
+        __r1 = (n1) % __d1; \
+        __q1 = (n1) / __d1; \
+        __m = (UWtype) __q1 * __d0; \
+        __r1 = __r1 * __ll_B | __ll_highpart(n0); \
+        if (__r1 < __m) { \
+                __q1--, __r1 += (d); \
+                if (__r1 >= (d)) /* i.e. we didn't get carry when adding to __r1 */ \
+                if (__r1 < __m) \
+                        __q1--, __r1 += (d); \
+        } \
+        __r1 -= __m; \
+        \
+        __r0 = __r1 % __d1; \
+        __q0 = __r1 / __d1; \
+        __m = (UWtype) __q0 * __d0; \
+        __r0 = __r0 * __ll_B | __ll_lowpart(n0); \
+        if (__r0 < __m) { \
+                __q0--, __r0 += (d); \
+                if (__r0 >= (d)) \
+                        if (__r0 < __m) \
+                                __q0--, __r0 += (d); \
+        } \
+        __r0 -= __m; \
+        \
+        (q) = (UWtype) __q1 * __ll_B | __q0; \
+        (r) = __r0; \
+} while (0)
+
+/* If the processor has no udiv_qrnnd but sdiv_qrnnd, go through
+        __udiv_w_sdiv (defined in libgcc or elsewhere).  */
+#if !defined(udiv_qrnnd) && defined(sdiv_qrnnd)
+#define udiv_qrnnd(q, r, nh, nl, d) \
+do { \
+        UWtype __r; \
+        (q) = __MPN(udiv_w_sdiv) (&__r, nh, nl, d); \
+        (r) = __r; \
+} while (0)
+#endif
+
+        /* If udiv_qrnnd was not defined for this processor, use __udiv_qrnnd_c.  */
+#if !defined(udiv_qrnnd)
+#define UDIV_NEEDS_NORMALIZATION 1
+#define udiv_qrnnd __udiv_qrnnd_c
+#endif
+
+#ifndef UDIV_NEEDS_NORMALIZATION
+#define UDIV_NEEDS_NORMALIZATION 0
+#endif
diff --git a/lib/mpi/mpi-bit.c b/lib/mpi/mpi-bit.c
new file mode 100644
index 000000000000..503537e08436
--- /dev/null
+++ b/lib/mpi/mpi-bit.c
@@ -0,0 +1,56 @@
+/* mpi-bit.c  -  MPI bit level fucntions
+ * Copyright (C) 1998, 1999 Free Software Foundation, Inc.
+ *
+ * This file is part of GnuPG.
+ *
+ * GnuPG is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * GnuPG is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA
+ */
+
+#include "mpi-internal.h"
+#include "longlong.h"
+
+#define A_LIMB_1 ((mpi_limb_t) 1)
+
+/****************
+ * Sometimes we have MSL (most significant limbs) which are 0;
+ * this is for some reasons not good, so this function removes them.
+ */
+void mpi_normalize(MPI a)
+{
+        for (; a->nlimbs && !a->d[a->nlimbs - 1]; a->nlimbs--)
+                ;
+}
+
+/****************
+ * Return the number of bits in A.
+ */
+unsigned mpi_get_nbits(MPI a)
+{
+        unsigned n;
+
+        mpi_normalize(a);
+
+        if (a->nlimbs) {
+                mpi_limb_t alimb = a->d[a->nlimbs - 1];
+                if (alimb)
+                        n = count_leading_zeros(alimb);
+                else
+                        n = BITS_PER_MPI_LIMB;
+                n = BITS_PER_MPI_LIMB - n + (a->nlimbs - 1) * BITS_PER_MPI_LIMB;
+        } else
+                n = 0;
+        return n;
+}
+EXPORT_SYMBOL_GPL(mpi_get_nbits);
diff --git a/lib/mpi/mpi-cmp.c b/lib/mpi/mpi-cmp.c
new file mode 100644
index 000000000000..1871e7b61ca0
--- /dev/null
+++ b/lib/mpi/mpi-cmp.c
@@ -0,0 +1,70 @@
+/* mpi-cmp.c  -  MPI functions
+ * Copyright (C) 1998, 1999 Free Software Foundation, Inc.
+ *
+ * This file is part of GnuPG.
+ *
+ * GnuPG is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * GnuPG is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA
+ */
+
+#include "mpi-internal.h"
+
+int mpi_cmp_ui(MPI u, unsigned long v)
+{
+        mpi_limb_t limb = v;
+
+        mpi_normalize(u);
+        if (!u->nlimbs && !limb)
+                return 0;
+        if (u->sign)
+                return -1;
+        if (u->nlimbs > 1)
+                return 1;
+
+        if (u->d[0] == limb)
+                return 0;
+        else if (u->d[0] > limb)
+                return 1;
+        else
+                return -1;
+}
+EXPORT_SYMBOL_GPL(mpi_cmp_ui);
+
+int mpi_cmp(MPI u, MPI v)
+{
+        mpi_size_t usize, vsize;
+        int cmp;
+
+        mpi_normalize(u);
+        mpi_normalize(v);
+        usize = u->nlimbs;
+        vsize = v->nlimbs;
+        if (!u->sign && v->sign)
+                return 1;
+        if (u->sign && !v->sign)
+                return -1;
+        if (usize != vsize && !u->sign && !v->sign)
+                return usize - vsize;
+        if (usize != vsize && u->sign && v->sign)
+                return vsize + usize;
+        if (!usize)
+                return 0;
+        cmp = mpihelp_cmp(u->d, v->d, usize);
+        if (!cmp)
+                return 0;
+        if ((cmp < 0 ? 1 : 0) == (u->sign ? 1 : 0))
+                return 1;
+        return -1;
+}
+EXPORT_SYMBOL_GPL(mpi_cmp);
diff --git a/lib/mpi/mpi-inline.h b/lib/mpi/mpi-inline.h
new file mode 100644
index 000000000000..e2b39852b30a
--- /dev/null
+++ b/lib/mpi/mpi-inline.h
@@ -0,0 +1,122 @@
+/* mpi-inline.h  -  Internal to the Multi Precision Integers
+ *      Copyright (C) 1994, 1996, 1998, 1999 Free Software Foundation, Inc.
+ *
+ * This file is part of GnuPG.
+ *
+ * GnuPG is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * GnuPG is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA
+ *
+ * Note: This code is heavily based on the GNU MP Library.
+ *       Actually it's the same code with only minor changes in the
+ *       way the data is stored; this is to support the abstraction
+ *       of an optional secure memory allocation which may be used
+ *       to avoid revealing of sensitive data due to paging etc.
+ *       The GNU MP Library itself is published under the LGPL;
+ *       however I decided to publish this code under the plain GPL.
+ */
+
+#ifndef G10_MPI_INLINE_H
+#define G10_MPI_INLINE_H
+
+#ifndef G10_MPI_INLINE_DECL
+#define G10_MPI_INLINE_DECL  extern inline
+#endif
+
+G10_MPI_INLINE_DECL mpi_limb_t
+mpihelp_add_1(mpi_ptr_t res_ptr, mpi_ptr_t s1_ptr,
+              mpi_size_t s1_size, mpi_limb_t s2_limb)
+{
+        mpi_limb_t x;
+
+        x = *s1_ptr++;
+        s2_limb += x;
+        *res_ptr++ = s2_limb;
+        if (s2_limb < x) {      /* sum is less than the left operand: handle carry */
+                while (--s1_size) {
+                        x = *s1_ptr++ + 1;      /* add carry */
+                        *res_ptr++ = x; /* and store */
+                        if (x)  /* not 0 (no overflow): we can stop */
+                                goto leave;
+                }
+                return 1;       /* return carry (size of s1 to small) */
+        }
+
+leave:
+        if (res_ptr != s1_ptr) {        /* not the same variable */
+                mpi_size_t i;   /* copy the rest */
+                for (i = 0; i < s1_size - 1; i++)
+                        res_ptr[i] = s1_ptr[i];
+        }
+        return 0;               /* no carry */
+}
+
+G10_MPI_INLINE_DECL mpi_limb_t
+mpihelp_add(mpi_ptr_t res_ptr, mpi_ptr_t s1_ptr, mpi_size_t s1_size,
+            mpi_ptr_t s2_ptr, mpi_size_t s2_size)
+{
+        mpi_limb_t cy = 0;
+
+        if (s2_size)
+                cy = mpihelp_add_n(res_ptr, s1_ptr, s2_ptr, s2_size);
+
+        if (s1_size - s2_size)
+                cy = mpihelp_add_1(res_ptr + s2_size, s1_ptr + s2_size,
+                                   s1_size - s2_size, cy);
+        return cy;
+}
+
+G10_MPI_INLINE_DECL mpi_limb_t
+mpihelp_sub_1(mpi_ptr_t res_ptr, mpi_ptr_t s1_ptr,
+              mpi_size_t s1_size, mpi_limb_t s2_limb)
+{
+        mpi_limb_t x;
+
+        x = *s1_ptr++;
+        s2_limb = x - s2_limb;
+        *res_ptr++ = s2_limb;
+        if (s2_limb > x) {
+                while (--s1_size) {
+                        x = *s1_ptr++;
+                        *res_ptr++ = x - 1;
+                        if (x)
+                                goto leave;
+                }
+                return 1;
+        }
+
+leave:
+        if (res_ptr != s1_ptr) {
+                mpi_size_t i;
+                for (i = 0; i < s1_size - 1; i++)
+                        res_ptr[i] = s1_ptr[i];
+        }
+        return 0;
+}
+
+G10_MPI_INLINE_DECL mpi_limb_t
+mpihelp_sub(mpi_ptr_t res_ptr, mpi_ptr_t s1_ptr, mpi_size_t s1_size,
+            mpi_ptr_t s2_ptr, mpi_size_t s2_size)
+{
+        mpi_limb_t cy = 0;
+
+        if (s2_size)
+                cy = mpihelp_sub_n(res_ptr, s1_ptr, s2_ptr, s2_size);
+
+        if (s1_size - s2_size)
+                cy = mpihelp_sub_1(res_ptr + s2_size, s1_ptr + s2_size,
+                                   s1_size - s2_size, cy);
+        return cy;
+}
+
+#endif /*G10_MPI_INLINE_H */
diff --git a/lib/mpi/mpi-internal.h b/lib/mpi/mpi-internal.h
new file mode 100644
index 000000000000..77adcf6bc257
--- /dev/null
+++ b/lib/mpi/mpi-internal.h
@@ -0,0 +1,261 @@
+/* mpi-internal.h  -  Internal to the Multi Precision Integers
+ *      Copyright (C) 1994, 1996 Free Software Foundation, Inc.
+ *      Copyright (C) 1998, 2000 Free Software Foundation, Inc.
+ *
+ * This file is part of GnuPG.
+ *
+ * GnuPG is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * GnuPG is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA
+ *
+ * Note: This code is heavily based on the GNU MP Library.
+ *       Actually it's the same code with only minor changes in the
+ *       way the data is stored; this is to support the abstraction
+ *       of an optional secure memory allocation which may be used
+ *       to avoid revealing of sensitive data due to paging etc.
+ *       The GNU MP Library itself is published under the LGPL;
+ *       however I decided to publish this code under the plain GPL.
+ */
+
+#ifndef G10_MPI_INTERNAL_H
+#define G10_MPI_INTERNAL_H
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/slab.h>
+#include <linux/string.h>
+#include <linux/mpi.h>
+#include <linux/errno.h>
+
+#define log_debug printk
+#define log_bug printk
+
+#define assert(x) \
+        do { \
+                if (!x) \
+                        log_bug("failed assertion\n"); \
+        } while (0);
+
+/* If KARATSUBA_THRESHOLD is not already defined, define it to a
+ * value which is good on most machines.  */
+
+/* tested 4, 16, 32 and 64, where 16 gave the best performance when
+ * checking a 768 and a 1024 bit ElGamal signature.
+ * (wk 22.12.97) */
+#ifndef KARATSUBA_THRESHOLD
+#define KARATSUBA_THRESHOLD 16
+#endif
+
+/* The code can't handle KARATSUBA_THRESHOLD smaller than 2.  */
+#if KARATSUBA_THRESHOLD < 2
+#undef KARATSUBA_THRESHOLD
+#define KARATSUBA_THRESHOLD 2
+#endif
+
+typedef mpi_limb_t *mpi_ptr_t;  /* pointer to a limb */
+typedef int mpi_size_t;         /* (must be a signed type) */
+
+#define ABS(x) (x >= 0 ? x : -x)
+#define MIN(l, o) ((l) < (o) ? (l) : (o))
+#define MAX(h, i) ((h) > (i) ? (h) : (i))
+
+static inline int RESIZE_IF_NEEDED(MPI a, unsigned b)
+{
+        if (a->alloced < b)
+                return mpi_resize(a, b);
+        return 0;
+}
+
+/* Copy N limbs from S to D.  */
+#define MPN_COPY(d, s, n) \
+        do {                                    \
+                mpi_size_t _i;                  \
+                for (_i = 0; _i < (n); _i++)    \
+                        (d)[_i] = (s)[_i];      \
+        } while (0)
+
+#define MPN_COPY_INCR(d, s, n) \
+        do {                                    \
+                mpi_size_t _i;                  \
+                for (_i = 0; _i < (n); _i++)    \
+                        (d)[_i] = (d)[_i];      \
+        } while (0)
+
+#define MPN_COPY_DECR(d, s, n) \
+        do {                                    \
+                mpi_size_t _i;                  \
+                for (_i = (n)-1; _i >= 0; _i--) \
+                        (d)[_i] = (s)[_i];      \
+        } while (0)
+
+/* Zero N limbs at D */
+#define MPN_ZERO(d, n) \
+        do {                                    \
+                int  _i;                        \
+                for (_i = 0; _i < (n); _i++)    \
+                        (d)[_i] = 0;            \
+        } while (0)
+
+#define MPN_NORMALIZE(d, n)  \
+        do {                                    \
+                while ((n) > 0) {               \
+                        if ((d)[(n)-1])         \
+                                break;          \
+                        (n)--;                  \
+                }                               \
+        } while (0)
+
+#define MPN_NORMALIZE_NOT_ZERO(d, n) \
+        do {                            \
+                for (;;) {              \
+                        if ((d)[(n)-1]) \
+                                break;  \
+                        (n)--;          \
+                }                       \
+        } while (0)
+
+#define MPN_MUL_N_RECURSE(prodp, up, vp, size, tspace) \
+        do {                                                    \
+                if ((size) < KARATSUBA_THRESHOLD)               \
+                        mul_n_basecase(prodp, up, vp, size);    \
+                else                                            \
+                        mul_n(prodp, up, vp, size, tspace);     \
+        } while (0);
+
+/* Divide the two-limb number in (NH,,NL) by D, with DI being the largest
+ * limb not larger than (2**(2*BITS_PER_MP_LIMB))/D - (2**BITS_PER_MP_LIMB).
+ * If this would yield overflow, DI should be the largest possible number
+ * (i.e., only ones).  For correct operation, the most significant bit of D
+ * has to be set.  Put the quotient in Q and the remainder in R.
+ */
+#define UDIV_QRNND_PREINV(q, r, nh, nl, d, di) \
+        do {                                                            \
+                mpi_limb_t _q, _ql, _r;                                 \
+                mpi_limb_t _xh, _xl;                                    \
+                umul_ppmm(_q, _ql, (nh), (di));                         \
+                _q += (nh);     /* DI is 2**BITS_PER_MPI_LIMB too small */ \
+                umul_ppmm(_xh, _xl, _q, (d));                           \
+                sub_ddmmss(_xh, _r, (nh), (nl), _xh, _xl);              \
+                if (_xh) {                                              \
+                        sub_ddmmss(_xh, _r, _xh, _r, 0, (d));           \
+                        _q++;                                           \
+                        if (_xh) {                                      \
+                                sub_ddmmss(_xh, _r, _xh, _r, 0, (d));   \
+                                _q++;                                   \
+                        }                                               \
+                }                                                       \
+                if (_r >= (d)) {                                        \
+                        _r -= (d);                                      \
+                        _q++;                                           \
+                }                                                       \
+                (r) = _r;                                               \
+                (q) = _q;                                               \
+        } while (0)
+
+/*-- mpiutil.c --*/
+mpi_ptr_t mpi_alloc_limb_space(unsigned nlimbs);
+void mpi_free_limb_space(mpi_ptr_t a);
+void mpi_assign_limb_space(MPI a, mpi_ptr_t ap, unsigned nlimbs);
+
+/*-- mpi-bit.c --*/
+void mpi_rshift_limbs(MPI a, unsigned int count);
+int mpi_lshift_limbs(MPI a, unsigned int count);
+
+/*-- mpihelp-add.c --*/
+mpi_limb_t mpihelp_add_1(mpi_ptr_t res_ptr, mpi_ptr_t s1_ptr,
+                         mpi_size_t s1_size, mpi_limb_t s2_limb);
+mpi_limb_t mpihelp_add_n(mpi_ptr_t res_ptr, mpi_ptr_t s1_ptr,
+                         mpi_ptr_t s2_ptr, mpi_size_t size);
+mpi_limb_t mpihelp_add(mpi_ptr_t res_ptr, mpi_ptr_t s1_ptr, mpi_size_t s1_size,
+                       mpi_ptr_t s2_ptr, mpi_size_t s2_size);
+
+/*-- mpihelp-sub.c --*/
+mpi_limb_t mpihelp_sub_1(mpi_ptr_t res_ptr, mpi_ptr_t s1_ptr,
+                         mpi_size_t s1_size, mpi_limb_t s2_limb);
+mpi_limb_t mpihelp_sub_n(mpi_ptr_t res_ptr, mpi_ptr_t s1_ptr,
+                         mpi_ptr_t s2_ptr, mpi_size_t size);
+mpi_limb_t mpihelp_sub(mpi_ptr_t res_ptr, mpi_ptr_t s1_ptr, mpi_size_t s1_size,
+                       mpi_ptr_t s2_ptr, mpi_size_t s2_size);
+
+/*-- mpihelp-cmp.c --*/
+int mpihelp_cmp(mpi_ptr_t op1_ptr, mpi_ptr_t op2_ptr, mpi_size_t size);
+
+/*-- mpihelp-mul.c --*/
+
+struct karatsuba_ctx {
+        struct karatsuba_ctx *next;
+        mpi_ptr_t tspace;
+        mpi_size_t tspace_size;
+        mpi_ptr_t tp;
+        mpi_size_t tp_size;
+};
+
+void mpihelp_release_karatsuba_ctx(struct karatsuba_ctx *ctx);
+
+mpi_limb_t mpihelp_addmul_1(mpi_ptr_t res_ptr, mpi_ptr_t s1_ptr,
+                            mpi_size_t s1_size, mpi_limb_t s2_limb);
+mpi_limb_t mpihelp_submul_1(mpi_ptr_t res_ptr, mpi_ptr_t s1_ptr,
+                            mpi_size_t s1_size, mpi_limb_t s2_limb);
+int mpihelp_mul_n(mpi_ptr_t prodp, mpi_ptr_t up, mpi_ptr_t vp, mpi_size_t size);
+int mpihelp_mul(mpi_ptr_t prodp, mpi_ptr_t up, mpi_size_t usize,
+                mpi_ptr_t vp, mpi_size_t vsize, mpi_limb_t *_result);
+void mpih_sqr_n_basecase(mpi_ptr_t prodp, mpi_ptr_t up, mpi_size_t size);
+void mpih_sqr_n(mpi_ptr_t prodp, mpi_ptr_t up, mpi_size_t size,
+                mpi_ptr_t tspace);
+
+int mpihelp_mul_karatsuba_case(mpi_ptr_t prodp,
+                               mpi_ptr_t up, mpi_size_t usize,
+                               mpi_ptr_t vp, mpi_size_t vsize,
+                               struct karatsuba_ctx *ctx);
+
+/*-- mpihelp-mul_1.c (or xxx/cpu/ *.S) --*/
+mpi_limb_t mpihelp_mul_1(mpi_ptr_t res_ptr, mpi_ptr_t s1_ptr,
+                         mpi_size_t s1_size, mpi_limb_t s2_limb);
+
+/*-- mpihelp-div.c --*/
+mpi_limb_t mpihelp_mod_1(mpi_ptr_t dividend_ptr, mpi_size_t dividend_size,
+                         mpi_limb_t divisor_limb);
+mpi_limb_t mpihelp_divrem(mpi_ptr_t qp, mpi_size_t qextra_limbs,
+                          mpi_ptr_t np, mpi_size_t nsize,
+                          mpi_ptr_t dp, mpi_size_t dsize);
+mpi_limb_t mpihelp_divmod_1(mpi_ptr_t quot_ptr,
+                            mpi_ptr_t dividend_ptr, mpi_size_t dividend_size,
+                            mpi_limb_t divisor_limb);
+
+/*-- mpihelp-shift.c --*/
+mpi_limb_t mpihelp_lshift(mpi_ptr_t wp, mpi_ptr_t up, mpi_size_t usize,
+                          unsigned cnt);
+mpi_limb_t mpihelp_rshift(mpi_ptr_t wp, mpi_ptr_t up, mpi_size_t usize,
+                          unsigned cnt);
+
+/* Define stuff for longlong.h.  */
+#define W_TYPE_SIZE BITS_PER_MPI_LIMB
+typedef mpi_limb_t UWtype;
+typedef unsigned int UHWtype;
+#if defined(__GNUC__)
+typedef unsigned int UQItype __attribute__ ((mode(QI)));
+typedef int SItype __attribute__ ((mode(SI)));
+typedef unsigned int USItype __attribute__ ((mode(SI)));
+typedef int DItype __attribute__ ((mode(DI)));
+typedef unsigned int UDItype __attribute__ ((mode(DI)));
+#else
+typedef unsigned char UQItype;
+typedef long SItype;
+typedef unsigned long USItype;
+#endif
+
+#ifdef __GNUC__
+#include "mpi-inline.h"
+#endif
+
+#endif /*G10_MPI_INTERNAL_H */
diff --git a/lib/mpi/mpi-pow.c b/lib/mpi/mpi-pow.c
new file mode 100644
index 000000000000..5464c8744ea9
--- /dev/null
+++ b/lib/mpi/mpi-pow.c
@@ -0,0 +1,323 @@
+/* mpi-pow.c  -  MPI functions
+ *      Copyright (C) 1994, 1996, 1998, 2000 Free Software Foundation, Inc.
+ *
+ * This file is part of GnuPG.
+ *
+ * GnuPG is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * GnuPG is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA
+ *
+ * Note: This code is heavily based on the GNU MP Library.
+ *       Actually it's the same code with only minor changes in the
+ *       way the data is stored; this is to support the abstraction
+ *       of an optional secure memory allocation which may be used
+ *       to avoid revealing of sensitive data due to paging etc.
+ *       The GNU MP Library itself is published under the LGPL;
+ *       however I decided to publish this code under the plain GPL.
+ */
+
+#include <linux/string.h>
+#include "mpi-internal.h"
+#include "longlong.h"
+
+/****************
+ * RES = BASE ^ EXP mod MOD
+ */
+int mpi_powm(MPI res, MPI base, MPI exp, MPI mod)
+{
+        mpi_ptr_t mp_marker = NULL, bp_marker = NULL, ep_marker = NULL;
+        mpi_ptr_t xp_marker = NULL;
+        mpi_ptr_t tspace = NULL;
+        mpi_ptr_t rp, ep, mp, bp;
+        mpi_size_t esize, msize, bsize, rsize;
+        int esign, msign, bsign, rsign;
+        mpi_size_t size;
+        int mod_shift_cnt;
+        int negative_result;
+        int assign_rp = 0;
+        mpi_size_t tsize = 0;   /* to avoid compiler warning */
+        /* fixme: we should check that the warning is void */
+        int rc = -ENOMEM;
+
+        esize = exp->nlimbs;
+        msize = mod->nlimbs;
+        size = 2 * msize;
+        esign = exp->sign;
+        msign = mod->sign;
+
+        rp = res->d;
+        ep = exp->d;
+
+        if (!msize)
+                return -EINVAL;
+
+        if (!esize) {
+                /* Exponent is zero, result is 1 mod MOD, i.e., 1 or 0
+                 * depending on if MOD equals 1.  */
+                rp[0] = 1;
+                res->nlimbs = (msize == 1 && mod->d[0] == 1) ? 0 : 1;
+                res->sign = 0;
+                goto leave;
+        }
+
+        /* Normalize MOD (i.e. make its most significant bit set) as required by
+         * mpn_divrem.  This will make the intermediate values in the calculation
+         * slightly larger, but the correct result is obtained after a final
+         * reduction using the original MOD value.  */
+        mp = mp_marker = mpi_alloc_limb_space(msize);
+        if (!mp)
+                goto enomem;
+        mod_shift_cnt = count_leading_zeros(mod->d[msize - 1]);
+        if (mod_shift_cnt)
+                mpihelp_lshift(mp, mod->d, msize, mod_shift_cnt);
+        else
+                MPN_COPY(mp, mod->d, msize);
+
+        bsize = base->nlimbs;
+        bsign = base->sign;
+        if (bsize > msize) {    /* The base is larger than the module. Reduce it. */
+                /* Allocate (BSIZE + 1) with space for remainder and quotient.
+                 * (The quotient is (bsize - msize + 1) limbs.)  */
+                bp = bp_marker = mpi_alloc_limb_space(bsize + 1);
+                if (!bp)
+                        goto enomem;
+                MPN_COPY(bp, base->d, bsize);
+                /* We don't care about the quotient, store it above the remainder,
+                 * at BP + MSIZE.  */
+                mpihelp_divrem(bp + msize, 0, bp, bsize, mp, msize);
+                bsize = msize;
+                /* Canonicalize the base, since we are going to multiply with it
+                 * quite a few times.  */
+                MPN_NORMALIZE(bp, bsize);
+        } else
+                bp = base->d;
+
+        if (!bsize) {
+                res->nlimbs = 0;
+                res->sign = 0;
+                goto leave;
+        }
+
+        if (res->alloced < size) {
+                /* We have to allocate more space for RES.  If any of the input
+                 * parameters are identical to RES, defer deallocation of the old
+                 * space.  */
+                if (rp == ep || rp == mp || rp == bp) {
+                        rp = mpi_alloc_limb_space(size);
+                        if (!rp)
+                                goto enomem;
+                        assign_rp = 1;
+                } else {
+                        if (mpi_resize(res, size) < 0)
+                                goto enomem;
+                        rp = res->d;
+                }
+        } else {                /* Make BASE, EXP and MOD not overlap with RES.  */
+                if (rp == bp) {
+                        /* RES and BASE are identical.  Allocate temp. space for BASE.  */
+                        BUG_ON(bp_marker);
+                        bp = bp_marker = mpi_alloc_limb_space(bsize);
+                        if (!bp)
+                                goto enomem;
+                        MPN_COPY(bp, rp, bsize);
+                }
+                if (rp == ep) {
+                        /* RES and EXP are identical.  Allocate temp. space for EXP.  */
+                        ep = ep_marker = mpi_alloc_limb_space(esize);
+                        if (!ep)
+                                goto enomem;
+                        MPN_COPY(ep, rp, esize);
+                }
+                if (rp == mp) {
+                        /* RES and MOD are identical.  Allocate temporary space for MOD. */
+                        BUG_ON(mp_marker);
+                        mp = mp_marker = mpi_alloc_limb_space(msize);
+                        if (!mp)
+                                goto enomem;
+                        MPN_COPY(mp, rp, msize);
+                }
+        }
+
+        MPN_COPY(rp, bp, bsize);
+        rsize = bsize;
+        rsign = bsign;
+
+        {
+                mpi_size_t i;
+                mpi_ptr_t xp;
+                int c;
+                mpi_limb_t e;
+                mpi_limb_t carry_limb;
+                struct karatsuba_ctx karactx;
+
+                xp = xp_marker = mpi_alloc_limb_space(2 * (msize + 1));
+                if (!xp)
+                        goto enomem;
+
+                memset(&karactx, 0, sizeof karactx);
+                negative_result = (ep[0] & 1) && base->sign;
+
+                i = esize - 1;
+                e = ep[i];
+                c = count_leading_zeros(e);
+                e = (e << c) << 1;      /* shift the exp bits to the left, lose msb */
+                c = BITS_PER_MPI_LIMB - 1 - c;
+
+                /* Main loop.
+                 *
+                 * Make the result be pointed to alternately by XP and RP.  This
+                 * helps us avoid block copying, which would otherwise be necessary
+                 * with the overlap restrictions of mpihelp_divmod. With 50% probability
+                 * the result after this loop will be in the area originally pointed
+                 * by RP (==RES->d), and with 50% probability in the area originally
+                 * pointed to by XP.
+                 */
+
+                for (;;) {
+                        while (c) {
+                                mpi_ptr_t tp;
+                                mpi_size_t xsize;
+
+                                /*if (mpihelp_mul_n(xp, rp, rp, rsize) < 0) goto enomem */
+                                if (rsize < KARATSUBA_THRESHOLD)
+                                        mpih_sqr_n_basecase(xp, rp, rsize);
+                                else {
+                                        if (!tspace) {
+                                                tsize = 2 * rsize;
+                                                tspace =
+                                                    mpi_alloc_limb_space(tsize);
+                                                if (!tspace)
+                                                        goto enomem;
+                                        } else if (tsize < (2 * rsize)) {
+                                                mpi_free_limb_space(tspace);
+                                                tsize = 2 * rsize;
+                                                tspace =
+                                                    mpi_alloc_limb_space(tsize);
+                                                if (!tspace)
+                                                        goto enomem;
+                                        }
+                                        mpih_sqr_n(xp, rp, rsize, tspace);
+                                }
+
+                                xsize = 2 * rsize;
+                                if (xsize > msize) {
+                                        mpihelp_divrem(xp + msize, 0, xp, xsize,
+                                                       mp, msize);
+                                        xsize = msize;
+                                }
+
+                                tp = rp;
+                                rp = xp;
+                                xp = tp;
+                                rsize = xsize;
+
+                                if ((mpi_limb_signed_t) e < 0) {
+                                        /*mpihelp_mul( xp, rp, rsize, bp, bsize ); */
+                                        if (bsize < KARATSUBA_THRESHOLD) {
+                                                mpi_limb_t tmp;
+                                                if (mpihelp_mul
+                                                    (xp, rp, rsize, bp, bsize,
+                                                     &tmp) < 0)
+                                                        goto enomem;
+                                        } else {
+                                                if (mpihelp_mul_karatsuba_case
+                                                    (xp, rp, rsize, bp, bsize,
+                                                     &karactx) < 0)
+                                                        goto enomem;
+                                        }
+
+                                        xsize = rsize + bsize;
+                                        if (xsize > msize) {
+                                                mpihelp_divrem(xp + msize, 0,
+                                                               xp, xsize, mp,
+                                                               msize);
+                                                xsize = msize;
+                                        }
+
+                                        tp = rp;
+                                        rp = xp;
+                                        xp = tp;
+                                        rsize = xsize;
+                                }
+                                e <<= 1;
+                                c--;
+                        }
+
+                        i--;
+                        if (i < 0)
+                                break;
+                        e = ep[i];
+                        c = BITS_PER_MPI_LIMB;
+                }
+
+                /* We shifted MOD, the modulo reduction argument, left MOD_SHIFT_CNT
+                 * steps.  Adjust the result by reducing it with the original MOD.
+                 *
+                 * Also make sure the result is put in RES->d (where it already
+                 * might be, see above).
+                 */
+                if (mod_shift_cnt) {
+                        carry_limb =
+                            mpihelp_lshift(res->d, rp, rsize, mod_shift_cnt);
+                        rp = res->d;
+                        if (carry_limb) {
+                                rp[rsize] = carry_limb;
+                                rsize++;
+                        }
+                } else {
+                        MPN_COPY(res->d, rp, rsize);
+                        rp = res->d;
+                }
+
+                if (rsize >= msize) {
+                        mpihelp_divrem(rp + msize, 0, rp, rsize, mp, msize);
+                        rsize = msize;
+                }
+
+                /* Remove any leading zero words from the result.  */
+                if (mod_shift_cnt)
+                        mpihelp_rshift(rp, rp, rsize, mod_shift_cnt);
+                MPN_NORMALIZE(rp, rsize);
+
+                mpihelp_release_karatsuba_ctx(&karactx);
+        }
+
+        if (negative_result && rsize) {
+                if (mod_shift_cnt)
+                        mpihelp_rshift(mp, mp, msize, mod_shift_cnt);
+                mpihelp_sub(rp, mp, msize, rp, rsize);
+                rsize = msize;
+                rsign = msign;
+                MPN_NORMALIZE(rp, rsize);
+        }
+        res->nlimbs = rsize;
+        res->sign = rsign;
+
+leave:
+        rc = 0;
+enomem:
+        if (assign_rp)
+                mpi_assign_limb_space(res, rp, size);
+        if (mp_marker)
+                mpi_free_limb_space(mp_marker);
+        if (bp_marker)
+                mpi_free_limb_space(bp_marker);
+        if (ep_marker)
+                mpi_free_limb_space(ep_marker);
+        if (xp_marker)
+                mpi_free_limb_space(xp_marker);
+        if (tspace)
+                mpi_free_limb_space(tspace);
+        return rc;
+}
+EXPORT_SYMBOL_GPL(mpi_powm);
diff --git a/lib/mpi/mpicoder.c b/lib/mpi/mpicoder.c
new file mode 100644
index 000000000000..3962b7f7fe3f
--- /dev/null
+++ b/lib/mpi/mpicoder.c
@@ -0,0 +1,260 @@
+/* mpicoder.c  -  Coder for the external representation of MPIs
+ * Copyright (C) 1998, 1999 Free Software Foundation, Inc.
+ *
+ * This file is part of GnuPG.
+ *
+ * GnuPG is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * GnuPG is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA
+ */
+
+#include <linux/bitops.h>
+#include <asm-generic/bitops/count_zeros.h>
+#include "mpi-internal.h"
+
+#define MAX_EXTERN_MPI_BITS 16384
+
+/**
+ * mpi_read_raw_data - Read a raw byte stream as a positive integer
+ * @xbuffer: The data to read
+ * @nbytes: The amount of data to read
+ */
+MPI mpi_read_raw_data(const void *xbuffer, size_t nbytes)
+{
+        const uint8_t *buffer = xbuffer;
+        int i, j;
+        unsigned nbits, nlimbs;
+        mpi_limb_t a;
+        MPI val = NULL;
+
+        while (nbytes >= 0 && buffer[0] == 0) {
+                buffer++;
+                nbytes--;
+        }
+
+        nbits = nbytes * 8;
+        if (nbits > MAX_EXTERN_MPI_BITS) {
+                pr_info("MPI: mpi too large (%u bits)\n", nbits);
+                return NULL;
+        }
+        if (nbytes > 0)
+                nbits -= count_leading_zeros(buffer[0]);
+        else
+                nbits = 0;
+
+        nlimbs = (nbytes + BYTES_PER_MPI_LIMB - 1) / BYTES_PER_MPI_LIMB;
+        val = mpi_alloc(nlimbs);
+        if (!val)
+                return NULL;
+        val->nbits = nbits;
+        val->sign = 0;
+        val->nlimbs = nlimbs;
+
+        if (nbytes > 0) {
+                i = BYTES_PER_MPI_LIMB - nbytes % BYTES_PER_MPI_LIMB;
+                i %= BYTES_PER_MPI_LIMB;
+                for (j = nlimbs; j > 0; j--) {
+                        a = 0;
+                        for (; i < BYTES_PER_MPI_LIMB; i++) {
+                                a <<= 8;
+                                a |= *buffer++;
+                        }
+                        i = 0;
+                        val->d[j - 1] = a;
+                }
+        }
+        return val;
+}
+EXPORT_SYMBOL_GPL(mpi_read_raw_data);
+
+MPI mpi_read_from_buffer(const void *xbuffer, unsigned *ret_nread)
+{
+        const uint8_t *buffer = xbuffer;
+        int i, j;
+        unsigned nbits, nbytes, nlimbs, nread = 0;
+        mpi_limb_t a;
+        MPI val = NULL;
+
+        if (*ret_nread < 2)
+                goto leave;
+        nbits = buffer[0] << 8 | buffer[1];
+
+        if (nbits > MAX_EXTERN_MPI_BITS) {
+                pr_info("MPI: mpi too large (%u bits)\n", nbits);
+                goto leave;
+        }
+        buffer += 2;
+        nread = 2;
+
+        nbytes = (nbits + 7) / 8;
+        nlimbs = (nbytes + BYTES_PER_MPI_LIMB - 1) / BYTES_PER_MPI_LIMB;
+        val = mpi_alloc(nlimbs);
+        if (!val)
+                return NULL;
+        i = BYTES_PER_MPI_LIMB - nbytes % BYTES_PER_MPI_LIMB;
+        i %= BYTES_PER_MPI_LIMB;
+        val->nbits = nbits;
+        j = val->nlimbs = nlimbs;
+        val->sign = 0;
+        for (; j > 0; j--) {
+                a = 0;
+                for (; i < BYTES_PER_MPI_LIMB; i++) {
+                        if (++nread > *ret_nread) {
+                                printk
+                                    ("MPI: mpi larger than buffer nread=%d ret_nread=%d\n",
+                                     nread, *ret_nread);
+                                goto leave;
+                        }
+                        a <<= 8;
+                        a |= *buffer++;
+                }
+                i = 0;
+                val->d[j - 1] = a;
+        }
+
+leave:
+        *ret_nread = nread;
+        return val;
+}
+EXPORT_SYMBOL_GPL(mpi_read_from_buffer);
+
+/****************
+ * Return an allocated buffer with the MPI (msb first).
+ * NBYTES receives the length of this buffer. Caller must free the
+ * return string (This function does return a 0 byte buffer with NBYTES
+ * set to zero if the value of A is zero. If sign is not NULL, it will
+ * be set to the sign of the A.
+ */
+void *mpi_get_buffer(MPI a, unsigned *nbytes, int *sign)
+{
+        uint8_t *p, *buffer;
+        mpi_limb_t alimb;
+        int i;
+        unsigned int n;
+
+        if (sign)
+                *sign = a->sign;
+        *nbytes = n = a->nlimbs * BYTES_PER_MPI_LIMB;
+        if (!n)
+                n++;            /* avoid zero length allocation */
+        p = buffer = kmalloc(n, GFP_KERNEL);
+        if (!p)
+                return NULL;
+
+        for (i = a->nlimbs - 1; i >= 0; i--) {
+                alimb = a->d[i];
+#if BYTES_PER_MPI_LIMB == 4
+                *p++ = alimb >> 24;
+                *p++ = alimb >> 16;
+                *p++ = alimb >> 8;
+                *p++ = alimb;
+#elif BYTES_PER_MPI_LIMB == 8
+                *p++ = alimb >> 56;
+                *p++ = alimb >> 48;
+                *p++ = alimb >> 40;
+                *p++ = alimb >> 32;
+                *p++ = alimb >> 24;
+                *p++ = alimb >> 16;
+                *p++ = alimb >> 8;
+                *p++ = alimb;
+#else
+#error please implement for this limb size.
+#endif
+        }
+
+        /* this is sub-optimal but we need to do the shift operation
+         * because the caller has to free the returned buffer */
+        for (p = buffer; !*p && *nbytes; p++, --*nbytes)
+                ;
+        if (p != buffer)
+                memmove(buffer, p, *nbytes);
+
+        return buffer;
+}
+EXPORT_SYMBOL_GPL(mpi_get_buffer);
+
+/****************
+ * Use BUFFER to update MPI.
+ */
+int mpi_set_buffer(MPI a, const void *xbuffer, unsigned nbytes, int sign)
+{
+        const uint8_t *buffer = xbuffer, *p;
+        mpi_limb_t alimb;
+        int nlimbs;
+        int i;
+
+        nlimbs = (nbytes + BYTES_PER_MPI_LIMB - 1) / BYTES_PER_MPI_LIMB;
+        if (RESIZE_IF_NEEDED(a, nlimbs) < 0)
+                return -ENOMEM;
+        a->sign = sign;
+
+        for (i = 0, p = buffer + nbytes - 1; p >= buffer + BYTES_PER_MPI_LIMB;) {
+#if BYTES_PER_MPI_LIMB == 4
+                alimb = (mpi_limb_t) *p--;
+                alimb |= (mpi_limb_t) *p-- << 8;
+                alimb |= (mpi_limb_t) *p-- << 16;
+                alimb |= (mpi_limb_t) *p-- << 24;
+#elif BYTES_PER_MPI_LIMB == 8
+                alimb = (mpi_limb_t) *p--;
+                alimb |= (mpi_limb_t) *p-- << 8;
+                alimb |= (mpi_limb_t) *p-- << 16;
+                alimb |= (mpi_limb_t) *p-- << 24;
+                alimb |= (mpi_limb_t) *p-- << 32;
+                alimb |= (mpi_limb_t) *p-- << 40;
+                alimb |= (mpi_limb_t) *p-- << 48;
+                alimb |= (mpi_limb_t) *p-- << 56;
+#else
+#error please implement for this limb size.
+#endif
+                a->d[i++] = alimb;
+        }
+        if (p >= buffer) {
+#if BYTES_PER_MPI_LIMB == 4
+                alimb = *p--;
+                if (p >= buffer)
+                        alimb |= (mpi_limb_t) *p-- << 8;
+                if (p >= buffer)
+                        alimb |= (mpi_limb_t) *p-- << 16;
+                if (p >= buffer)
+                        alimb |= (mpi_limb_t) *p-- << 24;
+#elif BYTES_PER_MPI_LIMB == 8
+                alimb = (mpi_limb_t) *p--;
+                if (p >= buffer)
+                        alimb |= (mpi_limb_t) *p-- << 8;
+                if (p >= buffer)
+                        alimb |= (mpi_limb_t) *p-- << 16;
+                if (p >= buffer)
+                        alimb |= (mpi_limb_t) *p-- << 24;
+                if (p >= buffer)
+                        alimb |= (mpi_limb_t) *p-- << 32;
+                if (p >= buffer)
+                        alimb |= (mpi_limb_t) *p-- << 40;
+                if (p >= buffer)
+                        alimb |= (mpi_limb_t) *p-- << 48;
+                if (p >= buffer)
+                        alimb |= (mpi_limb_t) *p-- << 56;
+#else
+#error please implement for this limb size.
+#endif
+                a->d[i++] = alimb;
+        }
+        a->nlimbs = i;
+
+        if (i != nlimbs) {
+                pr_emerg("MPI: mpi_set_buffer: Assertion failed (%d != %d)", i,
+                       nlimbs);
+                BUG();
+        }
+        return 0;
+}
+EXPORT_SYMBOL_GPL(mpi_set_buffer);
diff --git a/lib/mpi/mpih-cmp.c b/lib/mpi/mpih-cmp.c
new file mode 100644
index 000000000000..b2fd39677f1b
--- /dev/null
+++ b/lib/mpi/mpih-cmp.c
@@ -0,0 +1,56 @@
+/* mpihelp-sub.c  -  MPI helper functions
+ *      Copyright (C) 1994, 1996 Free Software Foundation, Inc.
+ *      Copyright (C) 1998, 1999, 2000, 2001 Free Software Foundation, Inc.
+ *
+ * This file is part of GnuPG.
+ *
+ * GnuPG is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * GnuPG is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA
+ *
+ * Note: This code is heavily based on the GNU MP Library.
+ *       Actually it's the same code with only minor changes in the
+ *       way the data is stored; this is to support the abstraction
+ *       of an optional secure memory allocation which may be used
+ *       to avoid revealing of sensitive data due to paging etc.
+ *       The GNU MP Library itself is published under the LGPL;
+ *       however I decided to publish this code under the plain GPL.
+ */
+
+#include "mpi-internal.h"
+
+/****************
+ * Compare OP1_PTR/OP1_SIZE with OP2_PTR/OP2_SIZE.
+ * There are no restrictions on the relative sizes of
+ * the two arguments.
+ * Return 1 if OP1 > OP2, 0 if they are equal, and -1 if OP1 < OP2.
+ */
+int mpihelp_cmp(mpi_ptr_t op1_ptr, mpi_ptr_t op2_ptr, mpi_size_t size)
+{
+        mpi_size_t i;
+        mpi_limb_t op1_word, op2_word;
+
+        for (i = size - 1; i >= 0; i--) {
+                op1_word = op1_ptr[i];
+                op2_word = op2_ptr[i];
+                if (op1_word != op2_word)
+                        goto diff;
+        }
+        return 0;
+
+diff:
+        /* This can *not* be simplified to
+         *   op2_word - op2_word
+         * since that expression might give signed overflow.  */
+        return (op1_word > op2_word) ? 1 : -1;
+}
diff --git a/lib/mpi/mpih-div.c b/lib/mpi/mpih-div.c
new file mode 100644
index 000000000000..c57d1d46295e
--- /dev/null
+++ b/lib/mpi/mpih-div.c
@@ -0,0 +1,236 @@
+/* mpihelp-div.c  -  MPI helper functions
+ *      Copyright (C) 1994, 1996 Free Software Foundation, Inc.
+ *      Copyright (C) 1998, 1999 Free Software Foundation, Inc.
+ *
+ * This file is part of GnuPG.
+ *
+ * GnuPG is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * GnuPG is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA
+ *
+ * Note: This code is heavily based on the GNU MP Library.
+ *       Actually it's the same code with only minor changes in the
+ *       way the data is stored; this is to support the abstraction
+ *       of an optional secure memory allocation which may be used
+ *       to avoid revealing of sensitive data due to paging etc.
+ *       The GNU MP Library itself is published under the LGPL;
+ *       however I decided to publish this code under the plain GPL.
+ */
+
+#include "mpi-internal.h"
+#include "longlong.h"
+
+#ifndef UMUL_TIME
+#define UMUL_TIME 1
+#endif
+#ifndef UDIV_TIME
+#define UDIV_TIME UMUL_TIME
+#endif
+
+/* Divide num (NP/NSIZE) by den (DP/DSIZE) and write
+ * the NSIZE-DSIZE least significant quotient limbs at QP
+ * and the DSIZE long remainder at NP.  If QEXTRA_LIMBS is
+ * non-zero, generate that many fraction bits and append them after the
+ * other quotient limbs.
+ * Return the most significant limb of the quotient, this is always 0 or 1.
+ *
+ * Preconditions:
+ * 0. NSIZE >= DSIZE.
+ * 1. The most significant bit of the divisor must be set.
+ * 2. QP must either not overlap with the input operands at all, or
+ *    QP + DSIZE >= NP must hold true.  (This means that it's
+ *    possible to put the quotient in the high part of NUM, right after the
+ *    remainder in NUM.
+ * 3. NSIZE >= DSIZE, even if QEXTRA_LIMBS is non-zero.
+ */
+
+mpi_limb_t
+mpihelp_divrem(mpi_ptr_t qp, mpi_size_t qextra_limbs,
+               mpi_ptr_t np, mpi_size_t nsize, mpi_ptr_t dp, mpi_size_t dsize)
+{
+        mpi_limb_t most_significant_q_limb = 0;
+
+        switch (dsize) {
+        case 0:
+                /* We are asked to divide by zero, so go ahead and do it!  (To make
+                   the compiler not remove this statement, return the value.)  */
+                /*
+                 * existing clients of this function have been modified
+                 * not to call it with dsize == 0, so this should not happen
+                 */
+                return 1 / dsize;
+
+        case 1:
+                {
+                        mpi_size_t i;
+                        mpi_limb_t n1;
+                        mpi_limb_t d;
+
+                        d = dp[0];
+                        n1 = np[nsize - 1];
+
+                        if (n1 >= d) {
+                                n1 -= d;
+                                most_significant_q_limb = 1;
+                        }
+
+                        qp += qextra_limbs;
+                        for (i = nsize - 2; i >= 0; i--)
+                                udiv_qrnnd(qp[i], n1, n1, np[i], d);
+                        qp -= qextra_limbs;
+
+                        for (i = qextra_limbs - 1; i >= 0; i--)
+                                udiv_qrnnd(qp[i], n1, n1, 0, d);
+
+                        np[0] = n1;
+                }
+                break;
+
+        case 2:
+                {
+                        mpi_size_t i;
+                        mpi_limb_t n1, n0, n2;
+                        mpi_limb_t d1, d0;
+
+                        np += nsize - 2;
+                        d1 = dp[1];
+                        d0 = dp[0];
+                        n1 = np[1];
+                        n0 = np[0];
+
+                        if (n1 >= d1 && (n1 > d1 || n0 >= d0)) {
+                                sub_ddmmss(n1, n0, n1, n0, d1, d0);
+                                most_significant_q_limb = 1;
+                        }
+
+                        for (i = qextra_limbs + nsize - 2 - 1; i >= 0; i--) {
+                                mpi_limb_t q;
+                                mpi_limb_t r;
+
+                                if (i >= qextra_limbs)
+                                        np--;
+                                else
+                                        np[0] = 0;
+
+                                if (n1 == d1) {
+                                        /* Q should be either 111..111 or 111..110.  Need special
+                                         * treatment of this rare case as normal division would
+                                         * give overflow.  */
+                                        q = ~(mpi_limb_t) 0;
+
+                                        r = n0 + d1;
+                                        if (r < d1) {   /* Carry in the addition? */
+                                                add_ssaaaa(n1, n0, r - d0,
+                                                           np[0], 0, d0);
+                                                qp[i] = q;
+                                                continue;
+                                        }
+                                        n1 = d0 - (d0 != 0 ? 1 : 0);
+                                        n0 = -d0;
+                                } else {
+                                        udiv_qrnnd(q, r, n1, n0, d1);
+                                        umul_ppmm(n1, n0, d0, q);
+                                }
+
+                                n2 = np[0];
+q_test:
+                                if (n1 > r || (n1 == r && n0 > n2)) {
+                                        /* The estimated Q was too large.  */
+                                        q--;
+                                        sub_ddmmss(n1, n0, n1, n0, 0, d0);
+                                        r += d1;
+                                        if (r >= d1)    /* If not carry, test Q again.  */
+                                                goto q_test;
+                                }
+
+                                qp[i] = q;
+                                sub_ddmmss(n1, n0, r, n2, n1, n0);
+                        }
+                        np[1] = n1;
+                        np[0] = n0;
+                }
+                break;
+
+        default:
+                {
+                        mpi_size_t i;
+                        mpi_limb_t dX, d1, n0;
+
+                        np += nsize - dsize;
+                        dX = dp[dsize - 1];
+                        d1 = dp[dsize - 2];
+                        n0 = np[dsize - 1];
+
+                        if (n0 >= dX) {
+                                if (n0 > dX
+                                    || mpihelp_cmp(np, dp, dsize - 1) >= 0) {
+                                        mpihelp_sub_n(np, np, dp, dsize);
+                                        n0 = np[dsize - 1];
+                                        most_significant_q_limb = 1;
+                                }
+                        }
+
+                        for (i = qextra_limbs + nsize - dsize - 1; i >= 0; i--) {
+                                mpi_limb_t q;
+                                mpi_limb_t n1, n2;
+                                mpi_limb_t cy_limb;
+
+                                if (i >= qextra_limbs) {
+                                        np--;
+                                        n2 = np[dsize];
+                                } else {
+                                        n2 = np[dsize - 1];
+                                        MPN_COPY_DECR(np + 1, np, dsize - 1);
+                                        np[0] = 0;
+                                }
+
+                                if (n0 == dX) {
+                                        /* This might over-estimate q, but it's probably not worth
+                                         * the extra code here to find out.  */
+                                        q = ~(mpi_limb_t) 0;
+                                } else {
+                                        mpi_limb_t r;
+
+                                        udiv_qrnnd(q, r, n0, np[dsize - 1], dX);
+                                        umul_ppmm(n1, n0, d1, q);
+
+                                        while (n1 > r
+                                               || (n1 == r
+                                                   && n0 > np[dsize - 2])) {
+                                                q--;
+                                                r += dX;
+                                                if (r < dX)     /* I.e. "carry in previous addition?" */
+                                                        break;
+                                                n1 -= n0 < d1;
+                                                n0 -= d1;
+                                        }
+                                }
+
+                                /* Possible optimization: We already have (q * n0) and (1 * n1)
+                                 * after the calculation of q.  Taking advantage of that, we
+                                 * could make this loop make two iterations less.  */
+                                cy_limb = mpihelp_submul_1(np, dp, dsize, q);
+
+                                if (n2 != cy_limb) {
+                                        mpihelp_add_n(np, np, dp, dsize);
+                                        q--;
+                                }
+
+                                qp[i] = q;
+                                n0 = np[dsize - 1];
+                        }
+                }
+        }
+
+        return most_significant_q_limb;
+}
diff --git a/lib/mpi/mpih-mul.c b/lib/mpi/mpih-mul.c
new file mode 100644
index 000000000000..7c841719fdfb
--- /dev/null
+++ b/lib/mpi/mpih-mul.c
@@ -0,0 +1,497 @@
+/* mpihelp-mul.c  -  MPI helper functions
+ * Copyright (C) 1994, 1996, 1998, 1999,
+ *               2000 Free Software Foundation, Inc.
+ *
+ * This file is part of GnuPG.
+ *
+ * GnuPG is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * GnuPG is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA
+ *
+ * Note: This code is heavily based on the GNU MP Library.
+ *       Actually it's the same code with only minor changes in the
+ *       way the data is stored; this is to support the abstraction
+ *       of an optional secure memory allocation which may be used
+ *       to avoid revealing of sensitive data due to paging etc.
+ *       The GNU MP Library itself is published under the LGPL;
+ *       however I decided to publish this code under the plain GPL.
+ */
+
+#include <linux/string.h>
+#include "mpi-internal.h"
+#include "longlong.h"
+
+#define MPN_MUL_N_RECURSE(prodp, up, vp, size, tspace)          \
+        do {                                                    \
+                if ((size) < KARATSUBA_THRESHOLD)               \
+                        mul_n_basecase(prodp, up, vp, size);    \
+                else                                            \
+                        mul_n(prodp, up, vp, size, tspace);     \
+        } while (0);
+
+#define MPN_SQR_N_RECURSE(prodp, up, size, tspace)              \
+        do {                                                    \
+                if ((size) < KARATSUBA_THRESHOLD)               \
+                        mpih_sqr_n_basecase(prodp, up, size);   \
+                else                                            \
+                        mpih_sqr_n(prodp, up, size, tspace);    \
+        } while (0);
+
+/* Multiply the natural numbers u (pointed to by UP) and v (pointed to by VP),
+ * both with SIZE limbs, and store the result at PRODP.  2 * SIZE limbs are
+ * always stored.  Return the most significant limb.
+ *
+ * Argument constraints:
+ * 1. PRODP != UP and PRODP != VP, i.e. the destination
+ *    must be distinct from the multiplier and the multiplicand.
+ *
+ *
+ * Handle simple cases with traditional multiplication.
+ *
+ * This is the most critical code of multiplication.  All multiplies rely
+ * on this, both small and huge.  Small ones arrive here immediately.  Huge
+ * ones arrive here as this is the base case for Karatsuba's recursive
+ * algorithm below.
+ */
+
+static mpi_limb_t
+mul_n_basecase(mpi_ptr_t prodp, mpi_ptr_t up, mpi_ptr_t vp, mpi_size_t size)
+{
+        mpi_size_t i;
+        mpi_limb_t cy;
+        mpi_limb_t v_limb;
+
+        /* Multiply by the first limb in V separately, as the result can be
+         * stored (not added) to PROD.  We also avoid a loop for zeroing.  */
+        v_limb = vp[0];
+        if (v_limb <= 1) {
+                if (v_limb == 1)
+                        MPN_COPY(prodp, up, size);
+                else
+                        MPN_ZERO(prodp, size);
+                cy = 0;
+        } else
+                cy = mpihelp_mul_1(prodp, up, size, v_limb);
+
+        prodp[size] = cy;
+        prodp++;
+
+        /* For each iteration in the outer loop, multiply one limb from
+         * U with one limb from V, and add it to PROD.  */
+        for (i = 1; i < size; i++) {
+                v_limb = vp[i];
+                if (v_limb <= 1) {
+                        cy = 0;
+                        if (v_limb == 1)
+                                cy = mpihelp_add_n(prodp, prodp, up, size);
+                } else
+                        cy = mpihelp_addmul_1(prodp, up, size, v_limb);
+
+                prodp[size] = cy;
+                prodp++;
+        }
+
+        return cy;
+}
+
+static void
+mul_n(mpi_ptr_t prodp, mpi_ptr_t up, mpi_ptr_t vp,
+                mpi_size_t size, mpi_ptr_t tspace)
+{
+        if (size & 1) {
+                /* The size is odd, and the code below doesn't handle that.
+                 * Multiply the least significant (size - 1) limbs with a recursive
+                 * call, and handle the most significant limb of S1 and S2
+                 * separately.
+                 * A slightly faster way to do this would be to make the Karatsuba
+                 * code below behave as if the size were even, and let it check for
+                 * odd size in the end.  I.e., in essence move this code to the end.
+                 * Doing so would save us a recursive call, and potentially make the
+                 * stack grow a lot less.
+                 */
+                mpi_size_t esize = size - 1;    /* even size */
+                mpi_limb_t cy_limb;
+
+                MPN_MUL_N_RECURSE(prodp, up, vp, esize, tspace);
+                cy_limb = mpihelp_addmul_1(prodp + esize, up, esize, vp[esize]);
+                prodp[esize + esize] = cy_limb;
+                cy_limb = mpihelp_addmul_1(prodp + esize, vp, size, up[esize]);
+                prodp[esize + size] = cy_limb;
+        } else {
+                /* Anatolij Alekseevich Karatsuba's divide-and-conquer algorithm.
+                 *
+                 * Split U in two pieces, U1 and U0, such that
+                 * U = U0 + U1*(B**n),
+                 * and V in V1 and V0, such that
+                 * V = V0 + V1*(B**n).
+                 *
+                 * UV is then computed recursively using the identity
+                 *
+                 *        2n   n          n                     n
+                 * UV = (B  + B )U V  +  B (U -U )(V -V )  +  (B + 1)U V
+                 *                1 1        1  0   0  1              0 0
+                 *
+                 * Where B = 2**BITS_PER_MP_LIMB.
+                 */
+                mpi_size_t hsize = size >> 1;
+                mpi_limb_t cy;
+                int negflg;
+
+                /* Product H.      ________________  ________________
+                 *                |_____U1 x V1____||____U0 x V0_____|
+                 * Put result in upper part of PROD and pass low part of TSPACE
+                 * as new TSPACE.
+                 */
+                MPN_MUL_N_RECURSE(prodp + size, up + hsize, vp + hsize, hsize,
+                                  tspace);
+
+                /* Product M.      ________________
+                 *                |_(U1-U0)(V0-V1)_|
+                 */
+                if (mpihelp_cmp(up + hsize, up, hsize) >= 0) {
+                        mpihelp_sub_n(prodp, up + hsize, up, hsize);
+                        negflg = 0;
+                } else {
+                        mpihelp_sub_n(prodp, up, up + hsize, hsize);
+                        negflg = 1;
+                }
+                if (mpihelp_cmp(vp + hsize, vp, hsize) >= 0) {
+                        mpihelp_sub_n(prodp + hsize, vp + hsize, vp, hsize);
+                        negflg ^= 1;
+                } else {
+                        mpihelp_sub_n(prodp + hsize, vp, vp + hsize, hsize);
+                        /* No change of NEGFLG.  */
+                }
+                /* Read temporary operands from low part of PROD.
+                 * Put result in low part of TSPACE using upper part of TSPACE
+                 * as new TSPACE.
+                 */
+                MPN_MUL_N_RECURSE(tspace, prodp, prodp + hsize, hsize,
+                                  tspace + size);
+
+                /* Add/copy product H. */
+                MPN_COPY(prodp + hsize, prodp + size, hsize);
+                cy = mpihelp_add_n(prodp + size, prodp + size,
+                                   prodp + size + hsize, hsize);
+
+                /* Add product M (if NEGFLG M is a negative number) */
+                if (negflg)
+                        cy -=
+                            mpihelp_sub_n(prodp + hsize, prodp + hsize, tspace,
+                                          size);
+                else
+                        cy +=
+                            mpihelp_add_n(prodp + hsize, prodp + hsize, tspace,
+                                          size);
+
+                /* Product L.      ________________  ________________
+                 *                |________________||____U0 x V0_____|
+                 * Read temporary operands from low part of PROD.
+                 * Put result in low part of TSPACE using upper part of TSPACE
+                 * as new TSPACE.
+                 */
+                MPN_MUL_N_RECURSE(tspace, up, vp, hsize, tspace + size);
+
+                /* Add/copy Product L (twice) */
+
+                cy += mpihelp_add_n(prodp + hsize, prodp + hsize, tspace, size);
+                if (cy)
+                        mpihelp_add_1(prodp + hsize + size,
+                                      prodp + hsize + size, hsize, cy);
+
+                MPN_COPY(prodp, tspace, hsize);
+                cy = mpihelp_add_n(prodp + hsize, prodp + hsize, tspace + hsize,
+                                   hsize);
+                if (cy)
+                        mpihelp_add_1(prodp + size, prodp + size, size, 1);
+        }
+}
+
+void mpih_sqr_n_basecase(mpi_ptr_t prodp, mpi_ptr_t up, mpi_size_t size)
+{
+        mpi_size_t i;
+        mpi_limb_t cy_limb;
+        mpi_limb_t v_limb;
+
+        /* Multiply by the first limb in V separately, as the result can be
+         * stored (not added) to PROD.  We also avoid a loop for zeroing.  */
+        v_limb = up[0];
+        if (v_limb <= 1) {
+                if (v_limb == 1)
+                        MPN_COPY(prodp, up, size);
+                else
+                        MPN_ZERO(prodp, size);
+                cy_limb = 0;
+        } else
+                cy_limb = mpihelp_mul_1(prodp, up, size, v_limb);
+
+        prodp[size] = cy_limb;
+        prodp++;
+
+        /* For each iteration in the outer loop, multiply one limb from
+         * U with one limb from V, and add it to PROD.  */
+        for (i = 1; i < size; i++) {
+                v_limb = up[i];
+                if (v_limb <= 1) {
+                        cy_limb = 0;
+                        if (v_limb == 1)
+                                cy_limb = mpihelp_add_n(prodp, prodp, up, size);
+                } else
+                        cy_limb = mpihelp_addmul_1(prodp, up, size, v_limb);
+
+                prodp[size] = cy_limb;
+                prodp++;
+        }
+}
+
+void
+mpih_sqr_n(mpi_ptr_t prodp, mpi_ptr_t up, mpi_size_t size, mpi_ptr_t tspace)
+{
+        if (size & 1) {
+                /* The size is odd, and the code below doesn't handle that.
+                 * Multiply the least significant (size - 1) limbs with a recursive
+                 * call, and handle the most significant limb of S1 and S2
+                 * separately.
+                 * A slightly faster way to do this would be to make the Karatsuba
+                 * code below behave as if the size were even, and let it check for
+                 * odd size in the end.  I.e., in essence move this code to the end.
+                 * Doing so would save us a recursive call, and potentially make the
+                 * stack grow a lot less.
+                 */
+                mpi_size_t esize = size - 1;    /* even size */
+                mpi_limb_t cy_limb;
+
+                MPN_SQR_N_RECURSE(prodp, up, esize, tspace);
+                cy_limb = mpihelp_addmul_1(prodp + esize, up, esize, up[esize]);
+                prodp[esize + esize] = cy_limb;
+                cy_limb = mpihelp_addmul_1(prodp + esize, up, size, up[esize]);
+
+                prodp[esize + size] = cy_limb;
+        } else {
+                mpi_size_t hsize = size >> 1;
+                mpi_limb_t cy;
+
+                /* Product H.      ________________  ________________
+                 *                |_____U1 x U1____||____U0 x U0_____|
+                 * Put result in upper part of PROD and pass low part of TSPACE
+                 * as new TSPACE.
+                 */
+                MPN_SQR_N_RECURSE(prodp + size, up + hsize, hsize, tspace);
+
+                /* Product M.      ________________
+                 *                |_(U1-U0)(U0-U1)_|
+                 */
+                if (mpihelp_cmp(up + hsize, up, hsize) >= 0)
+                        mpihelp_sub_n(prodp, up + hsize, up, hsize);
+                else
+                        mpihelp_sub_n(prodp, up, up + hsize, hsize);
+
+                /* Read temporary operands from low part of PROD.
+                 * Put result in low part of TSPACE using upper part of TSPACE
+                 * as new TSPACE.  */
+                MPN_SQR_N_RECURSE(tspace, prodp, hsize, tspace + size);
+
+                /* Add/copy product H  */
+                MPN_COPY(prodp + hsize, prodp + size, hsize);
+                cy = mpihelp_add_n(prodp + size, prodp + size,
+                                   prodp + size + hsize, hsize);
+
+                /* Add product M (if NEGFLG M is a negative number).  */
+                cy -= mpihelp_sub_n(prodp + hsize, prodp + hsize, tspace, size);
+
+                /* Product L.      ________________  ________________
+                 *                |________________||____U0 x U0_____|
+                 * Read temporary operands from low part of PROD.
+                 * Put result in low part of TSPACE using upper part of TSPACE
+                 * as new TSPACE.  */
+                MPN_SQR_N_RECURSE(tspace, up, hsize, tspace + size);
+
+                /* Add/copy Product L (twice).  */
+                cy += mpihelp_add_n(prodp + hsize, prodp + hsize, tspace, size);
+                if (cy)
+                        mpihelp_add_1(prodp + hsize + size,
+                                      prodp + hsize + size, hsize, cy);
+
+                MPN_COPY(prodp, tspace, hsize);
+                cy = mpihelp_add_n(prodp + hsize, prodp + hsize, tspace + hsize,
+                                   hsize);
+                if (cy)
+                        mpihelp_add_1(prodp + size, prodp + size, size, 1);
+        }
+}
+
+int
+mpihelp_mul_karatsuba_case(mpi_ptr_t prodp,
+                           mpi_ptr_t up, mpi_size_t usize,
+                           mpi_ptr_t vp, mpi_size_t vsize,
+                           struct karatsuba_ctx *ctx)
+{
+        mpi_limb_t cy;
+
+        if (!ctx->tspace || ctx->tspace_size < vsize) {
+                if (ctx->tspace)
+                        mpi_free_limb_space(ctx->tspace);
+                ctx->tspace = mpi_alloc_limb_space(2 * vsize);
+                if (!ctx->tspace)
+                        return -ENOMEM;
+                ctx->tspace_size = vsize;
+        }
+
+        MPN_MUL_N_RECURSE(prodp, up, vp, vsize, ctx->tspace);
+
+        prodp += vsize;
+        up += vsize;
+        usize -= vsize;
+        if (usize >= vsize) {
+                if (!ctx->tp || ctx->tp_size < vsize) {
+                        if (ctx->tp)
+                                mpi_free_limb_space(ctx->tp);
+                        ctx->tp = mpi_alloc_limb_space(2 * vsize);
+                        if (!ctx->tp) {
+                                if (ctx->tspace)
+                                        mpi_free_limb_space(ctx->tspace);
+                                ctx->tspace = NULL;
+                                return -ENOMEM;
+                        }
+                        ctx->tp_size = vsize;
+                }
+
+                do {
+                        MPN_MUL_N_RECURSE(ctx->tp, up, vp, vsize, ctx->tspace);
+                        cy = mpihelp_add_n(prodp, prodp, ctx->tp, vsize);
+                        mpihelp_add_1(prodp + vsize, ctx->tp + vsize, vsize,
+                                      cy);
+                        prodp += vsize;
+                        up += vsize;
+                        usize -= vsize;
+                } while (usize >= vsize);
+        }
+
+        if (usize) {
+                if (usize < KARATSUBA_THRESHOLD) {
+                        mpi_limb_t tmp;
+                        if (mpihelp_mul(ctx->tspace, vp, vsize, up, usize, &tmp)
+                            < 0)
+                                return -ENOMEM;
+                } else {
+                        if (!ctx->next) {
+                                ctx->next = kzalloc(sizeof *ctx, GFP_KERNEL);
+                                if (!ctx->next)
+                                        return -ENOMEM;
+                        }
+                        if (mpihelp_mul_karatsuba_case(ctx->tspace,
+                                                       vp, vsize,
+                                                       up, usize,
+                                                       ctx->next) < 0)
+                                return -ENOMEM;
+                }
+
+                cy = mpihelp_add_n(prodp, prodp, ctx->tspace, vsize);
+                mpihelp_add_1(prodp + vsize, ctx->tspace + vsize, usize, cy);
+        }
+
+        return 0;
+}
+
+void mpihelp_release_karatsuba_ctx(struct karatsuba_ctx *ctx)
+{
+        struct karatsuba_ctx *ctx2;
+
+        if (ctx->tp)
+                mpi_free_limb_space(ctx->tp);
+        if (ctx->tspace)
+                mpi_free_limb_space(ctx->tspace);
+        for (ctx = ctx->next; ctx; ctx = ctx2) {
+                ctx2 = ctx->next;
+                if (ctx->tp)
+                        mpi_free_limb_space(ctx->tp);
+                if (ctx->tspace)
+                        mpi_free_limb_space(ctx->tspace);
+                kfree(ctx);
+        }
+}
+
+/* Multiply the natural numbers u (pointed to by UP, with USIZE limbs)
+ * and v (pointed to by VP, with VSIZE limbs), and store the result at
+ * PRODP.  USIZE + VSIZE limbs are always stored, but if the input
+ * operands are normalized.  Return the most significant limb of the
+ * result.
+ *
+ * NOTE: The space pointed to by PRODP is overwritten before finished
+ * with U and V, so overlap is an error.
+ *
+ * Argument constraints:
+ * 1. USIZE >= VSIZE.
+ * 2. PRODP != UP and PRODP != VP, i.e. the destination
+ *    must be distinct from the multiplier and the multiplicand.
+ */
+
+int
+mpihelp_mul(mpi_ptr_t prodp, mpi_ptr_t up, mpi_size_t usize,
+            mpi_ptr_t vp, mpi_size_t vsize, mpi_limb_t *_result)
+{
+        mpi_ptr_t prod_endp = prodp + usize + vsize - 1;
+        mpi_limb_t cy;
+        struct karatsuba_ctx ctx;
+
+        if (vsize < KARATSUBA_THRESHOLD) {
+                mpi_size_t i;
+                mpi_limb_t v_limb;
+
+                if (!vsize) {
+                        *_result = 0;
+                        return 0;
+                }
+
+                /* Multiply by the first limb in V separately, as the result can be
+                 * stored (not added) to PROD.  We also avoid a loop for zeroing.  */
+                v_limb = vp[0];
+                if (v_limb <= 1) {
+                        if (v_limb == 1)
+                                MPN_COPY(prodp, up, usize);
+                        else
+                                MPN_ZERO(prodp, usize);
+                        cy = 0;
+                } else
+                        cy = mpihelp_mul_1(prodp, up, usize, v_limb);
+
+                prodp[usize] = cy;
+                prodp++;
+
+                /* For each iteration in the outer loop, multiply one limb from
+                 * U with one limb from V, and add it to PROD.  */
+                for (i = 1; i < vsize; i++) {
+                        v_limb = vp[i];
+                        if (v_limb <= 1) {
+                                cy = 0;
+                                if (v_limb == 1)
+                                        cy = mpihelp_add_n(prodp, prodp, up,
+                                                           usize);
+                        } else
+                                cy = mpihelp_addmul_1(prodp, up, usize, v_limb);
+
+                        prodp[usize] = cy;
+                        prodp++;
+                }
+
+                *_result = cy;
+                return 0;
+        }
+
+        memset(&ctx, 0, sizeof ctx);
+        if (mpihelp_mul_karatsuba_case(prodp, up, usize, vp, vsize, &ctx) < 0)
+                return -ENOMEM;
+        mpihelp_release_karatsuba_ctx(&ctx);
+        *_result = *prod_endp;
+        return 0;
+}
diff --git a/lib/mpi/mpiutil.c b/lib/mpi/mpiutil.c
new file mode 100644
index 000000000000..657979f71bef
--- /dev/null
+++ b/lib/mpi/mpiutil.c
@@ -0,0 +1,123 @@
+/* mpiutil.ac  -  Utility functions for MPI
+ * Copyright (C) 1998, 1999 Free Software Foundation, Inc.
+ *
+ * This file is part of GnuPG.
+ *
+ * GnuPG is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * GnuPG is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA
+ */
+
+#include "mpi-internal.h"
+
+/****************
+ * Note:  It was a bad idea to use the number of limbs to allocate
+ *        because on a alpha the limbs are large but we normally need
+ *        integers of n bits - So we should chnage this to bits (or bytes).
+ *
+ *        But mpi_alloc is used in a lot of places :-)
+ */
+MPI mpi_alloc(unsigned nlimbs)
+{
+        MPI a;
+
+        a = kmalloc(sizeof *a, GFP_KERNEL);
+        if (!a)
+                return a;
+
+        if (nlimbs) {
+                a->d = mpi_alloc_limb_space(nlimbs);
+                if (!a->d) {
+                        kfree(a);
+                        return NULL;
+                }
+        } else {
+                a->d = NULL;
+        }
+
+        a->alloced = nlimbs;
+        a->nlimbs = 0;
+        a->sign = 0;
+        a->flags = 0;
+        a->nbits = 0;
+        return a;
+}
+EXPORT_SYMBOL_GPL(mpi_alloc);
+
+mpi_ptr_t mpi_alloc_limb_space(unsigned nlimbs)
+{
+        size_t len = nlimbs * sizeof(mpi_limb_t);
+
+        if (!len)
+                return NULL;
+
+        return kmalloc(len, GFP_KERNEL);
+}
+
+void mpi_free_limb_space(mpi_ptr_t a)
+{
+        if (!a)
+                return;
+
+        kfree(a);
+}
+
+void mpi_assign_limb_space(MPI a, mpi_ptr_t ap, unsigned nlimbs)
+{
+        mpi_free_limb_space(a->d);
+        a->d = ap;
+        a->alloced = nlimbs;
+}
+
+/****************
+ * Resize the array of A to NLIMBS. the additional space is cleared
+ * (set to 0) [done by m_realloc()]
+ */
+int mpi_resize(MPI a, unsigned nlimbs)
+{
+        void *p;
+
+        if (nlimbs <= a->alloced)
+                return 0;       /* no need to do it */
+
+        if (a->d) {
+                p = kmalloc(nlimbs * sizeof(mpi_limb_t), GFP_KERNEL);
+                if (!p)
+                        return -ENOMEM;
+                memcpy(p, a->d, a->alloced * sizeof(mpi_limb_t));
+                kfree(a->d);
+                a->d = p;
+        } else {
+                a->d = kzalloc(nlimbs * sizeof(mpi_limb_t), GFP_KERNEL);
+                if (!a->d)
+                        return -ENOMEM;
+        }
+        a->alloced = nlimbs;
+        return 0;
+}
+
+void mpi_free(MPI a)
+{
+        if (!a)
+                return;
+
+        if (a->flags & 4)
+                kfree(a->d);
+        else
+                mpi_free_limb_space(a->d);
+
+        if (a->flags & ~7)
+                pr_info("invalid flag value in mpi\n");
+        kfree(a);
+}
+EXPORT_SYMBOL_GPL(mpi_free);
diff --git a/lib/nlattr.c b/lib/nlattr.c
index ac09f2226dc7..18eca7809b08 100644
--- a/lib/nlattr.c
+++ b/lib/nlattr.c
@@ -5,7 +5,7 @@
  *                              Alexey Kuznetsov <kuznet@ms2.inr.ac.ru>
  */
 
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/kernel.h>
 #include <linux/errno.h>
 #include <linux/jiffies.h>
@@ -20,7 +20,12 @@ static const u16 nla_attr_minlen[NLA_TYPE_MAX+1] = {
         [NLA_U16]       = sizeof(u16),
         [NLA_U32]       = sizeof(u32),
         [NLA_U64]       = sizeof(u64),
+        [NLA_MSECS]     = sizeof(u64),
         [NLA_NESTED]    = NLA_HDRLEN,
+        [NLA_S8]        = sizeof(s8),
+        [NLA_S16]       = sizeof(s16),
+        [NLA_S32]       = sizeof(s32),
+        [NLA_S64]       = sizeof(s64),
 };
 
 static int validate_nla(const struct nlattr *nla, int maxtype,
diff --git a/lib/notifier-error-inject.c b/lib/notifier-error-inject.c
new file mode 100644
index 000000000000..44b92cb6224f
--- /dev/null
+++ b/lib/notifier-error-inject.c
@@ -0,0 +1,112 @@
+#include <linux/module.h>
+
+#include "notifier-error-inject.h"
+
+static int debugfs_errno_set(void *data, u64 val)
+{
+        *(int *)data = clamp_t(int, val, -MAX_ERRNO, 0);
+        return 0;
+}
+
+static int debugfs_errno_get(void *data, u64 *val)
+{
+        *val = *(int *)data;
+        return 0;
+}
+
+DEFINE_SIMPLE_ATTRIBUTE(fops_errno, debugfs_errno_get, debugfs_errno_set,
+                        "%lld\n");
+
+static struct dentry *debugfs_create_errno(const char *name, mode_t mode,
+                                struct dentry *parent, int *value)
+{
+        return debugfs_create_file(name, mode, parent, value, &fops_errno);
+}
+
+static int notifier_err_inject_callback(struct notifier_block *nb,
+                                unsigned long val, void *p)
+{
+        int err = 0;
+        struct notifier_err_inject *err_inject =
+                container_of(nb, struct notifier_err_inject, nb);
+        struct notifier_err_inject_action *action;
+
+        for (action = err_inject->actions; action->name; action++) {
+                if (action->val == val) {
+                        err = action->error;
+                        break;
+                }
+        }
+        if (err)
+                pr_info("Injecting error (%d) to %s\n", err, action->name);
+
+        return notifier_from_errno(err);
+}
+
+struct dentry *notifier_err_inject_dir;
+EXPORT_SYMBOL_GPL(notifier_err_inject_dir);
+
+struct dentry *notifier_err_inject_init(const char *name, struct dentry *parent,
+                        struct notifier_err_inject *err_inject, int priority)
+{
+        struct notifier_err_inject_action *action;
+        mode_t mode = S_IFREG | S_IRUSR | S_IWUSR;
+        struct dentry *dir;
+        struct dentry *actions_dir;
+
+        err_inject->nb.notifier_call = notifier_err_inject_callback;
+        err_inject->nb.priority = priority;
+
+        dir = debugfs_create_dir(name, parent);
+        if (!dir)
+                return ERR_PTR(-ENOMEM);
+
+        actions_dir = debugfs_create_dir("actions", dir);
+        if (!actions_dir)
+                goto fail;
+
+        for (action = err_inject->actions; action->name; action++) {
+                struct dentry *action_dir;
+
+                action_dir = debugfs_create_dir(action->name, actions_dir);
+                if (!action_dir)
+                        goto fail;
+
+                /*
+                 * Create debugfs r/w file containing action->error. If
+                 * notifier call chain is called with action->val, it will
+                 * fail with the error code
+                 */
+                if (!debugfs_create_errno("error", mode, action_dir,
+                                        &action->error))
+                        goto fail;
+        }
+        return dir;
+fail:
+        debugfs_remove_recursive(dir);
+        return ERR_PTR(-ENOMEM);
+}
+EXPORT_SYMBOL_GPL(notifier_err_inject_init);
+
+static int __init err_inject_init(void)
+{
+        notifier_err_inject_dir =
+                debugfs_create_dir("notifier-error-inject", NULL);
+
+        if (!notifier_err_inject_dir)
+                return -ENOMEM;
+
+        return 0;
+}
+
+static void __exit err_inject_exit(void)
+{
+        debugfs_remove_recursive(notifier_err_inject_dir);
+}
+
+module_init(err_inject_init);
+module_exit(err_inject_exit);
+
+MODULE_DESCRIPTION("Notifier error injection module");
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Akinobu Mita <akinobu.mita@gmail.com>");
diff --git a/lib/notifier-error-inject.h b/lib/notifier-error-inject.h
new file mode 100644
index 000000000000..99b3b6fc470b
--- /dev/null
+++ b/lib/notifier-error-inject.h
@@ -0,0 +1,24 @@
+#include <linux/atomic.h>
+#include <linux/debugfs.h>
+#include <linux/notifier.h>
+
+struct notifier_err_inject_action {
+        unsigned long val;
+        int error;
+        const char *name;
+};
+
+#define NOTIFIER_ERR_INJECT_ACTION(action)      \
+        .name = #action, .val = (action),
+
+struct notifier_err_inject {
+        struct notifier_block nb;
+        struct notifier_err_inject_action actions[];
+        /* The last slot must be terminated with zero sentinel */
+};
+
+extern struct dentry *notifier_err_inject_dir;
+
+extern struct dentry *notifier_err_inject_init(const char *name,
+                struct dentry *parent, struct notifier_err_inject *err_inject,
+                int priority);
diff --git a/lib/oid_registry.c b/lib/oid_registry.c
new file mode 100644
index 000000000000..d8de11f45908
--- /dev/null
+++ b/lib/oid_registry.c
@@ -0,0 +1,170 @@
+/* ASN.1 Object identifier (OID) registry
+ *
+ * Copyright (C) 2012 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+
+#include <linux/export.h>
+#include <linux/oid_registry.h>
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/bug.h>
+#include "oid_registry_data.c"
+
+/**
+ * look_up_OID - Find an OID registration for the specified data
+ * @data: Binary representation of the OID
+ * @datasize: Size of the binary representation
+ */
+enum OID look_up_OID(const void *data, size_t datasize)
+{
+        const unsigned char *octets = data;
+        enum OID oid;
+        unsigned char xhash;
+        unsigned i, j, k, hash;
+        size_t len;
+
+        /* Hash the OID data */
+        hash = datasize - 1;
+
+        for (i = 0; i < datasize; i++)
+                hash += octets[i] * 33;
+        hash = (hash >> 24) ^ (hash >> 16) ^ (hash >> 8) ^ hash;
+        hash &= 0xff;
+
+        /* Binary search the OID registry.  OIDs are stored in ascending order
+         * of hash value then ascending order of size and then in ascending
+         * order of reverse value.
+         */
+        i = 0;
+        k = OID__NR;
+        while (i < k) {
+                j = (i + k) / 2;
+
+                xhash = oid_search_table[j].hash;
+                if (xhash > hash) {
+                        k = j;
+                        continue;
+                }
+                if (xhash < hash) {
+                        i = j + 1;
+                        continue;
+                }
+
+                oid = oid_search_table[j].oid;
+                len = oid_index[oid + 1] - oid_index[oid];
+                if (len > datasize) {
+                        k = j;
+                        continue;
+                }
+                if (len < datasize) {
+                        i = j + 1;
+                        continue;
+                }
+
+                /* Variation is most likely to be at the tail end of the
+                 * OID, so do the comparison in reverse.
+                 */
+                while (len > 0) {
+                        unsigned char a = oid_data[oid_index[oid] + --len];
+                        unsigned char b = octets[len];
+                        if (a > b) {
+                                k = j;
+                                goto next;
+                        }
+                        if (a < b) {
+                                i = j + 1;
+                                goto next;
+                        }
+                }
+                return oid;
+        next:
+                ;
+        }
+
+        return OID__NR;
+}
+EXPORT_SYMBOL_GPL(look_up_OID);
+
+/*
+ * sprint_OID - Print an Object Identifier into a buffer
+ * @data: The encoded OID to print
+ * @datasize: The size of the encoded OID
+ * @buffer: The buffer to render into
+ * @bufsize: The size of the buffer
+ *
+ * The OID is rendered into the buffer in "a.b.c.d" format and the number of
+ * bytes is returned.  -EBADMSG is returned if the data could not be intepreted
+ * and -ENOBUFS if the buffer was too small.
+ */
+int sprint_oid(const void *data, size_t datasize, char *buffer, size_t bufsize)
+{
+        const unsigned char *v = data, *end = v + datasize;
+        unsigned long num;
+        unsigned char n;
+        size_t ret;
+        int count;
+
+        if (v >= end)
+                return -EBADMSG;
+
+        n = *v++;
+        ret = count = snprintf(buffer, bufsize, "%u.%u", n / 40, n % 40);
+        buffer += count;
+        bufsize -= count;
+        if (bufsize == 0)
+                return -ENOBUFS;
+
+        while (v < end) {
+                num = 0;
+                n = *v++;
+                if (!(n & 0x80)) {
+                        num = n;
+                } else {
+                        num = n & 0x7f;
+                        do {
+                                if (v >= end)
+                                        return -EBADMSG;
+                                n = *v++;
+                                num <<= 7;
+                                num |= n & 0x7f;
+                        } while (n & 0x80);
+                }
+                ret += count = snprintf(buffer, bufsize, ".%lu", num);
+                buffer += count;
+                bufsize -= count;
+                if (bufsize == 0)
+                        return -ENOBUFS;
+        }
+
+        return ret;
+}
+EXPORT_SYMBOL_GPL(sprint_oid);
+
+/**
+ * sprint_OID - Print an Object Identifier into a buffer
+ * @oid: The OID to print
+ * @buffer: The buffer to render into
+ * @bufsize: The size of the buffer
+ *
+ * The OID is rendered into the buffer in "a.b.c.d" format and the number of
+ * bytes is returned.
+ */
+int sprint_OID(enum OID oid, char *buffer, size_t bufsize)
+{
+        int ret;
+
+        BUG_ON(oid >= OID__NR);
+
+        ret = sprint_oid(oid_data + oid_index[oid],
+                         oid_index[oid + 1] - oid_index[oid],
+                         buffer, bufsize);
+        BUG_ON(ret == -EBADMSG);
+        return ret;
+}
+EXPORT_SYMBOL_GPL(sprint_OID);
diff --git a/lib/pSeries-reconfig-notifier-error-inject.c b/lib/pSeries-reconfig-notifier-error-inject.c
new file mode 100644
index 000000000000..7f7c98dcd5c4
--- /dev/null
+++ b/lib/pSeries-reconfig-notifier-error-inject.c
@@ -0,0 +1,51 @@
+#include <linux/kernel.h>
+#include <linux/module.h>
+
+#include <asm/pSeries_reconfig.h>
+
+#include "notifier-error-inject.h"
+
+static int priority;
+module_param(priority, int, 0);
+MODULE_PARM_DESC(priority, "specify pSeries reconfig notifier priority");
+
+static struct notifier_err_inject reconfig_err_inject = {
+        .actions = {
+                { NOTIFIER_ERR_INJECT_ACTION(PSERIES_RECONFIG_ADD) },
+                { NOTIFIER_ERR_INJECT_ACTION(PSERIES_RECONFIG_REMOVE) },
+                { NOTIFIER_ERR_INJECT_ACTION(PSERIES_DRCONF_MEM_ADD) },
+                { NOTIFIER_ERR_INJECT_ACTION(PSERIES_DRCONF_MEM_REMOVE) },
+                {}
+        }
+};
+
+static struct dentry *dir;
+
+static int err_inject_init(void)
+{
+        int err;
+
+        dir = notifier_err_inject_init("pSeries-reconfig",
+                notifier_err_inject_dir, &reconfig_err_inject, priority);
+        if (IS_ERR(dir))
+                return PTR_ERR(dir);
+
+        err = pSeries_reconfig_notifier_register(&reconfig_err_inject.nb);
+        if (err)
+                debugfs_remove_recursive(dir);
+
+        return err;
+}
+
+static void err_inject_exit(void)
+{
+        pSeries_reconfig_notifier_unregister(&reconfig_err_inject.nb);
+        debugfs_remove_recursive(dir);
+}
+
+module_init(err_inject_init);
+module_exit(err_inject_exit);
+
+MODULE_DESCRIPTION("pSeries reconfig notifier error injection module");
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Akinobu Mita <akinobu.mita@gmail.com>");
diff --git a/lib/parser.c b/lib/parser.c
index dcbaaef6cf11..52cfa69f73df 100644
--- a/lib/parser.c
+++ b/lib/parser.c
@@ -6,7 +6,8 @@
  */
 
 #include <linux/ctype.h>
-#include <linux/module.h>
+#include <linux/types.h>
+#include <linux/export.h>
 #include <linux/parser.h>
 #include <linux/slab.h>
 #include <linux/string.h>
@@ -121,13 +122,14 @@ int match_token(char *s, const match_table_t table, substring_t args[])
  *
  * Description: Given a &substring_t and a base, attempts to parse the substring
  * as a number in that base. On success, sets @result to the integer represented
- * by the string and returns 0. Returns either -ENOMEM or -EINVAL on failure.
+ * by the string and returns 0. Returns -ENOMEM, -EINVAL, or -ERANGE on failure.
  */
 static int match_number(substring_t *s, int *result, int base)
 {
         char *endp;
         char *buf;
         int ret;
+        long val;
         size_t len = s->to - s->from;
 
         buf = kmalloc(len + 1, GFP_KERNEL);
@@ -135,10 +137,15 @@ static int match_number(substring_t *s, int *result, int base)
                 return -ENOMEM;
         memcpy(buf, s->from, len);
         buf[len] = '\0';
-        *result = simple_strtol(buf, &endp, base);
+
         ret = 0;
+        val = simple_strtol(buf, &endp, base);
         if (endp == buf)
                 ret = -EINVAL;
+        else if (val < (long)INT_MIN || val > (long)INT_MAX)
+                ret = -ERANGE;
+        else
+                *result = (int) val;
         kfree(buf);
         return ret;
 }
diff --git a/lib/pci_iomap.c b/lib/pci_iomap.c
new file mode 100644
index 000000000000..0d83ea8a9605
--- /dev/null
+++ b/lib/pci_iomap.c
@@ -0,0 +1,48 @@
+/*
+ * Implement the default iomap interfaces
+ *
+ * (C) Copyright 2004 Linus Torvalds
+ */
+#include <linux/pci.h>
+#include <linux/io.h>
+
+#include <linux/export.h>
+
+#ifdef CONFIG_PCI
+/**
+ * pci_iomap - create a virtual mapping cookie for a PCI BAR
+ * @dev: PCI device that owns the BAR
+ * @bar: BAR number
+ * @maxlen: length of the memory to map
+ *
+ * Using this function you will get a __iomem address to your device BAR.
+ * You can access it using ioread*() and iowrite*(). These functions hide
+ * the details if this is a MMIO or PIO address space and will just do what
+ * you expect from them in the correct way.
+ *
+ * @maxlen specifies the maximum length to map. If you want to get access to
+ * the complete BAR without checking for its length first, pass %0 here.
+ * */
+void __iomem *pci_iomap(struct pci_dev *dev, int bar, unsigned long maxlen)
+{
+        resource_size_t start = pci_resource_start(dev, bar);
+        resource_size_t len = pci_resource_len(dev, bar);
+        unsigned long flags = pci_resource_flags(dev, bar);
+
+        if (!len || !start)
+                return NULL;
+        if (maxlen && len > maxlen)
+                len = maxlen;
+        if (flags & IORESOURCE_IO)
+                return __pci_ioport_map(dev, start, len);
+        if (flags & IORESOURCE_MEM) {
+                if (flags & IORESOURCE_CACHEABLE)
+                        return ioremap(start, len);
+                return ioremap_nocache(start, len);
+        }
+        /* What? */
+        return NULL;
+}
+
+EXPORT_SYMBOL(pci_iomap);
+#endif /* CONFIG_PCI */
diff --git a/lib/percpu_counter.c b/lib/percpu_counter.c
index 28f2c33c6b53..ba6085d9c741 100644
--- a/lib/percpu_counter.c
+++ b/lib/percpu_counter.c
@@ -10,8 +10,10 @@
 #include <linux/module.h>
 #include <linux/debugobjects.h>
 
+#ifdef CONFIG_HOTPLUG_CPU
 static LIST_HEAD(percpu_counters);
-static DEFINE_MUTEX(percpu_counters_lock);
+static DEFINE_SPINLOCK(percpu_counters_lock);
+#endif
 
 #ifdef CONFIG_DEBUG_OBJECTS_PERCPU_COUNTER
 
@@ -59,13 +61,13 @@ void percpu_counter_set(struct percpu_counter *fbc, s64 amount)
 {
         int cpu;
 
-        spin_lock(&fbc->lock);
+        raw_spin_lock(&fbc->lock);
         for_each_possible_cpu(cpu) {
                 s32 *pcount = per_cpu_ptr(fbc->counters, cpu);
                 *pcount = 0;
         }
         fbc->count = amount;
-        spin_unlock(&fbc->lock);
+        raw_spin_unlock(&fbc->lock);
 }
 EXPORT_SYMBOL(percpu_counter_set);
 
@@ -76,10 +78,10 @@ void __percpu_counter_add(struct percpu_counter *fbc, s64 amount, s32 batch)
         preempt_disable();
         count = __this_cpu_read(*fbc->counters) + amount;
         if (count >= batch || count <= -batch) {
-                spin_lock(&fbc->lock);
+                raw_spin_lock(&fbc->lock);
                 fbc->count += count;
                 __this_cpu_write(*fbc->counters, 0);
-                spin_unlock(&fbc->lock);
+                raw_spin_unlock(&fbc->lock);
         } else {
                 __this_cpu_write(*fbc->counters, count);
         }
@@ -96,13 +98,13 @@ s64 __percpu_counter_sum(struct percpu_counter *fbc)
         s64 ret;
         int cpu;
 
-        spin_lock(&fbc->lock);
+        raw_spin_lock(&fbc->lock);
         ret = fbc->count;
         for_each_online_cpu(cpu) {
                 s32 *pcount = per_cpu_ptr(fbc->counters, cpu);
                 ret += *pcount;
         }
-        spin_unlock(&fbc->lock);
+        raw_spin_unlock(&fbc->lock);
         return ret;
 }
 EXPORT_SYMBOL(__percpu_counter_sum);
@@ -110,7 +112,7 @@ EXPORT_SYMBOL(__percpu_counter_sum);
 int __percpu_counter_init(struct percpu_counter *fbc, s64 amount,
                           struct lock_class_key *key)
 {
-        spin_lock_init(&fbc->lock);
+        raw_spin_lock_init(&fbc->lock);
         lockdep_set_class(&fbc->lock, key);
         fbc->count = amount;
         fbc->counters = alloc_percpu(s32);
@@ -121,9 +123,9 @@ int __percpu_counter_init(struct percpu_counter *fbc, s64 amount,
 
 #ifdef CONFIG_HOTPLUG_CPU
         INIT_LIST_HEAD(&fbc->list);
-        mutex_lock(&percpu_counters_lock);
+        spin_lock(&percpu_counters_lock);
         list_add(&fbc->list, &percpu_counters);
-        mutex_unlock(&percpu_counters_lock);
+        spin_unlock(&percpu_counters_lock);
 #endif
         return 0;
 }
@@ -137,9 +139,9 @@ void percpu_counter_destroy(struct percpu_counter *fbc)
         debug_percpu_counter_deactivate(fbc);
 
 #ifdef CONFIG_HOTPLUG_CPU
-        mutex_lock(&percpu_counters_lock);
+        spin_lock(&percpu_counters_lock);
         list_del(&fbc->list);
-        mutex_unlock(&percpu_counters_lock);
+        spin_unlock(&percpu_counters_lock);
 #endif
         free_percpu(fbc->counters);
         fbc->counters = NULL;
@@ -168,18 +170,18 @@ static int __cpuinit percpu_counter_hotcpu_callback(struct notifier_block *nb,
                 return NOTIFY_OK;
 
         cpu = (unsigned long)hcpu;
-        mutex_lock(&percpu_counters_lock);
+        spin_lock(&percpu_counters_lock);
         list_for_each_entry(fbc, &percpu_counters, list) {
                 s32 *pcount;
                 unsigned long flags;
 
-                spin_lock_irqsave(&fbc->lock, flags);
+                raw_spin_lock_irqsave(&fbc->lock, flags);
                 pcount = per_cpu_ptr(fbc->counters, cpu);
                 fbc->count += *pcount;
                 *pcount = 0;
-                spin_unlock_irqrestore(&fbc->lock, flags);
+                raw_spin_unlock_irqrestore(&fbc->lock, flags);
         }
-        mutex_unlock(&percpu_counters_lock);
+        spin_unlock(&percpu_counters_lock);
 #endif
         return NOTIFY_OK;
 }
diff --git a/lib/plist.c b/lib/plist.c
index a0a4da489c22..1ebc95f7a46f 100644
--- a/lib/plist.c
+++ b/lib/plist.c
@@ -23,6 +23,7 @@
  * information.
  */
 
+#include <linux/bug.h>
 #include <linux/plist.h>
 #include <linux/spinlock.h>
 
@@ -174,7 +175,7 @@ static int  __init plist_test(void)
         int nr_expect = 0, i, loop;
         unsigned int r = local_clock();
 
-        printk(KERN_INFO "start plist test\n");
+        pr_debug("start plist test\n");
         plist_head_init(&test_head);
         for (i = 0; i < ARRAY_SIZE(test_node); i++)
                 plist_node_init(test_node + i, 0);
@@ -202,7 +203,7 @@ static int  __init plist_test(void)
                 plist_test_check(nr_expect);
         }
 
-        printk(KERN_INFO "end plist test\n");
+        pr_debug("end plist test\n");
         return 0;
 }
 
diff --git a/lib/pm-notifier-error-inject.c b/lib/pm-notifier-error-inject.c
new file mode 100644
index 000000000000..c094b2dedc23
--- /dev/null
+++ b/lib/pm-notifier-error-inject.c
@@ -0,0 +1,49 @@
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/suspend.h>
+
+#include "notifier-error-inject.h"
+
+static int priority;
+module_param(priority, int, 0);
+MODULE_PARM_DESC(priority, "specify PM notifier priority");
+
+static struct notifier_err_inject pm_notifier_err_inject = {
+        .actions = {
+                { NOTIFIER_ERR_INJECT_ACTION(PM_HIBERNATION_PREPARE) },
+                { NOTIFIER_ERR_INJECT_ACTION(PM_SUSPEND_PREPARE) },
+                { NOTIFIER_ERR_INJECT_ACTION(PM_RESTORE_PREPARE) },
+                {}
+        }
+};
+
+static struct dentry *dir;
+
+static int err_inject_init(void)
+{
+        int err;
+
+        dir = notifier_err_inject_init("pm", notifier_err_inject_dir,
+                                        &pm_notifier_err_inject, priority);
+        if (IS_ERR(dir))
+                return PTR_ERR(dir);
+
+        err = register_pm_notifier(&pm_notifier_err_inject.nb);
+        if (err)
+                debugfs_remove_recursive(dir);
+
+        return err;
+}
+
+static void err_inject_exit(void)
+{
+        unregister_pm_notifier(&pm_notifier_err_inject.nb);
+        debugfs_remove_recursive(dir);
+}
+
+module_init(err_inject_init);
+module_exit(err_inject_exit);
+
+MODULE_DESCRIPTION("PM notifier error injection module");
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Akinobu Mita <akinobu.mita@gmail.com>");
diff --git a/lib/prio_tree.c b/lib/prio_tree.c
deleted file mode 100644
index ccfd850b0dec..000000000000
--- a/lib/prio_tree.c
+++ /dev/null
@@ -1,484 +0,0 @@
-/*
- * lib/prio_tree.c - priority search tree
- *
- * Copyright (C) 2004, Rajesh Venkatasubramanian <vrajesh@umich.edu>
- *
- * This file is released under the GPL v2.
- *
- * Based on the radix priority search tree proposed by Edward M. McCreight
- * SIAM Journal of Computing, vol. 14, no.2, pages 257-276, May 1985
- *
- * 02Feb2004    Initial version
- */
-
-#include <linux/init.h>
-#include <linux/mm.h>
-#include <linux/prio_tree.h>
-
-/*
- * A clever mix of heap and radix trees forms a radix priority search tree (PST)
- * which is useful for storing intervals, e.g, we can consider a vma as a closed
- * interval of file pages [offset_begin, offset_end], and store all vmas that
- * map a file in a PST. Then, using the PST, we can answer a stabbing query,
- * i.e., selecting a set of stored intervals (vmas) that overlap with (map) a
- * given input interval X (a set of consecutive file pages), in "O(log n + m)"
- * time where 'log n' is the height of the PST, and 'm' is the number of stored
- * intervals (vmas) that overlap (map) with the input interval X (the set of
- * consecutive file pages).
- *
- * In our implementation, we store closed intervals of the form [radix_index,
- * heap_index]. We assume that always radix_index <= heap_index. McCreight's PST
- * is designed for storing intervals with unique radix indices, i.e., each
- * interval have different radix_index. However, this limitation can be easily
- * overcome by using the size, i.e., heap_index - radix_index, as part of the
- * index, so we index the tree using [(radix_index,size), heap_index].
- *
- * When the above-mentioned indexing scheme is used, theoretically, in a 32 bit
- * machine, the maximum height of a PST can be 64. We can use a balanced version
- * of the priority search tree to optimize the tree height, but the balanced
- * tree proposed by McCreight is too complex and memory-hungry for our purpose.
- */
-
-/*
- * The following macros are used for implementing prio_tree for i_mmap
- */
-
-#define RADIX_INDEX(vma)  ((vma)->vm_pgoff)
-#define VMA_SIZE(vma)     (((vma)->vm_end - (vma)->vm_start) >> PAGE_SHIFT)
-/* avoid overflow */
-#define HEAP_INDEX(vma)   ((vma)->vm_pgoff + (VMA_SIZE(vma) - 1))
-
-
-static void get_index(const struct prio_tree_root *root,
-    const struct prio_tree_node *node,
-    unsigned long *radix, unsigned long *heap)
-{
-        if (root->raw) {
-                struct vm_area_struct *vma = prio_tree_entry(
-                    node, struct vm_area_struct, shared.prio_tree_node);
-
-                *radix = RADIX_INDEX(vma);
-                *heap = HEAP_INDEX(vma);
-        }
-        else {
-                *radix = node->start;
-                *heap = node->last;
-        }
-}
-
-static unsigned long index_bits_to_maxindex[BITS_PER_LONG];
-
-void __init prio_tree_init(void)
-{
-        unsigned int i;
-
-        for (i = 0; i < ARRAY_SIZE(index_bits_to_maxindex) - 1; i++)
-                index_bits_to_maxindex[i] = (1UL << (i + 1)) - 1;
-        index_bits_to_maxindex[ARRAY_SIZE(index_bits_to_maxindex) - 1] = ~0UL;
-}
-
-/*
- * Maximum heap_index that can be stored in a PST with index_bits bits
- */
-static inline unsigned long prio_tree_maxindex(unsigned int bits)
-{
-        return index_bits_to_maxindex[bits - 1];
-}
-
-/*
- * Extend a priority search tree so that it can store a node with heap_index
- * max_heap_index. In the worst case, this algorithm takes O((log n)^2).
- * However, this function is used rarely and the common case performance is
- * not bad.
- */
-static struct prio_tree_node *prio_tree_expand(struct prio_tree_root *root,
-                struct prio_tree_node *node, unsigned long max_heap_index)
-{
-        struct prio_tree_node *first = NULL, *prev, *last = NULL;
-
-        if (max_heap_index > prio_tree_maxindex(root->index_bits))
-                root->index_bits++;
-
-        while (max_heap_index > prio_tree_maxindex(root->index_bits)) {
-                root->index_bits++;
-
-                if (prio_tree_empty(root))
-                        continue;
-
-                if (first == NULL) {
-                        first = root->prio_tree_node;
-                        prio_tree_remove(root, root->prio_tree_node);
-                        INIT_PRIO_TREE_NODE(first);
-                        last = first;
-                } else {
-                        prev = last;
-                        last = root->prio_tree_node;
-                        prio_tree_remove(root, root->prio_tree_node);
-                        INIT_PRIO_TREE_NODE(last);
-                        prev->left = last;
-                        last->parent = prev;
-                }
-        }
-
-        INIT_PRIO_TREE_NODE(node);
-
-        if (first) {
-                node->left = first;
-                first->parent = node;
-        } else
-                last = node;
-
-        if (!prio_tree_empty(root)) {
-                last->left = root->prio_tree_node;
-                last->left->parent = last;
-        }
-
-        root->prio_tree_node = node;
-        return node;
-}
-
-/*
- * Replace a prio_tree_node with a new node and return the old node
- */
-struct prio_tree_node *prio_tree_replace(struct prio_tree_root *root,
-                struct prio_tree_node *old, struct prio_tree_node *node)
-{
-        INIT_PRIO_TREE_NODE(node);
-
-        if (prio_tree_root(old)) {
-                BUG_ON(root->prio_tree_node != old);
-                /*
-                 * We can reduce root->index_bits here. However, it is complex
-                 * and does not help much to improve performance (IMO).
-                 */
-                node->parent = node;
-                root->prio_tree_node = node;
-        } else {
-                node->parent = old->parent;
-                if (old->parent->left == old)
-                        old->parent->left = node;
-                else
-                        old->parent->right = node;
-        }
-
-        if (!prio_tree_left_empty(old)) {
-                node->left = old->left;
-                old->left->parent = node;
-        }
-
-        if (!prio_tree_right_empty(old)) {
-                node->right = old->right;
-                old->right->parent = node;
-        }
-
-        return old;
-}
-
-/*
- * Insert a prio_tree_node @node into a radix priority search tree @root. The
- * algorithm typically takes O(log n) time where 'log n' is the number of bits
- * required to represent the maximum heap_index. In the worst case, the algo
- * can take O((log n)^2) - check prio_tree_expand.
- *
- * If a prior node with same radix_index and heap_index is already found in
- * the tree, then returns the address of the prior node. Otherwise, inserts
- * @node into the tree and returns @node.
- */
-struct prio_tree_node *prio_tree_insert(struct prio_tree_root *root,
-                struct prio_tree_node *node)
-{
-        struct prio_tree_node *cur, *res = node;
-        unsigned long radix_index, heap_index;
-        unsigned long r_index, h_index, index, mask;
-        int size_flag = 0;
-
-        get_index(root, node, &radix_index, &heap_index);
-
-        if (prio_tree_empty(root) ||
-                        heap_index > prio_tree_maxindex(root->index_bits))
-                return prio_tree_expand(root, node, heap_index);
-
-        cur = root->prio_tree_node;
-        mask = 1UL << (root->index_bits - 1);
-
-        while (mask) {
-                get_index(root, cur, &r_index, &h_index);
-
-                if (r_index == radix_index && h_index == heap_index)
-                        return cur;
-
-                if (h_index < heap_index ||
-                    (h_index == heap_index && r_index > radix_index)) {
-                        struct prio_tree_node *tmp = node;
-                        node = prio_tree_replace(root, cur, node);
-                        cur = tmp;
-                        /* swap indices */
-                        index = r_index;
-                        r_index = radix_index;
-                        radix_index = index;
-                        index = h_index;
-                        h_index = heap_index;
-                        heap_index = index;
-                }
-
-                if (size_flag)
-                        index = heap_index - radix_index;
-                else
-                        index = radix_index;
-
-                if (index & mask) {
-                        if (prio_tree_right_empty(cur)) {
-                                INIT_PRIO_TREE_NODE(node);
-                                cur->right = node;
-                                node->parent = cur;
-                                return res;
-                        } else
-                                cur = cur->right;
-                } else {
-                        if (prio_tree_left_empty(cur)) {
-                                INIT_PRIO_TREE_NODE(node);
-                                cur->left = node;
-                                node->parent = cur;
-                                return res;
-                        } else
-                                cur = cur->left;
-                }
-
-                mask >>= 1;
-
-                if (!mask) {
-                        mask = 1UL << (BITS_PER_LONG - 1);
-                        size_flag = 1;
-                }
-        }
-        /* Should not reach here */
-        BUG();
-        return NULL;
-}
-
-/*
- * Remove a prio_tree_node @node from a radix priority search tree @root. The
- * algorithm takes O(log n) time where 'log n' is the number of bits required
- * to represent the maximum heap_index.
- */
-void prio_tree_remove(struct prio_tree_root *root, struct prio_tree_node *node)
-{
-        struct prio_tree_node *cur;
-        unsigned long r_index, h_index_right, h_index_left;
-
-        cur = node;
-
-        while (!prio_tree_left_empty(cur) || !prio_tree_right_empty(cur)) {
-                if (!prio_tree_left_empty(cur))
-                        get_index(root, cur->left, &r_index, &h_index_left);
-                else {
-                        cur = cur->right;
-                        continue;
-                }
-
-                if (!prio_tree_right_empty(cur))
-                        get_index(root, cur->right, &r_index, &h_index_right);
-                else {
-                        cur = cur->left;
-                        continue;
-                }
-
-                /* both h_index_left and h_index_right cannot be 0 */
-                if (h_index_left >= h_index_right)
-                        cur = cur->left;
-                else
-                        cur = cur->right;
-        }
-
-        if (prio_tree_root(cur)) {
-                BUG_ON(root->prio_tree_node != cur);
-                __INIT_PRIO_TREE_ROOT(root, root->raw);
-                return;
-        }
-
-        if (cur->parent->right == cur)
-                cur->parent->right = cur->parent;
-        else
-                cur->parent->left = cur->parent;
-
-        while (cur != node)
-                cur = prio_tree_replace(root, cur->parent, cur);
-}
-
-/*
- * Following functions help to enumerate all prio_tree_nodes in the tree that
- * overlap with the input interval X [radix_index, heap_index]. The enumeration
- * takes O(log n + m) time where 'log n' is the height of the tree (which is
- * proportional to # of bits required to represent the maximum heap_index) and
- * 'm' is the number of prio_tree_nodes that overlap the interval X.
- */
-
-static struct prio_tree_node *prio_tree_left(struct prio_tree_iter *iter,
-                unsigned long *r_index, unsigned long *h_index)
-{
-        if (prio_tree_left_empty(iter->cur))
-                return NULL;
-
-        get_index(iter->root, iter->cur->left, r_index, h_index);
-
-        if (iter->r_index <= *h_index) {
-                iter->cur = iter->cur->left;
-                iter->mask >>= 1;
-                if (iter->mask) {
-                        if (iter->size_level)
-                                iter->size_level++;
-                } else {
-                        if (iter->size_level) {
-                                BUG_ON(!prio_tree_left_empty(iter->cur));
-                                BUG_ON(!prio_tree_right_empty(iter->cur));
-                                iter->size_level++;
-                                iter->mask = ULONG_MAX;
-                        } else {
-                                iter->size_level = 1;
-                                iter->mask = 1UL << (BITS_PER_LONG - 1);
-                        }
-                }
-                return iter->cur;
-        }
-
-        return NULL;
-}
-
-static struct prio_tree_node *prio_tree_right(struct prio_tree_iter *iter,
-                unsigned long *r_index, unsigned long *h_index)
-{
-        unsigned long value;
-
-        if (prio_tree_right_empty(iter->cur))
-                return NULL;
-
-        if (iter->size_level)
-                value = iter->value;
-        else
-                value = iter->value | iter->mask;
-
-        if (iter->h_index < value)
-                return NULL;
-
-        get_index(iter->root, iter->cur->right, r_index, h_index);
-
-        if (iter->r_index <= *h_index) {
-                iter->cur = iter->cur->right;
-                iter->mask >>= 1;
-                iter->value = value;
-                if (iter->mask) {
-                        if (iter->size_level)
-                                iter->size_level++;
-                } else {
-                        if (iter->size_level) {
-                                BUG_ON(!prio_tree_left_empty(iter->cur));
-                                BUG_ON(!prio_tree_right_empty(iter->cur));
-                                iter->size_level++;
-                                iter->mask = ULONG_MAX;
-                        } else {
-                                iter->size_level = 1;
-                                iter->mask = 1UL << (BITS_PER_LONG - 1);
-                        }
-                }
-                return iter->cur;
-        }
-
-        return NULL;
-}
-
-static struct prio_tree_node *prio_tree_parent(struct prio_tree_iter *iter)
-{
-        iter->cur = iter->cur->parent;
-        if (iter->mask == ULONG_MAX)
-                iter->mask = 1UL;
-        else if (iter->size_level == 1)
-                iter->mask = 1UL;
-        else
-                iter->mask <<= 1;
-        if (iter->size_level)
-                iter->size_level--;
-        if (!iter->size_level && (iter->value & iter->mask))
-                iter->value ^= iter->mask;
-        return iter->cur;
-}
-
-static inline int overlap(struct prio_tree_iter *iter,
-                unsigned long r_index, unsigned long h_index)
-{
-        return iter->h_index >= r_index && iter->r_index <= h_index;
-}
-
-/*
- * prio_tree_first:
- *
- * Get the first prio_tree_node that overlaps with the interval [radix_index,
- * heap_index]. Note that always radix_index <= heap_index. We do a pre-order
- * traversal of the tree.
- */
-static struct prio_tree_node *prio_tree_first(struct prio_tree_iter *iter)
-{
-        struct prio_tree_root *root;
-        unsigned long r_index, h_index;
-
-        INIT_PRIO_TREE_ITER(iter);
-
-        root = iter->root;
-        if (prio_tree_empty(root))
-                return NULL;
-
-        get_index(root, root->prio_tree_node, &r_index, &h_index);
-
-        if (iter->r_index > h_index)
-                return NULL;
-
-        iter->mask = 1UL << (root->index_bits - 1);
-        iter->cur = root->prio_tree_node;
-
-        while (1) {
-                if (overlap(iter, r_index, h_index))
-                        return iter->cur;
-
-                if (prio_tree_left(iter, &r_index, &h_index))
-                        continue;
-
-                if (prio_tree_right(iter, &r_index, &h_index))
-                        continue;
-
-                break;
-        }
-        return NULL;
-}
-
-/*
- * prio_tree_next:
- *
- * Get the next prio_tree_node that overlaps with the input interval in iter
- */
-struct prio_tree_node *prio_tree_next(struct prio_tree_iter *iter)
-{
-        unsigned long r_index, h_index;
-
-        if (iter->cur == NULL)
-                return prio_tree_first(iter);
-
-repeat:
-        while (prio_tree_left(iter, &r_index, &h_index))
-                if (overlap(iter, r_index, h_index))
-                        return iter->cur;
-
-        while (!prio_tree_right(iter, &r_index, &h_index)) {
-                while (!prio_tree_root(iter->cur) &&
-                                iter->cur->parent->right == iter->cur)
-                        prio_tree_parent(iter);
-
-                if (prio_tree_root(iter->cur))
-                        return NULL;
-
-                prio_tree_parent(iter);
-        }
-
-        if (overlap(iter, r_index, h_index))
-                return iter->cur;
-
-        goto repeat;
-}
diff --git a/lib/proportions.c b/lib/proportions.c
index d50746a79de2..05df84801b56 100644
--- a/lib/proportions.c
+++ b/lib/proportions.c
@@ -190,7 +190,7 @@ prop_adjust_shift(int *pl_shift, unsigned long *pl_period, int new_shift)
 
 int prop_local_init_percpu(struct prop_local_percpu *pl)
 {
-        spin_lock_init(&pl->lock);
+        raw_spin_lock_init(&pl->lock);
         pl->shift = 0;
         pl->period = 0;
         return percpu_counter_init(&pl->events, 0);
@@ -226,7 +226,7 @@ void prop_norm_percpu(struct prop_global *pg, struct prop_local_percpu *pl)
         if (pl->period == global_period)
                 return;
 
-        spin_lock_irqsave(&pl->lock, flags);
+        raw_spin_lock_irqsave(&pl->lock, flags);
         prop_adjust_shift(&pl->shift, &pl->period, pg->shift);
 
         /*
@@ -247,7 +247,7 @@ void prop_norm_percpu(struct prop_global *pg, struct prop_local_percpu *pl)
                 percpu_counter_set(&pl->events, 0);
 
         pl->period = global_period;
-        spin_unlock_irqrestore(&pl->lock, flags);
+        raw_spin_unlock_irqrestore(&pl->lock, flags);
 }
 
 /*
@@ -324,7 +324,7 @@ void prop_fraction_percpu(struct prop_descriptor *pd,
 
 int prop_local_init_single(struct prop_local_single *pl)
 {
-        spin_lock_init(&pl->lock);
+        raw_spin_lock_init(&pl->lock);
         pl->shift = 0;
         pl->period = 0;
         pl->events = 0;
@@ -356,7 +356,7 @@ void prop_norm_single(struct prop_global *pg, struct prop_local_single *pl)
         if (pl->period == global_period)
                 return;
 
-        spin_lock_irqsave(&pl->lock, flags);
+        raw_spin_lock_irqsave(&pl->lock, flags);
         prop_adjust_shift(&pl->shift, &pl->period, pg->shift);
         /*
          * For each missed period, we half the local counter.
@@ -367,7 +367,7 @@ void prop_norm_single(struct prop_global *pg, struct prop_local_single *pl)
         else
                 pl->events = 0;
         pl->period = global_period;
-        spin_unlock_irqrestore(&pl->lock, flags);
+        raw_spin_unlock_irqrestore(&pl->lock, flags);
 }
 
 /*
diff --git a/lib/radix-tree.c b/lib/radix-tree.c
index a2f9da59c197..e7964296fd50 100644
--- a/lib/radix-tree.c
+++ b/lib/radix-tree.c
@@ -3,6 +3,7 @@
  * Portions Copyright (C) 2001 Christoph Hellwig
  * Copyright (C) 2005 SGI, Christoph Lameter
  * Copyright (C) 2006 Nick Piggin
+ * Copyright (C) 2012 Konstantin Khlebnikov
  *
  * This program is free software; you can redistribute it and/or
  * modify it under the terms of the GNU General Public License as
@@ -22,7 +23,7 @@
 #include <linux/errno.h>
 #include <linux/init.h>
 #include <linux/kernel.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/radix-tree.h>
 #include <linux/percpu.h>
 #include <linux/slab.h>
@@ -48,16 +49,14 @@
 struct radix_tree_node {
         unsigned int    height;         /* Height from the bottom */
         unsigned int    count;
-        struct rcu_head rcu_head;
+        union {
+                struct radix_tree_node *parent; /* Used when ascending tree */
+                struct rcu_head rcu_head;       /* Used when freeing node */
+        };
         void __rcu      *slots[RADIX_TREE_MAP_SIZE];
         unsigned long   tags[RADIX_TREE_MAX_TAGS][RADIX_TREE_TAG_LONGS];
 };
 
-struct radix_tree_path {
-        struct radix_tree_node *node;
-        int offset;
-};
-
 #define RADIX_TREE_INDEX_BITS  (8 /* CHAR_BIT */ * sizeof(unsigned long))
 #define RADIX_TREE_MAX_PATH (DIV_ROUND_UP(RADIX_TREE_INDEX_BITS, \
                                           RADIX_TREE_MAP_SHIFT))
@@ -74,11 +73,24 @@ static unsigned long height_to_maxindex[RADIX_TREE_MAX_PATH + 1] __read_mostly;
 static struct kmem_cache *radix_tree_node_cachep;
 
 /*
+ * The radix tree is variable-height, so an insert operation not only has
+ * to build the branch to its corresponding item, it also has to build the
+ * branch to existing items if the size has to be increased (by
+ * radix_tree_extend).
+ *
+ * The worst case is a zero height tree with just a single item at index 0,
+ * and then inserting an item at index ULONG_MAX. This requires 2 new branches
+ * of RADIX_TREE_MAX_PATH size to be created, with only the root node shared.
+ * Hence:
+ */
+#define RADIX_TREE_PRELOAD_SIZE (RADIX_TREE_MAX_PATH * 2 - 1)
+
+/*
  * Per-cpu pool of preloaded nodes
  */
 struct radix_tree_preload {
         int nr;
-        struct radix_tree_node *nodes[RADIX_TREE_MAX_PATH];
+        struct radix_tree_node *nodes[RADIX_TREE_PRELOAD_SIZE];
 };
 static DEFINE_PER_CPU(struct radix_tree_preload, radix_tree_preloads) = { 0, };
 
@@ -148,6 +160,43 @@ static inline int any_tag_set(struct radix_tree_node *node, unsigned int tag)
         }
         return 0;
 }
+
+/**
+ * radix_tree_find_next_bit - find the next set bit in a memory region
+ *
+ * @addr: The address to base the search on
+ * @size: The bitmap size in bits
+ * @offset: The bitnumber to start searching at
+ *
+ * Unrollable variant of find_next_bit() for constant size arrays.
+ * Tail bits starting from size to roundup(size, BITS_PER_LONG) must be zero.
+ * Returns next bit offset, or size if nothing found.
+ */
+static __always_inline unsigned long
+radix_tree_find_next_bit(const unsigned long *addr,
+                         unsigned long size, unsigned long offset)
+{
+        if (!__builtin_constant_p(size))
+                return find_next_bit(addr, size, offset);
+
+        if (offset < size) {
+                unsigned long tmp;
+
+                addr += offset / BITS_PER_LONG;
+                tmp = *addr >> (offset % BITS_PER_LONG);
+                if (tmp)
+                        return __ffs(tmp) + offset;
+                offset = (offset + BITS_PER_LONG) & ~(BITS_PER_LONG - 1);
+                while (offset < size) {
+                        tmp = *++addr;
+                        if (tmp)
+                                return __ffs(tmp) + offset;
+                        offset += BITS_PER_LONG;
+                }
+        }
+        return size;
+}
+
 /*
  * This assumes that the caller has performed appropriate preallocation, and
  * that the caller has pinned this thread of control to the current CPU.
@@ -256,6 +305,7 @@ static inline unsigned long radix_tree_maxindex(unsigned int height)
 static int radix_tree_extend(struct radix_tree_root *root, unsigned long index)
 {
         struct radix_tree_node *node;
+        struct radix_tree_node *slot;
         unsigned int height;
         int tag;
 
@@ -274,18 +324,23 @@ static int radix_tree_extend(struct radix_tree_root *root, unsigned long index)
                 if (!(node = radix_tree_node_alloc(root)))
                         return -ENOMEM;
 
-                /* Increase the height.  */
-                node->slots[0] = indirect_to_ptr(root->rnode);
-
                 /* Propagate the aggregated tag info into the new root */
                 for (tag = 0; tag < RADIX_TREE_MAX_TAGS; tag++) {
                         if (root_tag_get(root, tag))
                                 tag_set(node, tag, 0);
                 }
 
+                /* Increase the height.  */
                 newheight = root->height+1;
                 node->height = newheight;
                 node->count = 1;
+                node->parent = NULL;
+                slot = root->rnode;
+                if (newheight > 1) {
+                        slot = indirect_to_ptr(slot);
+                        slot->parent = node;
+                }
+                node->slots[0] = slot;
                 node = ptr_to_indirect(node);
                 rcu_assign_pointer(root->rnode, node);
                 root->height = newheight;
@@ -331,6 +386,7 @@ int radix_tree_insert(struct radix_tree_root *root,
                         if (!(slot = radix_tree_node_alloc(root)))
                                 return -ENOMEM;
                         slot->height = height;
+                        slot->parent = node;
                         if (node) {
                                 rcu_assign_pointer(node->slots[offset], slot);
                                 node->count++;
@@ -504,47 +560,41 @@ EXPORT_SYMBOL(radix_tree_tag_set);
 void *radix_tree_tag_clear(struct radix_tree_root *root,
                         unsigned long index, unsigned int tag)
 {
-        /*
-         * The radix tree path needs to be one longer than the maximum path
-         * since the "list" is null terminated.
-         */
-        struct radix_tree_path path[RADIX_TREE_MAX_PATH + 1], *pathp = path;
+        struct radix_tree_node *node = NULL;
         struct radix_tree_node *slot = NULL;
         unsigned int height, shift;
+        int uninitialized_var(offset);
 
         height = root->height;
         if (index > radix_tree_maxindex(height))
                 goto out;
 
-        shift = (height - 1) * RADIX_TREE_MAP_SHIFT;
-        pathp->node = NULL;
+        shift = height * RADIX_TREE_MAP_SHIFT;
         slot = indirect_to_ptr(root->rnode);
 
-        while (height > 0) {
-                int offset;
-
+        while (shift) {
                 if (slot == NULL)
                         goto out;
 
+                shift -= RADIX_TREE_MAP_SHIFT;
                 offset = (index >> shift) & RADIX_TREE_MAP_MASK;
-                pathp[1].offset = offset;
-                pathp[1].node = slot;
+                node = slot;
                 slot = slot->slots[offset];
-                pathp++;
-                shift -= RADIX_TREE_MAP_SHIFT;
-                height--;
         }
 
         if (slot == NULL)
                 goto out;
 
-        while (pathp->node) {
-                if (!tag_get(pathp->node, tag, pathp->offset))
+        while (node) {
+                if (!tag_get(node, tag, offset))
                         goto out;
-                tag_clear(pathp->node, tag, pathp->offset);
-                if (any_tag_set(pathp->node, tag))
+                tag_clear(node, tag, offset);
+                if (any_tag_set(node, tag))
                         goto out;
-                pathp--;
+
+                index >>= RADIX_TREE_MAP_SHIFT;
+                offset = index & RADIX_TREE_MAP_MASK;
+                node = node->parent;
         }
 
         /* clear the root's tag bit */
@@ -576,7 +626,6 @@ int radix_tree_tag_get(struct radix_tree_root *root,
 {
         unsigned int height, shift;
         struct radix_tree_node *node;
-        int saw_unset_tag = 0;
 
         /* check the root's tag bit */
         if (!root_tag_get(root, tag))
@@ -603,15 +652,10 @@ int radix_tree_tag_get(struct radix_tree_root *root,
                         return 0;
 
                 offset = (index >> shift) & RADIX_TREE_MAP_MASK;
-
-                /*
-                 * This is just a debug check.  Later, we can bale as soon as
-                 * we see an unset tag.
-                 */
                 if (!tag_get(node, tag, offset))
-                        saw_unset_tag = 1;
+                        return 0;
                 if (height == 1)
-                        return !!tag_get(node, tag, offset);
+                        return 1;
                 node = rcu_dereference_raw(node->slots[offset]);
                 shift -= RADIX_TREE_MAP_SHIFT;
                 height--;
@@ -620,6 +664,122 @@ int radix_tree_tag_get(struct radix_tree_root *root,
 EXPORT_SYMBOL(radix_tree_tag_get);
 
 /**
+ * radix_tree_next_chunk - find next chunk of slots for iteration
+ *
+ * @root:       radix tree root
+ * @iter:       iterator state
+ * @flags:      RADIX_TREE_ITER_* flags and tag index
+ * Returns:     pointer to chunk first slot, or NULL if iteration is over
+ */
+void **radix_tree_next_chunk(struct radix_tree_root *root,
+                             struct radix_tree_iter *iter, unsigned flags)
+{
+        unsigned shift, tag = flags & RADIX_TREE_ITER_TAG_MASK;
+        struct radix_tree_node *rnode, *node;
+        unsigned long index, offset;
+
+        if ((flags & RADIX_TREE_ITER_TAGGED) && !root_tag_get(root, tag))
+                return NULL;
+
+        /*
+         * Catch next_index overflow after ~0UL. iter->index never overflows
+         * during iterating; it can be zero only at the beginning.
+         * And we cannot overflow iter->next_index in a single step,
+         * because RADIX_TREE_MAP_SHIFT < BITS_PER_LONG.
+         *
+         * This condition also used by radix_tree_next_slot() to stop
+         * contiguous iterating, and forbid swithing to the next chunk.
+         */
+        index = iter->next_index;
+        if (!index && iter->index)
+                return NULL;
+
+        rnode = rcu_dereference_raw(root->rnode);
+        if (radix_tree_is_indirect_ptr(rnode)) {
+                rnode = indirect_to_ptr(rnode);
+        } else if (rnode && !index) {
+                /* Single-slot tree */
+                iter->index = 0;
+                iter->next_index = 1;
+                iter->tags = 1;
+                return (void **)&root->rnode;
+        } else
+                return NULL;
+
+restart:
+        shift = (rnode->height - 1) * RADIX_TREE_MAP_SHIFT;
+        offset = index >> shift;
+
+        /* Index outside of the tree */
+        if (offset >= RADIX_TREE_MAP_SIZE)
+                return NULL;
+
+        node = rnode;
+        while (1) {
+                if ((flags & RADIX_TREE_ITER_TAGGED) ?
+                                !test_bit(offset, node->tags[tag]) :
+                                !node->slots[offset]) {
+                        /* Hole detected */
+                        if (flags & RADIX_TREE_ITER_CONTIG)
+                                return NULL;
+
+                        if (flags & RADIX_TREE_ITER_TAGGED)
+                                offset = radix_tree_find_next_bit(
+                                                node->tags[tag],
+                                                RADIX_TREE_MAP_SIZE,
+                                                offset + 1);
+                        else
+                                while (++offset < RADIX_TREE_MAP_SIZE) {
+                                        if (node->slots[offset])
+                                                break;
+                                }
+                        index &= ~((RADIX_TREE_MAP_SIZE << shift) - 1);
+                        index += offset << shift;
+                        /* Overflow after ~0UL */
+                        if (!index)
+                                return NULL;
+                        if (offset == RADIX_TREE_MAP_SIZE)
+                                goto restart;
+                }
+
+                /* This is leaf-node */
+                if (!shift)
+                        break;
+
+                node = rcu_dereference_raw(node->slots[offset]);
+                if (node == NULL)
+                        goto restart;
+                shift -= RADIX_TREE_MAP_SHIFT;
+                offset = (index >> shift) & RADIX_TREE_MAP_MASK;
+        }
+
+        /* Update the iterator state */
+        iter->index = index;
+        iter->next_index = (index | RADIX_TREE_MAP_MASK) + 1;
+
+        /* Construct iter->tags bit-mask from node->tags[tag] array */
+        if (flags & RADIX_TREE_ITER_TAGGED) {
+                unsigned tag_long, tag_bit;
+
+                tag_long = offset / BITS_PER_LONG;
+                tag_bit  = offset % BITS_PER_LONG;
+                iter->tags = node->tags[tag][tag_long] >> tag_bit;
+                /* This never happens if RADIX_TREE_TAG_LONGS == 1 */
+                if (tag_long < RADIX_TREE_TAG_LONGS - 1) {
+                        /* Pick tags from next element */
+                        if (tag_bit)
+                                iter->tags |= node->tags[tag][tag_long + 1] <<
+                                                (BITS_PER_LONG - tag_bit);
+                        /* Clip chunk size, here only BITS_PER_LONG tags */
+                        iter->next_index = index + BITS_PER_LONG;
+                }
+        }
+
+        return node->slots + offset;
+}
+EXPORT_SYMBOL(radix_tree_next_chunk);
+
+/**
  * radix_tree_range_tag_if_tagged - for each item in given range set given
  *                                 tag if item has another tag set
  * @root:               radix tree root
@@ -652,8 +812,7 @@ unsigned long radix_tree_range_tag_if_tagged(struct radix_tree_root *root,
                 unsigned int iftag, unsigned int settag)
 {
         unsigned int height = root->height;
-        struct radix_tree_path path[height];
-        struct radix_tree_path *pathp = path;
+        struct radix_tree_node *node = NULL;
         struct radix_tree_node *slot;
         unsigned int shift;
         unsigned long tagged = 0;
@@ -677,14 +836,8 @@ unsigned long radix_tree_range_tag_if_tagged(struct radix_tree_root *root,
         shift = (height - 1) * RADIX_TREE_MAP_SHIFT;
         slot = indirect_to_ptr(root->rnode);
 
-        /*
-         * we fill the path from (root->height - 2) to 0, leaving the index at
-         * (root->height - 1) as a terminator. Zero the node in the terminator
-         * so that we can use this to end walk loops back up the path.
-         */
-        path[height - 1].node = NULL;
-
         for (;;) {
+                unsigned long upindex;
                 int offset;
 
                 offset = (index >> shift) & RADIX_TREE_MAP_MASK;
@@ -692,12 +845,10 @@ unsigned long radix_tree_range_tag_if_tagged(struct radix_tree_root *root,
                         goto next;
                 if (!tag_get(slot, iftag, offset))
                         goto next;
-                if (height > 1) {
+                if (shift) {
                         /* Go down one level */
-                        height--;
                         shift -= RADIX_TREE_MAP_SHIFT;
-                        path[height - 1].node = slot;
-                        path[height - 1].offset = offset;
+                        node = slot;
                         slot = slot->slots[offset];
                         continue;
                 }
@@ -707,15 +858,27 @@ unsigned long radix_tree_range_tag_if_tagged(struct radix_tree_root *root,
                 tag_set(slot, settag, offset);
 
                 /* walk back up the path tagging interior nodes */
-                pathp = &path[0];
-                while (pathp->node) {
+                upindex = index;
+                while (node) {
+                        upindex >>= RADIX_TREE_MAP_SHIFT;
+                        offset = upindex & RADIX_TREE_MAP_MASK;
+
                         /* stop if we find a node with the tag already set */
-                        if (tag_get(pathp->node, settag, pathp->offset))
+                        if (tag_get(node, settag, offset))
                                 break;
-                        tag_set(pathp->node, settag, pathp->offset);
-                        pathp++;
+                        tag_set(node, settag, offset);
+                        node = node->parent;
                 }
 
+                /*
+                 * Small optimization: now clear that node pointer.
+                 * Since all of this slot's ancestors now have the tag set
+                 * from setting it above, we have no further need to walk
+                 * back up the tree setting tags, until we update slot to
+                 * point to another radix_tree_node.
+                 */
+                node = NULL;
+
 next:
                 /* Go to next item at level determined by 'shift' */
                 index = ((index >> shift) + 1) << shift;
@@ -730,8 +893,7 @@ next:
                          * last_index is guaranteed to be in the tree, what
                          * we do below cannot wander astray.
                          */
-                        slot = path[height - 1].node;
-                        height++;
+                        slot = slot->parent;
                         shift += RADIX_TREE_MAP_SHIFT;
                 }
         }
@@ -822,57 +984,6 @@ unsigned long radix_tree_prev_hole(struct radix_tree_root *root,
 }
 EXPORT_SYMBOL(radix_tree_prev_hole);
 
-static unsigned int
-__lookup(struct radix_tree_node *slot, void ***results, unsigned long *indices,
-        unsigned long index, unsigned int max_items, unsigned long *next_index)
-{
-        unsigned int nr_found = 0;
-        unsigned int shift, height;
-        unsigned long i;
-
-        height = slot->height;
-        if (height == 0)
-                goto out;
-        shift = (height-1) * RADIX_TREE_MAP_SHIFT;
-
-        for ( ; height > 1; height--) {
-                i = (index >> shift) & RADIX_TREE_MAP_MASK;
-                for (;;) {
-                        if (slot->slots[i] != NULL)
-                                break;
-                        index &= ~((1UL << shift) - 1);
-                        index += 1UL << shift;
-                        if (index == 0)
-                                goto out;       /* 32-bit wraparound */
-                        i++;
-                        if (i == RADIX_TREE_MAP_SIZE)
-                                goto out;
-                }
-
-                shift -= RADIX_TREE_MAP_SHIFT;
-                slot = rcu_dereference_raw(slot->slots[i]);
-                if (slot == NULL)
-                        goto out;
-        }
-
-        /* Bottom level: grab some items */
-        for (i = index & RADIX_TREE_MAP_MASK; i < RADIX_TREE_MAP_SIZE; i++) {
-                if (slot->slots[i]) {
-                        results[nr_found] = &(slot->slots[i]);
-                        if (indices)
-                                indices[nr_found] = index;
-                        if (++nr_found == max_items) {
-                                index++;
-                                goto out;
-                        }
-                }
-                index++;
-        }
-out:
-        *next_index = index;
-        return nr_found;
-}
-
 /**
  *      radix_tree_gang_lookup - perform multiple lookup on a radix tree
  *      @root:          radix tree root
@@ -896,48 +1007,19 @@ unsigned int
 radix_tree_gang_lookup(struct radix_tree_root *root, void **results,
                         unsigned long first_index, unsigned int max_items)
 {
-        unsigned long max_index;
-        struct radix_tree_node *node;
-        unsigned long cur_index = first_index;
-        unsigned int ret;
+        struct radix_tree_iter iter;
+        void **slot;
+        unsigned int ret = 0;
 
-        node = rcu_dereference_raw(root->rnode);
-        if (!node)
+        if (unlikely(!max_items))
                 return 0;
 
-        if (!radix_tree_is_indirect_ptr(node)) {
-                if (first_index > 0)
-                        return 0;
-                results[0] = node;
-                return 1;
-        }
-        node = indirect_to_ptr(node);
-
-        max_index = radix_tree_maxindex(node->height);
-
-        ret = 0;
-        while (ret < max_items) {
-                unsigned int nr_found, slots_found, i;
-                unsigned long next_index;       /* Index of next search */
-
-                if (cur_index > max_index)
-                        break;
-                slots_found = __lookup(node, (void ***)results + ret, NULL,
-                                cur_index, max_items - ret, &next_index);
-                nr_found = 0;
-                for (i = 0; i < slots_found; i++) {
-                        struct radix_tree_node *slot;
-                        slot = *(((void ***)results)[ret + i]);
-                        if (!slot)
-                                continue;
-                        results[ret + nr_found] =
-                                indirect_to_ptr(rcu_dereference_raw(slot));
-                        nr_found++;
-                }
-                ret += nr_found;
-                if (next_index == 0)
+        radix_tree_for_each_slot(slot, root, &iter, first_index) {
+                results[ret] = indirect_to_ptr(rcu_dereference_raw(*slot));
+                if (!results[ret])
+                        continue;
+                if (++ret == max_items)
                         break;
-                cur_index = next_index;
         }
 
         return ret;
@@ -967,112 +1049,25 @@ radix_tree_gang_lookup_slot(struct radix_tree_root *root,
                         void ***results, unsigned long *indices,
                         unsigned long first_index, unsigned int max_items)
 {
-        unsigned long max_index;
-        struct radix_tree_node *node;
-        unsigned long cur_index = first_index;
-        unsigned int ret;
+        struct radix_tree_iter iter;
+        void **slot;
+        unsigned int ret = 0;
 
-        node = rcu_dereference_raw(root->rnode);
-        if (!node)
+        if (unlikely(!max_items))
                 return 0;
 
-        if (!radix_tree_is_indirect_ptr(node)) {
-                if (first_index > 0)
-                        return 0;
-                results[0] = (void **)&root->rnode;
+        radix_tree_for_each_slot(slot, root, &iter, first_index) {
+                results[ret] = slot;
                 if (indices)
-                        indices[0] = 0;
-                return 1;
-        }
-        node = indirect_to_ptr(node);
-
-        max_index = radix_tree_maxindex(node->height);
-
-        ret = 0;
-        while (ret < max_items) {
-                unsigned int slots_found;
-                unsigned long next_index;       /* Index of next search */
-
-                if (cur_index > max_index)
-                        break;
-                slots_found = __lookup(node, results + ret,
-                                indices ? indices + ret : NULL,
-                                cur_index, max_items - ret, &next_index);
-                ret += slots_found;
-                if (next_index == 0)
+                        indices[ret] = iter.index;
+                if (++ret == max_items)
                         break;
-                cur_index = next_index;
         }
 
         return ret;
 }
 EXPORT_SYMBOL(radix_tree_gang_lookup_slot);
 
-/*
- * FIXME: the two tag_get()s here should use find_next_bit() instead of
- * open-coding the search.
- */
-static unsigned int
-__lookup_tag(struct radix_tree_node *slot, void ***results, unsigned long index,
-        unsigned int max_items, unsigned long *next_index, unsigned int tag)
-{
-        unsigned int nr_found = 0;
-        unsigned int shift, height;
-
-        height = slot->height;
-        if (height == 0)
-                goto out;
-        shift = (height-1) * RADIX_TREE_MAP_SHIFT;
-
-        while (height > 0) {
-                unsigned long i = (index >> shift) & RADIX_TREE_MAP_MASK ;
-
-                for (;;) {
-                        if (tag_get(slot, tag, i))
-                                break;
-                        index &= ~((1UL << shift) - 1);
-                        index += 1UL << shift;
-                        if (index == 0)
-                                goto out;       /* 32-bit wraparound */
-                        i++;
-                        if (i == RADIX_TREE_MAP_SIZE)
-                                goto out;
-                }
-                height--;
-                if (height == 0) {      /* Bottom level: grab some items */
-                        unsigned long j = index & RADIX_TREE_MAP_MASK;
-
-                        for ( ; j < RADIX_TREE_MAP_SIZE; j++) {
-                                index++;
-                                if (!tag_get(slot, tag, j))
-                                        continue;
-                                /*
-                                 * Even though the tag was found set, we need to
-                                 * recheck that we have a non-NULL node, because
-                                 * if this lookup is lockless, it may have been
-                                 * subsequently deleted.
-                                 *
-                                 * Similar care must be taken in any place that
-                                 * lookup ->slots[x] without a lock (ie. can't
-                                 * rely on its value remaining the same).
-                                 */
-                                if (slot->slots[j]) {
-                                        results[nr_found++] = &(slot->slots[j]);
-                                        if (nr_found == max_items)
-                                                goto out;
-                                }
-                        }
-                }
-                shift -= RADIX_TREE_MAP_SHIFT;
-                slot = rcu_dereference_raw(slot->slots[i]);
-                if (slot == NULL)
-                        break;
-        }
-out:
-        *next_index = index;
-        return nr_found;
-}
-
 /**
  *      radix_tree_gang_lookup_tag - perform multiple lookup on a radix tree
  *                                   based on a tag
@@ -1091,52 +1086,19 @@ radix_tree_gang_lookup_tag(struct radix_tree_root *root, void **results,
                 unsigned long first_index, unsigned int max_items,
                 unsigned int tag)
 {
-        struct radix_tree_node *node;
-        unsigned long max_index;
-        unsigned long cur_index = first_index;
-        unsigned int ret;
+        struct radix_tree_iter iter;
+        void **slot;
+        unsigned int ret = 0;
 
-        /* check the root's tag bit */
-        if (!root_tag_get(root, tag))
+        if (unlikely(!max_items))
                 return 0;
 
-        node = rcu_dereference_raw(root->rnode);
-        if (!node)
-                return 0;
-
-        if (!radix_tree_is_indirect_ptr(node)) {
-                if (first_index > 0)
-                        return 0;
-                results[0] = node;
-                return 1;
-        }
-        node = indirect_to_ptr(node);
-
-        max_index = radix_tree_maxindex(node->height);
-
-        ret = 0;
-        while (ret < max_items) {
-                unsigned int nr_found, slots_found, i;
-                unsigned long next_index;       /* Index of next search */
-
-                if (cur_index > max_index)
-                        break;
-                slots_found = __lookup_tag(node, (void ***)results + ret,
-                                cur_index, max_items - ret, &next_index, tag);
-                nr_found = 0;
-                for (i = 0; i < slots_found; i++) {
-                        struct radix_tree_node *slot;
-                        slot = *(((void ***)results)[ret + i]);
-                        if (!slot)
-                                continue;
-                        results[ret + nr_found] =
-                                indirect_to_ptr(rcu_dereference_raw(slot));
-                        nr_found++;
-                }
-                ret += nr_found;
-                if (next_index == 0)
+        radix_tree_for_each_tagged(slot, root, &iter, first_index, tag) {
+                results[ret] = indirect_to_ptr(rcu_dereference_raw(*slot));
+                if (!results[ret])
+                        continue;
+                if (++ret == max_items)
                         break;
-                cur_index = next_index;
         }
 
         return ret;
@@ -1161,42 +1123,17 @@ radix_tree_gang_lookup_tag_slot(struct radix_tree_root *root, void ***results,
                 unsigned long first_index, unsigned int max_items,
                 unsigned int tag)
 {
-        struct radix_tree_node *node;
-        unsigned long max_index;
-        unsigned long cur_index = first_index;
-        unsigned int ret;
+        struct radix_tree_iter iter;
+        void **slot;
+        unsigned int ret = 0;
 
-        /* check the root's tag bit */
-        if (!root_tag_get(root, tag))
+        if (unlikely(!max_items))
                 return 0;
 
-        node = rcu_dereference_raw(root->rnode);
-        if (!node)
-                return 0;
-
-        if (!radix_tree_is_indirect_ptr(node)) {
-                if (first_index > 0)
-                        return 0;
-                results[0] = (void **)&root->rnode;
-                return 1;
-        }
-        node = indirect_to_ptr(node);
-
-        max_index = radix_tree_maxindex(node->height);
-
-        ret = 0;
-        while (ret < max_items) {
-                unsigned int slots_found;
-                unsigned long next_index;       /* Index of next search */
-
-                if (cur_index > max_index)
-                        break;
-                slots_found = __lookup_tag(node, results + ret,
-                                cur_index, max_items - ret, &next_index, tag);
-                ret += slots_found;
-                if (next_index == 0)
+        radix_tree_for_each_tagged(slot, root, &iter, first_index, tag) {
+                results[ret] = slot;
+                if (++ret == max_items)
                         break;
-                cur_index = next_index;
         }
 
         return ret;
@@ -1305,7 +1242,7 @@ static inline void radix_tree_shrink(struct radix_tree_root *root)
         /* try to shrink tree height */
         while (root->height > 0) {
                 struct radix_tree_node *to_free = root->rnode;
-                void *newptr;
+                struct radix_tree_node *slot;
 
                 BUG_ON(!radix_tree_is_indirect_ptr(to_free));
                 to_free = indirect_to_ptr(to_free);
@@ -1326,10 +1263,12 @@ static inline void radix_tree_shrink(struct radix_tree_root *root)
                  * (to_free->slots[0]), it will be safe to dereference the new
                  * one (root->rnode) as far as dependent read barriers go.
                  */
-                newptr = to_free->slots[0];
-                if (root->height > 1)
-                        newptr = ptr_to_indirect(newptr);
-                root->rnode = newptr;
+                slot = to_free->slots[0];
+                if (root->height > 1) {
+                        slot->parent = NULL;
+                        slot = ptr_to_indirect(slot);
+                }
+                root->rnode = slot;
                 root->height--;
 
                 /*
@@ -1369,16 +1308,12 @@ static inline void radix_tree_shrink(struct radix_tree_root *root)
  */
 void *radix_tree_delete(struct radix_tree_root *root, unsigned long index)
 {
-        /*
-         * The radix tree path needs to be one longer than the maximum path
-         * since the "list" is null terminated.
-         */
-        struct radix_tree_path path[RADIX_TREE_MAX_PATH + 1], *pathp = path;
+        struct radix_tree_node *node = NULL;
         struct radix_tree_node *slot = NULL;
         struct radix_tree_node *to_free;
         unsigned int height, shift;
         int tag;
-        int offset;
+        int uninitialized_var(offset);
 
         height = root->height;
         if (index > radix_tree_maxindex(height))
@@ -1391,39 +1326,35 @@ void *radix_tree_delete(struct radix_tree_root *root, unsigned long index)
                 goto out;
         }
         slot = indirect_to_ptr(slot);
-
-        shift = (height - 1) * RADIX_TREE_MAP_SHIFT;
-        pathp->node = NULL;
+        shift = height * RADIX_TREE_MAP_SHIFT;
 
         do {
                 if (slot == NULL)
                         goto out;
 
-                pathp++;
+                shift -= RADIX_TREE_MAP_SHIFT;
                 offset = (index >> shift) & RADIX_TREE_MAP_MASK;
-                pathp->offset = offset;
-                pathp->node = slot;
+                node = slot;
                 slot = slot->slots[offset];
-                shift -= RADIX_TREE_MAP_SHIFT;
-                height--;
-        } while (height > 0);
+        } while (shift);
 
         if (slot == NULL)
                 goto out;
 
         /*
-         * Clear all tags associated with the just-deleted item
+         * Clear all tags associated with the item to be deleted.
+         * This way of doing it would be inefficient, but seldom is any set.
          */
         for (tag = 0; tag < RADIX_TREE_MAX_TAGS; tag++) {
-                if (tag_get(pathp->node, tag, pathp->offset))
+                if (tag_get(node, tag, offset))
                         radix_tree_tag_clear(root, index, tag);
         }
 
         to_free = NULL;
         /* Now free the nodes we do not need anymore */
-        while (pathp->node) {
-                pathp->node->slots[pathp->offset] = NULL;
-                pathp->node->count--;
+        while (node) {
+                node->slots[offset] = NULL;
+                node->count--;
                 /*
                  * Queue the node for deferred freeing after the
                  * last reference to it disappears (set NULL, above).
@@ -1431,17 +1362,20 @@ void *radix_tree_delete(struct radix_tree_root *root, unsigned long index)
                 if (to_free)
                         radix_tree_node_free(to_free);
 
-                if (pathp->node->count) {
-                        if (pathp->node == indirect_to_ptr(root->rnode))
+                if (node->count) {
+                        if (node == indirect_to_ptr(root->rnode))
                                 radix_tree_shrink(root);
                         goto out;
                 }
 
                 /* Node with zero slots in use so free it */
-                to_free = pathp->node;
-                pathp--;
+                to_free = node;
 
+                index >>= RADIX_TREE_MAP_SHIFT;
+                offset = index & RADIX_TREE_MAP_MASK;
+                node = node->parent;
         }
+
         root_tag_clear_all(root);
         root->height = 0;
         root->rnode = NULL;
diff --git a/lib/raid6/Makefile b/lib/raid6/Makefile
index 8a38102770f3..de06dfe165b8 100644
--- a/lib/raid6/Makefile
+++ b/lib/raid6/Makefile
@@ -1,6 +1,6 @@
 obj-$(CONFIG_RAID6_PQ)  += raid6_pq.o
 
-raid6_pq-y      += algos.o recov.o tables.o int1.o int2.o int4.o \
+raid6_pq-y      += algos.o recov.o recov_ssse3.o tables.o int1.o int2.o int4.o \
                    int8.o int16.o int32.o altivec1.o altivec2.o altivec4.o \
                    altivec8.o mmx.o sse1.o sse2.o
 hostprogs-y     += mktables
diff --git a/lib/raid6/algos.c b/lib/raid6/algos.c
index b595f560bee7..589f5f50ad2e 100644
--- a/lib/raid6/algos.c
+++ b/lib/raid6/algos.c
@@ -21,6 +21,7 @@
 #include <sys/mman.h>
 #include <stdio.h>
 #else
+#include <linux/module.h>
 #include <linux/gfp.h>
 #if !RAID6_USE_EMPTY_ZERO_PAGE
 /* In .bss so it's zeroed */
@@ -33,10 +34,6 @@ struct raid6_calls raid6_call;
 EXPORT_SYMBOL_GPL(raid6_call);
 
 const struct raid6_calls * const raid6_algos[] = {
-        &raid6_intx1,
-        &raid6_intx2,
-        &raid6_intx4,
-        &raid6_intx8,
 #if defined(__ia64__)
         &raid6_intx16,
         &raid6_intx32,
@@ -60,6 +57,24 @@ const struct raid6_calls * const raid6_algos[] = {
         &raid6_altivec4,
         &raid6_altivec8,
 #endif
+        &raid6_intx1,
+        &raid6_intx2,
+        &raid6_intx4,
+        &raid6_intx8,
+        NULL
+};
+
+void (*raid6_2data_recov)(int, size_t, int, int, void **);
+EXPORT_SYMBOL_GPL(raid6_2data_recov);
+
+void (*raid6_datap_recov)(int, size_t, int, void **);
+EXPORT_SYMBOL_GPL(raid6_datap_recov);
+
+const struct raid6_recov_calls *const raid6_recov_algos[] = {
+#if (defined(__i386__) || defined(__x86_64__)) && !defined(__arch_um__)
+        &raid6_recov_ssse3,
+#endif
+        &raid6_recov_intx1,
         NULL
 };
 
@@ -71,59 +86,55 @@ const struct raid6_calls * const raid6_algos[] = {
 #define time_before(x, y) ((x) < (y))
 #endif
 
-/* Try to pick the best algorithm */
-/* This code uses the gfmul table as convenient data set to abuse */
-
-int __init raid6_select_algo(void)
+static inline const struct raid6_recov_calls *raid6_choose_recov(void)
 {
-        const struct raid6_calls * const * algo;
-        const struct raid6_calls * best;
-        char *syndromes;
-        void *dptrs[(65536/PAGE_SIZE)+2];
-        int i, disks;
-        unsigned long perf, bestperf;
-        int bestprefer;
-        unsigned long j0, j1;
+        const struct raid6_recov_calls *const *algo;
+        const struct raid6_recov_calls *best;
 
-        disks = (65536/PAGE_SIZE)+2;
-        for ( i = 0 ; i < disks-2 ; i++ ) {
-                dptrs[i] = ((char *)raid6_gfmul) + PAGE_SIZE*i;
-        }
+        for (best = NULL, algo = raid6_recov_algos; *algo; algo++)
+                if (!best || (*algo)->priority > best->priority)
+                        if (!(*algo)->valid || (*algo)->valid())
+                                best = *algo;
 
-        /* Normal code - use a 2-page allocation to avoid D$ conflict */
-        syndromes = (void *) __get_free_pages(GFP_KERNEL, 1);
+        if (best) {
+                raid6_2data_recov = best->data2;
+                raid6_datap_recov = best->datap;
 
-        if ( !syndromes ) {
-                printk("raid6: Yikes!  No memory available.\n");
-                return -ENOMEM;
-        }
+                printk("raid6: using %s recovery algorithm\n", best->name);
+        } else
+                printk("raid6: Yikes! No recovery algorithm found!\n");
 
-        dptrs[disks-2] = syndromes;
-        dptrs[disks-1] = syndromes + PAGE_SIZE;
+        return best;
+}
+
+static inline const struct raid6_calls *raid6_choose_gen(
+        void *(*const dptrs)[(65536/PAGE_SIZE)+2], const int disks)
+{
+        unsigned long perf, bestperf, j0, j1;
+        const struct raid6_calls *const *algo;
+        const struct raid6_calls *best;
 
-        bestperf = 0;  bestprefer = 0;  best = NULL;
+        for (bestperf = 0, best = NULL, algo = raid6_algos; *algo; algo++) {
+                if (!best || (*algo)->prefer >= best->prefer) {
+                        if ((*algo)->valid && !(*algo)->valid())
+                                continue;
 
-        for ( algo = raid6_algos ; *algo ; algo++ ) {
-                if ( !(*algo)->valid || (*algo)->valid() ) {
                         perf = 0;
 
                         preempt_disable();
                         j0 = jiffies;
-                        while ( (j1 = jiffies) == j0 )
+                        while ((j1 = jiffies) == j0)
                                 cpu_relax();
                         while (time_before(jiffies,
                                             j1 + (1<<RAID6_TIME_JIFFIES_LG2))) {
-                                (*algo)->gen_syndrome(disks, PAGE_SIZE, dptrs);
+                                (*algo)->gen_syndrome(disks, PAGE_SIZE, *dptrs);
                                 perf++;
                         }
                         preempt_enable();
 
-                        if ( (*algo)->prefer > bestprefer ||
-                             ((*algo)->prefer == bestprefer &&
-                              perf > bestperf) ) {
-                                best = *algo;
-                                bestprefer = best->prefer;
+                        if (perf > bestperf) {
                                 bestperf = perf;
+                                best = *algo;
                         }
                         printk("raid6: %-8s %5ld MB/s\n", (*algo)->name,
                                (perf*HZ) >> (20-16+RAID6_TIME_JIFFIES_LG2));
@@ -138,9 +149,46 @@ int __init raid6_select_algo(void)
         } else
                 printk("raid6: Yikes!  No algorithm found!\n");
 
+        return best;
+}
+
+
+/* Try to pick the best algorithm */
+/* This code uses the gfmul table as convenient data set to abuse */
+
+int __init raid6_select_algo(void)
+{
+        const int disks = (65536/PAGE_SIZE)+2;
+
+        const struct raid6_calls *gen_best;
+        const struct raid6_recov_calls *rec_best;
+        char *syndromes;
+        void *dptrs[(65536/PAGE_SIZE)+2];
+        int i;
+
+        for (i = 0; i < disks-2; i++)
+                dptrs[i] = ((char *)raid6_gfmul) + PAGE_SIZE*i;
+
+        /* Normal code - use a 2-page allocation to avoid D$ conflict */
+        syndromes = (void *) __get_free_pages(GFP_KERNEL, 1);
+
+        if (!syndromes) {
+                printk("raid6: Yikes!  No memory available.\n");
+                return -ENOMEM;
+        }
+
+        dptrs[disks-2] = syndromes;
+        dptrs[disks-1] = syndromes + PAGE_SIZE;
+
+        /* select raid gen_syndrome function */
+        gen_best = raid6_choose_gen(&dptrs, disks);
+
+        /* select raid recover functions */
+        rec_best = raid6_choose_recov();
+
         free_pages((unsigned long)syndromes, 1);
 
-        return best ? 0 : -EINVAL;
+        return gen_best && rec_best ? 0 : -EINVAL;
 }
 
 static void raid6_exit(void)
diff --git a/lib/raid6/altivec.uc b/lib/raid6/altivec.uc
index 2654d5c854be..b71012b756f4 100644
--- a/lib/raid6/altivec.uc
+++ b/lib/raid6/altivec.uc
@@ -28,8 +28,8 @@
 
 #include <altivec.h>
 #ifdef __KERNEL__
-# include <asm/system.h>
 # include <asm/cputable.h>
+# include <asm/switch_to.h>
 #endif
 
 /*
diff --git a/lib/raid6/int.uc b/lib/raid6/int.uc
index d1e276a14fab..5b50f8dfc5d2 100644
--- a/lib/raid6/int.uc
+++ b/lib/raid6/int.uc
@@ -11,7 +11,7 @@
  * ----------------------------------------------------------------------- */
 
 /*
- * raid6int$#.c
+ * int$#.c
  *
  * $#-way unrolled portable integer math RAID-6 instruction set
  *
diff --git a/lib/raid6/mktables.c b/lib/raid6/mktables.c
index 3b1500843bba..39787db588b0 100644
--- a/lib/raid6/mktables.c
+++ b/lib/raid6/mktables.c
@@ -60,6 +60,7 @@ int main(int argc, char *argv[])
         uint8_t exptbl[256], invtbl[256];
 
         printf("#include <linux/raid/pq.h>\n");
+        printf("#include <linux/export.h>\n");
 
         /* Compute multiplication table */
         printf("\nconst u8  __attribute__((aligned(256)))\n"
@@ -80,6 +81,31 @@ int main(int argc, char *argv[])
         printf("EXPORT_SYMBOL(raid6_gfmul);\n");
         printf("#endif\n");
 
+        /* Compute vector multiplication table */
+        printf("\nconst u8  __attribute__((aligned(256)))\n"
+                "raid6_vgfmul[256][32] =\n"
+                "{\n");
+        for (i = 0; i < 256; i++) {
+                printf("\t{\n");
+                for (j = 0; j < 16; j += 8) {
+                        printf("\t\t");
+                        for (k = 0; k < 8; k++)
+                                printf("0x%02x,%c", gfmul(i, j + k),
+                                       (k == 7) ? '\n' : ' ');
+                }
+                for (j = 0; j < 16; j += 8) {
+                        printf("\t\t");
+                        for (k = 0; k < 8; k++)
+                                printf("0x%02x,%c", gfmul(i, (j + k) << 4),
+                                       (k == 7) ? '\n' : ' ');
+                }
+                printf("\t},\n");
+        }
+        printf("};\n");
+        printf("#ifdef __KERNEL__\n");
+        printf("EXPORT_SYMBOL(raid6_vgfmul);\n");
+        printf("#endif\n");
+
         /* Compute power-of-2 table (exponent) */
         v = 1;
         printf("\nconst u8 __attribute__((aligned(256)))\n"
diff --git a/lib/raid6/recov.c b/lib/raid6/recov.c
index 8590d19cf522..a95bccb8497d 100644
--- a/lib/raid6/recov.c
+++ b/lib/raid6/recov.c
@@ -18,11 +18,12 @@
  * the syndrome.)
  */
 
+#include <linux/export.h>
 #include <linux/raid/pq.h>
 
 /* Recover two failed data blocks. */
-void raid6_2data_recov(int disks, size_t bytes, int faila, int failb,
-                       void **ptrs)
+static void raid6_2data_recov_intx1(int disks, size_t bytes, int faila,
+                int failb, void **ptrs)
 {
         u8 *p, *q, *dp, *dq;
         u8 px, qx, db;
@@ -63,10 +64,10 @@ void raid6_2data_recov(int disks, size_t bytes, int faila, int failb,
                 p++; q++;
         }
 }
-EXPORT_SYMBOL_GPL(raid6_2data_recov);
 
 /* Recover failure of one data block plus the P block */
-void raid6_datap_recov(int disks, size_t bytes, int faila, void **ptrs)
+static void raid6_datap_recov_intx1(int disks, size_t bytes, int faila,
+                void **ptrs)
 {
         u8 *p, *q, *dq;
         const u8 *qmul;         /* Q multiplier table */
@@ -95,7 +96,15 @@ void raid6_datap_recov(int disks, size_t bytes, int faila, void **ptrs)
                 q++; dq++;
         }
 }
-EXPORT_SYMBOL_GPL(raid6_datap_recov);
+
+
+const struct raid6_recov_calls raid6_recov_intx1 = {
+        .data2 = raid6_2data_recov_intx1,
+        .datap = raid6_datap_recov_intx1,
+        .valid = NULL,
+        .name = "intx1",
+        .priority = 0,
+};
 
 #ifndef __KERNEL__
 /* Testing only */
diff --git a/lib/raid6/recov_ssse3.c b/lib/raid6/recov_ssse3.c
new file mode 100644
index 000000000000..ecb710c0b4d9
--- /dev/null
+++ b/lib/raid6/recov_ssse3.c
@@ -0,0 +1,336 @@
+/*
+ * Copyright (C) 2012 Intel Corporation
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; version 2
+ * of the License.
+ */
+
+#if (defined(__i386__) || defined(__x86_64__)) && !defined(__arch_um__)
+
+#include <linux/raid/pq.h>
+#include "x86.h"
+
+static int raid6_has_ssse3(void)
+{
+        return boot_cpu_has(X86_FEATURE_XMM) &&
+                boot_cpu_has(X86_FEATURE_XMM2) &&
+                boot_cpu_has(X86_FEATURE_SSSE3);
+}
+
+static void raid6_2data_recov_ssse3(int disks, size_t bytes, int faila,
+                int failb, void **ptrs)
+{
+        u8 *p, *q, *dp, *dq;
+        const u8 *pbmul;        /* P multiplier table for B data */
+        const u8 *qmul;         /* Q multiplier table (for both) */
+        static const u8 __aligned(16) x0f[16] = {
+                 0x0f, 0x0f, 0x0f, 0x0f, 0x0f, 0x0f, 0x0f, 0x0f,
+                 0x0f, 0x0f, 0x0f, 0x0f, 0x0f, 0x0f, 0x0f, 0x0f};
+
+        p = (u8 *)ptrs[disks-2];
+        q = (u8 *)ptrs[disks-1];
+
+        /* Compute syndrome with zero for the missing data pages
+           Use the dead data pages as temporary storage for
+           delta p and delta q */
+        dp = (u8 *)ptrs[faila];
+        ptrs[faila] = (void *)raid6_empty_zero_page;
+        ptrs[disks-2] = dp;
+        dq = (u8 *)ptrs[failb];
+        ptrs[failb] = (void *)raid6_empty_zero_page;
+        ptrs[disks-1] = dq;
+
+        raid6_call.gen_syndrome(disks, bytes, ptrs);
+
+        /* Restore pointer table */
+        ptrs[faila]   = dp;
+        ptrs[failb]   = dq;
+        ptrs[disks-2] = p;
+        ptrs[disks-1] = q;
+
+        /* Now, pick the proper data tables */
+        pbmul = raid6_vgfmul[raid6_gfexi[failb-faila]];
+        qmul  = raid6_vgfmul[raid6_gfinv[raid6_gfexp[faila] ^
+                raid6_gfexp[failb]]];
+
+        kernel_fpu_begin();
+
+        asm volatile("movdqa %0,%%xmm7" : : "m" (x0f[0]));
+
+#ifdef CONFIG_X86_64
+        asm volatile("movdqa %0,%%xmm6" : : "m" (qmul[0]));
+        asm volatile("movdqa %0,%%xmm14" : : "m" (pbmul[0]));
+        asm volatile("movdqa %0,%%xmm15" : : "m" (pbmul[16]));
+#endif
+
+        /* Now do it... */
+        while (bytes) {
+#ifdef CONFIG_X86_64
+                /* xmm6, xmm14, xmm15 */
+
+                asm volatile("movdqa %0,%%xmm1" : : "m" (q[0]));
+                asm volatile("movdqa %0,%%xmm9" : : "m" (q[16]));
+                asm volatile("movdqa %0,%%xmm0" : : "m" (p[0]));
+                asm volatile("movdqa %0,%%xmm8" : : "m" (p[16]));
+                asm volatile("pxor   %0,%%xmm1" : : "m" (dq[0]));
+                asm volatile("pxor   %0,%%xmm9" : : "m" (dq[16]));
+                asm volatile("pxor   %0,%%xmm0" : : "m" (dp[0]));
+                asm volatile("pxor   %0,%%xmm8" : : "m" (dp[16]));
+
+                /* xmm0/8 = px */
+
+                asm volatile("movdqa %xmm6,%xmm4");
+                asm volatile("movdqa %0,%%xmm5" : : "m" (qmul[16]));
+                asm volatile("movdqa %xmm6,%xmm12");
+                asm volatile("movdqa %xmm5,%xmm13");
+                asm volatile("movdqa %xmm1,%xmm3");
+                asm volatile("movdqa %xmm9,%xmm11");
+                asm volatile("movdqa %xmm0,%xmm2"); /* xmm2/10 = px */
+                asm volatile("movdqa %xmm8,%xmm10");
+                asm volatile("psraw  $4,%xmm1");
+                asm volatile("psraw  $4,%xmm9");
+                asm volatile("pand   %xmm7,%xmm3");
+                asm volatile("pand   %xmm7,%xmm11");
+                asm volatile("pand   %xmm7,%xmm1");
+                asm volatile("pand   %xmm7,%xmm9");
+                asm volatile("pshufb %xmm3,%xmm4");
+                asm volatile("pshufb %xmm11,%xmm12");
+                asm volatile("pshufb %xmm1,%xmm5");
+                asm volatile("pshufb %xmm9,%xmm13");
+                asm volatile("pxor   %xmm4,%xmm5");
+                asm volatile("pxor   %xmm12,%xmm13");
+
+                /* xmm5/13 = qx */
+
+                asm volatile("movdqa %xmm14,%xmm4");
+                asm volatile("movdqa %xmm15,%xmm1");
+                asm volatile("movdqa %xmm14,%xmm12");
+                asm volatile("movdqa %xmm15,%xmm9");
+                asm volatile("movdqa %xmm2,%xmm3");
+                asm volatile("movdqa %xmm10,%xmm11");
+                asm volatile("psraw  $4,%xmm2");
+                asm volatile("psraw  $4,%xmm10");
+                asm volatile("pand   %xmm7,%xmm3");
+                asm volatile("pand   %xmm7,%xmm11");
+                asm volatile("pand   %xmm7,%xmm2");
+                asm volatile("pand   %xmm7,%xmm10");
+                asm volatile("pshufb %xmm3,%xmm4");
+                asm volatile("pshufb %xmm11,%xmm12");
+                asm volatile("pshufb %xmm2,%xmm1");
+                asm volatile("pshufb %xmm10,%xmm9");
+                asm volatile("pxor   %xmm4,%xmm1");
+                asm volatile("pxor   %xmm12,%xmm9");
+
+                /* xmm1/9 = pbmul[px] */
+                asm volatile("pxor   %xmm5,%xmm1");
+                asm volatile("pxor   %xmm13,%xmm9");
+                /* xmm1/9 = db = DQ */
+                asm volatile("movdqa %%xmm1,%0" : "=m" (dq[0]));
+                asm volatile("movdqa %%xmm9,%0" : "=m" (dq[16]));
+
+                asm volatile("pxor   %xmm1,%xmm0");
+                asm volatile("pxor   %xmm9,%xmm8");
+                asm volatile("movdqa %%xmm0,%0" : "=m" (dp[0]));
+                asm volatile("movdqa %%xmm8,%0" : "=m" (dp[16]));
+
+                bytes -= 32;
+                p += 32;
+                q += 32;
+                dp += 32;
+                dq += 32;
+#else
+                asm volatile("movdqa %0,%%xmm1" : : "m" (*q));
+                asm volatile("movdqa %0,%%xmm0" : : "m" (*p));
+                asm volatile("pxor   %0,%%xmm1" : : "m" (*dq));
+                asm volatile("pxor   %0,%%xmm0" : : "m" (*dp));
+
+                /* 1 = dq ^ q
+                 * 0 = dp ^ p
+                 */
+                asm volatile("movdqa %0,%%xmm4" : : "m" (qmul[0]));
+                asm volatile("movdqa %0,%%xmm5" : : "m" (qmul[16]));
+
+                asm volatile("movdqa %xmm1,%xmm3");
+                asm volatile("psraw  $4,%xmm1");
+                asm volatile("pand   %xmm7,%xmm3");
+                asm volatile("pand   %xmm7,%xmm1");
+                asm volatile("pshufb %xmm3,%xmm4");
+                asm volatile("pshufb %xmm1,%xmm5");
+                asm volatile("pxor   %xmm4,%xmm5");
+
+                asm volatile("movdqa %xmm0,%xmm2"); /* xmm2 = px */
+
+                /* xmm5 = qx */
+
+                asm volatile("movdqa %0,%%xmm4" : : "m" (pbmul[0]));
+                asm volatile("movdqa %0,%%xmm1" : : "m" (pbmul[16]));
+                asm volatile("movdqa %xmm2,%xmm3");
+                asm volatile("psraw  $4,%xmm2");
+                asm volatile("pand   %xmm7,%xmm3");
+                asm volatile("pand   %xmm7,%xmm2");
+                asm volatile("pshufb %xmm3,%xmm4");
+                asm volatile("pshufb %xmm2,%xmm1");
+                asm volatile("pxor   %xmm4,%xmm1");
+
+                /* xmm1 = pbmul[px] */
+                asm volatile("pxor   %xmm5,%xmm1");
+                /* xmm1 = db = DQ */
+                asm volatile("movdqa %%xmm1,%0" : "=m" (*dq));
+
+                asm volatile("pxor   %xmm1,%xmm0");
+                asm volatile("movdqa %%xmm0,%0" : "=m" (*dp));
+
+                bytes -= 16;
+                p += 16;
+                q += 16;
+                dp += 16;
+                dq += 16;
+#endif
+        }
+
+        kernel_fpu_end();
+}
+
+
+static void raid6_datap_recov_ssse3(int disks, size_t bytes, int faila,
+                void **ptrs)
+{
+        u8 *p, *q, *dq;
+        const u8 *qmul;         /* Q multiplier table */
+        static const u8 __aligned(16) x0f[16] = {
+                 0x0f, 0x0f, 0x0f, 0x0f, 0x0f, 0x0f, 0x0f, 0x0f,
+                 0x0f, 0x0f, 0x0f, 0x0f, 0x0f, 0x0f, 0x0f, 0x0f};
+
+        p = (u8 *)ptrs[disks-2];
+        q = (u8 *)ptrs[disks-1];
+
+        /* Compute syndrome with zero for the missing data page
+           Use the dead data page as temporary storage for delta q */
+        dq = (u8 *)ptrs[faila];
+        ptrs[faila] = (void *)raid6_empty_zero_page;
+        ptrs[disks-1] = dq;
+
+        raid6_call.gen_syndrome(disks, bytes, ptrs);
+
+        /* Restore pointer table */
+        ptrs[faila]   = dq;
+        ptrs[disks-1] = q;
+
+        /* Now, pick the proper data tables */
+        qmul  = raid6_vgfmul[raid6_gfinv[raid6_gfexp[faila]]];
+
+        kernel_fpu_begin();
+
+        asm volatile("movdqa %0, %%xmm7" : : "m" (x0f[0]));
+
+        while (bytes) {
+#ifdef CONFIG_X86_64
+                asm volatile("movdqa %0, %%xmm3" : : "m" (dq[0]));
+                asm volatile("movdqa %0, %%xmm4" : : "m" (dq[16]));
+                asm volatile("pxor %0, %%xmm3" : : "m" (q[0]));
+                asm volatile("movdqa %0, %%xmm0" : : "m" (qmul[0]));
+
+                /* xmm3 = q[0] ^ dq[0] */
+
+                asm volatile("pxor %0, %%xmm4" : : "m" (q[16]));
+                asm volatile("movdqa %0, %%xmm1" : : "m" (qmul[16]));
+
+                /* xmm4 = q[16] ^ dq[16] */
+
+                asm volatile("movdqa %xmm3, %xmm6");
+                asm volatile("movdqa %xmm4, %xmm8");
+
+                /* xmm4 = xmm8 = q[16] ^ dq[16] */
+
+                asm volatile("psraw $4, %xmm3");
+                asm volatile("pand %xmm7, %xmm6");
+                asm volatile("pand %xmm7, %xmm3");
+                asm volatile("pshufb %xmm6, %xmm0");
+                asm volatile("pshufb %xmm3, %xmm1");
+                asm volatile("movdqa %0, %%xmm10" : : "m" (qmul[0]));
+                asm volatile("pxor %xmm0, %xmm1");
+                asm volatile("movdqa %0, %%xmm11" : : "m" (qmul[16]));
+
+                /* xmm1 = qmul[q[0] ^ dq[0]] */
+
+                asm volatile("psraw $4, %xmm4");
+                asm volatile("pand %xmm7, %xmm8");
+                asm volatile("pand %xmm7, %xmm4");
+                asm volatile("pshufb %xmm8, %xmm10");
+                asm volatile("pshufb %xmm4, %xmm11");
+                asm volatile("movdqa %0, %%xmm2" : : "m" (p[0]));
+                asm volatile("pxor %xmm10, %xmm11");
+                asm volatile("movdqa %0, %%xmm12" : : "m" (p[16]));
+
+                /* xmm11 = qmul[q[16] ^ dq[16]] */
+
+                asm volatile("pxor %xmm1, %xmm2");
+
+                /* xmm2 = p[0] ^ qmul[q[0] ^ dq[0]] */
+
+                asm volatile("pxor %xmm11, %xmm12");
+
+                /* xmm12 = p[16] ^ qmul[q[16] ^ dq[16]] */
+
+                asm volatile("movdqa %%xmm1, %0" : "=m" (dq[0]));
+                asm volatile("movdqa %%xmm11, %0" : "=m" (dq[16]));
+
+                asm volatile("movdqa %%xmm2, %0" : "=m" (p[0]));
+                asm volatile("movdqa %%xmm12, %0" : "=m" (p[16]));
+
+                bytes -= 32;
+                p += 32;
+                q += 32;
+                dq += 32;
+
+#else
+                asm volatile("movdqa %0, %%xmm3" : : "m" (dq[0]));
+                asm volatile("movdqa %0, %%xmm0" : : "m" (qmul[0]));
+                asm volatile("pxor %0, %%xmm3" : : "m" (q[0]));
+                asm volatile("movdqa %0, %%xmm1" : : "m" (qmul[16]));
+
+                /* xmm3 = *q ^ *dq */
+
+                asm volatile("movdqa %xmm3, %xmm6");
+                asm volatile("movdqa %0, %%xmm2" : : "m" (p[0]));
+                asm volatile("psraw $4, %xmm3");
+                asm volatile("pand %xmm7, %xmm6");
+                asm volatile("pand %xmm7, %xmm3");
+                asm volatile("pshufb %xmm6, %xmm0");
+                asm volatile("pshufb %xmm3, %xmm1");
+                asm volatile("pxor %xmm0, %xmm1");
+
+                /* xmm1 = qmul[*q ^ *dq */
+
+                asm volatile("pxor %xmm1, %xmm2");
+
+                /* xmm2 = *p ^ qmul[*q ^ *dq] */
+
+                asm volatile("movdqa %%xmm1, %0" : "=m" (dq[0]));
+                asm volatile("movdqa %%xmm2, %0" : "=m" (p[0]));
+
+                bytes -= 16;
+                p += 16;
+                q += 16;
+                dq += 16;
+#endif
+        }
+
+        kernel_fpu_end();
+}
+
+const struct raid6_recov_calls raid6_recov_ssse3 = {
+        .data2 = raid6_2data_recov_ssse3,
+        .datap = raid6_datap_recov_ssse3,
+        .valid = raid6_has_ssse3,
+#ifdef CONFIG_X86_64
+        .name = "ssse3x2",
+#else
+        .name = "ssse3x1",
+#endif
+        .priority = 1,
+};
+
+#endif
diff --git a/lib/raid6/test/Makefile b/lib/raid6/test/Makefile
index aa651697b6dc..c76151d94764 100644
--- a/lib/raid6/test/Makefile
+++ b/lib/raid6/test/Makefile
@@ -23,7 +23,7 @@ RANLIB	 = ranlib
 all:    raid6.a raid6test
 
 raid6.a: int1.o int2.o int4.o int8.o int16.o int32.o mmx.o sse1.o sse2.o \
-         altivec1.o altivec2.o altivec4.o altivec8.o recov.o algos.o \
+         altivec1.o altivec2.o altivec4.o altivec8.o recov.o recov_ssse3.o algos.o \
          tables.o
          rm -f $@
          $(AR) cq $@ $^
diff --git a/lib/raid6/test/test.c b/lib/raid6/test/test.c
index 7a930318b17d..5a485b7a7d3c 100644
--- a/lib/raid6/test/test.c
+++ b/lib/raid6/test/test.c
@@ -90,25 +90,35 @@ static int test_disks(int i, int j)
 int main(int argc, char *argv[])
 {
         const struct raid6_calls *const *algo;
+        const struct raid6_recov_calls *const *ra;
         int i, j;
         int err = 0;
 
         makedata();
 
-        for (algo = raid6_algos; *algo; algo++) {
-                if (!(*algo)->valid || (*algo)->valid()) {
-                        raid6_call = **algo;
+        for (ra = raid6_recov_algos; *ra; ra++) {
+                if ((*ra)->valid  && !(*ra)->valid())
+                        continue;
+                raid6_2data_recov = (*ra)->data2;
+                raid6_datap_recov = (*ra)->datap;
 
-                        /* Nuke syndromes */
-                        memset(data[NDISKS-2], 0xee, 2*PAGE_SIZE);
+                printf("using recovery %s\n", (*ra)->name);
 
-                        /* Generate assumed good syndrome */
-                        raid6_call.gen_syndrome(NDISKS, PAGE_SIZE,
-                                                (void **)&dataptrs);
+                for (algo = raid6_algos; *algo; algo++) {
+                        if (!(*algo)->valid || (*algo)->valid()) {
+                                raid6_call = **algo;
 
-                        for (i = 0; i < NDISKS-1; i++)
-                                for (j = i+1; j < NDISKS; j++)
-                                        err += test_disks(i, j);
+                                /* Nuke syndromes */
+                                memset(data[NDISKS-2], 0xee, 2*PAGE_SIZE);
+
+                                /* Generate assumed good syndrome */
+                                raid6_call.gen_syndrome(NDISKS, PAGE_SIZE,
+                                                        (void **)&dataptrs);
+
+                                for (i = 0; i < NDISKS-1; i++)
+                                        for (j = i+1; j < NDISKS; j++)
+                                                err += test_disks(i, j);
+                        }
                 }
                 printf("\n");
         }
diff --git a/lib/raid6/x86.h b/lib/raid6/x86.h
index cb2a8c91c886..d55d63232c55 100644
--- a/lib/raid6/x86.h
+++ b/lib/raid6/x86.h
@@ -35,24 +35,29 @@ static inline void kernel_fpu_end(void)
 {
 }
 
+#define __aligned(x) __attribute__((aligned(x)))
+
 #define X86_FEATURE_MMX         (0*32+23) /* Multimedia Extensions */
 #define X86_FEATURE_FXSR        (0*32+24) /* FXSAVE and FXRSTOR instructions
                                            * (fast save and restore) */
 #define X86_FEATURE_XMM         (0*32+25) /* Streaming SIMD Extensions */
 #define X86_FEATURE_XMM2        (0*32+26) /* Streaming SIMD Extensions-2 */
+#define X86_FEATURE_XMM3        (4*32+ 0) /* "pni" SSE-3 */
+#define X86_FEATURE_SSSE3       (4*32+ 9) /* Supplemental SSE-3 */
+#define X86_FEATURE_AVX (4*32+28) /* Advanced Vector Extensions */
 #define X86_FEATURE_MMXEXT      (1*32+22) /* AMD MMX extensions */
 
 /* Should work well enough on modern CPUs for testing */
 static inline int boot_cpu_has(int flag)
 {
-        u32 eax = (flag >> 5) ? 0x80000001 : 1;
-        u32 edx;
+        u32 eax = (flag & 0x20) ? 0x80000001 : 1;
+        u32 ecx, edx;
 
         asm volatile("cpuid"
-                     : "+a" (eax), "=d" (edx)
-                     : : "ecx", "ebx");
+                     : "+a" (eax), "=d" (edx), "=c" (ecx)
+                     : : "ebx");
 
-        return (edx >> (flag & 31)) & 1;
+        return ((flag & 0x80 ? ecx : edx) >> (flag & 31)) & 1;
 }
 
 #endif /* ndef __KERNEL__ */
diff --git a/lib/random32.c b/lib/random32.c
index fc3545a32771..938bde5876ac 100644
--- a/lib/random32.c
+++ b/lib/random32.c
@@ -35,7 +35,7 @@
 
 #include <linux/types.h>
 #include <linux/percpu.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/jiffies.h>
 #include <linux/random.h>
 
diff --git a/lib/ratelimit.c b/lib/ratelimit.c
index 027a03f4c56d..40e03ea2a967 100644
--- a/lib/ratelimit.c
+++ b/lib/ratelimit.c
@@ -11,7 +11,7 @@
 
 #include <linux/ratelimit.h>
 #include <linux/jiffies.h>
-#include <linux/module.h>
+#include <linux/export.h>
 
 /*
  * __ratelimit - rate limiting
@@ -39,7 +39,7 @@ int ___ratelimit(struct ratelimit_state *rs, const char *func)
          * in addition to the one that will be printed by
          * the entity that is holding the lock already:
          */
-        if (!spin_trylock_irqsave(&rs->lock, flags))
+        if (!raw_spin_trylock_irqsave(&rs->lock, flags))
                 return 0;
 
         if (!rs->begin)
@@ -60,7 +60,7 @@ int ___ratelimit(struct ratelimit_state *rs, const char *func)
                 rs->missed++;
                 ret = 0;
         }
-        spin_unlock_irqrestore(&rs->lock, flags);
+        raw_spin_unlock_irqrestore(&rs->lock, flags);
 
         return ret;
 }
diff --git a/lib/rational.c b/lib/rational.c
index 3ed247b80662..f0aa21c2a762 100644
--- a/lib/rational.c
+++ b/lib/rational.c
@@ -1,13 +1,14 @@
 /*
  * rational fractions
  *
- * Copyright (C) 2009 emlix GmbH, Oskar Schirmer <os@emlix.com>
+ * Copyright (C) 2009 emlix GmbH, Oskar Schirmer <oskar@scara.com>
  *
  * helper functions when coping with rational numbers
  */
 
 #include <linux/rational.h>
-#include <linux/module.h>
+#include <linux/compiler.h>
+#include <linux/export.h>
 
 /*
  * calculate best rational approximation for a given fraction
diff --git a/lib/rbtree.c b/lib/rbtree.c
index a16be19a1305..4f56a11d67fa 100644
--- a/lib/rbtree.c
+++ b/lib/rbtree.c
@@ -2,7 +2,8 @@
   Red Black Trees
   (C) 1999  Andrea Arcangeli <andrea@suse.de>
   (C) 2002  David Woodhouse <dwmw2@infradead.org>
-  
+  (C) 2012  Michel Lespinasse <walken@google.com>
+
   This program is free software; you can redistribute it and/or modify
   it under the terms of the GNU General Public License as published by
   the Free Software Foundation; either version 2 of the License, or
@@ -20,339 +21,382 @@
   linux/lib/rbtree.c
 */
 
-#include <linux/rbtree.h>
-#include <linux/module.h>
-
-static void __rb_rotate_left(struct rb_node *node, struct rb_root *root)
-{
-        struct rb_node *right = node->rb_right;
-        struct rb_node *parent = rb_parent(node);
-
-        if ((node->rb_right = right->rb_left))
-                rb_set_parent(right->rb_left, node);
-        right->rb_left = node;
+#include <linux/rbtree_augmented.h>
+#include <linux/export.h>
 
-        rb_set_parent(right, parent);
+/*
+ * red-black trees properties:  http://en.wikipedia.org/wiki/Rbtree
+ *
+ *  1) A node is either red or black
+ *  2) The root is black
+ *  3) All leaves (NULL) are black
+ *  4) Both children of every red node are black
+ *  5) Every simple path from root to leaves contains the same number
+ *     of black nodes.
+ *
+ *  4 and 5 give the O(log n) guarantee, since 4 implies you cannot have two
+ *  consecutive red nodes in a path and every red node is therefore followed by
+ *  a black. So if B is the number of black nodes on every simple path (as per
+ *  5), then the longest possible path due to 4 is 2B.
+ *
+ *  We shall indicate color with case, where black nodes are uppercase and red
+ *  nodes will be lowercase. Unknown color nodes shall be drawn as red within
+ *  parentheses and have some accompanying text comment.
+ */
 
-        if (parent)
-        {
-                if (node == parent->rb_left)
-                        parent->rb_left = right;
-                else
-                        parent->rb_right = right;
-        }
-        else
-                root->rb_node = right;
-        rb_set_parent(node, right);
+static inline void rb_set_black(struct rb_node *rb)
+{
+        rb->__rb_parent_color |= RB_BLACK;
 }
 
-static void __rb_rotate_right(struct rb_node *node, struct rb_root *root)
+static inline struct rb_node *rb_red_parent(struct rb_node *red)
 {
-        struct rb_node *left = node->rb_left;
-        struct rb_node *parent = rb_parent(node);
-
-        if ((node->rb_left = left->rb_right))
-                rb_set_parent(left->rb_right, node);
-        left->rb_right = node;
-
-        rb_set_parent(left, parent);
+        return (struct rb_node *)red->__rb_parent_color;
+}
 
-        if (parent)
-        {
-                if (node == parent->rb_right)
-                        parent->rb_right = left;
-                else
-                        parent->rb_left = left;
-        }
-        else
-                root->rb_node = left;
-        rb_set_parent(node, left);
+/*
+ * Helper function for rotations:
+ * - old's parent and color get assigned to new
+ * - old gets assigned new as a parent and 'color' as a color.
+ */
+static inline void
+__rb_rotate_set_parents(struct rb_node *old, struct rb_node *new,
+                        struct rb_root *root, int color)
+{
+        struct rb_node *parent = rb_parent(old);
+        new->__rb_parent_color = old->__rb_parent_color;
+        rb_set_parent_color(old, new, color);
+        __rb_change_child(old, new, parent, root);
 }
 
-void rb_insert_color(struct rb_node *node, struct rb_root *root)
+static __always_inline void
+__rb_insert(struct rb_node *node, struct rb_root *root,
+            void (*augment_rotate)(struct rb_node *old, struct rb_node *new))
 {
-        struct rb_node *parent, *gparent;
-
-        while ((parent = rb_parent(node)) && rb_is_red(parent))
-        {
-                gparent = rb_parent(parent);
-
-                if (parent == gparent->rb_left)
-                {
-                        {
-                                register struct rb_node *uncle = gparent->rb_right;
-                                if (uncle && rb_is_red(uncle))
-                                {
-                                        rb_set_black(uncle);
-                                        rb_set_black(parent);
-                                        rb_set_red(gparent);
-                                        node = gparent;
-                                        continue;
-                                }
+        struct rb_node *parent = rb_red_parent(node), *gparent, *tmp;
+
+        while (true) {
+                /*
+                 * Loop invariant: node is red
+                 *
+                 * If there is a black parent, we are done.
+                 * Otherwise, take some corrective action as we don't
+                 * want a red root or two consecutive red nodes.
+                 */
+                if (!parent) {
+                        rb_set_parent_color(node, NULL, RB_BLACK);
+                        break;
+                } else if (rb_is_black(parent))
+                        break;
+
+                gparent = rb_red_parent(parent);
+
+                tmp = gparent->rb_right;
+                if (parent != tmp) {    /* parent == gparent->rb_left */
+                        if (tmp && rb_is_red(tmp)) {
+                                /*
+                                 * Case 1 - color flips
+                                 *
+                                 *       G            g
+                                 *      / \          / \
+                                 *     p   u  -->   P   U
+                                 *    /            /
+                                 *   n            N
+                                 *
+                                 * However, since g's parent might be red, and
+                                 * 4) does not allow this, we need to recurse
+                                 * at g.
+                                 */
+                                rb_set_parent_color(tmp, gparent, RB_BLACK);
+                                rb_set_parent_color(parent, gparent, RB_BLACK);
+                                node = gparent;
+                                parent = rb_parent(node);
+                                rb_set_parent_color(node, parent, RB_RED);
+                                continue;
                         }
 
-                        if (parent->rb_right == node)
-                        {
-                                register struct rb_node *tmp;
-                                __rb_rotate_left(parent, root);
-                                tmp = parent;
+                        tmp = parent->rb_right;
+                        if (node == tmp) {
+                                /*
+                                 * Case 2 - left rotate at parent
+                                 *
+                                 *      G             G
+                                 *     / \           / \
+                                 *    p   U  -->    n   U
+                                 *     \           /
+                                 *      n         p
+                                 *
+                                 * This still leaves us in violation of 4), the
+                                 * continuation into Case 3 will fix that.
+                                 */
+                                parent->rb_right = tmp = node->rb_left;
+                                node->rb_left = parent;
+                                if (tmp)
+                                        rb_set_parent_color(tmp, parent,
+                                                            RB_BLACK);
+                                rb_set_parent_color(parent, node, RB_RED);
+                                augment_rotate(parent, node);
                                 parent = node;
-                                node = tmp;
+                                tmp = node->rb_right;
                         }
 
-                        rb_set_black(parent);
-                        rb_set_red(gparent);
-                        __rb_rotate_right(gparent, root);
+                        /*
+                         * Case 3 - right rotate at gparent
+                         *
+                         *        G           P
+                         *       / \         / \
+                         *      p   U  -->  n   g
+                         *     /                 \
+                         *    n                   U
+                         */
+                        gparent->rb_left = tmp;  /* == parent->rb_right */
+                        parent->rb_right = gparent;
+                        if (tmp)
+                                rb_set_parent_color(tmp, gparent, RB_BLACK);
+                        __rb_rotate_set_parents(gparent, parent, root, RB_RED);
+                        augment_rotate(gparent, parent);
+                        break;
                 } else {
-                        {
-                                register struct rb_node *uncle = gparent->rb_left;
-                                if (uncle && rb_is_red(uncle))
-                                {
-                                        rb_set_black(uncle);
-                                        rb_set_black(parent);
-                                        rb_set_red(gparent);
-                                        node = gparent;
-                                        continue;
-                                }
+                        tmp = gparent->rb_left;
+                        if (tmp && rb_is_red(tmp)) {
+                                /* Case 1 - color flips */
+                                rb_set_parent_color(tmp, gparent, RB_BLACK);
+                                rb_set_parent_color(parent, gparent, RB_BLACK);
+                                node = gparent;
+                                parent = rb_parent(node);
+                                rb_set_parent_color(node, parent, RB_RED);
+                                continue;
                         }
 
-                        if (parent->rb_left == node)
-                        {
-                                register struct rb_node *tmp;
-                                __rb_rotate_right(parent, root);
-                                tmp = parent;
+                        tmp = parent->rb_left;
+                        if (node == tmp) {
+                                /* Case 2 - right rotate at parent */
+                                parent->rb_left = tmp = node->rb_right;
+                                node->rb_right = parent;
+                                if (tmp)
+                                        rb_set_parent_color(tmp, parent,
+                                                            RB_BLACK);
+                                rb_set_parent_color(parent, node, RB_RED);
+                                augment_rotate(parent, node);
                                 parent = node;
-                                node = tmp;
+                                tmp = node->rb_left;
                         }
 
-                        rb_set_black(parent);
-                        rb_set_red(gparent);
-                        __rb_rotate_left(gparent, root);
+                        /* Case 3 - left rotate at gparent */
+                        gparent->rb_right = tmp;  /* == parent->rb_left */
+                        parent->rb_left = gparent;
+                        if (tmp)
+                                rb_set_parent_color(tmp, gparent, RB_BLACK);
+                        __rb_rotate_set_parents(gparent, parent, root, RB_RED);
+                        augment_rotate(gparent, parent);
+                        break;
                 }
         }
-
-        rb_set_black(root->rb_node);
 }
-EXPORT_SYMBOL(rb_insert_color);
 
-static void __rb_erase_color(struct rb_node *node, struct rb_node *parent,
-                             struct rb_root *root)
+__always_inline void
+__rb_erase_color(struct rb_node *parent, struct rb_root *root,
+        void (*augment_rotate)(struct rb_node *old, struct rb_node *new))
 {
-        struct rb_node *other;
-
-        while ((!node || rb_is_black(node)) && node != root->rb_node)
-        {
-                if (parent->rb_left == node)
-                {
-                        other = parent->rb_right;
-                        if (rb_is_red(other))
-                        {
-                                rb_set_black(other);
-                                rb_set_red(parent);
-                                __rb_rotate_left(parent, root);
-                                other = parent->rb_right;
+        struct rb_node *node = NULL, *sibling, *tmp1, *tmp2;
+
+        while (true) {
+                /*
+                 * Loop invariants:
+                 * - node is black (or NULL on first iteration)
+                 * - node is not the root (parent is not NULL)
+                 * - All leaf paths going through parent and node have a
+                 *   black node count that is 1 lower than other leaf paths.
+                 */
+                sibling = parent->rb_right;
+                if (node != sibling) {  /* node == parent->rb_left */
+                        if (rb_is_red(sibling)) {
+                                /*
+                                 * Case 1 - left rotate at parent
+                                 *
+                                 *     P               S
+                                 *    / \             / \
+                                 *   N   s    -->    p   Sr
+                                 *      / \         / \
+                                 *     Sl  Sr      N   Sl
+                                 */
+                                parent->rb_right = tmp1 = sibling->rb_left;
+                                sibling->rb_left = parent;
+                                rb_set_parent_color(tmp1, parent, RB_BLACK);
+                                __rb_rotate_set_parents(parent, sibling, root,
+                                                        RB_RED);
+                                augment_rotate(parent, sibling);
+                                sibling = tmp1;
                         }
-                        if ((!other->rb_left || rb_is_black(other->rb_left)) &&
-                            (!other->rb_right || rb_is_black(other->rb_right)))
-                        {
-                                rb_set_red(other);
-                                node = parent;
-                                parent = rb_parent(node);
-                        }
-                        else
-                        {
-                                if (!other->rb_right || rb_is_black(other->rb_right))
-                                {
-                                        rb_set_black(other->rb_left);
-                                        rb_set_red(other);
-                                        __rb_rotate_right(other, root);
-                                        other = parent->rb_right;
+                        tmp1 = sibling->rb_right;
+                        if (!tmp1 || rb_is_black(tmp1)) {
+                                tmp2 = sibling->rb_left;
+                                if (!tmp2 || rb_is_black(tmp2)) {
+                                        /*
+                                         * Case 2 - sibling color flip
+                                         * (p could be either color here)
+                                         *
+                                         *    (p)           (p)
+                                         *    / \           / \
+                                         *   N   S    -->  N   s
+                                         *      / \           / \
+                                         *     Sl  Sr        Sl  Sr
+                                         *
+                                         * This leaves us violating 5) which
+                                         * can be fixed by flipping p to black
+                                         * if it was red, or by recursing at p.
+                                         * p is red when coming from Case 1.
+                                         */
+                                        rb_set_parent_color(sibling, parent,
+                                                            RB_RED);
+                                        if (rb_is_red(parent))
+                                                rb_set_black(parent);
+                                        else {
+                                                node = parent;
+                                                parent = rb_parent(node);
+                                                if (parent)
+                                                        continue;
+                                        }
+                                        break;
                                 }
-                                rb_set_color(other, rb_color(parent));
-                                rb_set_black(parent);
-                                rb_set_black(other->rb_right);
-                                __rb_rotate_left(parent, root);
-                                node = root->rb_node;
-                                break;
-                        }
-                }
-                else
-                {
-                        other = parent->rb_left;
-                        if (rb_is_red(other))
-                        {
-                                rb_set_black(other);
-                                rb_set_red(parent);
-                                __rb_rotate_right(parent, root);
-                                other = parent->rb_left;
+                                /*
+                                 * Case 3 - right rotate at sibling
+                                 * (p could be either color here)
+                                 *
+                                 *   (p)           (p)
+                                 *   / \           / \
+                                 *  N   S    -->  N   Sl
+                                 *     / \             \
+                                 *    sl  Sr            s
+                                 *                       \
+                                 *                        Sr
+                                 */
+                                sibling->rb_left = tmp1 = tmp2->rb_right;
+                                tmp2->rb_right = sibling;
+                                parent->rb_right = tmp2;
+                                if (tmp1)
+                                        rb_set_parent_color(tmp1, sibling,
+                                                            RB_BLACK);
+                                augment_rotate(sibling, tmp2);
+                                tmp1 = sibling;
+                                sibling = tmp2;
                         }
-                        if ((!other->rb_left || rb_is_black(other->rb_left)) &&
-                            (!other->rb_right || rb_is_black(other->rb_right)))
-                        {
-                                rb_set_red(other);
-                                node = parent;
-                                parent = rb_parent(node);
+                        /*
+                         * Case 4 - left rotate at parent + color flips
+                         * (p and sl could be either color here.
+                         *  After rotation, p becomes black, s acquires
+                         *  p's color, and sl keeps its color)
+                         *
+                         *      (p)             (s)
+                         *      / \             / \
+                         *     N   S     -->   P   Sr
+                         *        / \         / \
+                         *      (sl) sr      N  (sl)
+                         */
+                        parent->rb_right = tmp2 = sibling->rb_left;
+                        sibling->rb_left = parent;
+                        rb_set_parent_color(tmp1, sibling, RB_BLACK);
+                        if (tmp2)
+                                rb_set_parent(tmp2, parent);
+                        __rb_rotate_set_parents(parent, sibling, root,
+                                                RB_BLACK);
+                        augment_rotate(parent, sibling);
+                        break;
+                } else {
+                        sibling = parent->rb_left;
+                        if (rb_is_red(sibling)) {
+                                /* Case 1 - right rotate at parent */
+                                parent->rb_left = tmp1 = sibling->rb_right;
+                                sibling->rb_right = parent;
+                                rb_set_parent_color(tmp1, parent, RB_BLACK);
+                                __rb_rotate_set_parents(parent, sibling, root,
+                                                        RB_RED);
+                                augment_rotate(parent, sibling);
+                                sibling = tmp1;
                         }
-                        else
-                        {
-                                if (!other->rb_left || rb_is_black(other->rb_left))
-                                {
-                                        rb_set_black(other->rb_right);
-                                        rb_set_red(other);
-                                        __rb_rotate_left(other, root);
-                                        other = parent->rb_left;
+                        tmp1 = sibling->rb_left;
+                        if (!tmp1 || rb_is_black(tmp1)) {
+                                tmp2 = sibling->rb_right;
+                                if (!tmp2 || rb_is_black(tmp2)) {
+                                        /* Case 2 - sibling color flip */
+                                        rb_set_parent_color(sibling, parent,
+                                                            RB_RED);
+                                        if (rb_is_red(parent))
+                                                rb_set_black(parent);
+                                        else {
+                                                node = parent;
+                                                parent = rb_parent(node);
+                                                if (parent)
+                                                        continue;
+                                        }
+                                        break;
                                 }
-                                rb_set_color(other, rb_color(parent));
-                                rb_set_black(parent);
-                                rb_set_black(other->rb_left);
-                                __rb_rotate_right(parent, root);
-                                node = root->rb_node;
-                                break;
+                                /* Case 3 - right rotate at sibling */
+                                sibling->rb_right = tmp1 = tmp2->rb_left;
+                                tmp2->rb_left = sibling;
+                                parent->rb_left = tmp2;
+                                if (tmp1)
+                                        rb_set_parent_color(tmp1, sibling,
+                                                            RB_BLACK);
+                                augment_rotate(sibling, tmp2);
+                                tmp1 = sibling;
+                                sibling = tmp2;
                         }
+                        /* Case 4 - left rotate at parent + color flips */
+                        parent->rb_left = tmp2 = sibling->rb_right;
+                        sibling->rb_right = parent;
+                        rb_set_parent_color(tmp1, sibling, RB_BLACK);
+                        if (tmp2)
+                                rb_set_parent(tmp2, parent);
+                        __rb_rotate_set_parents(parent, sibling, root,
+                                                RB_BLACK);
+                        augment_rotate(parent, sibling);
+                        break;
                 }
         }
-        if (node)
-                rb_set_black(node);
 }
+EXPORT_SYMBOL(__rb_erase_color);
 
-void rb_erase(struct rb_node *node, struct rb_root *root)
-{
-        struct rb_node *child, *parent;
-        int color;
-
-        if (!node->rb_left)
-                child = node->rb_right;
-        else if (!node->rb_right)
-                child = node->rb_left;
-        else
-        {
-                struct rb_node *old = node, *left;
-
-                node = node->rb_right;
-                while ((left = node->rb_left) != NULL)
-                        node = left;
-
-                if (rb_parent(old)) {
-                        if (rb_parent(old)->rb_left == old)
-                                rb_parent(old)->rb_left = node;
-                        else
-                                rb_parent(old)->rb_right = node;
-                } else
-                        root->rb_node = node;
-
-                child = node->rb_right;
-                parent = rb_parent(node);
-                color = rb_color(node);
-
-                if (parent == old) {
-                        parent = node;
-                } else {
-                        if (child)
-                                rb_set_parent(child, parent);
-                        parent->rb_left = child;
-
-                        node->rb_right = old->rb_right;
-                        rb_set_parent(old->rb_right, node);
-                }
-
-                node->rb_parent_color = old->rb_parent_color;
-                node->rb_left = old->rb_left;
-                rb_set_parent(old->rb_left, node);
+/*
+ * Non-augmented rbtree manipulation functions.
+ *
+ * We use dummy augmented callbacks here, and have the compiler optimize them
+ * out of the rb_insert_color() and rb_erase() function definitions.
+ */
 
-                goto color;
-        }
+static inline void dummy_propagate(struct rb_node *node, struct rb_node *stop) {}
+static inline void dummy_copy(struct rb_node *old, struct rb_node *new) {}
+static inline void dummy_rotate(struct rb_node *old, struct rb_node *new) {}
 
-        parent = rb_parent(node);
-        color = rb_color(node);
-
-        if (child)
-                rb_set_parent(child, parent);
-        if (parent)
-        {
-                if (parent->rb_left == node)
-                        parent->rb_left = child;
-                else
-                        parent->rb_right = child;
-        }
-        else
-                root->rb_node = child;
+static const struct rb_augment_callbacks dummy_callbacks = {
+        dummy_propagate, dummy_copy, dummy_rotate
+};
 
- color:
-        if (color == RB_BLACK)
-                __rb_erase_color(child, parent, root);
-}
-EXPORT_SYMBOL(rb_erase);
-
-static void rb_augment_path(struct rb_node *node, rb_augment_f func, void *data)
+void rb_insert_color(struct rb_node *node, struct rb_root *root)
 {
-        struct rb_node *parent;
-
-up:
-        func(node, data);
-        parent = rb_parent(node);
-        if (!parent)
-                return;
-
-        if (node == parent->rb_left && parent->rb_right)
-                func(parent->rb_right, data);
-        else if (parent->rb_left)
-                func(parent->rb_left, data);
-
-        node = parent;
-        goto up;
+        __rb_insert(node, root, dummy_rotate);
 }
+EXPORT_SYMBOL(rb_insert_color);
 
-/*
- * after inserting @node into the tree, update the tree to account for
- * both the new entry and any damage done by rebalance
- */
-void rb_augment_insert(struct rb_node *node, rb_augment_f func, void *data)
+void rb_erase(struct rb_node *node, struct rb_root *root)
 {
-        if (node->rb_left)
-                node = node->rb_left;
-        else if (node->rb_right)
-                node = node->rb_right;
-
-        rb_augment_path(node, func, data);
+        rb_erase_augmented(node, root, &dummy_callbacks);
 }
-EXPORT_SYMBOL(rb_augment_insert);
+EXPORT_SYMBOL(rb_erase);
 
 /*
- * before removing the node, find the deepest node on the rebalance path
- * that will still be there after @node gets removed
+ * Augmented rbtree manipulation functions.
+ *
+ * This instantiates the same __always_inline functions as in the non-augmented
+ * case, but this time with user-defined callbacks.
  */
-struct rb_node *rb_augment_erase_begin(struct rb_node *node)
-{
-        struct rb_node *deepest;
-
-        if (!node->rb_right && !node->rb_left)
-                deepest = rb_parent(node);
-        else if (!node->rb_right)
-                deepest = node->rb_left;
-        else if (!node->rb_left)
-                deepest = node->rb_right;
-        else {
-                deepest = rb_next(node);
-                if (deepest->rb_right)
-                        deepest = deepest->rb_right;
-                else if (rb_parent(deepest) != node)
-                        deepest = rb_parent(deepest);
-        }
-
-        return deepest;
-}
-EXPORT_SYMBOL(rb_augment_erase_begin);
 
-/*
- * after removal, update the tree to account for the removed entry
- * and any rebalance damage.
- */
-void rb_augment_erase_end(struct rb_node *node, rb_augment_f func, void *data)
+void __rb_insert_augmented(struct rb_node *node, struct rb_root *root,
+        void (*augment_rotate)(struct rb_node *old, struct rb_node *new))
 {
-        if (node)
-                rb_augment_path(node, func, data);
+        __rb_insert(node, root, augment_rotate);
 }
-EXPORT_SYMBOL(rb_augment_erase_end);
+EXPORT_SYMBOL(__rb_insert_augmented);
 
 /*
  * This function returns the first node (in sort order) of the tree.
@@ -387,11 +431,13 @@ struct rb_node *rb_next(const struct rb_node *node)
 {
         struct rb_node *parent;
 
-        if (rb_parent(node) == node)
+        if (RB_EMPTY_NODE(node))
                 return NULL;
 
-        /* If we have a right-hand child, go down and then left as far
-           as we can. */
+        /*
+         * If we have a right-hand child, go down and then left as far
+         * as we can.
+         */
         if (node->rb_right) {
                 node = node->rb_right; 
                 while (node->rb_left)
@@ -399,12 +445,13 @@ struct rb_node *rb_next(const struct rb_node *node)
                 return (struct rb_node *)node;
         }
 
-        /* No right-hand children.  Everything down and left is
-           smaller than us, so any 'next' node must be in the general
-           direction of our parent. Go up the tree; any time the
-           ancestor is a right-hand child of its parent, keep going
-           up. First time it's a left-hand child of its parent, said
-           parent is our 'next' node. */
+        /*
+         * No right-hand children. Everything down and left is smaller than us,
+         * so any 'next' node must be in the general direction of our parent.
+         * Go up the tree; any time the ancestor is a right-hand child of its
+         * parent, keep going up. First time it's a left-hand child of its
+         * parent, said parent is our 'next' node.
+         */
         while ((parent = rb_parent(node)) && node == parent->rb_right)
                 node = parent;
 
@@ -416,11 +463,13 @@ struct rb_node *rb_prev(const struct rb_node *node)
 {
         struct rb_node *parent;
 
-        if (rb_parent(node) == node)
+        if (RB_EMPTY_NODE(node))
                 return NULL;
 
-        /* If we have a left-hand child, go down and then right as far
-           as we can. */
+        /*
+         * If we have a left-hand child, go down and then right as far
+         * as we can.
+         */
         if (node->rb_left) {
                 node = node->rb_left; 
                 while (node->rb_right)
@@ -428,8 +477,10 @@ struct rb_node *rb_prev(const struct rb_node *node)
                 return (struct rb_node *)node;
         }
 
-        /* No left-hand children. Go up till we find an ancestor which
-           is a right-hand child of its parent */
+        /*
+         * No left-hand children. Go up till we find an ancestor which
+         * is a right-hand child of its parent.
+         */
         while ((parent = rb_parent(node)) && node == parent->rb_left)
                 node = parent;
 
@@ -443,14 +494,7 @@ void rb_replace_node(struct rb_node *victim, struct rb_node *new,
         struct rb_node *parent = rb_parent(victim);
 
         /* Set the surrounding nodes to point to the replacement */
-        if (parent) {
-                if (victim == parent->rb_left)
-                        parent->rb_left = new;
-                else
-                        parent->rb_right = new;
-        } else {
-                root->rb_node = new;
-        }
+        __rb_change_child(victim, new, parent, root);
         if (victim->rb_left)
                 rb_set_parent(victim->rb_left, new);
         if (victim->rb_right)
diff --git a/lib/rbtree_test.c b/lib/rbtree_test.c
new file mode 100644
index 000000000000..268b23951fec
--- /dev/null
+++ b/lib/rbtree_test.c
@@ -0,0 +1,234 @@
+#include <linux/module.h>
+#include <linux/rbtree_augmented.h>
+#include <linux/random.h>
+#include <asm/timex.h>
+
+#define NODES       100
+#define PERF_LOOPS  100000
+#define CHECK_LOOPS 100
+
+struct test_node {
+        struct rb_node rb;
+        u32 key;
+
+        /* following fields used for testing augmented rbtree functionality */
+        u32 val;
+        u32 augmented;
+};
+
+static struct rb_root root = RB_ROOT;
+static struct test_node nodes[NODES];
+
+static struct rnd_state rnd;
+
+static void insert(struct test_node *node, struct rb_root *root)
+{
+        struct rb_node **new = &root->rb_node, *parent = NULL;
+        u32 key = node->key;
+
+        while (*new) {
+                parent = *new;
+                if (key < rb_entry(parent, struct test_node, rb)->key)
+                        new = &parent->rb_left;
+                else
+                        new = &parent->rb_right;
+        }
+
+        rb_link_node(&node->rb, parent, new);
+        rb_insert_color(&node->rb, root);
+}
+
+static inline void erase(struct test_node *node, struct rb_root *root)
+{
+        rb_erase(&node->rb, root);
+}
+
+static inline u32 augment_recompute(struct test_node *node)
+{
+        u32 max = node->val, child_augmented;
+        if (node->rb.rb_left) {
+                child_augmented = rb_entry(node->rb.rb_left, struct test_node,
+                                           rb)->augmented;
+                if (max < child_augmented)
+                        max = child_augmented;
+        }
+        if (node->rb.rb_right) {
+                child_augmented = rb_entry(node->rb.rb_right, struct test_node,
+                                           rb)->augmented;
+                if (max < child_augmented)
+                        max = child_augmented;
+        }
+        return max;
+}
+
+RB_DECLARE_CALLBACKS(static, augment_callbacks, struct test_node, rb,
+                     u32, augmented, augment_recompute)
+
+static void insert_augmented(struct test_node *node, struct rb_root *root)
+{
+        struct rb_node **new = &root->rb_node, *rb_parent = NULL;
+        u32 key = node->key;
+        u32 val = node->val;
+        struct test_node *parent;
+
+        while (*new) {
+                rb_parent = *new;
+                parent = rb_entry(rb_parent, struct test_node, rb);
+                if (parent->augmented < val)
+                        parent->augmented = val;
+                if (key < parent->key)
+                        new = &parent->rb.rb_left;
+                else
+                        new = &parent->rb.rb_right;
+        }
+
+        node->augmented = val;
+        rb_link_node(&node->rb, rb_parent, new);
+        rb_insert_augmented(&node->rb, root, &augment_callbacks);
+}
+
+static void erase_augmented(struct test_node *node, struct rb_root *root)
+{
+        rb_erase_augmented(&node->rb, root, &augment_callbacks);
+}
+
+static void init(void)
+{
+        int i;
+        for (i = 0; i < NODES; i++) {
+                nodes[i].key = prandom32(&rnd);
+                nodes[i].val = prandom32(&rnd);
+        }
+}
+
+static bool is_red(struct rb_node *rb)
+{
+        return !(rb->__rb_parent_color & 1);
+}
+
+static int black_path_count(struct rb_node *rb)
+{
+        int count;
+        for (count = 0; rb; rb = rb_parent(rb))
+                count += !is_red(rb);
+        return count;
+}
+
+static void check(int nr_nodes)
+{
+        struct rb_node *rb;
+        int count = 0;
+        int blacks;
+        u32 prev_key = 0;
+
+        for (rb = rb_first(&root); rb; rb = rb_next(rb)) {
+                struct test_node *node = rb_entry(rb, struct test_node, rb);
+                WARN_ON_ONCE(node->key < prev_key);
+                WARN_ON_ONCE(is_red(rb) &&
+                             (!rb_parent(rb) || is_red(rb_parent(rb))));
+                if (!count)
+                        blacks = black_path_count(rb);
+                else
+                        WARN_ON_ONCE((!rb->rb_left || !rb->rb_right) &&
+                                     blacks != black_path_count(rb));
+                prev_key = node->key;
+                count++;
+        }
+        WARN_ON_ONCE(count != nr_nodes);
+}
+
+static void check_augmented(int nr_nodes)
+{
+        struct rb_node *rb;
+
+        check(nr_nodes);
+        for (rb = rb_first(&root); rb; rb = rb_next(rb)) {
+                struct test_node *node = rb_entry(rb, struct test_node, rb);
+                WARN_ON_ONCE(node->augmented != augment_recompute(node));
+        }
+}
+
+static int rbtree_test_init(void)
+{
+        int i, j;
+        cycles_t time1, time2, time;
+
+        printk(KERN_ALERT "rbtree testing");
+
+        prandom32_seed(&rnd, 3141592653589793238ULL);
+        init();
+
+        time1 = get_cycles();
+
+        for (i = 0; i < PERF_LOOPS; i++) {
+                for (j = 0; j < NODES; j++)
+                        insert(nodes + j, &root);
+                for (j = 0; j < NODES; j++)
+                        erase(nodes + j, &root);
+        }
+
+        time2 = get_cycles();
+        time = time2 - time1;
+
+        time = div_u64(time, PERF_LOOPS);
+        printk(" -> %llu cycles\n", (unsigned long long)time);
+
+        for (i = 0; i < CHECK_LOOPS; i++) {
+                init();
+                for (j = 0; j < NODES; j++) {
+                        check(j);
+                        insert(nodes + j, &root);
+                }
+                for (j = 0; j < NODES; j++) {
+                        check(NODES - j);
+                        erase(nodes + j, &root);
+                }
+                check(0);
+        }
+
+        printk(KERN_ALERT "augmented rbtree testing");
+
+        init();
+
+        time1 = get_cycles();
+
+        for (i = 0; i < PERF_LOOPS; i++) {
+                for (j = 0; j < NODES; j++)
+                        insert_augmented(nodes + j, &root);
+                for (j = 0; j < NODES; j++)
+                        erase_augmented(nodes + j, &root);
+        }
+
+        time2 = get_cycles();
+        time = time2 - time1;
+
+        time = div_u64(time, PERF_LOOPS);
+        printk(" -> %llu cycles\n", (unsigned long long)time);
+
+        for (i = 0; i < CHECK_LOOPS; i++) {
+                init();
+                for (j = 0; j < NODES; j++) {
+                        check_augmented(j);
+                        insert_augmented(nodes + j, &root);
+                }
+                for (j = 0; j < NODES; j++) {
+                        check_augmented(NODES - j);
+                        erase_augmented(nodes + j, &root);
+                }
+                check_augmented(0);
+        }
+
+        return -EAGAIN; /* Fail will directly unload the module */
+}
+
+static void rbtree_test_exit(void)
+{
+        printk(KERN_ALERT "test exit\n");
+}
+
+module_init(rbtree_test_init)
+module_exit(rbtree_test_exit)
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Michel Lespinasse");
+MODULE_DESCRIPTION("Red Black Tree test");
diff --git a/lib/reciprocal_div.c b/lib/reciprocal_div.c
index 6a3bd48fa2a0..75510e94f7d0 100644
--- a/lib/reciprocal_div.c
+++ b/lib/reciprocal_div.c
@@ -1,5 +1,6 @@
 #include <asm/div64.h>
 #include <linux/reciprocal_div.h>
+#include <linux/export.h>
 
 u32 reciprocal_value(u32 k)
 {
@@ -7,3 +8,4 @@ u32 reciprocal_value(u32 k)
         do_div(val, k);
         return (u32)val;
 }
+EXPORT_SYMBOL(reciprocal_value);
diff --git a/lib/rwsem-spinlock.c b/lib/rwsem-spinlock.c
index ffc9fc7f3b05..7e0d6a58fc83 100644
--- a/lib/rwsem-spinlock.c
+++ b/lib/rwsem-spinlock.c
@@ -7,7 +7,7 @@
  */
 #include <linux/rwsem.h>
 #include <linux/sched.h>
-#include <linux/module.h>
+#include <linux/export.h>
 
 struct rwsem_waiter {
         struct list_head list;
@@ -22,9 +22,9 @@ int rwsem_is_locked(struct rw_semaphore *sem)
         int ret = 1;
         unsigned long flags;
 
-        if (spin_trylock_irqsave(&sem->wait_lock, flags)) {
+        if (raw_spin_trylock_irqsave(&sem->wait_lock, flags)) {
                 ret = (sem->activity != 0);
-                spin_unlock_irqrestore(&sem->wait_lock, flags);
+                raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
         }
         return ret;
 }
@@ -44,7 +44,7 @@ void __init_rwsem(struct rw_semaphore *sem, const char *name,
         lockdep_init_map(&sem->dep_map, name, key, 0);
 #endif
         sem->activity = 0;
-        spin_lock_init(&sem->wait_lock);
+        raw_spin_lock_init(&sem->wait_lock);
         INIT_LIST_HEAD(&sem->wait_list);
 }
 EXPORT_SYMBOL(__init_rwsem);
@@ -145,12 +145,12 @@ void __sched __down_read(struct rw_semaphore *sem)
         struct task_struct *tsk;
         unsigned long flags;
 
-        spin_lock_irqsave(&sem->wait_lock, flags);
+        raw_spin_lock_irqsave(&sem->wait_lock, flags);
 
         if (sem->activity >= 0 && list_empty(&sem->wait_list)) {
                 /* granted */
                 sem->activity++;
-                spin_unlock_irqrestore(&sem->wait_lock, flags);
+                raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
                 goto out;
         }
 
@@ -165,7 +165,7 @@ void __sched __down_read(struct rw_semaphore *sem)
         list_add_tail(&waiter.list, &sem->wait_list);
 
         /* we don't need to touch the semaphore struct anymore */
-        spin_unlock_irqrestore(&sem->wait_lock, flags);
+        raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
 
         /* wait to be given the lock */
         for (;;) {
@@ -189,7 +189,7 @@ int __down_read_trylock(struct rw_semaphore *sem)
         int ret = 0;
 
 
-        spin_lock_irqsave(&sem->wait_lock, flags);
+        raw_spin_lock_irqsave(&sem->wait_lock, flags);
 
         if (sem->activity >= 0 && list_empty(&sem->wait_list)) {
                 /* granted */
@@ -197,7 +197,7 @@ int __down_read_trylock(struct rw_semaphore *sem)
                 ret = 1;
         }
 
-        spin_unlock_irqrestore(&sem->wait_lock, flags);
+        raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
 
         return ret;
 }
@@ -212,12 +212,12 @@ void __sched __down_write_nested(struct rw_semaphore *sem, int subclass)
         struct task_struct *tsk;
         unsigned long flags;
 
-        spin_lock_irqsave(&sem->wait_lock, flags);
+        raw_spin_lock_irqsave(&sem->wait_lock, flags);
 
         if (sem->activity == 0 && list_empty(&sem->wait_list)) {
                 /* granted */
                 sem->activity = -1;
-                spin_unlock_irqrestore(&sem->wait_lock, flags);
+                raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
                 goto out;
         }
 
@@ -232,7 +232,7 @@ void __sched __down_write_nested(struct rw_semaphore *sem, int subclass)
         list_add_tail(&waiter.list, &sem->wait_list);
 
         /* we don't need to touch the semaphore struct anymore */
-        spin_unlock_irqrestore(&sem->wait_lock, flags);
+        raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
 
         /* wait to be given the lock */
         for (;;) {
@@ -260,7 +260,7 @@ int __down_write_trylock(struct rw_semaphore *sem)
         unsigned long flags;
         int ret = 0;
 
-        spin_lock_irqsave(&sem->wait_lock, flags);
+        raw_spin_lock_irqsave(&sem->wait_lock, flags);
 
         if (sem->activity == 0 && list_empty(&sem->wait_list)) {
                 /* granted */
@@ -268,7 +268,7 @@ int __down_write_trylock(struct rw_semaphore *sem)
                 ret = 1;
         }
 
-        spin_unlock_irqrestore(&sem->wait_lock, flags);
+        raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
 
         return ret;
 }
@@ -280,12 +280,12 @@ void __up_read(struct rw_semaphore *sem)
 {
         unsigned long flags;
 
-        spin_lock_irqsave(&sem->wait_lock, flags);
+        raw_spin_lock_irqsave(&sem->wait_lock, flags);
 
         if (--sem->activity == 0 && !list_empty(&sem->wait_list))
                 sem = __rwsem_wake_one_writer(sem);
 
-        spin_unlock_irqrestore(&sem->wait_lock, flags);
+        raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
 }
 
 /*
@@ -295,13 +295,13 @@ void __up_write(struct rw_semaphore *sem)
 {
         unsigned long flags;
 
-        spin_lock_irqsave(&sem->wait_lock, flags);
+        raw_spin_lock_irqsave(&sem->wait_lock, flags);
 
         sem->activity = 0;
         if (!list_empty(&sem->wait_list))
                 sem = __rwsem_do_wake(sem, 1);
 
-        spin_unlock_irqrestore(&sem->wait_lock, flags);
+        raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
 }
 
 /*
@@ -312,12 +312,12 @@ void __downgrade_write(struct rw_semaphore *sem)
 {
         unsigned long flags;
 
-        spin_lock_irqsave(&sem->wait_lock, flags);
+        raw_spin_lock_irqsave(&sem->wait_lock, flags);
 
         sem->activity = 1;
         if (!list_empty(&sem->wait_list))
                 sem = __rwsem_do_wake(sem, 0);
 
-        spin_unlock_irqrestore(&sem->wait_lock, flags);
+        raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
 }
 
diff --git a/lib/rwsem.c b/lib/rwsem.c
index aa7c3052261f..8337e1b9bb8d 100644
--- a/lib/rwsem.c
+++ b/lib/rwsem.c
@@ -6,7 +6,7 @@
 #include <linux/rwsem.h>
 #include <linux/sched.h>
 #include <linux/init.h>
-#include <linux/module.h>
+#include <linux/export.h>
 
 /*
  * Initialize an rwsem:
@@ -22,7 +22,7 @@ void __init_rwsem(struct rw_semaphore *sem, const char *name,
         lockdep_init_map(&sem->dep_map, name, key, 0);
 #endif
         sem->count = RWSEM_UNLOCKED_VALUE;
-        spin_lock_init(&sem->wait_lock);
+        raw_spin_lock_init(&sem->wait_lock);
         INIT_LIST_HEAD(&sem->wait_list);
 }
 
@@ -180,7 +180,7 @@ rwsem_down_failed_common(struct rw_semaphore *sem,
         set_task_state(tsk, TASK_UNINTERRUPTIBLE);
 
         /* set up my own style of waitqueue */
-        spin_lock_irq(&sem->wait_lock);
+        raw_spin_lock_irq(&sem->wait_lock);
         waiter.task = tsk;
         waiter.flags = flags;
         get_task_struct(tsk);
@@ -204,7 +204,7 @@ rwsem_down_failed_common(struct rw_semaphore *sem,
                  adjustment == -RWSEM_ACTIVE_WRITE_BIAS)
                 sem = __rwsem_do_wake(sem, RWSEM_WAKE_READ_OWNED);
 
-        spin_unlock_irq(&sem->wait_lock);
+        raw_spin_unlock_irq(&sem->wait_lock);
 
         /* wait to be given the lock */
         for (;;) {
@@ -245,13 +245,13 @@ struct rw_semaphore *rwsem_wake(struct rw_semaphore *sem)
 {
         unsigned long flags;
 
-        spin_lock_irqsave(&sem->wait_lock, flags);
+        raw_spin_lock_irqsave(&sem->wait_lock, flags);
 
         /* do nothing if list empty */
         if (!list_empty(&sem->wait_list))
                 sem = __rwsem_do_wake(sem, RWSEM_WAKE_ANY);
 
-        spin_unlock_irqrestore(&sem->wait_lock, flags);
+        raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
 
         return sem;
 }
@@ -265,13 +265,13 @@ struct rw_semaphore *rwsem_downgrade_wake(struct rw_semaphore *sem)
 {
         unsigned long flags;
 
-        spin_lock_irqsave(&sem->wait_lock, flags);
+        raw_spin_lock_irqsave(&sem->wait_lock, flags);
 
         /* do nothing if list empty */
         if (!list_empty(&sem->wait_list))
                 sem = __rwsem_do_wake(sem, RWSEM_WAKE_READ_OWNED);
 
-        spin_unlock_irqrestore(&sem->wait_lock, flags);
+        raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
 
         return sem;
 }
diff --git a/lib/scatterlist.c b/lib/scatterlist.c
index 4ceb05d772ae..3675452b23ca 100644
--- a/lib/scatterlist.c
+++ b/lib/scatterlist.c
@@ -6,7 +6,7 @@
  * This source code is licensed under the GNU General Public License,
  * Version 2. See the file COPYING for more details.
  */
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/slab.h>
 #include <linux/scatterlist.h>
 #include <linux/highmem.h>
@@ -39,6 +39,25 @@ struct scatterlist *sg_next(struct scatterlist *sg)
 EXPORT_SYMBOL(sg_next);
 
 /**
+ * sg_nents - return total count of entries in scatterlist
+ * @sg:         The scatterlist
+ *
+ * Description:
+ * Allows to know how many entries are in sg, taking into acount
+ * chaining as well
+ *
+ **/
+int sg_nents(struct scatterlist *sg)
+{
+        int nents;
+        for (nents = 0; sg; sg = sg_next(sg))
+                nents++;
+        return nents;
+}
+EXPORT_SYMBOL(sg_nents);
+
+
+/**
  * sg_last - return the last scatterlist entry in a list
  * @sgl:        First entry in the scatterlist
  * @nents:      Number of entries in the scatterlist
@@ -279,14 +298,6 @@ int __sg_alloc_table(struct sg_table *table, unsigned int nents,
                 if (!left)
                         sg_mark_end(&sg[sg_size - 1]);
 
-                /*
-                 * only really needed for mempool backed sg allocations (like
-                 * SCSI), a possible improvement here would be to pass the
-                 * table pointer into the allocator and let that clear these
-                 * flags
-                 */
-                gfp_mask &= ~__GFP_WAIT;
-                gfp_mask |= __GFP_HIGH;
                 prv = sg;
         } while (left);
 
@@ -319,6 +330,70 @@ int sg_alloc_table(struct sg_table *table, unsigned int nents, gfp_t gfp_mask)
 EXPORT_SYMBOL(sg_alloc_table);
 
 /**
+ * sg_alloc_table_from_pages - Allocate and initialize an sg table from
+ *                             an array of pages
+ * @sgt:        The sg table header to use
+ * @pages:      Pointer to an array of page pointers
+ * @n_pages:    Number of pages in the pages array
+ * @offset:     Offset from start of the first page to the start of a buffer
+ * @size:       Number of valid bytes in the buffer (after offset)
+ * @gfp_mask:   GFP allocation mask
+ *
+ *  Description:
+ *    Allocate and initialize an sg table from a list of pages. Contiguous
+ *    ranges of the pages are squashed into a single scatterlist node. A user
+ *    may provide an offset at a start and a size of valid data in a buffer
+ *    specified by the page array. The returned sg table is released by
+ *    sg_free_table.
+ *
+ * Returns:
+ *   0 on success, negative error on failure
+ */
+int sg_alloc_table_from_pages(struct sg_table *sgt,
+        struct page **pages, unsigned int n_pages,
+        unsigned long offset, unsigned long size,
+        gfp_t gfp_mask)
+{
+        unsigned int chunks;
+        unsigned int i;
+        unsigned int cur_page;
+        int ret;
+        struct scatterlist *s;
+
+        /* compute number of contiguous chunks */
+        chunks = 1;
+        for (i = 1; i < n_pages; ++i)
+                if (page_to_pfn(pages[i]) != page_to_pfn(pages[i - 1]) + 1)
+                        ++chunks;
+
+        ret = sg_alloc_table(sgt, chunks, gfp_mask);
+        if (unlikely(ret))
+                return ret;
+
+        /* merging chunks and putting them into the scatterlist */
+        cur_page = 0;
+        for_each_sg(sgt->sgl, s, sgt->orig_nents, i) {
+                unsigned long chunk_size;
+                unsigned int j;
+
+                /* look for the end of the current chunk */
+                for (j = cur_page + 1; j < n_pages; ++j)
+                        if (page_to_pfn(pages[j]) !=
+                            page_to_pfn(pages[j - 1]) + 1)
+                                break;
+
+                chunk_size = ((j - cur_page) << PAGE_SHIFT) - offset;
+                sg_set_page(s, pages[cur_page], min(size, chunk_size), offset);
+                size -= chunk_size;
+                offset = 0;
+                cur_page = j;
+        }
+
+        return 0;
+}
+EXPORT_SYMBOL(sg_alloc_table_from_pages);
+
+/**
  * sg_miter_start - start mapping iteration over a sg list
  * @miter: sg mapping iter to be started
  * @sgl: sg list to iterate over
@@ -348,14 +423,13 @@ EXPORT_SYMBOL(sg_miter_start);
  * @miter: sg mapping iter to proceed
  *
  * Description:
- *   Proceeds @miter@ to the next mapping.  @miter@ should have been
- *   started using sg_miter_start().  On successful return,
- *   @miter@->page, @miter@->addr and @miter@->length point to the
- *   current mapping.
+ *   Proceeds @miter to the next mapping.  @miter should have been started
+ *   using sg_miter_start().  On successful return, @miter->page,
+ *   @miter->addr and @miter->length point to the current mapping.
  *
  * Context:
- *   IRQ disabled if SG_MITER_ATOMIC.  IRQ must stay disabled till
- *   @miter@ is stopped.  May sleep if !SG_MITER_ATOMIC.
+ *   Preemption disabled if SG_MITER_ATOMIC.  Preemption must stay disabled
+ *   till @miter is stopped.  May sleep if !SG_MITER_ATOMIC.
  *
  * Returns:
  *   true if @miter contains the next mapping.  false if end of sg
@@ -390,7 +464,7 @@ bool sg_miter_next(struct sg_mapping_iter *miter)
         miter->consumed = miter->length;
 
         if (miter->__flags & SG_MITER_ATOMIC)
-                miter->addr = kmap_atomic(miter->page, KM_BIO_SRC_IRQ) + off;
+                miter->addr = kmap_atomic(miter->page) + off;
         else
                 miter->addr = kmap(miter->page) + off;
 
@@ -409,7 +483,8 @@ EXPORT_SYMBOL(sg_miter_next);
  *   resources (kmap) need to be released during iteration.
  *
  * Context:
- *   IRQ disabled if the SG_MITER_ATOMIC is set.  Don't care otherwise.
+ *   Preemption disabled if the SG_MITER_ATOMIC is set.  Don't care
+ *   otherwise.
  */
 void sg_miter_stop(struct sg_mapping_iter *miter)
 {
@@ -423,8 +498,8 @@ void sg_miter_stop(struct sg_mapping_iter *miter)
                         flush_kernel_dcache_page(miter->page);
 
                 if (miter->__flags & SG_MITER_ATOMIC) {
-                        WARN_ON(!irqs_disabled());
-                        kunmap_atomic(miter->addr, KM_BIO_SRC_IRQ);
+                        WARN_ON_ONCE(preemptible());
+                        kunmap_atomic(miter->addr);
                 } else
                         kunmap(miter->page);
 
diff --git a/lib/sha1.c b/lib/sha1.c
index f33271dd00cb..1df191e04a24 100644
--- a/lib/sha1.c
+++ b/lib/sha1.c
@@ -6,8 +6,9 @@
  */
 
 #include <linux/kernel.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/bitops.h>
+#include <linux/cryptohash.h>
 #include <asm/unaligned.h>
 
 /*
diff --git a/lib/smp_processor_id.c b/lib/smp_processor_id.c
index 4689cb073da4..4c0d0e51d49e 100644
--- a/lib/smp_processor_id.c
+++ b/lib/smp_processor_id.c
@@ -3,7 +3,7 @@
  *
  * DEBUG_PREEMPT variant of smp_processor_id().
  */
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/kallsyms.h>
 #include <linux/sched.h>
 
@@ -22,7 +22,7 @@ notrace unsigned int debug_smp_processor_id(void)
          * Kernel threads bound to a single CPU can safely use
          * smp_processor_id():
          */
-        if (cpumask_equal(&current->cpus_allowed, cpumask_of(this_cpu)))
+        if (cpumask_equal(tsk_cpus_allowed(current), cpumask_of(this_cpu)))
                 goto out;
 
         /*
diff --git a/lib/spinlock_debug.c b/lib/spinlock_debug.c
index 4755b98b6dfb..0374a596cffa 100644
--- a/lib/spinlock_debug.c
+++ b/lib/spinlock_debug.c
@@ -11,7 +11,7 @@
 #include <linux/interrupt.h>
 #include <linux/debug_locks.h>
 #include <linux/delay.h>
-#include <linux/module.h>
+#include <linux/export.h>
 
 void __raw_spin_lock_init(raw_spinlock_t *lock, const char *name,
                           struct lock_class_key *key)
@@ -49,19 +49,16 @@ void __rwlock_init(rwlock_t *lock, const char *name,
 
 EXPORT_SYMBOL(__rwlock_init);
 
-static void spin_bug(raw_spinlock_t *lock, const char *msg)
+static void spin_dump(raw_spinlock_t *lock, const char *msg)
 {
         struct task_struct *owner = NULL;
 
-        if (!debug_locks_off())
-                return;
-
         if (lock->owner && lock->owner != SPINLOCK_OWNER_INIT)
                 owner = lock->owner;
         printk(KERN_EMERG "BUG: spinlock %s on CPU#%d, %s/%d\n",
                 msg, raw_smp_processor_id(),
                 current->comm, task_pid_nr(current));
-        printk(KERN_EMERG " lock: %p, .magic: %08x, .owner: %s/%d, "
+        printk(KERN_EMERG " lock: %pS, .magic: %08x, .owner: %s/%d, "
                         ".owner_cpu: %d\n",
                 lock, lock->magic,
                 owner ? owner->comm : "<none>",
@@ -70,6 +67,14 @@ static void spin_bug(raw_spinlock_t *lock, const char *msg)
         dump_stack();
 }
 
+static void spin_bug(raw_spinlock_t *lock, const char *msg)
+{
+        if (!debug_locks_off())
+                return;
+
+        spin_dump(lock, msg);
+}
+
 #define SPIN_BUG_ON(cond, lock, msg) if (unlikely(cond)) spin_bug(lock, msg)
 
 static inline void
@@ -102,27 +107,27 @@ static void __spin_lock_debug(raw_spinlock_t *lock)
 {
         u64 i;
         u64 loops = loops_per_jiffy * HZ;
-        int print_once = 1;
 
-        for (;;) {
-                for (i = 0; i < loops; i++) {
-                        if (arch_spin_trylock(&lock->raw_lock))
-                                return;
-                        __delay(1);
-                }
-                /* lockup suspected: */
-                if (print_once) {
-                        print_once = 0;
-                        printk(KERN_EMERG "BUG: spinlock lockup on CPU#%d, "
-                                        "%s/%d, %p\n",
-                                raw_smp_processor_id(), current->comm,
-                                task_pid_nr(current), lock);
-                        dump_stack();
+        for (i = 0; i < loops; i++) {
+                if (arch_spin_trylock(&lock->raw_lock))
+                        return;
+                __delay(1);
+        }
+        /* lockup suspected: */
+        spin_dump(lock, "lockup suspected");
 #ifdef CONFIG_SMP
-                        trigger_all_cpu_backtrace();
+        trigger_all_cpu_backtrace();
 #endif
-                }
-        }
+
+        /*
+         * The trylock above was causing a livelock.  Give the lower level arch
+         * specific lock code a chance to acquire the lock. We have already
+         * printed a warning/backtrace at this point. The non-debug arch
+         * specific code might actually succeed in acquiring the lock.  If it is
+         * not successful, the end-result is the same - there is no forward
+         * progress.
+         */
+        arch_spin_lock(&lock->raw_lock);
 }
 
 void do_raw_spin_lock(raw_spinlock_t *lock)
diff --git a/lib/stmp_device.c b/lib/stmp_device.c
new file mode 100644
index 000000000000..8ac9bcc4289a
--- /dev/null
+++ b/lib/stmp_device.c
@@ -0,0 +1,80 @@
+/*
+ * Copyright (C) 1999 ARM Limited
+ * Copyright (C) 2000 Deep Blue Solutions Ltd
+ * Copyright 2006-2007,2010 Freescale Semiconductor, Inc. All Rights Reserved.
+ * Copyright 2008 Juergen Beisert, kernel@pengutronix.de
+ * Copyright 2009 Ilya Yanok, Emcraft Systems Ltd, yanok@emcraft.com
+ * Copyright (C) 2011 Wolfram Sang, Pengutronix e.K.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include <linux/io.h>
+#include <linux/errno.h>
+#include <linux/delay.h>
+#include <linux/module.h>
+#include <linux/stmp_device.h>
+
+#define STMP_MODULE_CLKGATE     (1 << 30)
+#define STMP_MODULE_SFTRST      (1 << 31)
+
+/*
+ * Clear the bit and poll it cleared.  This is usually called with
+ * a reset address and mask being either SFTRST(bit 31) or CLKGATE
+ * (bit 30).
+ */
+static int stmp_clear_poll_bit(void __iomem *addr, u32 mask)
+{
+        int timeout = 0x400;
+
+        writel(mask, addr + STMP_OFFSET_REG_CLR);
+        udelay(1);
+        while ((readl(addr) & mask) && --timeout)
+                /* nothing */;
+
+        return !timeout;
+}
+
+int stmp_reset_block(void __iomem *reset_addr)
+{
+        int ret;
+        int timeout = 0x400;
+
+        /* clear and poll SFTRST */
+        ret = stmp_clear_poll_bit(reset_addr, STMP_MODULE_SFTRST);
+        if (unlikely(ret))
+                goto error;
+
+        /* clear CLKGATE */
+        writel(STMP_MODULE_CLKGATE, reset_addr + STMP_OFFSET_REG_CLR);
+
+        /* set SFTRST to reset the block */
+        writel(STMP_MODULE_SFTRST, reset_addr + STMP_OFFSET_REG_SET);
+        udelay(1);
+
+        /* poll CLKGATE becoming set */
+        while ((!(readl(reset_addr) & STMP_MODULE_CLKGATE)) && --timeout)
+                /* nothing */;
+        if (unlikely(!timeout))
+                goto error;
+
+        /* clear and poll SFTRST */
+        ret = stmp_clear_poll_bit(reset_addr, STMP_MODULE_SFTRST);
+        if (unlikely(ret))
+                goto error;
+
+        /* clear and poll CLKGATE */
+        ret = stmp_clear_poll_bit(reset_addr, STMP_MODULE_CLKGATE);
+        if (unlikely(ret))
+                goto error;
+
+        return 0;
+
+error:
+        pr_err("%s(%p): module reset timeout\n", __func__, reset_addr);
+        return -ETIMEDOUT;
+}
+EXPORT_SYMBOL(stmp_reset_block);
diff --git a/lib/string.c b/lib/string.c
index 01fad9b203e1..e5878de4f101 100644
--- a/lib/string.c
+++ b/lib/string.c
@@ -22,7 +22,10 @@
 #include <linux/types.h>
 #include <linux/string.h>
 #include <linux/ctype.h>
-#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/export.h>
+#include <linux/bug.h>
+#include <linux/errno.h>
 
 #ifndef __HAVE_ARCH_STRNICMP
 /**
@@ -360,7 +363,6 @@ char *strim(char *s)
         size_t size;
         char *end;
 
-        s = skip_spaces(s);
         size = strlen(s);
         if (!size)
                 return s;
@@ -370,7 +372,7 @@ char *strim(char *s)
                 end--;
         *(end + 1) = '\0';
 
-        return s;
+        return skip_spaces(s);
 }
 EXPORT_SYMBOL(strim);
 
@@ -756,3 +758,69 @@ void *memchr(const void *s, int c, size_t n)
 }
 EXPORT_SYMBOL(memchr);
 #endif
+
+static void *check_bytes8(const u8 *start, u8 value, unsigned int bytes)
+{
+        while (bytes) {
+                if (*start != value)
+                        return (void *)start;
+                start++;
+                bytes--;
+        }
+        return NULL;
+}
+
+/**
+ * memchr_inv - Find an unmatching character in an area of memory.
+ * @start: The memory area
+ * @c: Find a character other than c
+ * @bytes: The size of the area.
+ *
+ * returns the address of the first character other than @c, or %NULL
+ * if the whole buffer contains just @c.
+ */
+void *memchr_inv(const void *start, int c, size_t bytes)
+{
+        u8 value = c;
+        u64 value64;
+        unsigned int words, prefix;
+
+        if (bytes <= 16)
+                return check_bytes8(start, value, bytes);
+
+        value64 = value;
+#if defined(ARCH_HAS_FAST_MULTIPLIER) && BITS_PER_LONG == 64
+        value64 *= 0x0101010101010101;
+#elif defined(ARCH_HAS_FAST_MULTIPLIER)
+        value64 *= 0x01010101;
+        value64 |= value64 << 32;
+#else
+        value64 |= value64 << 8;
+        value64 |= value64 << 16;
+        value64 |= value64 << 32;
+#endif
+
+        prefix = (unsigned long)start % 8;
+        if (prefix) {
+                u8 *r;
+
+                prefix = 8 - prefix;
+                r = check_bytes8(start, value, prefix);
+                if (r)
+                        return r;
+                start += prefix;
+                bytes -= prefix;
+        }
+
+        words = bytes / 8;
+
+        while (words) {
+                if (*(u64 *)start != value64)
+                        return check_bytes8(start, value, 8);
+                start += 8;
+                words--;
+        }
+
+        return check_bytes8(start, value, bytes % 8);
+}
+EXPORT_SYMBOL(memchr_inv);
diff --git a/lib/string_helpers.c b/lib/string_helpers.c
index ab431d4cc970..1cffc223bff5 100644
--- a/lib/string_helpers.c
+++ b/lib/string_helpers.c
@@ -5,7 +5,7 @@
  */
 #include <linux/kernel.h>
 #include <linux/math64.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/string_helpers.h>
 
 /**
@@ -23,15 +23,15 @@
 int string_get_size(u64 size, const enum string_size_units units,
                     char *buf, int len)
 {
-        const char *units_10[] = { "B", "kB", "MB", "GB", "TB", "PB",
+        static const char *units_10[] = { "B", "kB", "MB", "GB", "TB", "PB",
                                    "EB", "ZB", "YB", NULL};
-        const char *units_2[] = {"B", "KiB", "MiB", "GiB", "TiB", "PiB",
+        static const char *units_2[] = {"B", "KiB", "MiB", "GiB", "TiB", "PiB",
                                  "EiB", "ZiB", "YiB", NULL };
-        const char **units_str[] = {
+        static const char **units_str[] = {
                 [STRING_UNITS_10] =  units_10,
                 [STRING_UNITS_2] = units_2,
         };
-        const unsigned int divisor[] = {
+        static const unsigned int divisor[] = {
                 [STRING_UNITS_10] = 1000,
                 [STRING_UNITS_2] = 1024,
         };
diff --git a/lib/strncpy_from_user.c b/lib/strncpy_from_user.c
new file mode 100644
index 000000000000..bb2b201d6ad0
--- /dev/null
+++ b/lib/strncpy_from_user.c
@@ -0,0 +1,113 @@
+#include <linux/module.h>
+#include <linux/uaccess.h>
+#include <linux/kernel.h>
+#include <linux/errno.h>
+
+#include <asm/byteorder.h>
+#include <asm/word-at-a-time.h>
+
+#ifdef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
+#define IS_UNALIGNED(src, dst)  0
+#else
+#define IS_UNALIGNED(src, dst)  \
+        (((long) dst | (long) src) & (sizeof(long) - 1))
+#endif
+
+/*
+ * Do a strncpy, return length of string without final '\0'.
+ * 'count' is the user-supplied count (return 'count' if we
+ * hit it), 'max' is the address space maximum (and we return
+ * -EFAULT if we hit it).
+ */
+static inline long do_strncpy_from_user(char *dst, const char __user *src, long count, unsigned long max)
+{
+        const struct word_at_a_time constants = WORD_AT_A_TIME_CONSTANTS;
+        long res = 0;
+
+        /*
+         * Truncate 'max' to the user-specified limit, so that
+         * we only have one limit we need to check in the loop
+         */
+        if (max > count)
+                max = count;
+
+        if (IS_UNALIGNED(src, dst))
+                goto byte_at_a_time;
+
+        while (max >= sizeof(unsigned long)) {
+                unsigned long c, data;
+
+                /* Fall back to byte-at-a-time if we get a page fault */
+                if (unlikely(__get_user(c,(unsigned long __user *)(src+res))))
+                        break;
+                *(unsigned long *)(dst+res) = c;
+                if (has_zero(c, &data, &constants)) {
+                        data = prep_zero_mask(c, data, &constants);
+                        data = create_zero_mask(data);
+                        return res + find_zero(data);
+                }
+                res += sizeof(unsigned long);
+                max -= sizeof(unsigned long);
+        }
+
+byte_at_a_time:
+        while (max) {
+                char c;
+
+                if (unlikely(__get_user(c,src+res)))
+                        return -EFAULT;
+                dst[res] = c;
+                if (!c)
+                        return res;
+                res++;
+                max--;
+        }
+
+        /*
+         * Uhhuh. We hit 'max'. But was that the user-specified maximum
+         * too? If so, that's ok - we got as much as the user asked for.
+         */
+        if (res >= count)
+                return res;
+
+        /*
+         * Nope: we hit the address space limit, and we still had more
+         * characters the caller would have wanted. That's an EFAULT.
+         */
+        return -EFAULT;
+}
+
+/**
+ * strncpy_from_user: - Copy a NUL terminated string from userspace.
+ * @dst:   Destination address, in kernel space.  This buffer must be at
+ *         least @count bytes long.
+ * @src:   Source address, in user space.
+ * @count: Maximum number of bytes to copy, including the trailing NUL.
+ *
+ * Copies a NUL-terminated string from userspace to kernel space.
+ *
+ * On success, returns the length of the string (not including the trailing
+ * NUL).
+ *
+ * If access to userspace fails, returns -EFAULT (some data may have been
+ * copied).
+ *
+ * If @count is smaller than the length of the string, copies @count bytes
+ * and returns @count.
+ */
+long strncpy_from_user(char *dst, const char __user *src, long count)
+{
+        unsigned long max_addr, src_addr;
+
+        if (unlikely(count <= 0))
+                return 0;
+
+        max_addr = user_addr_max();
+        src_addr = (unsigned long)src;
+        if (likely(src_addr < max_addr)) {
+                unsigned long max = max_addr - src_addr;
+                return do_strncpy_from_user(dst, src, count, max);
+        }
+        return -EFAULT;
+}
+EXPORT_SYMBOL(strncpy_from_user);
diff --git a/lib/strnlen_user.c b/lib/strnlen_user.c
new file mode 100644
index 000000000000..a28df5206d95
--- /dev/null
+++ b/lib/strnlen_user.c
@@ -0,0 +1,138 @@
+#include <linux/kernel.h>
+#include <linux/export.h>
+#include <linux/uaccess.h>
+
+#include <asm/word-at-a-time.h>
+
+/* Set bits in the first 'n' bytes when loaded from memory */
+#ifdef __LITTLE_ENDIAN
+#  define aligned_byte_mask(n) ((1ul << 8*(n))-1)
+#else
+#  define aligned_byte_mask(n) (~0xfful << (BITS_PER_LONG - 8 - 8*(n)))
+#endif
+
+/*
+ * Do a strnlen, return length of string *with* final '\0'.
+ * 'count' is the user-supplied count, while 'max' is the
+ * address space maximum.
+ *
+ * Return 0 for exceptions (which includes hitting the address
+ * space maximum), or 'count+1' if hitting the user-supplied
+ * maximum count.
+ *
+ * NOTE! We can sometimes overshoot the user-supplied maximum
+ * if it fits in a aligned 'long'. The caller needs to check
+ * the return value against "> max".
+ */
+static inline long do_strnlen_user(const char __user *src, unsigned long count, unsigned long max)
+{
+        const struct word_at_a_time constants = WORD_AT_A_TIME_CONSTANTS;
+        long align, res = 0;
+        unsigned long c;
+
+        /*
+         * Truncate 'max' to the user-specified limit, so that
+         * we only have one limit we need to check in the loop
+         */
+        if (max > count)
+                max = count;
+
+        /*
+         * Do everything aligned. But that means that we
+         * need to also expand the maximum..
+         */
+        align = (sizeof(long) - 1) & (unsigned long)src;
+        src -= align;
+        max += align;
+
+        if (unlikely(__get_user(c,(unsigned long __user *)src)))
+                return 0;
+        c |= aligned_byte_mask(align);
+
+        for (;;) {
+                unsigned long data;
+                if (has_zero(c, &data, &constants)) {
+                        data = prep_zero_mask(c, data, &constants);
+                        data = create_zero_mask(data);
+                        return res + find_zero(data) + 1 - align;
+                }
+                res += sizeof(unsigned long);
+                if (unlikely(max < sizeof(unsigned long)))
+                        break;
+                max -= sizeof(unsigned long);
+                if (unlikely(__get_user(c,(unsigned long __user *)(src+res))))
+                        return 0;
+        }
+        res -= align;
+
+        /*
+         * Uhhuh. We hit 'max'. But was that the user-specified maximum
+         * too? If so, return the marker for "too long".
+         */
+        if (res >= count)
+                return count+1;
+
+        /*
+         * Nope: we hit the address space limit, and we still had more
+         * characters the caller would have wanted. That's 0.
+         */
+        return 0;
+}
+
+/**
+ * strnlen_user: - Get the size of a user string INCLUDING final NUL.
+ * @str: The string to measure.
+ * @count: Maximum count (including NUL character)
+ *
+ * Context: User context only.  This function may sleep.
+ *
+ * Get the size of a NUL-terminated string in user space.
+ *
+ * Returns the size of the string INCLUDING the terminating NUL.
+ * If the string is too long, returns 'count+1'.
+ * On exception (or invalid count), returns 0.
+ */
+long strnlen_user(const char __user *str, long count)
+{
+        unsigned long max_addr, src_addr;
+
+        if (unlikely(count <= 0))
+                return 0;
+
+        max_addr = user_addr_max();
+        src_addr = (unsigned long)str;
+        if (likely(src_addr < max_addr)) {
+                unsigned long max = max_addr - src_addr;
+                return do_strnlen_user(str, count, max);
+        }
+        return 0;
+}
+EXPORT_SYMBOL(strnlen_user);
+
+/**
+ * strlen_user: - Get the size of a user string INCLUDING final NUL.
+ * @str: The string to measure.
+ *
+ * Context: User context only.  This function may sleep.
+ *
+ * Get the size of a NUL-terminated string in user space.
+ *
+ * Returns the size of the string INCLUDING the terminating NUL.
+ * On exception, returns 0.
+ *
+ * If there is a limit on the length of a valid string, you may wish to
+ * consider using strnlen_user() instead.
+ */
+long strlen_user(const char __user *str)
+{
+        unsigned long max_addr, src_addr;
+
+        max_addr = user_addr_max();
+        src_addr = (unsigned long)str;
+        if (likely(src_addr < max_addr)) {
+                unsigned long max = max_addr - src_addr;
+                return do_strnlen_user(str, ~0ul, max);
+        }
+        return 0;
+}
+EXPORT_SYMBOL(strlen_user);
diff --git a/lib/swiotlb.c b/lib/swiotlb.c
index 99093b396145..f114bf6a8e13 100644
--- a/lib/swiotlb.c
+++ b/lib/swiotlb.c
@@ -20,7 +20,7 @@
 #include <linux/cache.h>
 #include <linux/dma-mapping.h>
 #include <linux/mm.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/spinlock.h>
 #include <linux/string.h>
 #include <linux/swiotlb.h>
@@ -110,11 +110,11 @@ setup_io_tlb_npages(char *str)
 __setup("swiotlb=", setup_io_tlb_npages);
 /* make io_tlb_overflow tunable too? */
 
-unsigned long swioltb_nr_tbl(void)
+unsigned long swiotlb_nr_tbl(void)
 {
         return io_tlb_nslabs;
 }
-
+EXPORT_SYMBOL_GPL(swiotlb_nr_tbl);
 /* Note that this doesn't work with highmem page */
 static dma_addr_t swiotlb_virt_to_bus(struct device *hwdev,
                                       volatile void *address)
@@ -130,11 +130,9 @@ void swiotlb_print_info(void)
         pstart = virt_to_phys(io_tlb_start);
         pend = virt_to_phys(io_tlb_end);
 
-        printk(KERN_INFO "Placing %luMB software IO TLB between %p - %p\n",
-               bytes >> 20, io_tlb_start, io_tlb_end);
-        printk(KERN_INFO "software IO TLB at phys %#llx - %#llx\n",
-               (unsigned long long)pstart,
-               (unsigned long long)pend);
+        printk(KERN_INFO "software IO TLB [mem %#010llx-%#010llx] (%luMB) mapped at [%p-%p]\n",
+               (unsigned long long)pstart, (unsigned long long)pend - 1,
+               bytes >> 20, io_tlb_start, io_tlb_end - 1);
 }
 
 void __init swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose)
@@ -172,7 +170,7 @@ void __init swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose)
  * Statically reserve bounce buffer space and initialize bounce buffer data
  * structures for the software IO TLB used to implement the DMA API.
  */
-void __init
+static void __init
 swiotlb_init_with_default_size(size_t default_size, int verbose)
 {
         unsigned long bytes;
@@ -208,8 +206,9 @@ swiotlb_init(int verbose)
 int
 swiotlb_late_init_with_default_size(size_t default_size)
 {
-        unsigned long i, bytes, req_nslabs = io_tlb_nslabs;
+        unsigned long bytes, req_nslabs = io_tlb_nslabs;
         unsigned int order;
+        int rc = 0;
 
         if (!io_tlb_nslabs) {
                 io_tlb_nslabs = (default_size >> IO_TLB_SHIFT);
@@ -231,16 +230,32 @@ swiotlb_late_init_with_default_size(size_t default_size)
                 order--;
         }
 
-        if (!io_tlb_start)
-                goto cleanup1;
-
+        if (!io_tlb_start) {
+                io_tlb_nslabs = req_nslabs;
+                return -ENOMEM;
+        }
         if (order != get_order(bytes)) {
                 printk(KERN_WARNING "Warning: only able to allocate %ld MB "
                        "for software IO TLB\n", (PAGE_SIZE << order) >> 20);
                 io_tlb_nslabs = SLABS_PER_PAGE << order;
-                bytes = io_tlb_nslabs << IO_TLB_SHIFT;
         }
+        rc = swiotlb_late_init_with_tbl(io_tlb_start, io_tlb_nslabs);
+        if (rc)
+                free_pages((unsigned long)io_tlb_start, order);
+        return rc;
+}
+
+int
+swiotlb_late_init_with_tbl(char *tlb, unsigned long nslabs)
+{
+        unsigned long i, bytes;
+
+        bytes = nslabs << IO_TLB_SHIFT;
+
+        io_tlb_nslabs = nslabs;
+        io_tlb_start = tlb;
         io_tlb_end = io_tlb_start + bytes;
+
         memset(io_tlb_start, 0, bytes);
 
         /*
@@ -290,10 +305,8 @@ cleanup3:
         io_tlb_list = NULL;
 cleanup2:
         io_tlb_end = NULL;
-        free_pages((unsigned long)io_tlb_start, order);
         io_tlb_start = NULL;
-cleanup1:
-        io_tlb_nslabs = req_nslabs;
+        io_tlb_nslabs = 0;
         return -ENOMEM;
 }
 
@@ -321,6 +334,7 @@ void __init swiotlb_free(void)
                 free_bootmem_late(__pa(io_tlb_start),
                                   PAGE_ALIGN(io_tlb_nslabs << IO_TLB_SHIFT));
         }
+        io_tlb_nslabs = 0;
 }
 
 static int is_swiotlb_buffer(phys_addr_t paddr)
@@ -348,13 +362,12 @@ void swiotlb_bounce(phys_addr_t phys, char *dma_addr, size_t size,
                         sz = min_t(size_t, PAGE_SIZE - offset, size);
 
                         local_irq_save(flags);
-                        buffer = kmap_atomic(pfn_to_page(pfn),
-                                             KM_BOUNCE_READ);
+                        buffer = kmap_atomic(pfn_to_page(pfn));
                         if (dir == DMA_TO_DEVICE)
                                 memcpy(dma_addr, buffer + offset, sz);
                         else
                                 memcpy(buffer + offset, dma_addr, sz);
-                        kunmap_atomic(buffer, KM_BOUNCE_READ);
+                        kunmap_atomic(buffer);
                         local_irq_restore(flags);
 
                         size -= sz;
diff --git a/lib/syscall.c b/lib/syscall.c
index a4f7067f72fa..58710eefeac8 100644
--- a/lib/syscall.c
+++ b/lib/syscall.c
@@ -1,6 +1,6 @@
 #include <linux/ptrace.h>
 #include <linux/sched.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <asm/syscall.h>
 
 static int collect_syscall(struct task_struct *target, long *callno,
diff --git a/lib/test-kstrtox.c b/lib/test-kstrtox.c
index d55769d63cb8..bea3f3fa3f02 100644
--- a/lib/test-kstrtox.c
+++ b/lib/test-kstrtox.c
@@ -11,7 +11,7 @@ struct test_fail {
 };
 
 #define DEFINE_TEST_FAIL(test)  \
-        const struct test_fail test[] __initdata
+        const struct test_fail test[] __initconst
 
 #define DECLARE_TEST_OK(type, test_type)        \
         test_type {                             \
@@ -21,7 +21,7 @@ struct test_fail {
         }
 
 #define DEFINE_TEST_OK(type, test)      \
-        const type test[] __initdata
+        const type test[] __initconst
 
 #define TEST_FAIL(fn, type, fmt, test)                                  \
 {                                                                       \
diff --git a/lib/timerqueue.c b/lib/timerqueue.c
index 191176a43e9a..a382e4a32609 100644
--- a/lib/timerqueue.c
+++ b/lib/timerqueue.c
@@ -22,9 +22,10 @@
  *  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
  */
 
+#include <linux/bug.h>
 #include <linux/timerqueue.h>
 #include <linux/rbtree.h>
-#include <linux/module.h>
+#include <linux/export.h>
 
 /**
  * timerqueue_add - Adds timer to timerqueue.
diff --git a/lib/uuid.c b/lib/uuid.c
index 8fadd7cef46c..52a6fe6387de 100644
--- a/lib/uuid.c
+++ b/lib/uuid.c
@@ -19,7 +19,7 @@
  */
 
 #include <linux/kernel.h>
-#include <linux/module.h>
+#include <linux/export.h>
 #include <linux/uuid.h>
 #include <linux/random.h>
 
diff --git a/lib/vsprintf.c b/lib/vsprintf.c
index d7222a9c8267..39c99fea7c03 100644
--- a/lib/vsprintf.c
+++ b/lib/vsprintf.c
@@ -17,7 +17,7 @@
  */
 
 #include <stdarg.h>
-#include <linux/module.h>
+#include <linux/module.h>       /* for KSYM_SYMBOL_LEN */
 #include <linux/types.h>
 #include <linux/string.h>
 #include <linux/ctype.h>
@@ -31,17 +31,7 @@
 #include <asm/div64.h>
 #include <asm/sections.h>       /* for dereference_function_descriptor() */
 
-static unsigned int simple_guess_base(const char *cp)
-{
-        if (cp[0] == '0') {
-                if (_tolower(cp[1]) == 'x' && isxdigit(cp[2]))
-                        return 16;
-                else
-                        return 8;
-        } else {
-                return 10;
-        }
-}
+#include "kstrtox.h"
 
 /**
  * simple_strtoull - convert a string to an unsigned long long
@@ -51,23 +41,14 @@ static unsigned int simple_guess_base(const char *cp)
  */
 unsigned long long simple_strtoull(const char *cp, char **endp, unsigned int base)
 {
-        unsigned long long result = 0;
+        unsigned long long result;
+        unsigned int rv;
 
-        if (!base)
-                base = simple_guess_base(cp);
+        cp = _parse_integer_fixup_radix(cp, &base);
+        rv = _parse_integer(cp, base, &result);
+        /* FIXME */
+        cp += (rv & ~KSTRTOX_OVERFLOW);
 
-        if (base == 16 && cp[0] == '0' && _tolower(cp[1]) == 'x')
-                cp += 2;
-
-        while (isxdigit(*cp)) {
-                unsigned int value;
-
-                value = isdigit(*cp) ? *cp - '0' : _tolower(*cp) - 'a' + 10;
-                if (value >= base)
-                        break;
-                result = result * base + value;
-                cp++;
-        }
         if (endp)
                 *endp = (char *)cp;
 
@@ -131,104 +112,220 @@ int skip_atoi(const char **s)
 /* Decimal conversion is by far the most typical, and is used
  * for /proc and /sys data. This directly impacts e.g. top performance
  * with many processes running. We optimize it for speed
- * using code from
- * http://www.cs.uiowa.edu/~jones/bcd/decimal.html
- * (with permission from the author, Douglas W. Jones). */
+ * using ideas described at <http://www.cs.uiowa.edu/~jones/bcd/divide.html>
+ * (with permission from the author, Douglas W. Jones).
+ */
 
-/* Formats correctly any integer in [0,99999].
- * Outputs from one to five digits depending on input.
- * On i386 gcc 4.1.2 -O2: ~250 bytes of code. */
+#if BITS_PER_LONG != 32 || BITS_PER_LONG_LONG != 64
+/* Formats correctly any integer in [0, 999999999] */
 static noinline_for_stack
-char *put_dec_trunc(char *buf, unsigned q)
+char *put_dec_full9(char *buf, unsigned q)
 {
-        unsigned d3, d2, d1, d0;
-        d1 = (q>>4) & 0xf;
-        d2 = (q>>8) & 0xf;
-        d3 = (q>>12);
-
-        d0 = 6*(d3 + d2 + d1) + (q & 0xf);
-        q = (d0 * 0xcd) >> 11;
-        d0 = d0 - 10*q;
-        *buf++ = d0 + '0'; /* least significant digit */
-        d1 = q + 9*d3 + 5*d2 + d1;
-        if (d1 != 0) {
-                q = (d1 * 0xcd) >> 11;
-                d1 = d1 - 10*q;
-                *buf++ = d1 + '0'; /* next digit */
-
-                d2 = q + 2*d2;
-                if ((d2 != 0) || (d3 != 0)) {
-                        q = (d2 * 0xd) >> 7;
-                        d2 = d2 - 10*q;
-                        *buf++ = d2 + '0'; /* next digit */
-
-                        d3 = q + 4*d3;
-                        if (d3 != 0) {
-                                q = (d3 * 0xcd) >> 11;
-                                d3 = d3 - 10*q;
-                                *buf++ = d3 + '0';  /* next digit */
-                                if (q != 0)
-                                        *buf++ = q + '0'; /* most sign. digit */
-                        }
-                }
-        }
+        unsigned r;
 
+        /*
+         * Possible ways to approx. divide by 10
+         * (x * 0x1999999a) >> 32 x < 1073741829 (multiply must be 64-bit)
+         * (x * 0xcccd) >> 19     x <      81920 (x < 262149 when 64-bit mul)
+         * (x * 0x6667) >> 18     x <      43699
+         * (x * 0x3334) >> 17     x <      16389
+         * (x * 0x199a) >> 16     x <      16389
+         * (x * 0x0ccd) >> 15     x <      16389
+         * (x * 0x0667) >> 14     x <       2739
+         * (x * 0x0334) >> 13     x <       1029
+         * (x * 0x019a) >> 12     x <       1029
+         * (x * 0x00cd) >> 11     x <       1029 shorter code than * 0x67 (on i386)
+         * (x * 0x0067) >> 10     x <        179
+         * (x * 0x0034) >>  9     x <         69 same
+         * (x * 0x001a) >>  8     x <         69 same
+         * (x * 0x000d) >>  7     x <         69 same, shortest code (on i386)
+         * (x * 0x0007) >>  6     x <         19
+         * See <http://www.cs.uiowa.edu/~jones/bcd/divide.html>
+         */
+        r      = (q * (uint64_t)0x1999999a) >> 32;
+        *buf++ = (q - 10 * r) + '0'; /* 1 */
+        q      = (r * (uint64_t)0x1999999a) >> 32;
+        *buf++ = (r - 10 * q) + '0'; /* 2 */
+        r      = (q * (uint64_t)0x1999999a) >> 32;
+        *buf++ = (q - 10 * r) + '0'; /* 3 */
+        q      = (r * (uint64_t)0x1999999a) >> 32;
+        *buf++ = (r - 10 * q) + '0'; /* 4 */
+        r      = (q * (uint64_t)0x1999999a) >> 32;
+        *buf++ = (q - 10 * r) + '0'; /* 5 */
+        /* Now value is under 10000, can avoid 64-bit multiply */
+        q      = (r * 0x199a) >> 16;
+        *buf++ = (r - 10 * q)  + '0'; /* 6 */
+        r      = (q * 0xcd) >> 11;
+        *buf++ = (q - 10 * r)  + '0'; /* 7 */
+        q      = (r * 0xcd) >> 11;
+        *buf++ = (r - 10 * q) + '0'; /* 8 */
+        *buf++ = q + '0'; /* 9 */
         return buf;
 }
-/* Same with if's removed. Always emits five digits */
+#endif
+
+/* Similar to above but do not pad with zeros.
+ * Code can be easily arranged to print 9 digits too, but our callers
+ * always call put_dec_full9() instead when the number has 9 decimal digits.
+ */
 static noinline_for_stack
-char *put_dec_full(char *buf, unsigned q)
+char *put_dec_trunc8(char *buf, unsigned r)
 {
-        /* BTW, if q is in [0,9999], 8-bit ints will be enough, */
-        /* but anyway, gcc produces better code with full-sized ints */
-        unsigned d3, d2, d1, d0;
-        d1 = (q>>4) & 0xf;
-        d2 = (q>>8) & 0xf;
-        d3 = (q>>12);
+        unsigned q;
 
-        /*
-         * Possible ways to approx. divide by 10
-         * gcc -O2 replaces multiply with shifts and adds
-         * (x * 0xcd) >> 11: 11001101 - shorter code than * 0x67 (on i386)
-         * (x * 0x67) >> 10:  1100111
-         * (x * 0x34) >> 9:    110100 - same
-         * (x * 0x1a) >> 8:     11010 - same
-         * (x * 0x0d) >> 7:      1101 - same, shortest code (on i386)
-         */
-        d0 = 6*(d3 + d2 + d1) + (q & 0xf);
-        q = (d0 * 0xcd) >> 11;
-        d0 = d0 - 10*q;
-        *buf++ = d0 + '0';
-        d1 = q + 9*d3 + 5*d2 + d1;
-                q = (d1 * 0xcd) >> 11;
-                d1 = d1 - 10*q;
-                *buf++ = d1 + '0';
-
-                d2 = q + 2*d2;
-                        q = (d2 * 0xd) >> 7;
-                        d2 = d2 - 10*q;
-                        *buf++ = d2 + '0';
-
-                        d3 = q + 4*d3;
-                                q = (d3 * 0xcd) >> 11; /* - shorter code */
-                                /* q = (d3 * 0x67) >> 10; - would also work */
-                                d3 = d3 - 10*q;
-                                *buf++ = d3 + '0';
-                                        *buf++ = q + '0';
+        /* Copy of previous function's body with added early returns */
+        while (r >= 10000) {
+                q = r + '0';
+                r  = (r * (uint64_t)0x1999999a) >> 32;
+                *buf++ = q - 10*r;
+        }
 
+        q      = (r * 0x199a) >> 16;    /* r <= 9999 */
+        *buf++ = (r - 10 * q)  + '0';
+        if (q == 0)
+                return buf;
+        r      = (q * 0xcd) >> 11;      /* q <= 999 */
+        *buf++ = (q - 10 * r)  + '0';
+        if (r == 0)
+                return buf;
+        q      = (r * 0xcd) >> 11;      /* r <= 99 */
+        *buf++ = (r - 10 * q) + '0';
+        if (q == 0)
+                return buf;
+        *buf++ = q + '0';                /* q <= 9 */
         return buf;
 }
-/* No inlining helps gcc to use registers better */
+
+/* There are two algorithms to print larger numbers.
+ * One is generic: divide by 1000000000 and repeatedly print
+ * groups of (up to) 9 digits. It's conceptually simple,
+ * but requires a (unsigned long long) / 1000000000 division.
+ *
+ * Second algorithm splits 64-bit unsigned long long into 16-bit chunks,
+ * manipulates them cleverly and generates groups of 4 decimal digits.
+ * It so happens that it does NOT require long long division.
+ *
+ * If long is > 32 bits, division of 64-bit values is relatively easy,
+ * and we will use the first algorithm.
+ * If long long is > 64 bits (strange architecture with VERY large long long),
+ * second algorithm can't be used, and we again use the first one.
+ *
+ * Else (if long is 32 bits and long long is 64 bits) we use second one.
+ */
+
+#if BITS_PER_LONG != 32 || BITS_PER_LONG_LONG != 64
+
+/* First algorithm: generic */
+
+static
+char *put_dec(char *buf, unsigned long long n)
+{
+        if (n >= 100*1000*1000) {
+                while (n >= 1000*1000*1000)
+                        buf = put_dec_full9(buf, do_div(n, 1000*1000*1000));
+                if (n >= 100*1000*1000)
+                        return put_dec_full9(buf, n);
+        }
+        return put_dec_trunc8(buf, n);
+}
+
+#else
+
+/* Second algorithm: valid only for 64-bit long longs */
+
+/* See comment in put_dec_full9 for choice of constants */
 static noinline_for_stack
-char *put_dec(char *buf, unsigned long long num)
+void put_dec_full4(char *buf, unsigned q)
+{
+        unsigned r;
+        r      = (q * 0xccd) >> 15;
+        buf[0] = (q - 10 * r) + '0';
+        q      = (r * 0xcd) >> 11;
+        buf[1] = (r - 10 * q)  + '0';
+        r      = (q * 0xcd) >> 11;
+        buf[2] = (q - 10 * r)  + '0';
+        buf[3] = r + '0';
+}
+
+/*
+ * Call put_dec_full4 on x % 10000, return x / 10000.
+ * The approximation x/10000 == (x * 0x346DC5D7) >> 43
+ * holds for all x < 1,128,869,999.  The largest value this
+ * helper will ever be asked to convert is 1,125,520,955.
+ * (d1 in the put_dec code, assuming n is all-ones).
+ */
+static
+unsigned put_dec_helper4(char *buf, unsigned x)
+{
+        uint32_t q = (x * (uint64_t)0x346DC5D7) >> 43;
+
+        put_dec_full4(buf, x - q * 10000);
+        return q;
+}
+
+/* Based on code by Douglas W. Jones found at
+ * <http://www.cs.uiowa.edu/~jones/bcd/decimal.html#sixtyfour>
+ * (with permission from the author).
+ * Performs no 64-bit division and hence should be fast on 32-bit machines.
+ */
+static
+char *put_dec(char *buf, unsigned long long n)
+{
+        uint32_t d3, d2, d1, q, h;
+
+        if (n < 100*1000*1000)
+                return put_dec_trunc8(buf, n);
+
+        d1  = ((uint32_t)n >> 16); /* implicit "& 0xffff" */
+        h   = (n >> 32);
+        d2  = (h      ) & 0xffff;
+        d3  = (h >> 16); /* implicit "& 0xffff" */
+
+        q   = 656 * d3 + 7296 * d2 + 5536 * d1 + ((uint32_t)n & 0xffff);
+        q = put_dec_helper4(buf, q);
+
+        q += 7671 * d3 + 9496 * d2 + 6 * d1;
+        q = put_dec_helper4(buf+4, q);
+
+        q += 4749 * d3 + 42 * d2;
+        q = put_dec_helper4(buf+8, q);
+
+        q += 281 * d3;
+        buf += 12;
+        if (q)
+                buf = put_dec_trunc8(buf, q);
+        else while (buf[-1] == '0')
+                --buf;
+
+        return buf;
+}
+
+#endif
+
+/*
+ * Convert passed number to decimal string.
+ * Returns the length of string.  On buffer overflow, returns 0.
+ *
+ * If speed is not important, use snprintf(). It's easy to read the code.
+ */
+int num_to_str(char *buf, int size, unsigned long long num)
 {
-        while (1) {
-                unsigned rem;
-                if (num < 100000)
-                        return put_dec_trunc(buf, num);
-                rem = do_div(num, 100000);
-                buf = put_dec_full(buf, rem);
+        char tmp[sizeof(num) * 3];
+        int idx, len;
+
+        /* put_dec() may work incorrectly for num = 0 (generate "", not "0") */
+        if (num <= 9) {
+                tmp[0] = '0' + num;
+                len = 1;
+        } else {
+                len = put_dec(tmp, num) - tmp;
         }
+
+        if (len > size)
+                return 0;
+        for (idx = 0; idx < len; ++idx)
+                buf[idx] = tmp[len - idx - 1];
+        return len;
 }
 
 #define ZEROPAD 1               /* pad with zero */
@@ -283,6 +380,7 @@ char *number(char *buf, char *end, unsigned long long num,
         char locase;
         int need_pfx = ((spec.flags & SPECIAL) && spec.base != 10);
         int i;
+        bool is_zero = num == 0LL;
 
         /* locase = 0 or 0x20. ORing digits or letters with 'locase'
          * produces same digits or (maybe lowercased) letters */
@@ -304,15 +402,16 @@ char *number(char *buf, char *end, unsigned long long num,
                 }
         }
         if (need_pfx) {
-                spec.field_width--;
                 if (spec.base == 16)
+                        spec.field_width -= 2;
+                else if (!is_zero)
                         spec.field_width--;
         }
 
         /* generate full string in tmp[], in reverse order */
         i = 0;
-        if (num == 0)
-                tmp[i++] = '0';
+        if (num < spec.base)
+                tmp[i++] = digits[num] | locase;
         /* Generic code, for any base:
         else do {
                 tmp[i++] = (digits[do_div(num,base)] | locase);
@@ -352,9 +451,11 @@ char *number(char *buf, char *end, unsigned long long num,
         }
         /* "0x" / "0" prefix */
         if (need_pfx) {
-                if (buf < end)
-                        *buf = '0';
-                ++buf;
+                if (spec.base == 16 || !is_zero) {
+                        if (buf < end)
+                                *buf = '0';
+                        ++buf;
+                }
                 if (spec.base == 16) {
                         if (buf < end)
                                 *buf = ('X' | locase);
@@ -435,7 +536,7 @@ char *symbol_string(char *buf, char *end, void *ptr,
         else if (ext != 'f' && ext != 's')
                 sprint_symbol(sym, value);
         else
-                kallsyms_lookup(value, NULL, NULL, NULL, sym);
+                sprint_symbol_no_offset(sym, value);
 
         return string(buf, end, sym, spec);
 #else
@@ -551,6 +652,50 @@ char *resource_string(char *buf, char *end, struct resource *res,
 }
 
 static noinline_for_stack
+char *hex_string(char *buf, char *end, u8 *addr, struct printf_spec spec,
+                 const char *fmt)
+{
+        int i, len = 1;         /* if we pass '%ph[CDN]', field witdh remains
+                                   negative value, fallback to the default */
+        char separator;
+
+        if (spec.field_width == 0)
+                /* nothing to print */
+                return buf;
+
+        if (ZERO_OR_NULL_PTR(addr))
+                /* NULL pointer */
+                return string(buf, end, NULL, spec);
+
+        switch (fmt[1]) {
+        case 'C':
+                separator = ':';
+                break;
+        case 'D':
+                separator = '-';
+                break;
+        case 'N':
+                separator = 0;
+                break;
+        default:
+                separator = ' ';
+                break;
+        }
+
+        if (spec.field_width > 0)
+                len = min_t(int, spec.field_width, 64);
+
+        for (i = 0; i < len && buf < end - 1; i++) {
+                buf = hex_byte_pack(buf, addr[i]);
+
+                if (buf < end && separator && i != len - 1)
+                        *buf++ = separator;
+        }
+
+        return buf;
+}
+
+static noinline_for_stack
 char *mac_address_string(char *buf, char *end, u8 *addr,
                          struct printf_spec spec, const char *fmt)
 {
@@ -558,15 +703,28 @@ char *mac_address_string(char *buf, char *end, u8 *addr,
         char *p = mac_addr;
         int i;
         char separator;
+        bool reversed = false;
 
-        if (fmt[1] == 'F') {            /* FDDI canonical format */
+        switch (fmt[1]) {
+        case 'F':
                 separator = '-';
-        } else {
+                break;
+
+        case 'R':
+                reversed = true;
+                /* fall through */
+
+        default:
                 separator = ':';
+                break;
         }
 
         for (i = 0; i < 6; i++) {
-                p = pack_hex_byte(p, addr[i]);
+                if (reversed)
+                        p = hex_byte_pack(p, addr[5 - i]);
+                else
+                        p = hex_byte_pack(p, addr[i]);
+
                 if (fmt[0] == 'M' && i != 5)
                         *p++ = separator;
         }
@@ -606,7 +764,7 @@ char *ip4_string(char *p, const u8 *addr, const char *fmt)
         }
         for (i = 0; i < 4; i++) {
                 char temp[3];   /* hold each IP quad in reverse order */
-                int digits = put_dec_trunc(temp, addr[index]) - temp;
+                int digits = put_dec_trunc8(temp, addr[index]) - temp;
                 if (leading_zeros) {
                         if (digits < 3)
                                 *p++ = '0';
@@ -686,13 +844,13 @@ char *ip6_compressed_string(char *p, const char *addr)
                 lo = word & 0xff;
                 if (hi) {
                         if (hi > 0x0f)
-                                p = pack_hex_byte(p, hi);
+                                p = hex_byte_pack(p, hi);
                         else
                                 *p++ = hex_asc_lo(hi);
-                        p = pack_hex_byte(p, lo);
+                        p = hex_byte_pack(p, lo);
                 }
                 else if (lo > 0x0f)
-                        p = pack_hex_byte(p, lo);
+                        p = hex_byte_pack(p, lo);
                 else
                         *p++ = hex_asc_lo(lo);
                 needcolon = true;
@@ -714,8 +872,8 @@ char *ip6_string(char *p, const char *addr, const char *fmt)
         int i;
 
         for (i = 0; i < 8; i++) {
-                p = pack_hex_byte(p, *addr++);
-                p = pack_hex_byte(p, *addr++);
+                p = hex_byte_pack(p, *addr++);
+                p = hex_byte_pack(p, *addr++);
                 if (fmt[0] == 'I' && i != 7)
                         *p++ = ':';
         }
@@ -773,7 +931,7 @@ char *uuid_string(char *buf, char *end, const u8 *addr,
         }
 
         for (i = 0; i < 16; i++) {
-                p = pack_hex_byte(p, addr[index[i]]);
+                p = hex_byte_pack(p, addr[index[i]]);
                 switch (i) {
                 case 3:
                 case 5:
@@ -796,6 +954,18 @@ char *uuid_string(char *buf, char *end, const u8 *addr,
         return string(buf, end, uuid, spec);
 }
 
+static
+char *netdev_feature_string(char *buf, char *end, const u8 *addr,
+                      struct printf_spec spec)
+{
+        spec.flags |= SPECIAL | SMALL | ZEROPAD;
+        if (spec.field_width == -1)
+                spec.field_width = 2 + 2 * sizeof(netdev_features_t);
+        spec.base = 16;
+
+        return number(buf, end, *(const netdev_features_t *)addr, spec);
+}
+
 int kptr_restrict __read_mostly;
 
 /*
@@ -817,6 +987,7 @@ int kptr_restrict __read_mostly;
  * - 'm' For a 6-byte MAC address, it prints the hex address without colons
  * - 'MF' For a 6-byte MAC FDDI address, it prints the address
  *       with a dash-separated hex notation
+ * - '[mM]R' For a 6-byte MAC address, Reverse order (Bluetooth)
  * - 'I' [46] for IPv4/IPv6 addresses printed in the usual way
  *       IPv4 uses dot-separated decimal without leading 0's (1.2.3.4)
  *       IPv6 uses colon separated network-order 16 bit hex with leading 0's
@@ -843,6 +1014,14 @@ int kptr_restrict __read_mostly;
  *       Do not use this feature without some mechanism to verify the
  *       correctness of the format string and va_list arguments.
  * - 'K' For a kernel pointer that should be hidden from unprivileged users
+ * - 'NF' For a netdev_features_t
+ * - 'h[CDN]' For a variable-length buffer, it prints it as a hex string with
+ *            a certain separator (' ' by default):
+ *              C colon
+ *              D dash
+ *              N no separator
+ *            The maximum supported length is 64 bytes of the input. Consider
+ *            to use print_hex_dump() for the larger input.
  *
  * Note: The difference between 'S' and 'F' is that on ia64 and ppc64
  * function pointers are really function descriptors, which contain a
@@ -852,13 +1031,15 @@ static noinline_for_stack
 char *pointer(const char *fmt, char *buf, char *end, void *ptr,
               struct printf_spec spec)
 {
+        int default_width = 2 * sizeof(void *) + (spec.flags & SPECIAL ? 2 : 0);
+
         if (!ptr && *fmt != 'K') {
                 /*
                  * Print (null) with the same width as a pointer so it makes
                  * tabular output look nice.
                  */
                 if (spec.field_width == -1)
-                        spec.field_width = 2 * sizeof(void *);
+                        spec.field_width = default_width;
                 return string(buf, end, "(null)", spec);
         }
 
@@ -874,9 +1055,12 @@ char *pointer(const char *fmt, char *buf, char *end, void *ptr,
         case 'R':
         case 'r':
                 return resource_string(buf, end, ptr, spec, fmt);
+        case 'h':
+                return hex_string(buf, end, ptr, spec, fmt);
         case 'M':                       /* Colon separated: 00:01:02:03:04:05 */
         case 'm':                       /* Contiguous: 000102030405 */
-                                        /* [mM]F (FDDI, bit reversed) */
+                                        /* [mM]F (FDDI) */
+                                        /* [mM]R (Reverse order; Bluetooth) */
                 return mac_address_string(buf, end, ptr, spec, fmt);
         case 'I':                       /* Formatted IP supported
                                          * 4:   1.2.3.4
@@ -897,17 +1081,24 @@ char *pointer(const char *fmt, char *buf, char *end, void *ptr,
         case 'U':
                 return uuid_string(buf, end, ptr, spec, fmt);
         case 'V':
-                return buf + vsnprintf(buf, end > buf ? end - buf : 0,
-                                       ((struct va_format *)ptr)->fmt,
-                                       *(((struct va_format *)ptr)->va));
+                {
+                        va_list va;
+
+                        va_copy(va, *((struct va_format *)ptr)->va);
+                        buf += vsnprintf(buf, end > buf ? end - buf : 0,
+                                         ((struct va_format *)ptr)->fmt, va);
+                        va_end(va);
+                        return buf;
+                }
         case 'K':
                 /*
                  * %pK cannot be used in IRQ context because its test
                  * for CAP_SYSLOG would be meaningless.
                  */
-                if (in_irq() || in_serving_softirq() || in_nmi()) {
+                if (kptr_restrict && (in_irq() || in_serving_softirq() ||
+                                      in_nmi())) {
                         if (spec.field_width == -1)
-                                spec.field_width = 2 * sizeof(void *);
+                                spec.field_width = default_width;
                         return string(buf, end, "pK-error", spec);
                 }
                 if (!((kptr_restrict == 0) ||
@@ -915,10 +1106,16 @@ char *pointer(const char *fmt, char *buf, char *end, void *ptr,
                        has_capability_noaudit(current, CAP_SYSLOG))))
                         ptr = NULL;
                 break;
+        case 'N':
+                switch (fmt[1]) {
+                case 'F':
+                        return netdev_feature_string(buf, end, ptr, spec);
+                }
+                break;
         }
         spec.flags |= SMALL;
         if (spec.field_width == -1) {
-                spec.field_width = 2 * sizeof(void *);
+                spec.field_width = default_width;
                 spec.flags |= ZEROPAD;
         }
         spec.base = 16;
@@ -1141,7 +1338,10 @@ qualifier:
  * %pR output the address range in a struct resource with decoded flags
  * %pr output the address range in a struct resource with raw flags
  * %pM output a 6-byte MAC address with colons
+ * %pMR output a 6-byte MAC address with colons in reversed order
+ * %pMF output a 6-byte MAC address with dashes
  * %pm output a 6-byte MAC address without colons
+ * %pmR output a 6-byte MAC address without colons in reversed order
  * %pI4 print an IPv4 address without leading zeros
  * %pi4 print an IPv4 address with leading zeros
  * %pI6 print an IPv6 address with colons
@@ -1149,8 +1349,12 @@ qualifier:
  * %pI6c print an IPv6 address as specified by RFC 5952
  * %pU[bBlL] print a UUID/GUID in big or little endian using lower or upper
  *   case.
+ * %*ph[CDN] a variable-length hex string with a separator (supports up to 64
+ *           bytes of the input)
  * %n is ignored
  *
+ * ** Please update Documentation/printk-formats.txt when making changes **
+ *
  * The return value is the number of characters which would
  * be generated for the given input, excluding the trailing
  * '\0', as per ISO C99. If you want to have the exact
@@ -1813,7 +2017,7 @@ int vsscanf(const char *buf, const char *fmt, va_list args)
         s16 field_width;
         bool is_sign;
 
-        while (*fmt && *str) {
+        while (*fmt) {
                 /* skip any white space in format */
                 /* white space in format matchs any amount of
                  * white space, including none, in the input.
@@ -1838,6 +2042,8 @@ int vsscanf(const char *buf, const char *fmt, va_list args)
                  * advance both strings to next white space
                  */
                 if (*fmt == '*') {
+                        if (!*str)
+                                break;
                         while (!isspace(*fmt) && *fmt != '%' && *fmt)
                                 fmt++;
                         while (!isspace(*str) && *str)
@@ -1866,7 +2072,17 @@ int vsscanf(const char *buf, const char *fmt, va_list args)
                         }
                 }
 
-                if (!*fmt || !*str)
+                if (!*fmt)
+                        break;
+
+                if (*fmt == 'n') {
+                        /* return number of characters read so far */
+                        *va_arg(args, int *) = str - buf;
+                        ++fmt;
+                        continue;
+                }
+
+                if (!*str)
                         break;
 
                 base = 10;
@@ -1899,13 +2115,6 @@ int vsscanf(const char *buf, const char *fmt, va_list args)
                         num++;
                 }
                 continue;
-                case 'n':
-                        /* return number of characters read so far */
-                {
-                        int *i = (int *)va_arg(args, int*);
-                        *i = str - buf;
-                }
-                continue;
                 case 'o':
                         base = 8;
                         break;
@@ -2006,16 +2215,6 @@ int vsscanf(const char *buf, const char *fmt, va_list args)
                 str = next;
         }
 
-        /*
-         * Now we've come all the way through so either the input string or the
-         * format ended. In the former case, there can be a %n at the current
-         * position in the format that needs to be filled.
-         */
-        if (*fmt == '%' && *(fmt + 1) == 'n') {
-                int *p = (int *)va_arg(args, int *);
-                *p = str - buf;
-        }
-
         return num;
 }
 EXPORT_SYMBOL(vsscanf);
diff --git a/lib/xz/xz_dec_bcj.c b/lib/xz/xz_dec_bcj.c
index e51e2558ca9d..a768e6d28bbb 100644
--- a/lib/xz/xz_dec_bcj.c
+++ b/lib/xz/xz_dec_bcj.c
@@ -441,8 +441,12 @@ XZ_EXTERN enum xz_ret xz_dec_bcj_run(struct xz_dec_bcj *s,
          * next filter in the chain. Apply the BCJ filter on the new data
          * in the output buffer. If everything cannot be filtered, copy it
          * to temp and rewind the output buffer position accordingly.
+         *
+         * This needs to be always run when temp.size == 0 to handle a special
+         * case where the output buffer is full and the next filter has no
+         * more output coming but hasn't returned XZ_STREAM_END yet.
          */
-        if (s->temp.size < b->out_size - b->out_pos) {
+        if (s->temp.size < b->out_size - b->out_pos || s->temp.size == 0) {
                 out_start = b->out_pos;
                 memcpy(b->out + b->out_pos, s->temp.buf, s->temp.size);
                 b->out_pos += s->temp.size;
@@ -465,16 +469,25 @@ XZ_EXTERN enum xz_ret xz_dec_bcj_run(struct xz_dec_bcj *s,
                 s->temp.size = b->out_pos - out_start;
                 b->out_pos -= s->temp.size;
                 memcpy(s->temp.buf, b->out + b->out_pos, s->temp.size);
+
+                /*
+                 * If there wasn't enough input to the next filter to fill
+                 * the output buffer with unfiltered data, there's no point
+                 * to try decoding more data to temp.
+                 */
+                if (b->out_pos + s->temp.size < b->out_size)
+                        return XZ_OK;
         }
 
         /*
-         * If we have unfiltered data in temp, try to fill by decoding more
-         * data from the next filter. Apply the BCJ filter on temp. Then we
-         * hopefully can fill the actual output buffer by copying filtered
-         * data from temp. A mix of filtered and unfiltered data may be left
-         * in temp; it will be taken care on the next call to this function.
+         * We have unfiltered data in temp. If the output buffer isn't full
+         * yet, try to fill the temp buffer by decoding more data from the
+         * next filter. Apply the BCJ filter on temp. Then we hopefully can
+         * fill the actual output buffer by copying filtered data from temp.
+         * A mix of filtered and unfiltered data may be left in temp; it will
+         * be taken care on the next call to this function.
          */
-        if (s->temp.size > 0) {
+        if (b->out_pos < b->out_size) {
                 /* Make b->out{,_pos,_size} temporarily point to s->temp. */
                 s->out = b->out;
                 s->out_pos = b->out_pos;