Creation of Cybook 2416 (actually Gen4) repository

lib/Kconfig

@@ -0,0 +1,114 @@
+#
+# Library configuration
+#
+
+menu "Library routines"
+
+config BITREVERSE
+	tristate
+
+config CRC_CCITT
+	tristate "CRC-CCITT functions"
+	help
+	  This option is provided for the case where no in-kernel-tree
+	  modules require CRC-CCITT functions, but a module built outside
+	  the kernel tree does. Such modules that use library CRC-CCITT
+	  functions require M here.
+
+config CRC16
+	tristate "CRC16 functions"
+	help
+	  This option is provided for the case where no in-kernel-tree
+	  modules require CRC16 functions, but a module built outside
+	  the kernel tree does. Such modules that use library CRC16
+	  functions require M here.
+
+config CRC32
+	tristate "CRC32 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.
+
+config LIBCRC32C
+	tristate "CRC32c (Castagnoli, et al) Cyclic Redundancy-Check"
+	help
+	  This option is provided for the case where no in-kernel-tree
+	  modules require CRC32c functions, but a module built outside the
+	  kernel tree does. Such modules that use library CRC32c functions
+	  require M here.  See Castagnoli93.
+	  Module will be libcrc32c.
+
+config AUDIT_GENERIC
+	bool
+	depends on AUDIT && !AUDIT_ARCH
+	default y
+
+#
+# compression support is select'ed if needed
+#
+config ZLIB_INFLATE
+	tristate
+
+config ZLIB_DEFLATE
+	tristate
+
+#
+# Generic allocator support is selected if needed
+#
+config GENERIC_ALLOCATOR
+	boolean
+
+#
+# reed solomon support is select'ed if needed
+#
+config REED_SOLOMON
+	tristate
+	
+config REED_SOLOMON_ENC8
+	boolean
+
+config REED_SOLOMON_DEC8
+	boolean
+
+config REED_SOLOMON_ENC16
+	boolean
+
+config REED_SOLOMON_DEC16
+	boolean
+
+#
+# Textsearch support is select'ed if needed
+#
+config TEXTSEARCH
+	boolean
+
+config TEXTSEARCH_KMP
+	tristate
+
+config TEXTSEARCH_BM
+	tristate
+
+config TEXTSEARCH_FSM
+	tristate
+
+#
+# plist support is select#ed if needed
+#
+config PLIST
+	boolean
+
+config HAS_IOMEM
+	boolean
+	depends on !NO_IOMEM
+	default y
+
+config HAS_IOPORT
+	boolean
+	depends on HAS_IOMEM && !NO_IOPORT
+	default y
+
+endmenu

lib/Kconfig.debug

@@ -0,0 +1,460 @@
+
+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.
+
+config ENABLE_MUST_CHECK
+	bool "Enable __must_check logic"
+	default y
+	help
+	  Enable the __must_check logic in the kernel build.  Disable this to
+	  suppress the "warning: ignoring return value of 'foo', declared with
+	  attribute warn_unused_result" messages.
+
+config MAGIC_SYSRQ
+	bool "Magic SysRq key"
+	depends on !UML
+	help
+	  If you say Y here, you will have some control over the system even
+	  if the system crashes for example during kernel debugging (e.g., you
+	  will be able to flush the buffer cache to disk, reboot the system
+	  immediately or dump some status information). This is accomplished
+	  by pressing various keys while holding SysRq (Alt+PrintScreen). It
+	  also works on a serial console (on PC hardware at least), if you
+	  send a BREAK and then within 5 seconds a command keypress. The
+	  keys are documented in <file:Documentation/sysrq.txt>. Don't say Y
+	  unless you really know what this hack does.
+
+config UNUSED_SYMBOLS
+	bool "Enable unused/obsolete exported symbols"
+	default y if X86
+	help
+	  Unused but exported symbols make the kernel needlessly bigger.  For
+	  that reason most of these unused exports will soon be removed.  This
+	  option is provided temporarily to provide a transition period in case
+	  some external kernel module needs one of these symbols anyway. If you
+	  encounter such a case in your module, consider if you are actually
+	  using the right API.  (rationale: since nobody in the kernel is using
+	  this in a module, there is a pretty good chance it's actually the
+	  wrong interface to use).  If you really need the symbol, please send a
+	  mail to the linux kernel mailing list mentioning the symbol and why
+	  you really need it, and what the merge plan to the mainline kernel for
+	  your module is.
+
+config DEBUG_FS
+	bool "Debug Filesystem"
+	depends on SYSFS
+	help
+	  debugfs is a virtual file system that kernel developers use to put
+	  debugging files into.  Enable this option to be able to read and
+	  write to these files.
+
+	  If unsure, say N.
+
+config HEADERS_CHECK
+	bool "Run 'make headers_check' when building vmlinux"
+	depends on !UML
+	help
+	  This option will extract the user-visible kernel headers whenever
+	  building the kernel, and will run basic sanity checks on them to
+	  ensure that exported files do not attempt to include files which
+	  were not exported, etc.
+
+	  If you're making modifications to header files which are
+	  relevant for userspace, say 'Y', and check the headers
+	  exported to $(INSTALL_HDR_PATH) (usually 'usr/include' in
+	  your build tree), to make sure they're suitable.
+
+config DEBUG_KERNEL
+	bool "Kernel debugging"
+	help
+	  Say Y here if you are developing drivers or trying to debug and
+	  identify kernel problems.
+
+config DEBUG_SHIRQ
+	bool "Debug shared IRQ handlers"
+	depends on DEBUG_KERNEL && GENERIC_HARDIRQS
+	help
+	  Enable this to generate a spurious interrupt as soon as a shared
+	  interrupt handler is registered, and just before one is deregistered.
+	  Drivers ought to be able to handle interrupts coming in at those
+	  points; some don't and need to be caught.
+
+config LOG_BUF_SHIFT
+	int "Kernel log buffer size (16 => 64KB, 17 => 128KB)" if DEBUG_KERNEL
+	range 12 21
+	default 17 if S390 || LOCKDEP
+	default 16 if X86_NUMAQ || IA64
+	default 15 if SMP
+	default 14
+	help
+	  Select kernel log buffer size as a power of 2.
+	  Defaults and Examples:
+	  	     17 => 128 KB for S/390
+		     16 => 64 KB for x86 NUMAQ or IA-64
+	             15 => 32 KB for SMP
+	             14 => 16 KB for uniprocessor
+		     13 =>  8 KB
+		     12 =>  4 KB
+
+config DETECT_SOFTLOCKUP
+	bool "Detect Soft Lockups"
+	depends on DEBUG_KERNEL && !S390
+	default y
+	help
+	  Say Y here to enable the kernel to detect "soft lockups",
+	  which are bugs that cause the kernel to loop in kernel
+	  mode for more than 10 seconds, without giving other tasks a
+	  chance to run.
+
+	  When a soft-lockup is detected, the kernel will print the
+	  current stack trace (which you should report), but the
+	  system will stay locked up. This feature has negligible
+	  overhead.
+
+	  (Note that "hard lockups" are separate type of bugs that
+	   can be detected via the NMI-watchdog, on platforms that
+	   support it.)
+
+config SCHED_DEBUG
+	bool "Collect scheduler debugging info"
+	depends on DEBUG_KERNEL && PROC_FS
+	default y
+	help
+	  If you say Y here, the /proc/sched_debug file will be provided
+	  that can help debug the scheduler. The runtime overhead of this
+	  option is minimal.
+
+config SCHEDSTATS
+	bool "Collect scheduler statistics"
+	depends on DEBUG_KERNEL && PROC_FS
+	help
+	  If you say Y here, additional code will be inserted into the
+	  scheduler and related routines to collect statistics about
+	  scheduler behavior and provide them in /proc/schedstat.  These
+	  stats may be useful for both tuning and debugging the scheduler
+	  If you aren't debugging the scheduler or trying to tune a specific
+	  application, you can say N to avoid the very slight overhead
+	  this adds.
+
+config TIMER_STATS
+	bool "Collect kernel timers statistics"
+	depends on DEBUG_KERNEL && PROC_FS
+	help
+	  If you say Y here, additional code will be inserted into the
+	  timer routines to collect statistics about kernel timers being
+	  reprogrammed. The statistics can be read from /proc/timer_stats.
+	  The statistics collection is started by writing 1 to /proc/timer_stats,
+	  writing 0 stops it. This feature is useful to collect information
+	  about timer usage patterns in kernel and userspace. This feature
+	  is lightweight if enabled in the kernel config but not activated
+	  (it defaults to deactivated on bootup and will only be activated
+	  if some application like powertop activates it explicitly).
+
+config DEBUG_SLAB
+	bool "Debug slab memory allocations"
+	depends on DEBUG_KERNEL && SLAB
+	help
+	  Say Y here to have the kernel do limited verification on memory
+	  allocation as well as poisoning memory on free to catch use of freed
+	  memory. This can make kmalloc/kfree-intensive workloads much slower.
+
+config DEBUG_SLAB_LEAK
+	bool "Memory leak debugging"
+	depends on DEBUG_SLAB
+
+config DEBUG_PREEMPT
+	bool "Debug preemptible kernel"
+	depends on DEBUG_KERNEL && PREEMPT && TRACE_IRQFLAGS_SUPPORT
+	default y
+	help
+	  If you say Y here then the kernel will use a debug variant of the
+	  commonly used smp_processor_id() function and will print warnings
+	  if kernel code uses it in a preemption-unsafe way. Also, the kernel
+	  will detect preemption count underflows.
+
+config DEBUG_RT_MUTEXES
+	bool "RT Mutex debugging, deadlock detection"
+	depends on DEBUG_KERNEL && RT_MUTEXES
+	help
+	 This allows rt mutex semantics violations and rt mutex related
+	 deadlocks (lockups) to be detected and reported automatically.
+
+config DEBUG_PI_LIST
+	bool
+	default y
+	depends on DEBUG_RT_MUTEXES
+
+config RT_MUTEX_TESTER
+	bool "Built-in scriptable tester for rt-mutexes"
+	depends on DEBUG_KERNEL && RT_MUTEXES
+	help
+	  This option enables a rt-mutex tester.
+
+config DEBUG_SPINLOCK
+	bool "Spinlock and rw-lock debugging: basic checks"
+	depends on DEBUG_KERNEL
+	help
+	  Say Y here and build SMP to catch missing spinlock initialization
+	  and certain other kinds of spinlock errors commonly made.  This is
+	  best used in conjunction with the NMI watchdog so that spinlock
+	  deadlocks are also debuggable.
+
+config DEBUG_MUTEXES
+	bool "Mutex debugging: basic checks"
+	depends on DEBUG_KERNEL
+	help
+	 This feature allows mutex semantics violations to be detected and
+	 reported.
+
+config DEBUG_LOCK_ALLOC
+	bool "Lock debugging: detect incorrect freeing of live locks"
+	depends on DEBUG_KERNEL && TRACE_IRQFLAGS_SUPPORT && STACKTRACE_SUPPORT && LOCKDEP_SUPPORT
+	select DEBUG_SPINLOCK
+	select DEBUG_MUTEXES
+	select LOCKDEP
+	help
+	 This feature will check whether any held lock (spinlock, rwlock,
+	 mutex or rwsem) is incorrectly freed by the kernel, via any of the
+	 memory-freeing routines (kfree(), kmem_cache_free(), free_pages(),
+	 vfree(), etc.), whether a live lock is incorrectly reinitialized via
+	 spin_lock_init()/mutex_init()/etc., or whether there is any lock
+	 held during task exit.
+
+config PROVE_LOCKING
+	bool "Lock debugging: prove locking correctness"
+	depends on DEBUG_KERNEL && TRACE_IRQFLAGS_SUPPORT && STACKTRACE_SUPPORT && LOCKDEP_SUPPORT
+	select LOCKDEP
+	select DEBUG_SPINLOCK
+	select DEBUG_MUTEXES
+	select DEBUG_LOCK_ALLOC
+	default n
+	help
+	 This feature enables the kernel to prove that all locking
+	 that occurs in the kernel runtime is mathematically
+	 correct: that under no circumstance could an arbitrary (and
+	 not yet triggered) combination of observed locking
+	 sequences (on an arbitrary number of CPUs, running an
+	 arbitrary number of tasks and interrupt contexts) cause a
+	 deadlock.
+
+	 In short, this feature enables the kernel to report locking
+	 related deadlocks before they actually occur.
+
+	 The proof does not depend on how hard and complex a
+	 deadlock scenario would be to trigger: how many
+	 participant CPUs, tasks and irq-contexts would be needed
+	 for it to trigger. The proof also does not depend on
+	 timing: if a race and a resulting deadlock is possible
+	 theoretically (no matter how unlikely the race scenario
+	 is), it will be proven so and will immediately be
+	 reported by the kernel (once the event is observed that
+	 makes the deadlock theoretically possible).
+
+	 If a deadlock is impossible (i.e. the locking rules, as
+	 observed by the kernel, are mathematically correct), the
+	 kernel reports nothing.
+
+	 NOTE: this feature can also be enabled for rwlocks, mutexes
+	 and rwsems - in which case all dependencies between these
+	 different locking variants are observed and mapped too, and
+	 the proof of observed correctness is also maintained for an
+	 arbitrary combination of these separate locking variants.
+
+	 For more details, see Documentation/lockdep-design.txt.
+
+config LOCKDEP
+	bool
+	depends on DEBUG_KERNEL && TRACE_IRQFLAGS_SUPPORT && STACKTRACE_SUPPORT && LOCKDEP_SUPPORT
+	select STACKTRACE
+	select FRAME_POINTER if !X86
+	select KALLSYMS
+	select KALLSYMS_ALL
+
+config DEBUG_LOCKDEP
+	bool "Lock dependency engine debugging"
+	depends on DEBUG_KERNEL && LOCKDEP
+	help
+	  If you say Y here, the lock dependency engine will do
+	  additional runtime checks to debug itself, at the price
+	  of more runtime overhead.
+
+config TRACE_IRQFLAGS
+	depends on DEBUG_KERNEL
+	bool
+	default y
+	depends on TRACE_IRQFLAGS_SUPPORT
+	depends on PROVE_LOCKING
+
+config DEBUG_SPINLOCK_SLEEP
+	bool "Spinlock debugging: sleep-inside-spinlock checking"
+	depends on DEBUG_KERNEL
+	help
+	  If you say Y here, various routines which may sleep will become very
+	  noisy if they are called with a spinlock held.
+
+config DEBUG_LOCKING_API_SELFTESTS
+	bool "Locking API boot-time self-tests"
+	depends on DEBUG_KERNEL
+	help
+	  Say Y here if you want the kernel to run a short self-test during
+	  bootup. The self-test checks whether common types of locking bugs
+	  are detected by debugging mechanisms or not. (if you disable
+	  lock debugging then those bugs wont be detected of course.)
+	  The following locking APIs are covered: spinlocks, rwlocks,
+	  mutexes and rwsems.
+
+config STACKTRACE
+	bool
+	depends on DEBUG_KERNEL
+	depends on STACKTRACE_SUPPORT
+
+config DEBUG_KOBJECT
+	bool "kobject debugging"
+	depends on DEBUG_KERNEL
+	help
+	  If you say Y here, some extra kobject debugging messages will be sent
+	  to the syslog. 
+
+config DEBUG_HIGHMEM
+	bool "Highmem debugging"
+	depends on DEBUG_KERNEL && HIGHMEM
+	help
+	  This options enables addition error checking for high memory systems.
+	  Disable for production systems.
+
+config DEBUG_BUGVERBOSE
+	bool "Verbose BUG() reporting (adds 70K)" if DEBUG_KERNEL && EMBEDDED
+	depends on BUG
+	depends on ARM || ARM26 || AVR32 || M32R || M68K || SPARC32 || SPARC64 || FRV || SUPERH || GENERIC_BUG
+	default !EMBEDDED
+	help
+	  Say Y here to make BUG() panics output the file name and line number
+	  of the BUG call as well as the EIP and oops trace.  This aids
+	  debugging but costs about 70-100K of memory.
+
+config DEBUG_INFO
+	bool "Compile the kernel with debug info"
+	depends on DEBUG_KERNEL
+	help
+          If you say Y here the resulting kernel image will include
+	  debugging info resulting in a larger kernel image.
+	  Say Y here only if you plan to debug the kernel.
+
+	  If unsure, say N.
+
+config DEBUG_VM
+	bool "Debug VM"
+	depends on DEBUG_KERNEL
+	help
+	  Enable this to turn on extended checks in the virtual-memory system
+          that may impact performance.
+
+	  If unsure, say N.
+
+config DEBUG_LIST
+	bool "Debug linked list manipulation"
+	depends on DEBUG_KERNEL
+	help
+	  Enable this to turn on extended checks in the linked-list
+	  walking routines.
+
+	  If unsure, say N.
+
+config FRAME_POINTER
+	bool "Compile the kernel with frame pointers"
+	depends on DEBUG_KERNEL && (X86 || CRIS || M68K || M68KNOMMU || FRV || UML || S390 || AVR32 || SUPERH)
+	default y if DEBUG_INFO && UML
+	help
+	  If you say Y here the resulting kernel image will be slightly larger
+	  and slower, but it might give very useful debugging information on
+	  some architectures or if you use external debuggers.
+	  If you don't debug the kernel, you can say N.
+
+config FORCED_INLINING
+	bool "Force gcc to inline functions marked 'inline'"
+	depends on DEBUG_KERNEL
+	default y
+	help
+	  This option determines if the kernel forces gcc to inline the functions
+	  developers have marked 'inline'. Doing so takes away freedom from gcc to
+	  do what it thinks is best, which is desirable for the gcc 3.x series of
+	  compilers. The gcc 4.x series have a rewritten inlining algorithm and
+	  disabling this option will generate a smaller kernel there. Hopefully
+	  this algorithm is so good that allowing gcc4 to make the decision can
+	  become the default in the future, until then this option is there to
+	  test gcc for this.
+
+config RCU_TORTURE_TEST
+	tristate "torture tests for RCU"
+	depends on DEBUG_KERNEL
+	default n
+	help
+	  This option provides a kernel module that runs torture tests
+	  on the RCU infrastructure.  The kernel module may be built
+	  after the fact on the running kernel to be tested, if desired.
+
+	  Say Y here if you want RCU torture tests to start automatically
+	  at boot time (you probably don't).
+	  Say M if you want the RCU torture tests to build as a module.
+	  Say N if you are unsure.
+
+config LKDTM
+	tristate "Linux Kernel Dump Test Tool Module"
+	depends on DEBUG_KERNEL
+	depends on KPROBES
+	default n
+	help
+	This module enables testing of the different dumping mechanisms by
+	inducing system failures at predefined crash points.
+	If you don't need it: say N
+	Choose M here to compile this code as a module. The module will be
+	called lkdtm.
+
+	Documentation on how to use the module can be found in
+	drivers/misc/lkdtm.c
+
+config FAULT_INJECTION
+	bool "Fault-injection framework"
+	depends on DEBUG_KERNEL
+	help
+	  Provide fault-injection framework.
+	  For more details, see Documentation/fault-injection/.
+
+config FAILSLAB
+	bool "Fault-injection capability for kmalloc"
+	depends on FAULT_INJECTION
+	help
+	  Provide fault-injection capability for kmalloc.
+
+config FAIL_PAGE_ALLOC
+	bool "Fault-injection capabilitiy for alloc_pages()"
+	depends on FAULT_INJECTION
+	help
+	  Provide fault-injection capability for alloc_pages().
+
+config FAIL_MAKE_REQUEST
+	bool "Fault-injection capability for disk IO"
+	depends on FAULT_INJECTION
+	help
+	  Provide fault-injection capability for disk IO.
+
+config FAULT_INJECTION_DEBUG_FS
+	bool "Debugfs entries for fault-injection capabilities"
+	depends on FAULT_INJECTION && SYSFS && DEBUG_FS
+	help
+	  Enable configuration of fault-injection capabilities via debugfs.
+
+config FAULT_INJECTION_STACKTRACE_FILTER
+	bool "stacktrace filter for fault-injection capabilities"
+	depends on FAULT_INJECTION_DEBUG_FS && STACKTRACE_SUPPORT
+	select STACKTRACE
+	select FRAME_POINTER
+	help
+	  Provide stacktrace filter for fault-injection capabilities

lib/Makefile

@@ -0,0 +1,73 @@
+#
+# Makefile for some libs needed in the kernel.
+#
+
+lib-y := ctype.o string.o vsprintf.o cmdline.o \
+	 rbtree.o radix-tree.o dump_stack.o \
+	 idr.o int_sqrt.o bitmap.o extable.o prio_tree.o \
+	 sha1.o irq_regs.o reciprocal_div.o
+
+lib-$(CONFIG_MMU) += ioremap.o
+lib-$(CONFIG_SMP) += cpumask.o
+
+lib-y	+= kobject.o kref.o kobject_uevent.o klist.o
+
+obj-y += div64.o sort.o parser.o halfmd4.o debug_locks.o random32.o \
+	 bust_spinlocks.o
+
+ifeq ($(CONFIG_DEBUG_KOBJECT),y)
+CFLAGS_kobject.o += -DDEBUG
+CFLAGS_kobject_uevent.o += -DDEBUG
+endif
+
+obj-$(CONFIG_GENERIC_IOMAP) += iomap.o
+obj-$(CONFIG_HAS_IOMEM) += iomap_copy.o devres.o
+obj-$(CONFIG_DEBUG_LOCKING_API_SELFTESTS) += locking-selftest.o
+obj-$(CONFIG_DEBUG_SPINLOCK) += spinlock_debug.o
+lib-$(CONFIG_RWSEM_GENERIC_SPINLOCK) += rwsem-spinlock.o
+lib-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += rwsem.o
+lib-$(CONFIG_SEMAPHORE_SLEEPERS) += semaphore-sleepers.o
+lib-$(CONFIG_GENERIC_FIND_NEXT_BIT) += find_next_bit.o
+obj-$(CONFIG_GENERIC_HWEIGHT) += hweight.o
+obj-$(CONFIG_LOCK_KERNEL) += kernel_lock.o
+obj-$(CONFIG_PLIST) += plist.o
+obj-$(CONFIG_DEBUG_PREEMPT) += smp_processor_id.o
+obj-$(CONFIG_DEBUG_LIST) += list_debug.o
+
+ifneq ($(CONFIG_HAVE_DEC_LOCK),y)
+  lib-y += dec_and_lock.o
+endif
+
+obj-$(CONFIG_BITREVERSE) += bitrev.o
+obj-$(CONFIG_CRC_CCITT)	+= crc-ccitt.o
+obj-$(CONFIG_CRC16)	+= crc16.o
+obj-$(CONFIG_CRC32)	+= crc32.o
+obj-$(CONFIG_LIBCRC32C)	+= libcrc32c.o
+obj-$(CONFIG_GENERIC_ALLOCATOR) += genalloc.o
+
+obj-$(CONFIG_ZLIB_INFLATE) += zlib_inflate/
+obj-$(CONFIG_ZLIB_DEFLATE) += zlib_deflate/
+obj-$(CONFIG_REED_SOLOMON) += reed_solomon/
+
+obj-$(CONFIG_TEXTSEARCH) += textsearch.o
+obj-$(CONFIG_TEXTSEARCH_KMP) += ts_kmp.o
+obj-$(CONFIG_TEXTSEARCH_BM) += ts_bm.o
+obj-$(CONFIG_TEXTSEARCH_FSM) += ts_fsm.o
+obj-$(CONFIG_SMP) += percpu_counter.o
+obj-$(CONFIG_AUDIT_GENERIC) += audit.o
+
+obj-$(CONFIG_SWIOTLB) += swiotlb.o
+obj-$(CONFIG_FAULT_INJECTION) += fault-inject.o
+
+lib-$(CONFIG_GENERIC_BUG) += bug.o
+
+hostprogs-y	:= gen_crc32table
+clean-files	:= crc32table.h
+
+$(obj)/crc32.o: $(obj)/crc32table.h
+
+quiet_cmd_crc32 = GEN     $@
+      cmd_crc32 = $< > $@
+
+$(obj)/crc32table.h: $(obj)/gen_crc32table
+	$(call cmd,crc32)

lib/audit.c

@@ -0,0 +1,55 @@
+#include <linux/init.h>
+#include <linux/types.h>
+#include <linux/audit.h>
+#include <asm/unistd.h>
+
+static unsigned dir_class[] = {
+#include <asm-generic/audit_dir_write.h>
+~0U
+};
+
+static unsigned read_class[] = {
+#include <asm-generic/audit_read.h>
+~0U
+};
+
+static unsigned write_class[] = {
+#include <asm-generic/audit_write.h>
+~0U
+};
+
+static unsigned chattr_class[] = {
+#include <asm-generic/audit_change_attr.h>
+~0U
+};
+
+int audit_classify_syscall(int abi, unsigned syscall)
+{
+	switch(syscall) {
+	case __NR_open:
+		return 2;
+#ifdef __NR_openat
+	case __NR_openat:
+		return 3;
+#endif
+#ifdef __NR_socketcall
+	case __NR_socketcall:
+		return 4;
+#endif
+	case __NR_execve:
+		return 5;
+	default:
+		return 0;
+	}
+}
+
+static int __init audit_classes_init(void)
+{
+	audit_register_class(AUDIT_CLASS_WRITE, write_class);
+	audit_register_class(AUDIT_CLASS_READ, read_class);
+	audit_register_class(AUDIT_CLASS_DIR_WRITE, dir_class);
+	audit_register_class(AUDIT_CLASS_CHATTR, chattr_class);
+	return 0;
+}
+
+__initcall(audit_classes_init);

lib/bitmap.c

@@ -0,0 +1,836 @@
+/*
+ * lib/bitmap.c
+ * Helper functions for bitmap.h.
+ *
+ * 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/ctype.h>
+#include <linux/errno.h>
+#include <linux/bitmap.h>
+#include <linux/bitops.h>
+#include <asm/uaccess.h>
+
+/*
+ * bitmaps provide an array of bits, implemented using an an
+ * array of unsigned longs.  The number of valid bits in a
+ * given bitmap does _not_ need to be an exact multiple of
+ * BITS_PER_LONG.
+ *
+ * The possible unused bits in the last, partially used word
+ * of a bitmap are 'don't care'.  The implementation makes
+ * no particular effort to keep them zero.  It ensures that
+ * their value will not affect the results of any operation.
+ * The bitmap operations that return Boolean (bitmap_empty,
+ * for example) or scalar (bitmap_weight, for example) results
+ * carefully filter out these unused bits from impacting their
+ * results.
+ *
+ * These operations actually hold to a slightly stronger rule:
+ * if you don't input any bitmaps to these ops that have some
+ * unused bits set, then they won't output any set unused bits
+ * in output bitmaps.
+ *
+ * The byte ordering of bitmaps is more natural on little
+ * endian architectures.  See the big-endian headers
+ * include/asm-ppc64/bitops.h and include/asm-s390/bitops.h
+ * for the best explanations of this ordering.
+ */
+
+int __bitmap_empty(const unsigned long *bitmap, int bits)
+{
+	int k, lim = bits/BITS_PER_LONG;
+	for (k = 0; k < lim; ++k)
+		if (bitmap[k])
+			return 0;
+
+	if (bits % BITS_PER_LONG)
+		if (bitmap[k] & BITMAP_LAST_WORD_MASK(bits))
+			return 0;
+
+	return 1;
+}
+EXPORT_SYMBOL(__bitmap_empty);
+
+int __bitmap_full(const unsigned long *bitmap, int bits)
+{
+	int k, lim = bits/BITS_PER_LONG;
+	for (k = 0; k < lim; ++k)
+		if (~bitmap[k])
+			return 0;
+
+	if (bits % BITS_PER_LONG)
+		if (~bitmap[k] & BITMAP_LAST_WORD_MASK(bits))
+			return 0;
+
+	return 1;
+}
+EXPORT_SYMBOL(__bitmap_full);
+
+int __bitmap_equal(const unsigned long *bitmap1,
+		const unsigned long *bitmap2, int bits)
+{
+	int k, lim = bits/BITS_PER_LONG;
+	for (k = 0; k < lim; ++k)
+		if (bitmap1[k] != bitmap2[k])
+			return 0;
+
+	if (bits % BITS_PER_LONG)
+		if ((bitmap1[k] ^ bitmap2[k]) & BITMAP_LAST_WORD_MASK(bits))
+			return 0;
+
+	return 1;
+}
+EXPORT_SYMBOL(__bitmap_equal);
+
+void __bitmap_complement(unsigned long *dst, const unsigned long *src, int bits)
+{
+	int k, lim = bits/BITS_PER_LONG;
+	for (k = 0; k < lim; ++k)
+		dst[k] = ~src[k];
+
+	if (bits % BITS_PER_LONG)
+		dst[k] = ~src[k] & BITMAP_LAST_WORD_MASK(bits);
+}
+EXPORT_SYMBOL(__bitmap_complement);
+
+/**
+ * __bitmap_shift_right - logical right shift of the bits in a bitmap
+ *   @dst : destination bitmap
+ *   @src : source bitmap
+ *   @shift : shift by this many bits
+ *   @bits : bitmap size, in bits
+ *
+ * Shifting right (dividing) means moving bits in the MS -> LS bit
+ * direction.  Zeros are fed into the vacated MS positions and the
+ * LS bits shifted off the bottom are lost.
+ */
+void __bitmap_shift_right(unsigned long *dst,
+			const unsigned long *src, int shift, int bits)
+{
+	int k, lim = BITS_TO_LONGS(bits), left = bits % BITS_PER_LONG;
+	int off = shift/BITS_PER_LONG, rem = shift % BITS_PER_LONG;
+	unsigned long mask = (1UL << left) - 1;
+	for (k = 0; off + k < lim; ++k) {
+		unsigned long upper, lower;
+
+		/*
+		 * If shift is not word aligned, take lower rem bits of
+		 * word above and make them the top rem bits of result.
+		 */
+		if (!rem || off + k + 1 >= lim)
+			upper = 0;
+		else {
+			upper = src[off + k + 1];
+			if (off + k + 1 == lim - 1 && left)
+				upper &= mask;
+		}
+		lower = src[off + k];
+		if (left && off + k == lim - 1)
+			lower &= mask;
+		dst[k] = upper << (BITS_PER_LONG - rem) | lower >> rem;
+		if (left && k == lim - 1)
+			dst[k] &= mask;
+	}
+	if (off)
+		memset(&dst[lim - off], 0, off*sizeof(unsigned long));
+}
+EXPORT_SYMBOL(__bitmap_shift_right);
+
+
+/**
+ * __bitmap_shift_left - logical left shift of the bits in a bitmap
+ *   @dst : destination bitmap
+ *   @src : source bitmap
+ *   @shift : shift by this many bits
+ *   @bits : bitmap size, in bits
+ *
+ * Shifting left (multiplying) means moving bits in the LS -> MS
+ * direction.  Zeros are fed into the vacated LS bit positions
+ * and those MS bits shifted off the top are lost.
+ */
+
+void __bitmap_shift_left(unsigned long *dst,
+			const unsigned long *src, int shift, int bits)
+{
+	int k, lim = BITS_TO_LONGS(bits), left = bits % BITS_PER_LONG;
+	int off = shift/BITS_PER_LONG, rem = shift % BITS_PER_LONG;
+	for (k = lim - off - 1; k >= 0; --k) {
+		unsigned long upper, lower;
+
+		/*
+		 * If shift is not word aligned, take upper rem bits of
+		 * word below and make them the bottom rem bits of result.
+		 */
+		if (rem && k > 0)
+			lower = src[k - 1];
+		else
+			lower = 0;
+		upper = src[k];
+		if (left && k == lim - 1)
+			upper &= (1UL << left) - 1;
+		dst[k + off] = lower  >> (BITS_PER_LONG - rem) | upper << rem;
+		if (left && k + off == lim - 1)
+			dst[k + off] &= (1UL << left) - 1;
+	}
+	if (off)
+		memset(dst, 0, off*sizeof(unsigned long));
+}
+EXPORT_SYMBOL(__bitmap_shift_left);
+
+void __bitmap_and(unsigned long *dst, const unsigned long *bitmap1,
+				const unsigned long *bitmap2, int bits)
+{
+	int k;
+	int nr = BITS_TO_LONGS(bits);
+
+	for (k = 0; k < nr; k++)
+		dst[k] = bitmap1[k] & bitmap2[k];
+}
+EXPORT_SYMBOL(__bitmap_and);
+
+void __bitmap_or(unsigned long *dst, const unsigned long *bitmap1,
+				const unsigned long *bitmap2, int bits)
+{
+	int k;
+	int nr = BITS_TO_LONGS(bits);
+
+	for (k = 0; k < nr; k++)
+		dst[k] = bitmap1[k] | bitmap2[k];
+}
+EXPORT_SYMBOL(__bitmap_or);
+
+void __bitmap_xor(unsigned long *dst, const unsigned long *bitmap1,
+				const unsigned long *bitmap2, int bits)
+{
+	int k;
+	int nr = BITS_TO_LONGS(bits);
+
+	for (k = 0; k < nr; k++)
+		dst[k] = bitmap1[k] ^ bitmap2[k];
+}
+EXPORT_SYMBOL(__bitmap_xor);
+
+void __bitmap_andnot(unsigned long *dst, const unsigned long *bitmap1,
+				const unsigned long *bitmap2, int bits)
+{
+	int k;
+	int nr = BITS_TO_LONGS(bits);
+
+	for (k = 0; k < nr; k++)
+		dst[k] = bitmap1[k] & ~bitmap2[k];
+}
+EXPORT_SYMBOL(__bitmap_andnot);
+
+int __bitmap_intersects(const unsigned long *bitmap1,
+				const unsigned long *bitmap2, int bits)
+{
+	int k, lim = bits/BITS_PER_LONG;
+	for (k = 0; k < lim; ++k)
+		if (bitmap1[k] & bitmap2[k])
+			return 1;
+
+	if (bits % BITS_PER_LONG)
+		if ((bitmap1[k] & bitmap2[k]) & BITMAP_LAST_WORD_MASK(bits))
+			return 1;
+	return 0;
+}
+EXPORT_SYMBOL(__bitmap_intersects);
+
+int __bitmap_subset(const unsigned long *bitmap1,
+				const unsigned long *bitmap2, int bits)
+{
+	int k, lim = bits/BITS_PER_LONG;
+	for (k = 0; k < lim; ++k)
+		if (bitmap1[k] & ~bitmap2[k])
+			return 0;
+
+	if (bits % BITS_PER_LONG)
+		if ((bitmap1[k] & ~bitmap2[k]) & BITMAP_LAST_WORD_MASK(bits))
+			return 0;
+	return 1;
+}
+EXPORT_SYMBOL(__bitmap_subset);
+
+int __bitmap_weight(const unsigned long *bitmap, int bits)
+{
+	int k, w = 0, lim = bits/BITS_PER_LONG;
+
+	for (k = 0; k < lim; k++)
+		w += hweight_long(bitmap[k]);
+
+	if (bits % BITS_PER_LONG)
+		w += hweight_long(bitmap[k] & BITMAP_LAST_WORD_MASK(bits));
+
+	return w;
+}
+EXPORT_SYMBOL(__bitmap_weight);
+
+/*
+ * Bitmap printing & parsing functions: first version by Bill Irwin,
+ * second version by Paul Jackson, third by Joe Korty.
+ */
+
+#define CHUNKSZ				32
+#define nbits_to_hold_value(val)	fls(val)
+#define unhex(c)			(isdigit(c) ? (c - '0') : (toupper(c) - 'A' + 10))
+#define BASEDEC 10		/* fancier cpuset lists input in decimal */
+
+/**
+ * bitmap_scnprintf - convert bitmap to an ASCII hex string.
+ * @buf: byte buffer into which string is placed
+ * @buflen: reserved size of @buf, in bytes
+ * @maskp: pointer to bitmap to convert
+ * @nmaskbits: size of bitmap, in bits
+ *
+ * Exactly @nmaskbits bits are displayed.  Hex digits are grouped into
+ * comma-separated sets of eight digits per set.
+ */
+int bitmap_scnprintf(char *buf, unsigned int buflen,
+	const unsigned long *maskp, int nmaskbits)
+{
+	int i, word, bit, len = 0;
+	unsigned long val;
+	const char *sep = "";
+	int chunksz;
+	u32 chunkmask;
+
+	chunksz = nmaskbits & (CHUNKSZ - 1);
+	if (chunksz == 0)
+		chunksz = CHUNKSZ;
+
+	i = ALIGN(nmaskbits, CHUNKSZ) - CHUNKSZ;
+	for (; i >= 0; i -= CHUNKSZ) {
+		chunkmask = ((1ULL << chunksz) - 1);
+		word = i / BITS_PER_LONG;
+		bit = i % BITS_PER_LONG;
+		val = (maskp[word] >> bit) & chunkmask;
+		len += scnprintf(buf+len, buflen-len, "%s%0*lx", sep,
+			(chunksz+3)/4, val);
+		chunksz = CHUNKSZ;
+		sep = ",";
+	}
+	return len;
+}
+EXPORT_SYMBOL(bitmap_scnprintf);
+
+/**
+ * __bitmap_parse - convert an ASCII hex string into a bitmap.
+ * @buf: pointer to buffer containing string.
+ * @buflen: buffer size in bytes.  If string is smaller than this
+ *    then it must be terminated with a \0.
+ * @is_user: location of buffer, 0 indicates kernel space
+ * @maskp: pointer to bitmap array that will contain result.
+ * @nmaskbits: size of bitmap, in bits.
+ *
+ * Commas group hex digits into chunks.  Each chunk defines exactly 32
+ * bits of the resultant bitmask.  No chunk may specify a value larger
+ * than 32 bits (%-EOVERFLOW), and if a chunk specifies a smaller value
+ * then leading 0-bits are prepended.  %-EINVAL is returned for illegal
+ * characters and for grouping errors such as "1,,5", ",44", "," and "".
+ * Leading and trailing whitespace accepted, but not embedded whitespace.
+ */
+int __bitmap_parse(const char *buf, unsigned int buflen,
+		int is_user, unsigned long *maskp,
+		int nmaskbits)
+{
+	int c, old_c, totaldigits, ndigits, nchunks, nbits;
+	u32 chunk;
+	const char __user *ubuf = buf;
+
+	bitmap_zero(maskp, nmaskbits);
+
+	nchunks = nbits = totaldigits = c = 0;
+	do {
+		chunk = ndigits = 0;
+
+		/* Get the next chunk of the bitmap */
+		while (buflen) {
+			old_c = c;
+			if (is_user) {
+				if (__get_user(c, ubuf++))
+					return -EFAULT;
+			}
+			else
+				c = *buf++;
+			buflen--;
+			if (isspace(c))
+				continue;
+
+			/*
+			 * If the last character was a space and the current
+			 * character isn't '\0', we've got embedded whitespace.
+			 * This is a no-no, so throw an error.
+			 */
+			if (totaldigits && c && isspace(old_c))
+				return -EINVAL;
+
+			/* A '\0' or a ',' signal the end of the chunk */
+			if (c == '\0' || c == ',')
+				break;
+
+			if (!isxdigit(c))
+				return -EINVAL;
+
+			/*
+			 * Make sure there are at least 4 free bits in 'chunk'.
+			 * If not, this hexdigit will overflow 'chunk', so
+			 * throw an error.
+			 */
+			if (chunk & ~((1UL << (CHUNKSZ - 4)) - 1))
+				return -EOVERFLOW;
+
+			chunk = (chunk << 4) | unhex(c);
+			ndigits++; totaldigits++;
+		}
+		if (ndigits == 0)
+			return -EINVAL;
+		if (nchunks == 0 && chunk == 0)
+			continue;
+
+		__bitmap_shift_left(maskp, maskp, CHUNKSZ, nmaskbits);
+		*maskp |= chunk;
+		nchunks++;
+		nbits += (nchunks == 1) ? nbits_to_hold_value(chunk) : CHUNKSZ;
+		if (nbits > nmaskbits)
+			return -EOVERFLOW;
+	} while (buflen && c == ',');
+
+	return 0;
+}
+EXPORT_SYMBOL(__bitmap_parse);
+
+/**
+ * bitmap_parse_user()
+ *
+ * @ubuf: pointer to user buffer containing string.
+ * @ulen: buffer size in bytes.  If string is smaller than this
+ *    then it must be terminated with a \0.
+ * @maskp: pointer to bitmap array that will contain result.
+ * @nmaskbits: size of bitmap, in bits.
+ *
+ * Wrapper for __bitmap_parse(), providing it with user buffer.
+ *
+ * We cannot have this as an inline function in bitmap.h because it needs
+ * linux/uaccess.h to get the access_ok() declaration and this causes
+ * cyclic dependencies.
+ */
+int bitmap_parse_user(const char __user *ubuf,
+			unsigned int ulen, unsigned long *maskp,
+			int nmaskbits)
+{
+	if (!access_ok(VERIFY_READ, ubuf, ulen))
+		return -EFAULT;
+	return __bitmap_parse((const char *)ubuf, ulen, 1, maskp, nmaskbits);
+}
+EXPORT_SYMBOL(bitmap_parse_user);
+
+/*
+ * bscnl_emit(buf, buflen, rbot, rtop, bp)
+ *
+ * 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.
+ */
+static inline int bscnl_emit(char *buf, int buflen, int rbot, int rtop, int len)
+{
+	if (len > 0)
+		len += scnprintf(buf + len, buflen - len, ",");
+	if (rbot == rtop)
+		len += scnprintf(buf + len, buflen - len, "%d", rbot);
+	else
+		len += scnprintf(buf + len, buflen - len, "%d-%d", rbot, rtop);
+	return len;
+}
+
+/**
+ * bitmap_scnlistprintf - convert bitmap to list format ASCII string
+ * @buf: byte buffer into which string is placed
+ * @buflen: reserved size of @buf, in bytes
+ * @maskp: pointer to bitmap to convert
+ * @nmaskbits: size of bitmap, in bits
+ *
+ * Output format is a comma-separated list of decimal numbers and
+ * ranges.  Consecutively set bits are shown as two hyphen-separated
+ * decimal numbers, the smallest and largest bit numbers set in
+ * 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.
+ */
+int bitmap_scnlistprintf(char *buf, unsigned int buflen,
+	const unsigned long *maskp, int nmaskbits)
+{
+	int len = 0;
+	/* current bit is 'cur', most recently seen range is [rbot, rtop] */
+	int cur, rbot, rtop;
+
+	rbot = cur = find_first_bit(maskp, nmaskbits);
+	while (cur < nmaskbits) {
+		rtop = cur;
+		cur = find_next_bit(maskp, nmaskbits, cur+1);
+		if (cur >= nmaskbits || cur > rtop + 1) {
+			len = bscnl_emit(buf, buflen, rbot, rtop, len);
+			rbot = cur;
+		}
+	}
+	return len;
+}
+EXPORT_SYMBOL(bitmap_scnlistprintf);
+
+/**
+ * bitmap_parselist - convert list format ASCII string to bitmap
+ * @bp: read nul-terminated user string from this buffer
+ * @maskp: write resulting mask here
+ * @nmaskbits: number of bits in mask to be written
+ *
+ * Input format is a comma-separated list of decimal numbers and
+ * ranges.  Consecutively set bits are shown as two hyphen-separated
+ * decimal numbers, the smallest and largest bit numbers set in
+ * the range.
+ *
+ * Returns 0 on success, -errno on invalid input strings.
+ * Error values:
+ *    %-EINVAL: second number in range smaller than first
+ *    %-EINVAL: invalid character in string
+ *    %-ERANGE: bit number specified too large for mask
+ */
+int bitmap_parselist(const char *bp, unsigned long *maskp, int nmaskbits)
+{
+	unsigned a, b;
+
+	bitmap_zero(maskp, nmaskbits);
+	do {
+		if (!isdigit(*bp))
+			return -EINVAL;
+		b = a = simple_strtoul(bp, (char **)&bp, BASEDEC);
+		if (*bp == '-') {
+			bp++;
+			if (!isdigit(*bp))
+				return -EINVAL;
+			b = simple_strtoul(bp, (char **)&bp, BASEDEC);
+		}
+		if (!(a <= b))
+			return -EINVAL;
+		if (b >= nmaskbits)
+			return -ERANGE;
+		while (a <= b) {
+			set_bit(a, maskp);
+			a++;
+		}
+		if (*bp == ',')
+			bp++;
+	} while (*bp != '\0' && *bp != '\n');
+	return 0;
+}
+EXPORT_SYMBOL(bitmap_parselist);
+
+/**
+ * bitmap_pos_to_ord(buf, pos, bits)
+ *	@buf: pointer to a bitmap
+ *	@pos: a bit position in @buf (0 <= @pos < @bits)
+ *	@bits: number of valid bit positions in @buf
+ *
+ * Map the bit at position @pos in @buf (of length @bits) to the
+ * ordinal of which set bit it is.  If it is not set or if @pos
+ * is not a valid bit position, map to -1.
+ *
+ * If for example, just bits 4 through 7 are set in @buf, then @pos
+ * values 4 through 7 will get mapped to 0 through 3, respectively,
+ * and other @pos values will get mapped to 0.  When @pos value 7
+ * gets mapped to (returns) @ord value 3 in this example, that means
+ * that bit 7 is the 3rd (starting with 0th) set bit in @buf.
+ *
+ * The bit positions 0 through @bits are valid positions in @buf.
+ */
+static int bitmap_pos_to_ord(const unsigned long *buf, int pos, int bits)
+{
+	int i, ord;
+
+	if (pos < 0 || pos >= bits || !test_bit(pos, buf))
+		return -1;
+
+	i = find_first_bit(buf, bits);
+	ord = 0;
+	while (i < pos) {
+		i = find_next_bit(buf, bits, i + 1);
+	     	ord++;
+	}
+	BUG_ON(i != pos);
+
+	return ord;
+}
+
+/**
+ * bitmap_ord_to_pos(buf, ord, bits)
+ *	@buf: pointer to bitmap
+ *	@ord: ordinal bit position (n-th set bit, n >= 0)
+ *	@bits: number of valid bit positions in @buf
+ *
+ * Map the ordinal offset of bit @ord in @buf to its position in @buf.
+ * Value of @ord should be in range 0 <= @ord < weight(buf), else
+ * results are undefined.
+ *
+ * If for example, just bits 4 through 7 are set in @buf, then @ord
+ * values 0 through 3 will get mapped to 4 through 7, respectively,
+ * and all other @ord values return undefined values.  When @ord value 3
+ * gets mapped to (returns) @pos value 7 in this example, that means
+ * that the 3rd set bit (starting with 0th) is at position 7 in @buf.
+ *
+ * The bit positions 0 through @bits are valid positions in @buf.
+ */
+static int bitmap_ord_to_pos(const unsigned long *buf, int ord, int bits)
+{
+	int pos = 0;
+
+	if (ord >= 0 && ord < bits) {
+		int i;
+
+		for (i = find_first_bit(buf, bits);
+		     i < bits && ord > 0;
+		     i = find_next_bit(buf, bits, i + 1))
+	     		ord--;
+		if (i < bits && ord == 0)
+			pos = i;
+	}
+
+	return pos;
+}
+
+/**
+ * bitmap_remap - Apply map defined by a pair of bitmaps to another bitmap
+ *	@dst: remapped result
+ *	@src: subset to be remapped
+ *	@old: defines domain of map
+ *	@new: defines range of map
+ *	@bits: number of bits in each of these bitmaps
+ *
+ * Let @old and @new define a mapping of bit positions, such that
+ * whatever position is held by the n-th set bit in @old is mapped
+ * to the n-th set bit in @new.  In the more general case, allowing
+ * for the possibility that the weight 'w' of @new is less than the
+ * weight of @old, map the position of the n-th set bit in @old to
+ * the position of the m-th set bit in @new, where m == n % w.
+ *
+ * If either of the @old and @new bitmaps are empty, or if @src and
+ * @dst point to the same location, then this routine copies @src
+ * to @dst.
+ *
+ * The positions of unset bits in @old are mapped to themselves
+ * (the identify map).
+ *
+ * Apply the above specified mapping to @src, placing the result in
+ * @dst, clearing any bits previously set in @dst.
+ *
+ * For example, lets say that @old has bits 4 through 7 set, and
+ * @new has bits 12 through 15 set.  This defines the mapping of bit
+ * position 4 to 12, 5 to 13, 6 to 14 and 7 to 15, and of all other
+ * bit positions unchanged.  So if say @src comes into this routine
+ * with bits 1, 5 and 7 set, then @dst should leave with bits 1,
+ * 13 and 15 set.
+ */
+void bitmap_remap(unsigned long *dst, const unsigned long *src,
+		const unsigned long *old, const unsigned long *new,
+		int bits)
+{
+	int oldbit, w;
+
+	if (dst == src)		/* following doesn't handle inplace remaps */
+		return;
+	bitmap_zero(dst, bits);
+
+	w = bitmap_weight(new, bits);
+	for (oldbit = find_first_bit(src, bits);
+	     oldbit < bits;
+	     oldbit = find_next_bit(src, bits, oldbit + 1)) {
+	     	int n = bitmap_pos_to_ord(old, oldbit, bits);
+		if (n < 0 || w == 0)
+			set_bit(oldbit, dst);	/* identity map */
+		else
+			set_bit(bitmap_ord_to_pos(new, n % w, bits), dst);
+	}
+}
+EXPORT_SYMBOL(bitmap_remap);
+
+/**
+ * bitmap_bitremap - Apply map defined by a pair of bitmaps to a single bit
+ *	@oldbit: bit position to be mapped
+ *	@old: defines domain of map
+ *	@new: defines range of map
+ *	@bits: number of bits in each of these bitmaps
+ *
+ * Let @old and @new define a mapping of bit positions, such that
+ * whatever position is held by the n-th set bit in @old is mapped
+ * to the n-th set bit in @new.  In the more general case, allowing
+ * for the possibility that the weight 'w' of @new is less than the
+ * weight of @old, map the position of the n-th set bit in @old to
+ * the position of the m-th set bit in @new, where m == n % w.
+ *
+ * The positions of unset bits in @old are mapped to themselves
+ * (the identify map).
+ *
+ * Apply the above specified mapping to bit position @oldbit, returning
+ * the new bit position.
+ *
+ * For example, lets say that @old has bits 4 through 7 set, and
+ * @new has bits 12 through 15 set.  This defines the mapping of bit
+ * position 4 to 12, 5 to 13, 6 to 14 and 7 to 15, and of all other
+ * bit positions unchanged.  So if say @oldbit is 5, then this routine
+ * returns 13.
+ */
+int bitmap_bitremap(int oldbit, const unsigned long *old,
+				const unsigned long *new, int bits)
+{
+	int w = bitmap_weight(new, bits);
+	int n = bitmap_pos_to_ord(old, oldbit, bits);
+	if (n < 0 || w == 0)
+		return oldbit;
+	else
+		return bitmap_ord_to_pos(new, n % w, bits);
+}
+EXPORT_SYMBOL(bitmap_bitremap);
+
+/*
+ * Common code for bitmap_*_region() routines.
+ *	bitmap: array of unsigned longs corresponding to the bitmap
+ *	pos: the beginning of the region
+ *	order: region size (log base 2 of number of bits)
+ *	reg_op: operation(s) to perform on that region of bitmap
+ *
+ * Can set, verify and/or release a region of bits in a bitmap,
+ * depending on which combination of REG_OP_* flag bits is set.
+ *
+ * A region of a bitmap is a sequence of bits in the bitmap, of
+ * some size '1 << order' (a power of two), aligned to that same
+ * '1 << order' power of two.
+ *
+ * Returns 1 if REG_OP_ISFREE succeeds (region is all zero bits).
+ * Returns 0 in all other cases and reg_ops.
+ */
+
+enum {
+	REG_OP_ISFREE,		/* true if region is all zero bits */
+	REG_OP_ALLOC,		/* set all bits in region */
+	REG_OP_RELEASE,		/* clear all bits in region */
+};
+
+static int __reg_op(unsigned long *bitmap, int pos, int order, int reg_op)
+{
+	int nbits_reg;		/* number of bits in region */
+	int index;		/* index first long of region in bitmap */
+	int offset;		/* bit offset region in bitmap[index] */
+	int nlongs_reg;		/* num longs spanned by region in bitmap */
+	int nbitsinlong;	/* num bits of region in each spanned long */
+	unsigned long mask;	/* bitmask for one long of region */
+	int i;			/* scans bitmap by longs */
+	int ret = 0;		/* return value */
+
+	/*
+	 * Either nlongs_reg == 1 (for small orders that fit in one long)
+	 * or (offset == 0 && mask == ~0UL) (for larger multiword orders.)
+	 */
+	nbits_reg = 1 << order;
+	index = pos / BITS_PER_LONG;
+	offset = pos - (index * BITS_PER_LONG);
+	nlongs_reg = BITS_TO_LONGS(nbits_reg);
+	nbitsinlong = min(nbits_reg,  BITS_PER_LONG);
+
+	/*
+	 * Can't do "mask = (1UL << nbitsinlong) - 1", as that
+	 * overflows if nbitsinlong == BITS_PER_LONG.
+	 */
+	mask = (1UL << (nbitsinlong - 1));
+	mask += mask - 1;
+	mask <<= offset;
+
+	switch (reg_op) {
+	case REG_OP_ISFREE:
+		for (i = 0; i < nlongs_reg; i++) {
+			if (bitmap[index + i] & mask)
+				goto done;
+		}
+		ret = 1;	/* all bits in region free (zero) */
+		break;
+
+	case REG_OP_ALLOC:
+		for (i = 0; i < nlongs_reg; i++)
+			bitmap[index + i] |= mask;
+		break;
+
+	case REG_OP_RELEASE:
+		for (i = 0; i < nlongs_reg; i++)
+			bitmap[index + i] &= ~mask;
+		break;
+	}
+done:
+	return ret;
+}
+
+/**
+ * bitmap_find_free_region - find a contiguous aligned mem region
+ *	@bitmap: array of unsigned longs corresponding to the bitmap
+ *	@bits: number of bits in the bitmap
+ *	@order: region size (log base 2 of number of bits) to find
+ *
+ * Find a region of free (zero) bits in a @bitmap of @bits bits and
+ * allocate them (set them to one).  Only consider regions of length
+ * a power (@order) of two, aligned to that power of two, which
+ * makes the search algorithm much faster.
+ *
+ * Return the bit offset in bitmap of the allocated region,
+ * or -errno on failure.
+ */
+int bitmap_find_free_region(unsigned long *bitmap, int bits, int order)
+{
+	int pos;		/* scans bitmap by regions of size order */
+
+	for (pos = 0; pos < bits; pos += (1 << order))
+		if (__reg_op(bitmap, pos, order, REG_OP_ISFREE))
+			break;
+	if (pos == bits)
+		return -ENOMEM;
+	__reg_op(bitmap, pos, order, REG_OP_ALLOC);
+	return pos;
+}
+EXPORT_SYMBOL(bitmap_find_free_region);
+
+/**
+ * bitmap_release_region - release allocated bitmap region
+ *	@bitmap: array of unsigned longs corresponding to the bitmap
+ *	@pos: beginning of bit region to release
+ *	@order: region size (log base 2 of number of bits) to release
+ *
+ * This is the complement to __bitmap_find_free_region() and releases
+ * the found region (by clearing it in the bitmap).
+ *
+ * No return value.
+ */
+void bitmap_release_region(unsigned long *bitmap, int pos, int order)
+{
+	__reg_op(bitmap, pos, order, REG_OP_RELEASE);
+}
+EXPORT_SYMBOL(bitmap_release_region);
+
+/**
+ * bitmap_allocate_region - allocate bitmap region
+ *	@bitmap: array of unsigned longs corresponding to the bitmap
+ *	@pos: beginning of bit region to allocate
+ *	@order: region size (log base 2 of number of bits) to allocate
+ *
+ * Allocate (set bits in) a specified region of a bitmap.
+ *
+ * Return 0 on success, or %-EBUSY if specified region wasn't
+ * free (not all bits were zero).
+ */
+int bitmap_allocate_region(unsigned long *bitmap, int pos, int order)
+{
+	if (!__reg_op(bitmap, pos, order, REG_OP_ISFREE))
+		return -EBUSY;
+	__reg_op(bitmap, pos, order, REG_OP_ALLOC);
+	return 0;
+}
+EXPORT_SYMBOL(bitmap_allocate_region);

lib/bitrev.c

@@ -0,0 +1,58 @@
+#include <linux/types.h>
+#include <linux/module.h>
+#include <linux/bitrev.h>
+
+MODULE_AUTHOR("Akinobu Mita <akinobu.mita@gmail.com>");
+MODULE_DESCRIPTION("Bit ordering reversal functions");
+MODULE_LICENSE("GPL");
+
+const u8 byte_rev_table[256] = {
+	0x00, 0x80, 0x40, 0xc0, 0x20, 0xa0, 0x60, 0xe0,
+	0x10, 0x90, 0x50, 0xd0, 0x30, 0xb0, 0x70, 0xf0,
+	0x08, 0x88, 0x48, 0xc8, 0x28, 0xa8, 0x68, 0xe8,
+	0x18, 0x98, 0x58, 0xd8, 0x38, 0xb8, 0x78, 0xf8,
+	0x04, 0x84, 0x44, 0xc4, 0x24, 0xa4, 0x64, 0xe4,
+	0x14, 0x94, 0x54, 0xd4, 0x34, 0xb4, 0x74, 0xf4,
+	0x0c, 0x8c, 0x4c, 0xcc, 0x2c, 0xac, 0x6c, 0xec,
+	0x1c, 0x9c, 0x5c, 0xdc, 0x3c, 0xbc, 0x7c, 0xfc,
+	0x02, 0x82, 0x42, 0xc2, 0x22, 0xa2, 0x62, 0xe2,
+	0x12, 0x92, 0x52, 0xd2, 0x32, 0xb2, 0x72, 0xf2,
+	0x0a, 0x8a, 0x4a, 0xca, 0x2a, 0xaa, 0x6a, 0xea,
+	0x1a, 0x9a, 0x5a, 0xda, 0x3a, 0xba, 0x7a, 0xfa,
+	0x06, 0x86, 0x46, 0xc6, 0x26, 0xa6, 0x66, 0xe6,
+	0x16, 0x96, 0x56, 0xd6, 0x36, 0xb6, 0x76, 0xf6,
+	0x0e, 0x8e, 0x4e, 0xce, 0x2e, 0xae, 0x6e, 0xee,
+	0x1e, 0x9e, 0x5e, 0xde, 0x3e, 0xbe, 0x7e, 0xfe,
+	0x01, 0x81, 0x41, 0xc1, 0x21, 0xa1, 0x61, 0xe1,
+	0x11, 0x91, 0x51, 0xd1, 0x31, 0xb1, 0x71, 0xf1,
+	0x09, 0x89, 0x49, 0xc9, 0x29, 0xa9, 0x69, 0xe9,
+	0x19, 0x99, 0x59, 0xd9, 0x39, 0xb9, 0x79, 0xf9,
+	0x05, 0x85, 0x45, 0xc5, 0x25, 0xa5, 0x65, 0xe5,
+	0x15, 0x95, 0x55, 0xd5, 0x35, 0xb5, 0x75, 0xf5,
+	0x0d, 0x8d, 0x4d, 0xcd, 0x2d, 0xad, 0x6d, 0xed,
+	0x1d, 0x9d, 0x5d, 0xdd, 0x3d, 0xbd, 0x7d, 0xfd,
+	0x03, 0x83, 0x43, 0xc3, 0x23, 0xa3, 0x63, 0xe3,
+	0x13, 0x93, 0x53, 0xd3, 0x33, 0xb3, 0x73, 0xf3,
+	0x0b, 0x8b, 0x4b, 0xcb, 0x2b, 0xab, 0x6b, 0xeb,
+	0x1b, 0x9b, 0x5b, 0xdb, 0x3b, 0xbb, 0x7b, 0xfb,
+	0x07, 0x87, 0x47, 0xc7, 0x27, 0xa7, 0x67, 0xe7,
+	0x17, 0x97, 0x57, 0xd7, 0x37, 0xb7, 0x77, 0xf7,
+	0x0f, 0x8f, 0x4f, 0xcf, 0x2f, 0xaf, 0x6f, 0xef,
+	0x1f, 0x9f, 0x5f, 0xdf, 0x3f, 0xbf, 0x7f, 0xff,
+};
+EXPORT_SYMBOL_GPL(byte_rev_table);
+
+static __always_inline u16 bitrev16(u16 x)
+{
+	return (bitrev8(x & 0xff) << 8) | bitrev8(x >> 8);
+}
+
+/**
+ * bitrev32 - reverse the order of bits in a u32 value
+ * @x: value to be bit-reversed
+ */
+u32 bitrev32(u32 x)
+{
+	return (bitrev16(x & 0xffff) << 16) | bitrev16(x >> 16);
+}
+EXPORT_SYMBOL(bitrev32);

lib/bug.c

@@ -0,0 +1,163 @@
+/*
+  Generic support for BUG()
+
+  This respects the following config options:
+
+  CONFIG_BUG - emit BUG traps.  Nothing happens without this.
+  CONFIG_GENERIC_BUG - enable this code.
+  CONFIG_DEBUG_BUGVERBOSE - emit full file+line information for each BUG
+
+  CONFIG_BUG and CONFIG_DEBUG_BUGVERBOSE are potentially user-settable
+  (though they're generally always on).
+
+  CONFIG_GENERIC_BUG is set by each architecture using this code.
+
+  To use this, your architecture must:
+
+  1. Set up the config options:
+     - Enable CONFIG_GENERIC_BUG if CONFIG_BUG
+
+  2. Implement BUG (and optionally BUG_ON, WARN, WARN_ON)
+     - Define HAVE_ARCH_BUG
+     - Implement BUG() to generate a faulting instruction
+     - NOTE: struct bug_entry does not have "file" or "line" entries
+       when CONFIG_DEBUG_BUGVERBOSE is not enabled, so you must generate
+       the values accordingly.
+
+  3. Implement the trap
+     - In the illegal instruction trap handler (typically), verify
+       that the fault was in kernel mode, and call report_bug()
+     - report_bug() will return whether it was a false alarm, a warning,
+       or an actual bug.
+     - You must implement the is_valid_bugaddr(bugaddr) callback which
+       returns true if the eip is a real kernel address, and it points
+       to the expected BUG trap instruction.
+
+    Jeremy Fitzhardinge <jeremy@goop.org> 2006
+ */
+#include <linux/list.h>
+#include <linux/module.h>
+#include <linux/bug.h>
+
+extern const struct bug_entry __start___bug_table[], __stop___bug_table[];
+
+#ifdef CONFIG_MODULES
+static LIST_HEAD(module_bug_list);
+
+static const struct bug_entry *module_find_bug(unsigned long bugaddr)
+{
+	struct module *mod;
+
+	list_for_each_entry(mod, &module_bug_list, bug_list) {
+		const struct bug_entry *bug = mod->bug_table;
+		unsigned i;
+
+		for (i = 0; i < mod->num_bugs; ++i, ++bug)
+			if (bugaddr == bug->bug_addr)
+				return bug;
+	}
+	return NULL;
+}
+
+int module_bug_finalize(const Elf_Ehdr *hdr, const Elf_Shdr *sechdrs,
+			struct module *mod)
+{
+	char *secstrings;
+	unsigned int i;
+
+	mod->bug_table = NULL;
+	mod->num_bugs = 0;
+
+	/* Find the __bug_table section, if present */
+	secstrings = (char *)hdr + sechdrs[hdr->e_shstrndx].sh_offset;
+	for (i = 1; i < hdr->e_shnum; i++) {
+		if (strcmp(secstrings+sechdrs[i].sh_name, "__bug_table"))
+			continue;
+		mod->bug_table = (void *) sechdrs[i].sh_addr;
+		mod->num_bugs = sechdrs[i].sh_size / sizeof(struct bug_entry);
+		break;
+	}
+
+	/*
+	 * Strictly speaking this should have a spinlock to protect against
+	 * traversals, but since we only traverse on BUG()s, a spinlock
+	 * could potentially lead to deadlock and thus be counter-productive.
+	 */
+	list_add(&mod->bug_list, &module_bug_list);
+
+	return 0;
+}
+
+void module_bug_cleanup(struct module *mod)
+{
+	list_del(&mod->bug_list);
+}
+
+#else
+
+static inline const struct bug_entry *module_find_bug(unsigned long bugaddr)
+{
+	return NULL;
+}
+#endif
+
+const struct bug_entry *find_bug(unsigned long bugaddr)
+{
+	const struct bug_entry *bug;
+
+	for (bug = __start___bug_table; bug < __stop___bug_table; ++bug)
+		if (bugaddr == bug->bug_addr)
+			return bug;
+
+	return module_find_bug(bugaddr);
+}
+
+enum bug_trap_type report_bug(unsigned long bugaddr)
+{
+	const struct bug_entry *bug;
+	const char *file;
+	unsigned line, warning;
+
+	if (!is_valid_bugaddr(bugaddr))
+		return BUG_TRAP_TYPE_NONE;
+
+	bug = find_bug(bugaddr);
+
+	printk(KERN_EMERG "------------[ cut here ]------------\n");
+
+	file = NULL;
+	line = 0;
+	warning = 0;
+
+	if (bug) {
+#ifdef CONFIG_DEBUG_BUGVERBOSE
+		file = bug->file;
+		line = bug->line;
+#endif
+		warning = (bug->flags & BUGFLAG_WARNING) != 0;
+	}
+
+	if (warning) {
+		/* this is a WARN_ON rather than BUG/BUG_ON */
+		if (file)
+			printk(KERN_ERR "Badness at %s:%u\n",
+			       file, line);
+		else
+			printk(KERN_ERR "Badness at %p "
+			       "[verbose debug info unavailable]\n",
+			       (void *)bugaddr);
+
+		dump_stack();
+		return BUG_TRAP_TYPE_WARN;
+	}
+
+	if (file)
+		printk(KERN_CRIT "kernel BUG at %s:%u!\n",
+		       file, line);
+	else
+		printk(KERN_CRIT "Kernel BUG at %p "
+		       "[verbose debug info unavailable]\n",
+		       (void *)bugaddr);
+
+	return BUG_TRAP_TYPE_BUG;
+}

lib/bust_spinlocks.c

@@ -0,0 +1,30 @@
+/*
+ * lib/bust_spinlocks.c
+ *
+ * Provides a minimal bust_spinlocks for architectures which don't have one of their own.
+ *
+ * bust_spinlocks() clears any spinlocks which would prevent oops, die(), BUG()
+ * and panic() information from reaching the user.
+ */
+
+#include <linux/kernel.h>
+#include <linux/spinlock.h>
+#include <linux/tty.h>
+#include <linux/wait.h>
+#include <linux/vt_kern.h>
+
+
+void __attribute__((weak)) bust_spinlocks(int yes)
+{
+	if (yes) {
+		oops_in_progress = 1;
+	} else {
+#ifdef CONFIG_VT
+		unblank_screen();
+#endif
+		oops_in_progress = 0;
+		wake_up_klogd();
+	}
+}
+
+

lib/cmdline.c

@@ -0,0 +1,153 @@
+/*
+ * linux/lib/cmdline.c
+ * Helper functions generally used for parsing kernel command line
+ * and module options.
+ *
+ * Code and copyrights come from init/main.c and arch/i386/kernel/setup.c.
+ *
+ * This source code is licensed under the GNU General Public License,
+ * Version 2.  See the file COPYING for more details.
+ *
+ * GNU Indent formatting options for this file: -kr -i8 -npsl -pcs
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/string.h>
+
+/*
+ *	If a hyphen was found in get_option, this will handle the
+ *	range of numbers, M-N.  This will expand the range and insert
+ *	the values[M, M+1, ..., N] into the ints array in get_options.
+ */
+
+static int get_range(char **str, int *pint)
+{
+	int x, inc_counter, upper_range;
+
+	(*str)++;
+	upper_range = simple_strtol((*str), NULL, 0);
+	inc_counter = upper_range - *pint;
+	for (x = *pint; x < upper_range; x++)
+		*pint++ = x;
+	return inc_counter;
+}
+
+/**
+ *	get_option - Parse integer from an option string
+ *	@str: option string
+ *	@pint: (output) integer value parsed from @str
+ *
+ *	Read an int from an option string; if available accept a subsequent
+ *	comma as well.
+ *
+ *	Return values:
+ *	0 - no int in string
+ *	1 - int found, no subsequent comma
+ *	2 - int found including a subsequent comma
+ *	3 - hyphen found to denote a range
+ */
+
+int get_option (char **str, int *pint)
+{
+	char *cur = *str;
+
+	if (!cur || !(*cur))
+		return 0;
+	*pint = simple_strtol (cur, str, 0);
+	if (cur == *str)
+		return 0;
+	if (**str == ',') {
+		(*str)++;
+		return 2;
+	}
+	if (**str == '-')
+		return 3;
+
+	return 1;
+}
+
+/**
+ *	get_options - Parse a string into a list of integers
+ *	@str: String to be parsed
+ *	@nints: size of integer array
+ *	@ints: integer array
+ *
+ *	This function parses a string containing a comma-separated
+ *	list of integers, a hyphen-separated range of _positive_ integers,
+ *	or a combination of both.  The parse halts when the array is
+ *	full, or when no more numbers can be retrieved from the
+ *	string.
+ *
+ *	Return value is the character in the string which caused
+ *	the parse to end (typically a null terminator, if @str is
+ *	completely parseable).
+ */
+ 
+char *get_options(const char *str, int nints, int *ints)
+{
+	int res, i = 1;
+
+	while (i < nints) {
+		res = get_option ((char **)&str, ints + i);
+		if (res == 0)
+			break;
+		if (res == 3) {
+			int range_nums;
+			range_nums = get_range((char **)&str, ints + i);
+			if (range_nums < 0)
+				break;
+			/*
+			 * Decrement the result by one to leave out the
+			 * last number in the range.  The next iteration
+			 * will handle the upper number in the range
+			 */
+			i += (range_nums - 1);
+		}
+		i++;
+		if (res == 1)
+			break;
+	}
+	ints[0] = i - 1;
+	return (char *)str;
+}
+
+/**
+ *	memparse - parse a string with mem suffixes into a number
+ *	@ptr: Where parse begins
+ *	@retptr: (output) Pointer to next char after parse completes
+ *
+ *	Parses a string into a number.  The number stored at @ptr is
+ *	potentially suffixed with %K (for kilobytes, or 1024 bytes),
+ *	%M (for megabytes, or 1048576 bytes), or %G (for gigabytes, or
+ *	1073741824).  If the number is suffixed with K, M, or G, then
+ *	the return value is the number multiplied by one kilobyte, one
+ *	megabyte, or one gigabyte, respectively.
+ */
+
+unsigned long long memparse (char *ptr, char **retptr)
+{
+	unsigned long long ret = simple_strtoull (ptr, retptr, 0);
+
+	switch (**retptr) {
+	case 'G':
+	case 'g':
+		ret <<= 10;
+	case 'M':
+	case 'm':
+		ret <<= 10;
+	case 'K':
+	case 'k':
+		ret <<= 10;
+		(*retptr)++;
+	default:
+		break;
+	}
+	return ret;
+}
+
+
+EXPORT_SYMBOL(memparse);
+EXPORT_SYMBOL(get_option);
+EXPORT_SYMBOL(get_options);

lib/cpumask.c

@@ -0,0 +1,28 @@
+#include <linux/kernel.h>
+#include <linux/bitops.h>
+#include <linux/cpumask.h>
+#include <linux/module.h>
+
+int __first_cpu(const cpumask_t *srcp)
+{
+	return min_t(int, NR_CPUS, find_first_bit(srcp->bits, NR_CPUS));
+}
+EXPORT_SYMBOL(__first_cpu);
+
+int __next_cpu(int n, const cpumask_t *srcp)
+{
+	return min_t(int, NR_CPUS, find_next_bit(srcp->bits, NR_CPUS, n+1));
+}
+EXPORT_SYMBOL(__next_cpu);
+
+int __any_online_cpu(const cpumask_t *mask)
+{
+	int cpu;
+
+	for_each_cpu_mask(cpu, *mask) {
+		if (cpu_online(cpu))
+			break;
+	}
+	return cpu;
+}
+EXPORT_SYMBOL(__any_online_cpu);

lib/crc-ccitt.c

@@ -0,0 +1,69 @@
+/*
+ *	linux/lib/crc-ccitt.c
+ *
+ *	This source code is licensed under the GNU General Public License,
+ *	Version 2. See the file COPYING for more details.
+ */
+
+#include <linux/types.h>
+#include <linux/module.h>
+#include <linux/crc-ccitt.h>
+
+/*
+ * This mysterious table is just the CRC of each possible byte. It can be
+ * computed using the standard bit-at-a-time methods. The polynomial can
+ * be seen in entry 128, 0x8408. This corresponds to x^0 + x^5 + x^12.
+ * Add the implicit x^16, and you have the standard CRC-CCITT.
+ */
+u16 const crc_ccitt_table[256] = {
+	0x0000, 0x1189, 0x2312, 0x329b, 0x4624, 0x57ad, 0x6536, 0x74bf,
+	0x8c48, 0x9dc1, 0xaf5a, 0xbed3, 0xca6c, 0xdbe5, 0xe97e, 0xf8f7,
+	0x1081, 0x0108, 0x3393, 0x221a, 0x56a5, 0x472c, 0x75b7, 0x643e,
+	0x9cc9, 0x8d40, 0xbfdb, 0xae52, 0xdaed, 0xcb64, 0xf9ff, 0xe876,
+	0x2102, 0x308b, 0x0210, 0x1399, 0x6726, 0x76af, 0x4434, 0x55bd,
+	0xad4a, 0xbcc3, 0x8e58, 0x9fd1, 0xeb6e, 0xfae7, 0xc87c, 0xd9f5,
+	0x3183, 0x200a, 0x1291, 0x0318, 0x77a7, 0x662e, 0x54b5, 0x453c,
+	0xbdcb, 0xac42, 0x9ed9, 0x8f50, 0xfbef, 0xea66, 0xd8fd, 0xc974,
+	0x4204, 0x538d, 0x6116, 0x709f, 0x0420, 0x15a9, 0x2732, 0x36bb,
+	0xce4c, 0xdfc5, 0xed5e, 0xfcd7, 0x8868, 0x99e1, 0xab7a, 0xbaf3,
+	0x5285, 0x430c, 0x7197, 0x601e, 0x14a1, 0x0528, 0x37b3, 0x263a,
+	0xdecd, 0xcf44, 0xfddf, 0xec56, 0x98e9, 0x8960, 0xbbfb, 0xaa72,
+	0x6306, 0x728f, 0x4014, 0x519d, 0x2522, 0x34ab, 0x0630, 0x17b9,
+	0xef4e, 0xfec7, 0xcc5c, 0xddd5, 0xa96a, 0xb8e3, 0x8a78, 0x9bf1,
+	0x7387, 0x620e, 0x5095, 0x411c, 0x35a3, 0x242a, 0x16b1, 0x0738,
+	0xffcf, 0xee46, 0xdcdd, 0xcd54, 0xb9eb, 0xa862, 0x9af9, 0x8b70,
+	0x8408, 0x9581, 0xa71a, 0xb693, 0xc22c, 0xd3a5, 0xe13e, 0xf0b7,
+	0x0840, 0x19c9, 0x2b52, 0x3adb, 0x4e64, 0x5fed, 0x6d76, 0x7cff,
+	0x9489, 0x8500, 0xb79b, 0xa612, 0xd2ad, 0xc324, 0xf1bf, 0xe036,
+	0x18c1, 0x0948, 0x3bd3, 0x2a5a, 0x5ee5, 0x4f6c, 0x7df7, 0x6c7e,
+	0xa50a, 0xb483, 0x8618, 0x9791, 0xe32e, 0xf2a7, 0xc03c, 0xd1b5,
+	0x2942, 0x38cb, 0x0a50, 0x1bd9, 0x6f66, 0x7eef, 0x4c74, 0x5dfd,
+	0xb58b, 0xa402, 0x9699, 0x8710, 0xf3af, 0xe226, 0xd0bd, 0xc134,
+	0x39c3, 0x284a, 0x1ad1, 0x0b58, 0x7fe7, 0x6e6e, 0x5cf5, 0x4d7c,
+	0xc60c, 0xd785, 0xe51e, 0xf497, 0x8028, 0x91a1, 0xa33a, 0xb2b3,
+	0x4a44, 0x5bcd, 0x6956, 0x78df, 0x0c60, 0x1de9, 0x2f72, 0x3efb,
+	0xd68d, 0xc704, 0xf59f, 0xe416, 0x90a9, 0x8120, 0xb3bb, 0xa232,
+	0x5ac5, 0x4b4c, 0x79d7, 0x685e, 0x1ce1, 0x0d68, 0x3ff3, 0x2e7a,
+	0xe70e, 0xf687, 0xc41c, 0xd595, 0xa12a, 0xb0a3, 0x8238, 0x93b1,
+	0x6b46, 0x7acf, 0x4854, 0x59dd, 0x2d62, 0x3ceb, 0x0e70, 0x1ff9,
+	0xf78f, 0xe606, 0xd49d, 0xc514, 0xb1ab, 0xa022, 0x92b9, 0x8330,
+	0x7bc7, 0x6a4e, 0x58d5, 0x495c, 0x3de3, 0x2c6a, 0x1ef1, 0x0f78
+};
+EXPORT_SYMBOL(crc_ccitt_table);
+
+/**
+ *	crc_ccitt - recompute the CRC for the data buffer
+ *	@crc: previous CRC value
+ *	@buffer: data pointer
+ *	@len: number of bytes in the buffer
+ */
+u16 crc_ccitt(u16 crc, u8 const *buffer, size_t len)
+{
+	while (len--)
+		crc = crc_ccitt_byte(crc, *buffer++);
+	return crc;
+}
+EXPORT_SYMBOL(crc_ccitt);
+
+MODULE_DESCRIPTION("CRC-CCITT calculations");
+MODULE_LICENSE("GPL");

lib/crc16.c

@@ -0,0 +1,67 @@
+/*
+ *      crc16.c
+ *
+ * This source code is licensed under the GNU General Public License,
+ * Version 2. See the file COPYING for more details.
+ */
+
+#include <linux/types.h>
+#include <linux/module.h>
+#include <linux/crc16.h>
+
+/** CRC table for the CRC-16. The poly is 0x8005 (x^16 + x^15 + x^2 + 1) */
+u16 const crc16_table[256] = {
+	0x0000, 0xC0C1, 0xC181, 0x0140, 0xC301, 0x03C0, 0x0280, 0xC241,
+	0xC601, 0x06C0, 0x0780, 0xC741, 0x0500, 0xC5C1, 0xC481, 0x0440,
+	0xCC01, 0x0CC0, 0x0D80, 0xCD41, 0x0F00, 0xCFC1, 0xCE81, 0x0E40,
+	0x0A00, 0xCAC1, 0xCB81, 0x0B40, 0xC901, 0x09C0, 0x0880, 0xC841,
+	0xD801, 0x18C0, 0x1980, 0xD941, 0x1B00, 0xDBC1, 0xDA81, 0x1A40,
+	0x1E00, 0xDEC1, 0xDF81, 0x1F40, 0xDD01, 0x1DC0, 0x1C80, 0xDC41,
+	0x1400, 0xD4C1, 0xD581, 0x1540, 0xD701, 0x17C0, 0x1680, 0xD641,
+	0xD201, 0x12C0, 0x1380, 0xD341, 0x1100, 0xD1C1, 0xD081, 0x1040,
+	0xF001, 0x30C0, 0x3180, 0xF141, 0x3300, 0xF3C1, 0xF281, 0x3240,
+	0x3600, 0xF6C1, 0xF781, 0x3740, 0xF501, 0x35C0, 0x3480, 0xF441,
+	0x3C00, 0xFCC1, 0xFD81, 0x3D40, 0xFF01, 0x3FC0, 0x3E80, 0xFE41,
+	0xFA01, 0x3AC0, 0x3B80, 0xFB41, 0x3900, 0xF9C1, 0xF881, 0x3840,
+	0x2800, 0xE8C1, 0xE981, 0x2940, 0xEB01, 0x2BC0, 0x2A80, 0xEA41,
+	0xEE01, 0x2EC0, 0x2F80, 0xEF41, 0x2D00, 0xEDC1, 0xEC81, 0x2C40,
+	0xE401, 0x24C0, 0x2580, 0xE541, 0x2700, 0xE7C1, 0xE681, 0x2640,
+	0x2200, 0xE2C1, 0xE381, 0x2340, 0xE101, 0x21C0, 0x2080, 0xE041,
+	0xA001, 0x60C0, 0x6180, 0xA141, 0x6300, 0xA3C1, 0xA281, 0x6240,
+	0x6600, 0xA6C1, 0xA781, 0x6740, 0xA501, 0x65C0, 0x6480, 0xA441,
+	0x6C00, 0xACC1, 0xAD81, 0x6D40, 0xAF01, 0x6FC0, 0x6E80, 0xAE41,
+	0xAA01, 0x6AC0, 0x6B80, 0xAB41, 0x6900, 0xA9C1, 0xA881, 0x6840,
+	0x7800, 0xB8C1, 0xB981, 0x7940, 0xBB01, 0x7BC0, 0x7A80, 0xBA41,
+	0xBE01, 0x7EC0, 0x7F80, 0xBF41, 0x7D00, 0xBDC1, 0xBC81, 0x7C40,
+	0xB401, 0x74C0, 0x7580, 0xB541, 0x7700, 0xB7C1, 0xB681, 0x7640,
+	0x7200, 0xB2C1, 0xB381, 0x7340, 0xB101, 0x71C0, 0x7080, 0xB041,
+	0x5000, 0x90C1, 0x9181, 0x5140, 0x9301, 0x53C0, 0x5280, 0x9241,
+	0x9601, 0x56C0, 0x5780, 0x9741, 0x5500, 0x95C1, 0x9481, 0x5440,
+	0x9C01, 0x5CC0, 0x5D80, 0x9D41, 0x5F00, 0x9FC1, 0x9E81, 0x5E40,
+	0x5A00, 0x9AC1, 0x9B81, 0x5B40, 0x9901, 0x59C0, 0x5880, 0x9841,
+	0x8801, 0x48C0, 0x4980, 0x8941, 0x4B00, 0x8BC1, 0x8A81, 0x4A40,
+	0x4E00, 0x8EC1, 0x8F81, 0x4F40, 0x8D01, 0x4DC0, 0x4C80, 0x8C41,
+	0x4400, 0x84C1, 0x8581, 0x4540, 0x8701, 0x47C0, 0x4680, 0x8641,
+	0x8201, 0x42C0, 0x4380, 0x8341, 0x4100, 0x81C1, 0x8081, 0x4040
+};
+EXPORT_SYMBOL(crc16_table);
+
+/**
+ * crc16 - compute the CRC-16 for the data buffer
+ * @crc:	previous CRC value
+ * @buffer:	data pointer
+ * @len:	number of bytes in the buffer
+ *
+ * Returns the updated CRC value.
+ */
+u16 crc16(u16 crc, u8 const *buffer, size_t len)
+{
+	while (len--)
+		crc = crc16_byte(crc, *buffer++);
+	return crc;
+}
+EXPORT_SYMBOL(crc16);
+
+MODULE_DESCRIPTION("CRC16 calculations");
+MODULE_LICENSE("GPL");
+

lib/crc32.c

@@ -0,0 +1,501 @@
+/*
+ * 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
+ * subsequently included in the kernel, thus was re-licensed under the
+ * GNU GPL v2.
+ *
+ * Oct 12, 2000 Matt Domsch <Matt_Domsch@dell.com>
+ * Same crc32 function was used in 5 other places in the kernel.
+ * I made one version, and deleted the others.
+ * There are various incantations of crc32().  Some use a seed of 0 or ~0.
+ * Some xor at the end with ~0.  The generic crc32() function takes
+ * seed as an argument, and doesn't xor at the end.  Then individual
+ * users can do whatever they need.
+ *   drivers/net/smc9194.c uses seed ~0, doesn't xor with ~0.
+ *   fs/jffs2 uses seed 0, doesn't xor with ~0.
+ *   fs/partitions/efi.c uses seed ~0, xor's with ~0.
+ *
+ * This source code is licensed under the GNU General Public License,
+ * Version 2.  See the file COPYING for more details.
+ */
+
+#include <linux/crc32.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/compiler.h>
+#include <linux/types.h>
+#include <linux/slab.h>
+#include <linux/init.h>
+#include <asm/atomic.h>
+#include "crc32defs.h"
+#if CRC_LE_BITS == 8
+#define tole(x) __constant_cpu_to_le32(x)
+#define tobe(x) __constant_cpu_to_be32(x)
+#else
+#define tole(x) (x)
+#define tobe(x) (x)
+#endif
+#include "crc32table.h"
+
+MODULE_AUTHOR("Matt Domsch <Matt_Domsch@dell.com>");
+MODULE_DESCRIPTION("Ethernet CRC32 calculations");
+MODULE_LICENSE("GPL");
+
+/**
+ * crc32_le() - Calculate bitwise little-endian Ethernet AUTODIN II CRC32
+ * @crc: seed value for computation.  ~0 for Ethernet, sometimes 0 for
+ *	other uses, or the previous crc32 value if computing incrementally.
+ * @p: pointer to buffer over which CRC is run
+ * @len: length of buffer @p
+ */
+u32 __attribute_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 __attribute_pure__ crc32_le(u32 crc, unsigned char const *p, size_t len)
+{
+	int i;
+	while (len--) {
+		crc ^= *p++;
+		for (i = 0; i < 8; i++)
+			crc = (crc >> 1) ^ ((crc & 1) ? CRCPOLY_LE : 0);
+	}
+	return crc;
+}
+#else				/* Table-based approach */
+
+u32 __attribute_pure__ crc32_le(u32 crc, unsigned char const *p, size_t len)
+{
+# if CRC_LE_BITS == 8
+	const u32      *b =(u32 *)p;
+	const u32      *tab = crc32table_le;
+
+# ifdef __LITTLE_ENDIAN
+#  define DO_CRC(x) crc = tab[ (crc ^ (x)) & 255 ] ^ (crc>>8)
+# else
+#  define DO_CRC(x) crc = tab[ ((crc >> 24) ^ (x)) & 255] ^ (crc<<8)
+# endif
+
+	crc = __cpu_to_le32(crc);
+	/* Align it */
+	if(unlikely(((long)b)&3 && len)){
+		do {
+			u8 *p = (u8 *)b;
+			DO_CRC(*p++);
+			b = (void *)p;
+		} while ((--len) && ((long)b)&3 );
+	}
+	if(likely(len >= 4)){
+		/* load data 32 bits wide, xor data 32 bits wide. */
+		size_t save_len = len & 3;
+	        len = len >> 2;
+		--b; /* use pre increment below(*++b) for speed */
+		do {
+			crc ^= *++b;
+			DO_CRC(0);
+			DO_CRC(0);
+			DO_CRC(0);
+			DO_CRC(0);
+		} while (--len);
+		b++; /* point to next byte(s) */
+		len = save_len;
+	}
+	/* And the last few bytes */
+	if(len){
+		do {
+			u8 *p = (u8 *)b;
+			DO_CRC(*p++);
+			b = (void *)p;
+		} while (--len);
+	}
+
+	return __le32_to_cpu(crc);
+#undef ENDIAN_SHIFT
+#undef DO_CRC
+
+# elif CRC_LE_BITS == 4
+	while (len--) {
+		crc ^= *p++;
+		crc = (crc >> 4) ^ crc32table_le[crc & 15];
+		crc = (crc >> 4) ^ crc32table_le[crc & 15];
+	}
+	return crc;
+# elif CRC_LE_BITS == 2
+	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];
+	}
+	return crc;
+# endif
+}
+#endif
+
+/**
+ * crc32_be() - Calculate bitwise big-endian Ethernet AUTODIN II CRC32
+ * @crc: seed value for computation.  ~0 for Ethernet, sometimes 0 for
+ *	other uses, or the previous crc32 value if computing incrementally.
+ * @p: pointer to buffer over which CRC is run
+ * @len: length of buffer @p
+ */
+u32 __attribute_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 __attribute_pure__ crc32_be(u32 crc, unsigned char const *p, size_t len)
+{
+	int i;
+	while (len--) {
+		crc ^= *p++ << 24;
+		for (i = 0; i < 8; i++)
+			crc =
+			    (crc << 1) ^ ((crc & 0x80000000) ? CRCPOLY_BE :
+					  0);
+	}
+	return crc;
+}
+
+#else				/* Table-based approach */
+u32 __attribute_pure__ crc32_be(u32 crc, unsigned char const *p, size_t len)
+{
+# if CRC_BE_BITS == 8
+	const u32      *b =(u32 *)p;
+	const u32      *tab = crc32table_be;
+
+# ifdef __LITTLE_ENDIAN
+#  define DO_CRC(x) crc = tab[ (crc ^ (x)) & 255 ] ^ (crc>>8)
+# else
+#  define DO_CRC(x) crc = tab[ ((crc >> 24) ^ (x)) & 255] ^ (crc<<8)
+# endif
+
+	crc = __cpu_to_be32(crc);
+	/* Align it */
+	if(unlikely(((long)b)&3 && len)){
+		do {
+			u8 *p = (u8 *)b;
+			DO_CRC(*p++);
+			b = (u32 *)p;
+		} while ((--len) && ((long)b)&3 );
+	}
+	if(likely(len >= 4)){
+		/* load data 32 bits wide, xor data 32 bits wide. */
+		size_t save_len = len & 3;
+	        len = len >> 2;
+		--b; /* use pre increment below(*++b) for speed */
+		do {
+			crc ^= *++b;
+			DO_CRC(0);
+			DO_CRC(0);
+			DO_CRC(0);
+			DO_CRC(0);
+		} while (--len);
+		b++; /* point to next byte(s) */
+		len = save_len;
+	}
+	/* And the last few bytes */
+	if(len){
+		do {
+			u8 *p = (u8 *)b;
+			DO_CRC(*p++);
+			b = (void *)p;
+		} while (--len);
+	}
+	return __be32_to_cpu(crc);
+#undef ENDIAN_SHIFT
+#undef DO_CRC
+
+# elif CRC_BE_BITS == 4
+	while (len--) {
+		crc ^= *p++ << 24;
+		crc = (crc << 4) ^ crc32table_be[crc >> 28];
+		crc = (crc << 4) ^ crc32table_be[crc >> 28];
+	}
+	return crc;
+# elif CRC_BE_BITS == 2
+	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];
+	}
+	return crc;
+# endif
+}
+#endif
+
+EXPORT_SYMBOL(crc32_le);
+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 multile 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
+
+#include <stdlib.h>
+#include <stdio.h>
+
+#if 0				/*Not used at present */
+static void
+buf_dump(char const *prefix, unsigned char const *buf, size_t len)
+{
+	fputs(prefix, stdout);
+	while (len--)
+		printf(" %02x", *buf++);
+	putchar('\n');
+
+}
+#endif
+
+static void bytereverse(unsigned char *buf, size_t len)
+{
+	while (len--) {
+		unsigned char x = bitrev8(*buf);
+		*buf++ = x;
+	}
+}
+
+static void random_garbage(unsigned char *buf, size_t len)
+{
+	while (len--)
+		*buf++ = (unsigned char) random();
+}
+
+#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
+
+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;
+}
+
+/*
+ * 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)
+{
+	u32 crc1, crc2;
+	size_t i;
+
+	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);
+	}
+
+	/* 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);
+	}
+
+	return crc1;
+}
+
+#define SIZE 64
+#define INIT1 0
+#define INIT2 0
+
+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);
+	}
+	printf("\nAll test complete.  No failures expected.\n");
+	return 0;
+}
+
+#endif				/* UNITTEST */

lib/crc32defs.h

@@ -0,0 +1,32 @@
+/*
+ * There are multiple 16-bit CRC polynomials in common use, but this is
+ * *the* standard CRC-32 polynomial, first popularized by Ethernet.
+ * x^32+x^26+x^23+x^22+x^16+x^12+x^11+x^10+x^8+x^7+x^5+x^4+x^2+x^1+x^0
+ */
+#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 
+# define CRC_LE_BITS 8
+#endif
+#ifndef CRC_BE_BITS
+# define CRC_BE_BITS 8
+#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
+#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
+#endif

lib/ctype.c

@@ -0,0 +1,36 @@
+/*
+ *  linux/lib/ctype.c
+ *
+ *  Copyright (C) 1991, 1992  Linus Torvalds
+ */
+
+#include <linux/ctype.h>
+#include <linux/module.h>
+
+unsigned char _ctype[] = {
+_C,_C,_C,_C,_C,_C,_C,_C,			/* 0-7 */
+_C,_C|_S,_C|_S,_C|_S,_C|_S,_C|_S,_C,_C,		/* 8-15 */
+_C,_C,_C,_C,_C,_C,_C,_C,			/* 16-23 */
+_C,_C,_C,_C,_C,_C,_C,_C,			/* 24-31 */
+_S|_SP,_P,_P,_P,_P,_P,_P,_P,			/* 32-39 */
+_P,_P,_P,_P,_P,_P,_P,_P,			/* 40-47 */
+_D,_D,_D,_D,_D,_D,_D,_D,			/* 48-55 */
+_D,_D,_P,_P,_P,_P,_P,_P,			/* 56-63 */
+_P,_U|_X,_U|_X,_U|_X,_U|_X,_U|_X,_U|_X,_U,	/* 64-71 */
+_U,_U,_U,_U,_U,_U,_U,_U,			/* 72-79 */
+_U,_U,_U,_U,_U,_U,_U,_U,			/* 80-87 */
+_U,_U,_U,_P,_P,_P,_P,_P,			/* 88-95 */
+_P,_L|_X,_L|_X,_L|_X,_L|_X,_L|_X,_L|_X,_L,	/* 96-103 */
+_L,_L,_L,_L,_L,_L,_L,_L,			/* 104-111 */
+_L,_L,_L,_L,_L,_L,_L,_L,			/* 112-119 */
+_L,_L,_L,_P,_P,_P,_P,_C,			/* 120-127 */
+0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,		/* 128-143 */
+0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,		/* 144-159 */
+_S|_SP,_P,_P,_P,_P,_P,_P,_P,_P,_P,_P,_P,_P,_P,_P,_P,   /* 160-175 */
+_P,_P,_P,_P,_P,_P,_P,_P,_P,_P,_P,_P,_P,_P,_P,_P,       /* 176-191 */
+_U,_U,_U,_U,_U,_U,_U,_U,_U,_U,_U,_U,_U,_U,_U,_U,       /* 192-207 */
+_U,_U,_U,_U,_U,_U,_U,_P,_U,_U,_U,_U,_U,_U,_U,_L,       /* 208-223 */
+_L,_L,_L,_L,_L,_L,_L,_L,_L,_L,_L,_L,_L,_L,_L,_L,       /* 224-239 */
+_L,_L,_L,_L,_L,_L,_L,_P,_L,_L,_L,_L,_L,_L,_L,_L};      /* 240-255 */
+
+EXPORT_SYMBOL(_ctype);

lib/debug_locks.c

@@ -0,0 +1,45 @@
+/*
+ * lib/debug_locks.c
+ *
+ * Generic place for common debugging facilities for various locks:
+ * spinlocks, rwlocks, mutexes and rwsems.
+ *
+ * Started by Ingo Molnar:
+ *
+ *  Copyright (C) 2006 Red Hat, Inc., Ingo Molnar <mingo@redhat.com>
+ */
+#include <linux/rwsem.h>
+#include <linux/mutex.h>
+#include <linux/module.h>
+#include <linux/spinlock.h>
+#include <linux/debug_locks.h>
+
+/*
+ * We want to turn all lock-debugging facilities on/off at once,
+ * via a global flag. The reason is that once a single bug has been
+ * detected and reported, there might be cascade of followup bugs
+ * that would just muddy the log. So we report the first one and
+ * shut up after that.
+ */
+int debug_locks = 1;
+
+/*
+ * The locking-testsuite uses <debug_locks_silent> to get a
+ * 'silent failure': nothing is printed to the console when
+ * a locking bug is detected.
+ */
+int debug_locks_silent;
+
+/*
+ * Generic 'turn off all lock debugging' function:
+ */
+int debug_locks_off(void)
+{
+	if (xchg(&debug_locks, 0)) {
+		if (!debug_locks_silent) {
+			console_verbose();
+			return 1;
+		}
+	}
+	return 0;
+}

lib/dec_and_lock.c

@@ -0,0 +1,35 @@
+#include <linux/module.h>
+#include <linux/spinlock.h>
+#include <asm/atomic.h>
+
+/*
+ * This is an implementation of the notion of "decrement a
+ * reference count, and return locked if it decremented to zero".
+ *
+ * NOTE NOTE NOTE! This is _not_ equivalent to
+ *
+ *	if (atomic_dec_and_test(&atomic)) {
+ *		spin_lock(&lock);
+ *		return 1;
+ *	}
+ *	return 0;
+ *
+ * because the spin-lock and the decrement must be
+ * "atomic".
+ */
+int _atomic_dec_and_lock(atomic_t *atomic, spinlock_t *lock)
+{
+#ifdef CONFIG_SMP
+	/* Subtract 1 from counter unless that drops it to 0 (ie. it was 1) */
+	if (atomic_add_unless(atomic, -1, 1))
+		return 0;
+#endif
+	/* Otherwise do it the slow way */
+	spin_lock(lock);
+	if (atomic_dec_and_test(atomic))
+		return 1;
+	spin_unlock(lock);
+	return 0;
+}
+
+EXPORT_SYMBOL(_atomic_dec_and_lock);

lib/devres.c

@@ -0,0 +1,300 @@
+#include <linux/pci.h>
+#include <linux/io.h>
+#include <linux/module.h>
+
+static void devm_ioremap_release(struct device *dev, void *res)
+{
+	iounmap(*(void __iomem **)res);
+}
+
+static int devm_ioremap_match(struct device *dev, void *res, void *match_data)
+{
+	return *(void **)res == match_data;
+}
+
+/**
+ * devm_ioremap - Managed ioremap()
+ * @dev: Generic device to remap IO address for
+ * @offset: BUS offset to map
+ * @size: Size of map
+ *
+ * Managed ioremap().  Map is automatically unmapped on driver detach.
+ */
+void __iomem *devm_ioremap(struct device *dev, unsigned long offset,
+			   unsigned long size)
+{
+	void __iomem **ptr, *addr;
+
+	ptr = devres_alloc(devm_ioremap_release, sizeof(*ptr), GFP_KERNEL);
+	if (!ptr)
+		return NULL;
+
+	addr = ioremap(offset, size);
+	if (addr) {
+		*ptr = addr;
+		devres_add(dev, ptr);
+	} else
+		devres_free(ptr);
+
+	return addr;
+}
+EXPORT_SYMBOL(devm_ioremap);
+
+/**
+ * devm_ioremap_nocache - Managed ioremap_nocache()
+ * @dev: Generic device to remap IO address for
+ * @offset: BUS offset to map
+ * @size: Size of map
+ *
+ * Managed ioremap_nocache().  Map is automatically unmapped on driver
+ * detach.
+ */
+void __iomem *devm_ioremap_nocache(struct device *dev, unsigned long offset,
+				   unsigned long size)
+{
+	void __iomem **ptr, *addr;
+
+	ptr = devres_alloc(devm_ioremap_release, sizeof(*ptr), GFP_KERNEL);
+	if (!ptr)
+		return NULL;
+
+	addr = ioremap_nocache(offset, size);
+	if (addr) {
+		*ptr = addr;
+		devres_add(dev, ptr);
+	} else
+		devres_free(ptr);
+
+	return addr;
+}
+EXPORT_SYMBOL(devm_ioremap_nocache);
+
+/**
+ * devm_iounmap - Managed iounmap()
+ * @dev: Generic device to unmap for
+ * @addr: Address to unmap
+ *
+ * Managed iounmap().  @addr must have been mapped using devm_ioremap*().
+ */
+void devm_iounmap(struct device *dev, void __iomem *addr)
+{
+	iounmap(addr);
+	WARN_ON(devres_destroy(dev, devm_ioremap_release, devm_ioremap_match,
+			       (void *)addr));
+}
+EXPORT_SYMBOL(devm_iounmap);
+
+#ifdef CONFIG_HAS_IOPORT
+/*
+ * Generic iomap devres
+ */
+static void devm_ioport_map_release(struct device *dev, void *res)
+{
+	ioport_unmap(*(void __iomem **)res);
+}
+
+static int devm_ioport_map_match(struct device *dev, void *res,
+				 void *match_data)
+{
+	return *(void **)res == match_data;
+}
+
+/**
+ * devm_ioport_map - Managed ioport_map()
+ * @dev: Generic device to map ioport for
+ * @port: Port to map
+ * @nr: Number of ports to map
+ *
+ * Managed ioport_map().  Map is automatically unmapped on driver
+ * detach.
+ */
+void __iomem * devm_ioport_map(struct device *dev, unsigned long port,
+			       unsigned int nr)
+{
+	void __iomem **ptr, *addr;
+
+	ptr = devres_alloc(devm_ioport_map_release, sizeof(*ptr), GFP_KERNEL);
+	if (!ptr)
+		return NULL;
+
+	addr = ioport_map(port, nr);
+	if (addr) {
+		*ptr = addr;
+		devres_add(dev, ptr);
+	} else
+		devres_free(ptr);
+
+	return addr;
+}
+EXPORT_SYMBOL(devm_ioport_map);
+
+/**
+ * devm_ioport_unmap - Managed ioport_unmap()
+ * @dev: Generic device to unmap for
+ * @addr: Address to unmap
+ *
+ * Managed ioport_unmap().  @addr must have been mapped using
+ * devm_ioport_map().
+ */
+void devm_ioport_unmap(struct device *dev, void __iomem *addr)
+{
+	ioport_unmap(addr);
+	WARN_ON(devres_destroy(dev, devm_ioport_map_release,
+			       devm_ioport_map_match, (void *)addr));
+}
+EXPORT_SYMBOL(devm_ioport_unmap);
+
+#ifdef CONFIG_PCI
+/*
+ * PCI iomap devres
+ */
+#define PCIM_IOMAP_MAX	PCI_ROM_RESOURCE
+
+struct pcim_iomap_devres {
+	void __iomem *table[PCIM_IOMAP_MAX];
+};
+
+static void pcim_iomap_release(struct device *gendev, void *res)
+{
+	struct pci_dev *dev = container_of(gendev, struct pci_dev, dev);
+	struct pcim_iomap_devres *this = res;
+	int i;
+
+	for (i = 0; i < PCIM_IOMAP_MAX; i++)
+		if (this->table[i])
+			pci_iounmap(dev, this->table[i]);
+}
+
+/**
+ * pcim_iomap_table - access iomap allocation table
+ * @pdev: PCI device to access iomap table for
+ *
+ * Access iomap allocation table for @dev.  If iomap table doesn't
+ * exist and @pdev is managed, it will be allocated.  All iomaps
+ * recorded in the iomap table are automatically unmapped on driver
+ * detach.
+ *
+ * This function might sleep when the table is first allocated but can
+ * be safely called without context and guaranteed to succed once
+ * allocated.
+ */
+void __iomem * const * pcim_iomap_table(struct pci_dev *pdev)
+{
+	struct pcim_iomap_devres *dr, *new_dr;
+
+	dr = devres_find(&pdev->dev, pcim_iomap_release, NULL, NULL);
+	if (dr)
+		return dr->table;
+
+	new_dr = devres_alloc(pcim_iomap_release, sizeof(*new_dr), GFP_KERNEL);
+	if (!new_dr)
+		return NULL;
+	dr = devres_get(&pdev->dev, new_dr, NULL, NULL);
+	return dr->table;
+}
+EXPORT_SYMBOL(pcim_iomap_table);
+
+/**
+ * pcim_iomap - Managed pcim_iomap()
+ * @pdev: PCI device to iomap for
+ * @bar: BAR to iomap
+ * @maxlen: Maximum length of iomap
+ *
+ * Managed pci_iomap().  Map is automatically unmapped on driver
+ * detach.
+ */
+void __iomem * pcim_iomap(struct pci_dev *pdev, int bar, unsigned long maxlen)
+{
+	void __iomem **tbl;
+
+	BUG_ON(bar >= PCIM_IOMAP_MAX);
+
+	tbl = (void __iomem **)pcim_iomap_table(pdev);
+	if (!tbl || tbl[bar])	/* duplicate mappings not allowed */
+		return NULL;
+
+	tbl[bar] = pci_iomap(pdev, bar, maxlen);
+	return tbl[bar];
+}
+EXPORT_SYMBOL(pcim_iomap);
+
+/**
+ * pcim_iounmap - Managed pci_iounmap()
+ * @pdev: PCI device to iounmap for
+ * @addr: Address to unmap
+ *
+ * Managed pci_iounmap().  @addr must have been mapped using pcim_iomap().
+ */
+void pcim_iounmap(struct pci_dev *pdev, void __iomem *addr)
+{
+	void __iomem **tbl;
+	int i;
+
+	pci_iounmap(pdev, addr);
+
+	tbl = (void __iomem **)pcim_iomap_table(pdev);
+	BUG_ON(!tbl);
+
+	for (i = 0; i < PCIM_IOMAP_MAX; i++)
+		if (tbl[i] == addr) {
+			tbl[i] = NULL;
+			return;
+		}
+	WARN_ON(1);
+}
+EXPORT_SYMBOL(pcim_iounmap);
+
+/**
+ * pcim_iomap_regions - Request and iomap PCI BARs
+ * @pdev: PCI device to map IO resources for
+ * @mask: Mask of BARs to request and iomap
+ * @name: Name used when requesting regions
+ *
+ * Request and iomap regions specified by @mask.
+ */
+int pcim_iomap_regions(struct pci_dev *pdev, u16 mask, const char *name)
+{
+	void __iomem * const *iomap;
+	int i, rc;
+
+	iomap = pcim_iomap_table(pdev);
+	if (!iomap)
+		return -ENOMEM;
+
+	for (i = 0; i < DEVICE_COUNT_RESOURCE; i++) {
+		unsigned long len;
+
+		if (!(mask & (1 << i)))
+			continue;
+
+		rc = -EINVAL;
+		len = pci_resource_len(pdev, i);
+		if (!len)
+			goto err_inval;
+
+		rc = pci_request_region(pdev, i, name);
+		if (rc)
+			goto err_inval;
+
+		rc = -ENOMEM;
+		if (!pcim_iomap(pdev, i, 0))
+			goto err_region;
+	}
+
+	return 0;
+
+ err_region:
+	pci_release_region(pdev, i);
+ err_inval:
+	while (--i >= 0) {
+		if (!(mask & (1 << i)))
+			continue;
+		pcim_iounmap(pdev, iomap[i]);
+		pci_release_region(pdev, i);
+	}
+
+	return rc;
+}
+EXPORT_SYMBOL(pcim_iomap_regions);
+#endif
+#endif

lib/div64.c

@@ -0,0 +1,83 @@
+/*
+ * Copyright (C) 2003 Bernardo Innocenti <bernie@develer.com>
+ *
+ * Based on former do_div() implementation from asm-parisc/div64.h:
+ *	Copyright (C) 1999 Hewlett-Packard Co
+ *	Copyright (C) 1999 David Mosberger-Tang <davidm@hpl.hp.com>
+ *
+ *
+ * Generic C version of 64bit/32bit division and modulo, with
+ * 64bit result and 32bit remainder.
+ *
+ * The fast case for (n>>32 == 0) is handled inline by do_div(). 
+ *
+ * Code generated for this function might be very inefficient
+ * for some CPUs. __div64_32() can be overridden by linking arch-specific
+ * assembly versions such as arch/ppc/lib/div64.S and arch/sh/lib/div64.S.
+ */
+
+#include <linux/types.h>
+#include <linux/module.h>
+#include <asm/div64.h>
+
+/* Not needed on 64bit architectures */
+#if BITS_PER_LONG == 32
+
+uint32_t __div64_32(uint64_t *n, uint32_t base)
+{
+	uint64_t rem = *n;
+	uint64_t b = base;
+	uint64_t res, d = 1;
+	uint32_t high = rem >> 32;
+
+	/* Reduce the thing a bit first */
+	res = 0;
+	if (high >= base) {
+		high /= base;
+		res = (uint64_t) high << 32;
+		rem -= (uint64_t) (high*base) << 32;
+	}
+
+	while ((int64_t)b > 0 && b < rem) {
+		b = b+b;
+		d = d+d;
+	}
+
+	do {
+		if (rem >= b) {
+			rem -= b;
+			res += d;
+		}
+		b >>= 1;
+		d >>= 1;
+	} while (d);
+
+	*n = res;
+	return rem;
+}
+
+EXPORT_SYMBOL(__div64_32);
+
+/* 64bit divisor, dividend and result. dynamic precision */
+uint64_t div64_64(uint64_t dividend, uint64_t divisor)
+{
+	uint32_t d = divisor;
+
+	if (divisor > 0xffffffffULL) {
+		unsigned int shift = fls(divisor >> 32);
+
+		d = divisor >> shift;
+		dividend >>= shift;
+	}
+
+	/* avoid 64 bit division if possible */
+	if (dividend >> 32)
+		do_div(dividend, d);
+	else
+		dividend = (uint32_t) dividend / d;
+
+	return dividend;
+}
+EXPORT_SYMBOL(div64_64);
+
+#endif /* BITS_PER_LONG == 32 */

lib/dump_stack.c

@@ -0,0 +1,15 @@
+/*
+ * Provide a default dump_stack() function for architectures
+ * which don't implement their own.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+
+void dump_stack(void)
+{
+	printk(KERN_NOTICE
+		"This architecture does not implement dump_stack()\n");
+}
+
+EXPORT_SYMBOL(dump_stack);

lib/extable.c

@@ -0,0 +1,74 @@
+/*
+ * Derived from arch/ppc/mm/extable.c and arch/i386/mm/extable.c.
+ *
+ * Copyright (C) 2004 Paul Mackerras, IBM Corp.
+ *
+ * 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/module.h>
+#include <linux/init.h>
+#include <linux/sort.h>
+#include <asm/uaccess.h>
+
+#ifndef ARCH_HAS_SORT_EXTABLE
+/*
+ * The exception table needs to be sorted so that the binary
+ * search that we use to find entries in it works properly.
+ * This is used both for the kernel exception table and for
+ * the exception tables of modules that get loaded.
+ */
+static int cmp_ex(const void *a, const void *b)
+{
+	const struct exception_table_entry *x = a, *y = b;
+
+	/* avoid overflow */
+	if (x->insn > y->insn)
+		return 1;
+	if (x->insn < y->insn)
+		return -1;
+	return 0;
+}
+
+void sort_extable(struct exception_table_entry *start,
+		  struct exception_table_entry *finish)
+{
+	sort(start, finish - start, sizeof(struct exception_table_entry),
+	     cmp_ex, NULL);
+}
+#endif
+
+#ifndef ARCH_HAS_SEARCH_EXTABLE
+/*
+ * Search one exception table for an entry corresponding to the
+ * given instruction address, and return the address of the entry,
+ * or NULL if none is found.
+ * We use a binary search, and thus we assume that the table is
+ * already sorted.
+ */
+const struct exception_table_entry *
+search_extable(const struct exception_table_entry *first,
+	       const struct exception_table_entry *last,
+	       unsigned long value)
+{
+	while (first <= last) {
+		const struct exception_table_entry *mid;
+
+		mid = (last - first) / 2 + first;
+		/*
+		 * careful, the distance between entries can be
+		 * larger than 2GB:
+		 */
+		if (mid->insn < value)
+			first = mid + 1;
+		else if (mid->insn > value)
+			last = mid - 1;
+		else
+			return mid;
+        }
+        return NULL;
+}
+#endif

lib/fault-inject.c

@@ -0,0 +1,307 @@
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/random.h>
+#include <linux/stat.h>
+#include <linux/types.h>
+#include <linux/fs.h>
+#include <linux/module.h>
+#include <linux/interrupt.h>
+#include <linux/unwind.h>
+#include <linux/stacktrace.h>
+#include <linux/kallsyms.h>
+#include <linux/fault-inject.h>
+
+/*
+ * 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)
+{
+	unsigned long probability;
+	unsigned long interval;
+	int times;
+	int space;
+
+	/* "<interval>,<probability>,<space>,<times>" */
+	if (sscanf(str, "%lu,%lu,%d,%d",
+			&interval, &probability, &space, &times) < 4) {
+		printk(KERN_WARNING
+			"FAULT_INJECTION: failed to parse arguments\n");
+		return 0;
+	}
+
+	attr->probability = probability;
+	attr->interval = interval;
+	atomic_set(&attr->times, times);
+	atomic_set(&attr->space, space);
+
+	return 1;
+}
+
+static void fail_dump(struct fault_attr *attr)
+{
+	if (attr->verbose > 0)
+		printk(KERN_NOTICE "FAULT_INJECTION: forcing a failure\n");
+	if (attr->verbose > 1)
+		dump_stack();
+}
+
+#define atomic_dec_not_zero(v)		atomic_add_unless((v), -1, 0)
+
+static bool fail_task(struct fault_attr *attr, struct task_struct *task)
+{
+	return !in_interrupt() && task->make_it_fail;
+}
+
+#define MAX_STACK_TRACE_DEPTH 32
+
+#ifdef CONFIG_FAULT_INJECTION_STACKTRACE_FILTER
+
+static bool fail_stacktrace(struct fault_attr *attr)
+{
+	struct stack_trace trace;
+	int depth = attr->stacktrace_depth;
+	unsigned long entries[MAX_STACK_TRACE_DEPTH];
+	int n;
+	bool found = (attr->require_start == 0 && attr->require_end == ULONG_MAX);
+
+	if (depth == 0)
+		return found;
+
+	trace.nr_entries = 0;
+	trace.entries = entries;
+	trace.max_entries = depth;
+	trace.skip = 1;
+	trace.all_contexts = 0;
+
+	save_stack_trace(&trace, NULL);
+	for (n = 0; n < trace.nr_entries; n++) {
+		if (attr->reject_start <= entries[n] &&
+			       entries[n] < attr->reject_end)
+			return false;
+		if (attr->require_start <= entries[n] &&
+			       entries[n] < attr->require_end)
+			found = true;
+	}
+	return found;
+}
+
+#else
+
+static inline bool fail_stacktrace(struct fault_attr *attr)
+{
+	return true;
+}
+
+#endif /* CONFIG_FAULT_INJECTION_STACKTRACE_FILTER */
+
+/*
+ * This code is stolen from failmalloc-1.0
+ * http://www.nongnu.org/failmalloc/
+ */
+
+bool should_fail(struct fault_attr *attr, ssize_t size)
+{
+	if (attr->task_filter && !fail_task(attr, current))
+		return false;
+
+	if (atomic_read(&attr->times) == 0)
+		return false;
+
+	if (atomic_read(&attr->space) > size) {
+		atomic_sub(size, &attr->space);
+		return false;
+	}
+
+	if (attr->interval > 1) {
+		attr->count++;
+		if (attr->count % attr->interval)
+			return false;
+	}
+
+	if (attr->probability <= random32() % 100)
+		return false;
+
+	if (!fail_stacktrace(attr))
+		return false;
+
+	fail_dump(attr);
+
+	if (atomic_read(&attr->times) != -1)
+		atomic_dec_not_zero(&attr->times);
+
+	return true;
+}
+
+#ifdef CONFIG_FAULT_INJECTION_DEBUG_FS
+
+static void debugfs_ul_set(void *data, u64 val)
+{
+	*(unsigned long *)data = val;
+}
+
+static void debugfs_ul_set_MAX_STACK_TRACE_DEPTH(void *data, u64 val)
+{
+	*(unsigned long *)data =
+		val < MAX_STACK_TRACE_DEPTH ?
+		val : MAX_STACK_TRACE_DEPTH;
+}
+
+static u64 debugfs_ul_get(void *data)
+{
+	return *(unsigned long *)data;
+}
+
+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,
+				struct dentry *parent, unsigned long *value)
+{
+	return debugfs_create_file(name, mode, parent, value, &fops_ul);
+}
+
+DEFINE_SIMPLE_ATTRIBUTE(fops_ul_MAX_STACK_TRACE_DEPTH, debugfs_ul_get,
+			debugfs_ul_set_MAX_STACK_TRACE_DEPTH, "%llu\n");
+
+static struct dentry *debugfs_create_ul_MAX_STACK_TRACE_DEPTH(
+	const char *name, mode_t mode,
+	struct dentry *parent, unsigned long *value)
+{
+	return debugfs_create_file(name, mode, parent, value,
+				   &fops_ul_MAX_STACK_TRACE_DEPTH);
+}
+
+static void debugfs_atomic_t_set(void *data, u64 val)
+{
+	atomic_set((atomic_t *)data, val);
+}
+
+static u64 debugfs_atomic_t_get(void *data)
+{
+	return atomic_read((atomic_t *)data);
+}
+
+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,
+				struct dentry *parent, atomic_t *value)
+{
+	return debugfs_create_file(name, mode, parent, value, &fops_atomic_t);
+}
+
+void cleanup_fault_attr_dentries(struct fault_attr *attr)
+{
+	debugfs_remove(attr->dentries.probability_file);
+	attr->dentries.probability_file = NULL;
+
+	debugfs_remove(attr->dentries.interval_file);
+	attr->dentries.interval_file = NULL;
+
+	debugfs_remove(attr->dentries.times_file);
+	attr->dentries.times_file = NULL;
+
+	debugfs_remove(attr->dentries.space_file);
+	attr->dentries.space_file = NULL;
+
+	debugfs_remove(attr->dentries.verbose_file);
+	attr->dentries.verbose_file = NULL;
+
+	debugfs_remove(attr->dentries.task_filter_file);
+	attr->dentries.task_filter_file = NULL;
+
+#ifdef CONFIG_FAULT_INJECTION_STACKTRACE_FILTER
+
+	debugfs_remove(attr->dentries.stacktrace_depth_file);
+	attr->dentries.stacktrace_depth_file = NULL;
+
+	debugfs_remove(attr->dentries.require_start_file);
+	attr->dentries.require_start_file = NULL;
+
+	debugfs_remove(attr->dentries.require_end_file);
+	attr->dentries.require_end_file = NULL;
+
+	debugfs_remove(attr->dentries.reject_start_file);
+	attr->dentries.reject_start_file = NULL;
+
+	debugfs_remove(attr->dentries.reject_end_file);
+	attr->dentries.reject_end_file = NULL;
+
+#endif /* CONFIG_FAULT_INJECTION_STACKTRACE_FILTER */
+
+	if (attr->dentries.dir)
+		WARN_ON(!simple_empty(attr->dentries.dir));
+
+	debugfs_remove(attr->dentries.dir);
+	attr->dentries.dir = NULL;
+}
+
+int init_fault_attr_dentries(struct fault_attr *attr, const char *name)
+{
+	mode_t mode = S_IFREG | S_IRUSR | S_IWUSR;
+	struct dentry *dir;
+
+	memset(&attr->dentries, 0, sizeof(attr->dentries));
+
+	dir = debugfs_create_dir(name, NULL);
+	if (!dir)
+		goto fail;
+	attr->dentries.dir = dir;
+
+	attr->dentries.probability_file =
+		debugfs_create_ul("probability", mode, dir, &attr->probability);
+
+	attr->dentries.interval_file =
+		debugfs_create_ul("interval", mode, dir, &attr->interval);
+
+	attr->dentries.times_file =
+		debugfs_create_atomic_t("times", mode, dir, &attr->times);
+
+	attr->dentries.space_file =
+		debugfs_create_atomic_t("space", mode, dir, &attr->space);
+
+	attr->dentries.verbose_file =
+		debugfs_create_ul("verbose", mode, dir, &attr->verbose);
+
+	attr->dentries.task_filter_file = debugfs_create_bool("task-filter",
+						mode, dir, &attr->task_filter);
+
+	if (!attr->dentries.probability_file || !attr->dentries.interval_file ||
+	    !attr->dentries.times_file || !attr->dentries.space_file ||
+	    !attr->dentries.verbose_file || !attr->dentries.task_filter_file)
+		goto fail;
+
+#ifdef CONFIG_FAULT_INJECTION_STACKTRACE_FILTER
+
+	attr->dentries.stacktrace_depth_file =
+		debugfs_create_ul_MAX_STACK_TRACE_DEPTH(
+			"stacktrace-depth", mode, dir, &attr->stacktrace_depth);
+
+	attr->dentries.require_start_file =
+		debugfs_create_ul("require-start", mode, dir, &attr->require_start);
+
+	attr->dentries.require_end_file =
+		debugfs_create_ul("require-end", mode, dir, &attr->require_end);
+
+	attr->dentries.reject_start_file =
+		debugfs_create_ul("reject-start", mode, dir, &attr->reject_start);
+
+	attr->dentries.reject_end_file =
+		debugfs_create_ul("reject-end", mode, dir, &attr->reject_end);
+
+	if (!attr->dentries.stacktrace_depth_file ||
+	    !attr->dentries.require_start_file ||
+	    !attr->dentries.require_end_file ||
+	    !attr->dentries.reject_start_file ||
+	    !attr->dentries.reject_end_file)
+		goto fail;
+
+#endif /* CONFIG_FAULT_INJECTION_STACKTRACE_FILTER */
+
+	return 0;
+fail:
+	cleanup_fault_attr_dentries(attr);
+	return -ENOMEM;
+}
+
+#endif /* CONFIG_FAULT_INJECTION_DEBUG_FS */

lib/find_next_bit.c

@@ -0,0 +1,181 @@
+/* find_next_bit.c: fallback find next bit implementation
+ *
+ * Copyright (C) 2004 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 License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/bitops.h>
+#include <linux/module.h>
+#include <asm/types.h>
+#include <asm/byteorder.h>
+
+#define BITOP_WORD(nr)		((nr) / BITS_PER_LONG)
+
+/**
+ * find_next_bit - find the next set bit in a memory region
+ * @addr: The address to base the search on
+ * @offset: The bitnumber to start searching at
+ * @size: The maximum size to search
+ */
+unsigned long find_next_bit(const unsigned long *addr, unsigned long size,
+		unsigned long offset)
+{
+	const unsigned long *p = addr + BITOP_WORD(offset);
+	unsigned long result = offset & ~(BITS_PER_LONG-1);
+	unsigned long tmp;
+
+	if (offset >= size)
+		return size;
+	size -= result;
+	offset %= BITS_PER_LONG;
+	if (offset) {
+		tmp = *(p++);
+		tmp &= (~0UL << offset);
+		if (size < BITS_PER_LONG)
+			goto found_first;
+		if (tmp)
+			goto found_middle;
+		size -= BITS_PER_LONG;
+		result += BITS_PER_LONG;
+	}
+	while (size & ~(BITS_PER_LONG-1)) {
+		if ((tmp = *(p++)))
+			goto found_middle;
+		result += BITS_PER_LONG;
+		size -= BITS_PER_LONG;
+	}
+	if (!size)
+		return result;
+	tmp = *p;
+
+found_first:
+	tmp &= (~0UL >> (BITS_PER_LONG - size));
+	if (tmp == 0UL)		/* Are any bits set? */
+		return result + size;	/* Nope. */
+found_middle:
+	return result + __ffs(tmp);
+}
+
+EXPORT_SYMBOL(find_next_bit);
+
+/*
+ * This implementation of find_{first,next}_zero_bit was stolen from
+ * Linus' asm-alpha/bitops.h.
+ */
+unsigned long find_next_zero_bit(const unsigned long *addr, unsigned long size,
+		unsigned long offset)
+{
+	const unsigned long *p = addr + BITOP_WORD(offset);
+	unsigned long result = offset & ~(BITS_PER_LONG-1);
+	unsigned long tmp;
+
+	if (offset >= size)
+		return size;
+	size -= result;
+	offset %= BITS_PER_LONG;
+	if (offset) {
+		tmp = *(p++);
+		tmp |= ~0UL >> (BITS_PER_LONG - offset);
+		if (size < BITS_PER_LONG)
+			goto found_first;
+		if (~tmp)
+			goto found_middle;
+		size -= BITS_PER_LONG;
+		result += BITS_PER_LONG;
+	}
+	while (size & ~(BITS_PER_LONG-1)) {
+		if (~(tmp = *(p++)))
+			goto found_middle;
+		result += BITS_PER_LONG;
+		size -= BITS_PER_LONG;
+	}
+	if (!size)
+		return result;
+	tmp = *p;
+
+found_first:
+	tmp |= ~0UL << size;
+	if (tmp == ~0UL)	/* Are any bits zero? */
+		return result + size;	/* Nope. */
+found_middle:
+	return result + ffz(tmp);
+}
+
+EXPORT_SYMBOL(find_next_zero_bit);
+
+#ifdef __BIG_ENDIAN
+
+/* include/linux/byteorder does not support "unsigned long" type */
+static inline unsigned long ext2_swabp(const unsigned long * x)
+{
+#if BITS_PER_LONG == 64
+	return (unsigned long) __swab64p((u64 *) x);
+#elif BITS_PER_LONG == 32
+	return (unsigned long) __swab32p((u32 *) x);
+#else
+#error BITS_PER_LONG not defined
+#endif
+}
+
+/* include/linux/byteorder doesn't support "unsigned long" type */
+static inline unsigned long ext2_swab(const unsigned long y)
+{
+#if BITS_PER_LONG == 64
+	return (unsigned long) __swab64((u64) y);
+#elif BITS_PER_LONG == 32
+	return (unsigned long) __swab32((u32) y);
+#else
+#error BITS_PER_LONG not defined
+#endif
+}
+
+unsigned long generic_find_next_zero_le_bit(const unsigned long *addr, unsigned
+		long size, unsigned long offset)
+{
+	const unsigned long *p = addr + BITOP_WORD(offset);
+	unsigned long result = offset & ~(BITS_PER_LONG - 1);
+	unsigned long tmp;
+
+	if (offset >= size)
+		return size;
+	size -= result;
+	offset &= (BITS_PER_LONG - 1UL);
+	if (offset) {
+		tmp = ext2_swabp(p++);
+		tmp |= (~0UL >> (BITS_PER_LONG - offset));
+		if (size < BITS_PER_LONG)
+			goto found_first;
+		if (~tmp)
+			goto found_middle;
+		size -= BITS_PER_LONG;
+		result += BITS_PER_LONG;
+	}
+
+	while (size & ~(BITS_PER_LONG - 1)) {
+		if (~(tmp = *(p++)))
+			goto found_middle_swap;
+		result += BITS_PER_LONG;
+		size -= BITS_PER_LONG;
+	}
+	if (!size)
+		return result;
+	tmp = ext2_swabp(p);
+found_first:
+	tmp |= ~0UL << size;
+	if (tmp == ~0UL)	/* Are any bits zero? */
+		return result + size; /* Nope. Skip ffz */
+found_middle:
+	return result + ffz(tmp);
+
+found_middle_swap:
+	return result + ffz(ext2_swab(tmp));
+}
+
+EXPORT_SYMBOL(generic_find_next_zero_le_bit);
+
+#endif /* __BIG_ENDIAN */

lib/gen_crc32table.c

@@ -0,0 +1,82 @@
+#include <stdio.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)
+
+static uint32_t crc32table_le[LE_TABLE_SIZE];
+static uint32_t crc32table_be[BE_TABLE_SIZE];
+
+/**
+ * crc32init_le() - allocate and initialize LE table data
+ *
+ * crc is the crc of the byte i; other entries are filled in based on the
+ * fact that crctable[i^j] = crctable[i] ^ crctable[j].
+ *
+ */
+static void crc32init_le(void)
+{
+	unsigned i, j;
+	uint32_t crc = 1;
+
+	crc32table_le[0] = 0;
+
+	for (i = 1 << (CRC_LE_BITS - 1); i; i >>= 1) {
+		crc = (crc >> 1) ^ ((crc & 1) ? CRCPOLY_LE : 0);
+		for (j = 0; j < LE_TABLE_SIZE; j += 2 * i)
+			crc32table_le[i + j] = crc ^ crc32table_le[j];
+	}
+}
+
+/**
+ * crc32init_be() - allocate and initialize BE table data
+ */
+static void crc32init_be(void)
+{
+	unsigned i, j;
+	uint32_t crc = 0x80000000;
+
+	crc32table_be[0] = 0;
+
+	for (i = 1; i < BE_TABLE_SIZE; i <<= 1) {
+		crc = (crc << 1) ^ ((crc & 0x80000000) ? CRCPOLY_BE : 0);
+		for (j = 0; j < i; j++)
+			crc32table_be[i + j] = crc ^ crc32table_be[j];
+	}
+}
+
+static void output_table(uint32_t table[], int len, char *trans)
+{
+	int i;
+
+	for (i = 0; i < len - 1; i++) {
+		if (i % ENTRIES_PER_LINE == 0)
+			printf("\n");
+		printf("%s(0x%8.8xL), ", trans, table[i]);
+	}
+	printf("%s(0x%8.8xL)\n", trans, table[len - 1]);
+}
+
+int main(int argc, char** argv)
+{
+	printf("/* this file is generated - do not edit */\n\n");
+
+	if (CRC_LE_BITS > 1) {
+		crc32init_le();
+		printf("static const u32 crc32table_le[] = {");
+		output_table(crc32table_le, LE_TABLE_SIZE, "tole");
+		printf("};\n");
+	}
+
+	if (CRC_BE_BITS > 1) {
+		crc32init_be();
+		printf("static const u32 crc32table_be[] = {");
+		output_table(crc32table_be, BE_TABLE_SIZE, "tobe");
+		printf("};\n");
+	}
+
+	return 0;
+}

lib/genalloc.c

@@ -0,0 +1,198 @@
+/*
+ * Basic general purpose allocator for managing special purpose memory
+ * not managed by the regular kmalloc/kfree interface.
+ * Uses for this includes on-device special memory, uncached memory
+ * etc.
+ *
+ * Copyright 2005 (C) Jes Sorensen <jes@trained-monkey.org>
+ *
+ * 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/genalloc.h>
+
+
+/**
+ * gen_pool_create - create a new special memory pool
+ * @min_alloc_order: log base 2 of number of bytes each bitmap bit represents
+ * @nid: node id of the node the pool structure should be allocated on, or -1
+ *
+ * Create a new special memory pool that can be used to manage special purpose
+ * memory not managed by the regular kmalloc/kfree interface.
+ */
+struct gen_pool *gen_pool_create(int min_alloc_order, int nid)
+{
+	struct gen_pool *pool;
+
+	pool = kmalloc_node(sizeof(struct gen_pool), GFP_KERNEL, nid);
+	if (pool != NULL) {
+		rwlock_init(&pool->lock);
+		INIT_LIST_HEAD(&pool->chunks);
+		pool->min_alloc_order = min_alloc_order;
+	}
+	return pool;
+}
+EXPORT_SYMBOL(gen_pool_create);
+
+/**
+ * gen_pool_add - add a new chunk of special memory to the pool
+ * @pool: pool to add new memory chunk to
+ * @addr: starting address of memory chunk to add to pool
+ * @size: size in bytes of the memory chunk to add to pool
+ * @nid: node id of the node the chunk structure and bitmap should be
+ *       allocated on, or -1
+ *
+ * Add a new chunk of special memory to the specified pool.
+ */
+int gen_pool_add(struct gen_pool *pool, unsigned long addr, size_t size,
+		 int nid)
+{
+	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;
+
+	chunk = kmalloc_node(nbytes, GFP_KERNEL, nid);
+	if (unlikely(chunk == NULL))
+		return -1;
+
+	memset(chunk, 0, nbytes);
+	spin_lock_init(&chunk->lock);
+	chunk->start_addr = addr;
+	chunk->end_addr = addr + size;
+
+	write_lock(&pool->lock);
+	list_add(&chunk->next_chunk, &pool->chunks);
+	write_unlock(&pool->lock);
+
+	return 0;
+}
+EXPORT_SYMBOL(gen_pool_add);
+
+/**
+ * gen_pool_destroy - destroy a special memory pool
+ * @pool: pool to destroy
+ *
+ * Destroy the specified special memory pool. Verifies that there are no
+ * outstanding allocations.
+ */
+void gen_pool_destroy(struct gen_pool *pool)
+{
+	struct list_head *_chunk, *_next_chunk;
+	struct gen_pool_chunk *chunk;
+	int order = pool->min_alloc_order;
+	int bit, end_bit;
+
+
+	write_lock(&pool->lock);
+	list_for_each_safe(_chunk, _next_chunk, &pool->chunks) {
+		chunk = list_entry(_chunk, struct gen_pool_chunk, next_chunk);
+		list_del(&chunk->next_chunk);
+
+		end_bit = (chunk->end_addr - chunk->start_addr) >> order;
+		bit = find_next_bit(chunk->bits, end_bit, 0);
+		BUG_ON(bit < end_bit);
+
+		kfree(chunk);
+	}
+	kfree(pool);
+	return;
+}
+EXPORT_SYMBOL(gen_pool_destroy);
+
+/**
+ * gen_pool_alloc - allocate special memory from the pool
+ * @pool: pool to allocate from
+ * @size: number of bytes to allocate from the pool
+ *
+ * Allocate the requested number of bytes from the specified pool.
+ * Uses a first-fit algorithm.
+ */
+unsigned long gen_pool_alloc(struct gen_pool *pool, size_t size)
+{
+	struct list_head *_chunk;
+	struct gen_pool_chunk *chunk;
+	unsigned long addr, flags;
+	int order = pool->min_alloc_order;
+	int nbits, bit, start_bit, end_bit;
+
+	if (size == 0)
+		return 0;
+
+	nbits = (size + (1UL << order) - 1) >> order;
+
+	read_lock(&pool->lock);
+	list_for_each(_chunk, &pool->chunks) {
+		chunk = list_entry(_chunk, struct gen_pool_chunk, next_chunk);
+
+		end_bit = (chunk->end_addr - chunk->start_addr) >> order;
+		end_bit -= nbits + 1;
+
+		spin_lock_irqsave(&chunk->lock, flags);
+		bit = -1;
+		while (bit + 1 < end_bit) {
+			bit = find_next_zero_bit(chunk->bits, end_bit, bit + 1);
+			if (bit >= end_bit)
+				break;
+
+			start_bit = bit;
+			if (nbits > 1) {
+				bit = find_next_bit(chunk->bits, bit + nbits,
+							bit + 1);
+				if (bit - start_bit < nbits)
+					continue;
+			}
+
+			addr = chunk->start_addr +
+					    ((unsigned long)start_bit << order);
+			while (nbits--)
+				__set_bit(start_bit++, chunk->bits);
+			spin_unlock_irqrestore(&chunk->lock, flags);
+			read_unlock(&pool->lock);
+			return addr;
+		}
+		spin_unlock_irqrestore(&chunk->lock, flags);
+	}
+	read_unlock(&pool->lock);
+	return 0;
+}
+EXPORT_SYMBOL(gen_pool_alloc);
+
+/**
+ * gen_pool_free - free allocated special memory back to the pool
+ * @pool: pool to free to
+ * @addr: starting address of memory to free back to pool
+ * @size: size in bytes of memory to free
+ *
+ * Free previously allocated special memory back to the specified pool.
+ */
+void gen_pool_free(struct gen_pool *pool, unsigned long addr, size_t size)
+{
+	struct list_head *_chunk;
+	struct gen_pool_chunk *chunk;
+	unsigned long flags;
+	int order = pool->min_alloc_order;
+	int bit, nbits;
+
+	nbits = (size + (1UL << order) - 1) >> order;
+
+	read_lock(&pool->lock);
+	list_for_each(_chunk, &pool->chunks) {
+		chunk = list_entry(_chunk, struct gen_pool_chunk, next_chunk);
+
+		if (addr >= chunk->start_addr && addr < chunk->end_addr) {
+			BUG_ON(addr + size > chunk->end_addr);
+			spin_lock_irqsave(&chunk->lock, flags);
+			bit = (addr - chunk->start_addr) >> order;
+			while (nbits--)
+				__clear_bit(bit++, chunk->bits);
+			spin_unlock_irqrestore(&chunk->lock, flags);
+			break;
+		}
+	}
+	BUG_ON(nbits > 0);
+	read_unlock(&pool->lock);
+}
+EXPORT_SYMBOL(gen_pool_free);

lib/halfmd4.c

@@ -0,0 +1,66 @@
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/cryptohash.h>
+
+/* F, G and H are basic MD4 functions: selection, majority, parity */
+#define F(x, y, z) ((z) ^ ((x) & ((y) ^ (z))))
+#define G(x, y, z) (((x) & (y)) + (((x) ^ (y)) & (z)))
+#define H(x, y, z) ((x) ^ (y) ^ (z))
+
+/*
+ * The generic round function.  The application is so specific that
+ * we don't bother protecting all the arguments with parens, as is generally
+ * good macro practice, in favor of extra legibility.
+ * Rotation is separate from addition to prevent recomputation
+ */
+#define ROUND(f, a, b, c, d, x, s)	\
+	(a += f(b, c, d) + x, a = (a << s) | (a >> (32 - s)))
+#define K1 0
+#define K2 013240474631UL
+#define K3 015666365641UL
+
+/*
+ * Basic cut-down MD4 transform.  Returns only 32 bits of result.
+ */
+__u32 half_md4_transform(__u32 buf[4], __u32 const in[8])
+{
+	__u32 a = buf[0], b = buf[1], c = buf[2], d = buf[3];
+
+	/* Round 1 */
+	ROUND(F, a, b, c, d, in[0] + K1,  3);
+	ROUND(F, d, a, b, c, in[1] + K1,  7);
+	ROUND(F, c, d, a, b, in[2] + K1, 11);
+	ROUND(F, b, c, d, a, in[3] + K1, 19);
+	ROUND(F, a, b, c, d, in[4] + K1,  3);
+	ROUND(F, d, a, b, c, in[5] + K1,  7);
+	ROUND(F, c, d, a, b, in[6] + K1, 11);
+	ROUND(F, b, c, d, a, in[7] + K1, 19);
+
+	/* Round 2 */
+	ROUND(G, a, b, c, d, in[1] + K2,  3);
+	ROUND(G, d, a, b, c, in[3] + K2,  5);
+	ROUND(G, c, d, a, b, in[5] + K2,  9);
+	ROUND(G, b, c, d, a, in[7] + K2, 13);
+	ROUND(G, a, b, c, d, in[0] + K2,  3);
+	ROUND(G, d, a, b, c, in[2] + K2,  5);
+	ROUND(G, c, d, a, b, in[4] + K2,  9);
+	ROUND(G, b, c, d, a, in[6] + K2, 13);
+
+	/* Round 3 */
+	ROUND(H, a, b, c, d, in[3] + K3,  3);
+	ROUND(H, d, a, b, c, in[7] + K3,  9);
+	ROUND(H, c, d, a, b, in[2] + K3, 11);
+	ROUND(H, b, c, d, a, in[6] + K3, 15);
+	ROUND(H, a, b, c, d, in[1] + K3,  3);
+	ROUND(H, d, a, b, c, in[5] + K3,  9);
+	ROUND(H, c, d, a, b, in[0] + K3, 11);
+	ROUND(H, b, c, d, a, in[4] + K3, 15);
+
+	buf[0] += a;
+	buf[1] += b;
+	buf[2] += c;
+	buf[3] += d;
+
+	return buf[1]; /* "most hashed" word */
+}
+EXPORT_SYMBOL(half_md4_transform);

lib/hweight.c

@@ -0,0 +1,59 @@
+#include <linux/module.h>
+#include <asm/types.h>
+#include <asm/bitops.h>
+
+/**
+ * hweightN - returns the hamming weight of a N-bit word
+ * @x: the word to weigh
+ *
+ * The Hamming Weight of a number is the total number of bits set in it.
+ */
+
+unsigned int hweight32(unsigned int w)
+{
+	unsigned int res = w - ((w >> 1) & 0x55555555);
+	res = (res & 0x33333333) + ((res >> 2) & 0x33333333);
+	res = (res + (res >> 4)) & 0x0F0F0F0F;
+	res = res + (res >> 8);
+	return (res + (res >> 16)) & 0x000000FF;
+}
+EXPORT_SYMBOL(hweight32);
+
+unsigned int hweight16(unsigned int w)
+{
+	unsigned int res = w - ((w >> 1) & 0x5555);
+	res = (res & 0x3333) + ((res >> 2) & 0x3333);
+	res = (res + (res >> 4)) & 0x0F0F;
+	return (res + (res >> 8)) & 0x00FF;
+}
+EXPORT_SYMBOL(hweight16);
+
+unsigned int hweight8(unsigned int w)
+{
+	unsigned int res = w - ((w >> 1) & 0x55);
+	res = (res & 0x33) + ((res >> 2) & 0x33);
+	return (res + (res >> 4)) & 0x0F;
+}
+EXPORT_SYMBOL(hweight8);
+
+unsigned long hweight64(__u64 w)
+{
+#if BITS_PER_LONG == 32
+	return hweight32((unsigned int)(w >> 32)) + hweight32((unsigned int)w);
+#elif BITS_PER_LONG == 64
+#ifdef ARCH_HAS_FAST_MULTIPLIER
+	w -= (w >> 1) & 0x5555555555555555ul;
+	w =  (w & 0x3333333333333333ul) + ((w >> 2) & 0x3333333333333333ul);
+	w =  (w + (w >> 4)) & 0x0f0f0f0f0f0f0f0ful;
+	return (w * 0x0101010101010101ul) >> 56;
+#else
+	__u64 res = w - ((w >> 1) & 0x5555555555555555ul);
+	res = (res & 0x3333333333333333ul) + ((res >> 2) & 0x3333333333333333ul);
+	res = (res + (res >> 4)) & 0x0F0F0F0F0F0F0F0Ful;
+	res = res + (res >> 8);
+	res = res + (res >> 16);
+	return (res + (res >> 32)) & 0x00000000000000FFul;
+#endif
+#endif
+}
+EXPORT_SYMBOL(hweight64);

lib/idr.c

@@ -0,0 +1,475 @@
+/*
+ * 2002-10-18  written by Jim Houston jim.houston@ccur.com
+ *	Copyright (C) 2002 by Concurrent Computer Corporation
+ *	Distributed under the GNU GPL license version 2.
+ *
+ * Modified by George Anzinger to reuse immediately and to use
+ * find bit instructions.  Also removed _irq on spinlocks.
+ *
+ * Small id to pointer translation service.
+ *
+ * It uses a radix tree like structure as a sparse array indexed
+ * by the id to obtain the pointer.  The bitmap makes allocating
+ * a new id quick.
+ *
+ * You call it to allocate an id (an int) an associate with that id a
+ * pointer or what ever, we treat it as a (void *).  You can pass this
+ * id to a user for him to pass back at a later time.  You then pass
+ * 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
+ * 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.
+ */
+
+#ifndef TEST                        // to test in user space...
+#include <linux/slab.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#endif
+#include <linux/err.h>
+#include <linux/string.h>
+#include <linux/idr.h>
+
+static struct kmem_cache *idr_layer_cache;
+
+static struct idr_layer *alloc_layer(struct idr *idp)
+{
+	struct idr_layer *p;
+	unsigned long flags;
+
+	spin_lock_irqsave(&idp->lock, flags);
+	if ((p = idp->id_free)) {
+		idp->id_free = p->ary[0];
+		idp->id_free_cnt--;
+		p->ary[0] = NULL;
+	}
+	spin_unlock_irqrestore(&idp->lock, flags);
+	return(p);
+}
+
+/* only called when idp->lock is held */
+static void __free_layer(struct idr *idp, struct idr_layer *p)
+{
+	p->ary[0] = idp->id_free;
+	idp->id_free = p;
+	idp->id_free_cnt++;
+}
+
+static void free_layer(struct idr *idp, struct idr_layer *p)
+{
+	unsigned long flags;
+
+	/*
+	 * Depends on the return element being zeroed.
+	 */
+	spin_lock_irqsave(&idp->lock, flags);
+	__free_layer(idp, p);
+	spin_unlock_irqrestore(&idp->lock, flags);
+}
+
+/**
+ * idr_pre_get - reserver resources for idr allocation
+ * @idp:	idr handle
+ * @gfp_mask:	memory allocation flags
+ *
+ * This function should be called prior to locking and calling the
+ * following function.  It preallocates enough memory to satisfy
+ * the worst possible allocation.
+ *
+ * If the system is REALLY out of memory this function returns 0,
+ * otherwise 1.
+ */
+int idr_pre_get(struct idr *idp, gfp_t gfp_mask)
+{
+	while (idp->id_free_cnt < IDR_FREE_MAX) {
+		struct idr_layer *new;
+		new = kmem_cache_alloc(idr_layer_cache, gfp_mask);
+		if (new == NULL)
+			return (0);
+		free_layer(idp, new);
+	}
+	return 1;
+}
+EXPORT_SYMBOL(idr_pre_get);
+
+static int sub_alloc(struct idr *idp, void *ptr, int *starting_id)
+{
+	int n, m, sh;
+	struct idr_layer *p, *new;
+	struct idr_layer *pa[MAX_LEVEL];
+	int l, id;
+	long bm;
+
+	id = *starting_id;
+	p = idp->top;
+	l = idp->layers;
+	pa[l--] = NULL;
+	while (1) {
+		/*
+		 * We run around this while until we reach the leaf node...
+		 */
+		n = (id >> (IDR_BITS*l)) & IDR_MASK;
+		bm = ~p->bitmap;
+		m = find_next_bit(&bm, IDR_SIZE, n);
+		if (m == IDR_SIZE) {
+			/* no space available go back to previous layer. */
+			l++;
+			id = (id | ((1 << (IDR_BITS * l)) - 1)) + 1;
+			if (!(p = pa[l])) {
+				*starting_id = id;
+				return -2;
+			}
+			continue;
+		}
+		if (m != n) {
+			sh = IDR_BITS*l;
+			id = ((id >> sh) ^ n ^ m) << sh;
+		}
+		if ((id >= MAX_ID_BIT) || (id < 0))
+			return -3;
+		if (l == 0)
+			break;
+		/*
+		 * Create the layer below if it is missing.
+		 */
+		if (!p->ary[m]) {
+			if (!(new = alloc_layer(idp)))
+				return -1;
+			p->ary[m] = new;
+			p->count++;
+		}
+		pa[l--] = p;
+		p = p->ary[m];
+	}
+	/*
+	 * We have reached the leaf node, plant the
+	 * users pointer and return the raw id.
+	 */
+	p->ary[m] = (struct idr_layer *)ptr;
+	__set_bit(m, &p->bitmap);
+	p->count++;
+	/*
+	 * If this layer is full mark the bit in the layer above
+	 * to show that this part of the radix tree is full.
+	 * This may complete the layer above and require walking
+	 * up the radix tree.
+	 */
+	n = id;
+	while (p->bitmap == IDR_FULL) {
+		if (!(p = pa[++l]))
+			break;
+		n = n >> IDR_BITS;
+		__set_bit((n & IDR_MASK), &p->bitmap);
+	}
+	return(id);
+}
+
+static int idr_get_new_above_int(struct idr *idp, void *ptr, int starting_id)
+{
+	struct idr_layer *p, *new;
+	int layers, v, id;
+	unsigned long flags;
+
+	id = starting_id;
+build_up:
+	p = idp->top;
+	layers = idp->layers;
+	if (unlikely(!p)) {
+		if (!(p = alloc_layer(idp)))
+			return -1;
+		layers = 1;
+	}
+	/*
+	 * 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)))) {
+		layers++;
+		if (!p->count)
+			continue;
+		if (!(new = alloc_layer(idp))) {
+			/*
+			 * The allocation failed.  If we built part of
+			 * the structure tear it down.
+			 */
+			spin_lock_irqsave(&idp->lock, flags);
+			for (new = p; p && p != idp->top; new = p) {
+				p = p->ary[0];
+				new->ary[0] = NULL;
+				new->bitmap = new->count = 0;
+				__free_layer(idp, new);
+			}
+			spin_unlock_irqrestore(&idp->lock, flags);
+			return -1;
+		}
+		new->ary[0] = p;
+		new->count = 1;
+		if (p->bitmap == IDR_FULL)
+			__set_bit(0, &new->bitmap);
+		p = new;
+	}
+	idp->top = p;
+	idp->layers = layers;
+	v = sub_alloc(idp, ptr, &id);
+	if (v == -2)
+		goto build_up;
+	return(v);
+}
+
+/**
+ * idr_get_new_above - allocate new idr entry above or equal to a start id
+ * @idp: idr handle
+ * @ptr: pointer you want associated with the ide
+ * @start_id: id to start search at
+ * @id: pointer to the allocated handle
+ *
+ * This is the allocate id function.  It should be called with any
+ * required locks.
+ *
+ * If memory is required, it will return -EAGAIN, you should unlock
+ * 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
+ */
+int idr_get_new_above(struct idr *idp, void *ptr, int starting_id, int *id)
+{
+	int rv;
+
+	rv = idr_get_new_above_int(idp, ptr, starting_id);
+	/*
+	 * This is a cheap hack until the IDR code can be fixed to
+	 * return proper error values.
+	 */
+	if (rv < 0) {
+		if (rv == -1)
+			return -EAGAIN;
+		else /* Will be -3 */
+			return -ENOSPC;
+	}
+	*id = rv;
+	return 0;
+}
+EXPORT_SYMBOL(idr_get_new_above);
+
+/**
+ * idr_get_new - allocate new idr entry
+ * @idp: idr handle
+ * @ptr: pointer you want associated with the ide
+ * @id: pointer to the allocated handle
+ *
+ * This is the allocate id function.  It should be called with any
+ * required locks.
+ *
+ * If memory is required, it will return -EAGAIN, you should unlock
+ * 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
+ */
+int idr_get_new(struct idr *idp, void *ptr, int *id)
+{
+	int rv;
+
+	rv = idr_get_new_above_int(idp, ptr, 0);
+	/*
+	 * This is a cheap hack until the IDR code can be fixed to
+	 * return proper error values.
+	 */
+	if (rv < 0) {
+		if (rv == -1)
+			return -EAGAIN;
+		else /* Will be -3 */
+			return -ENOSPC;
+	}
+	*id = rv;
+	return 0;
+}
+EXPORT_SYMBOL(idr_get_new);
+
+static void idr_remove_warning(int id)
+{
+	printk("idr_remove called for id=%d which is not allocated.\n", id);
+	dump_stack();
+}
+
+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 ***paa = &pa[0];
+	int n;
+
+	*paa = NULL;
+	*++paa = &idp->top;
+
+	while ((shift > 0) && p) {
+		n = (id >> shift) & IDR_MASK;
+		__clear_bit(n, &p->bitmap);
+		*++paa = &p->ary[n];
+		p = p->ary[n];
+		shift -= IDR_BITS;
+	}
+	n = id & IDR_MASK;
+	if (likely(p != NULL && test_bit(n, &p->bitmap))){
+		__clear_bit(n, &p->bitmap);
+		p->ary[n] = NULL;
+		while(*paa && ! --((**paa)->count)){
+			free_layer(idp, **paa);
+			**paa-- = NULL;
+		}
+		if (!*paa)
+			idp->layers = 0;
+	} else
+		idr_remove_warning(id);
+}
+
+/**
+ * idr_remove - remove the given id and free it's slot
+ * @idp: idr handle
+ * @id: unique key
+ */
+void idr_remove(struct idr *idp, int id)
+{
+	struct idr_layer *p;
+
+	/* Mask off upper bits we don't use for the search. */
+	id &= MAX_ID_MASK;
+
+	sub_remove(idp, (idp->layers - 1) * IDR_BITS, id);
+	if (idp->top && idp->top->count == 1 && (idp->layers > 1) &&
+	    idp->top->ary[0]) {  // We can drop a layer
+
+		p = idp->top->ary[0];
+		idp->top->bitmap = idp->top->count = 0;
+		free_layer(idp, idp->top);
+		idp->top = p;
+		--idp->layers;
+	}
+	while (idp->id_free_cnt >= IDR_FREE_MAX) {
+		p = alloc_layer(idp);
+		kmem_cache_free(idr_layer_cache, p);
+		return;
+	}
+}
+EXPORT_SYMBOL(idr_remove);
+
+/**
+ * idr_destroy - release all cached layers within an idr tree
+ * idp: idr handle
+ */
+void idr_destroy(struct idr *idp)
+{
+	while (idp->id_free_cnt) {
+		struct idr_layer *p = alloc_layer(idp);
+		kmem_cache_free(idr_layer_cache, p);
+	}
+}
+EXPORT_SYMBOL(idr_destroy);
+
+/**
+ * idr_find - return pointer for given id
+ * @idp: idr handle
+ * @id: lookup key
+ *
+ * Return the pointer given the id it has been registered with.  A %NULL
+ * return indicates that @id is not valid or you passed %NULL in
+ * idr_get_new().
+ *
+ * The caller must serialize idr_find() vs idr_get_new() and idr_remove().
+ */
+void *idr_find(struct idr *idp, int id)
+{
+	int n;
+	struct idr_layer *p;
+
+	n = idp->layers * IDR_BITS;
+	p = idp->top;
+
+	/* Mask off upper bits we don't use for the search. */
+	id &= MAX_ID_MASK;
+
+	if (id >= (1 << n))
+		return NULL;
+
+	while (n > 0 && p) {
+		n -= IDR_BITS;
+		p = p->ary[(id >> n) & IDR_MASK];
+	}
+	return((void *)p);
+}
+EXPORT_SYMBOL(idr_find);
+
+/**
+ * idr_replace - replace pointer for given id
+ * @idp: idr handle
+ * @ptr: pointer you want associated with the id
+ * @id: lookup key
+ *
+ * Replace the pointer registered with an id and return the old value.
+ * A -ENOENT return indicates that @id was not found.
+ * A -EINVAL return indicates that @id was not within valid constraints.
+ *
+ * The caller must serialize vs idr_find(), idr_get_new(), and idr_remove().
+ */
+void *idr_replace(struct idr *idp, void *ptr, int id)
+{
+	int n;
+	struct idr_layer *p, *old_p;
+
+	n = idp->layers * IDR_BITS;
+	p = idp->top;
+
+	id &= MAX_ID_MASK;
+
+	if (id >= (1 << n))
+		return ERR_PTR(-EINVAL);
+
+	n -= IDR_BITS;
+	while ((n > 0) && p) {
+		p = p->ary[(id >> n) & IDR_MASK];
+		n -= IDR_BITS;
+	}
+
+	n = id & IDR_MASK;
+	if (unlikely(p == NULL || !test_bit(n, &p->bitmap)))
+		return ERR_PTR(-ENOENT);
+
+	old_p = p->ary[n];
+	p->ary[n] = ptr;
+
+	return old_p;
+}
+EXPORT_SYMBOL(idr_replace);
+
+static void idr_cache_ctor(void * idr_layer, struct kmem_cache *idr_layer_cache,
+		unsigned long flags)
+{
+	memset(idr_layer, 0, sizeof(struct idr_layer));
+}
+
+static  int init_id_cache(void)
+{
+	if (!idr_layer_cache)
+		idr_layer_cache = kmem_cache_create("idr_layer_cache",
+			sizeof(struct idr_layer), 0, 0, idr_cache_ctor, NULL);
+	return 0;
+}
+
+/**
+ * idr_init - initialize idr handle
+ * @idp:	idr handle
+ *
+ * This function is use to set up the handle (@idp) that you will pass
+ * to the rest of the functions.
+ */
+void idr_init(struct idr *idp)
+{
+	init_id_cache();
+	memset(idp, 0, sizeof(struct idr));
+	spin_lock_init(&idp->lock);
+}
+EXPORT_SYMBOL(idr_init);

lib/int_sqrt.c

@@ -0,0 +1,32 @@
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+
+/**
+ * int_sqrt - rough approximation to sqrt
+ * @x: integer of which to calculate the sqrt
+ *
+ * A very rough approximation to the sqrt() function.
+ */
+unsigned long int_sqrt(unsigned long x)
+{
+	unsigned long op, res, one;
+
+	op = x;
+	res = 0;
+
+	one = 1UL << (BITS_PER_LONG - 2);
+	while (one > op)
+		one >>= 2;
+
+	while (one != 0) {
+		if (op >= res + one) {
+			op = op - (res + one);
+			res = res +  2 * one;
+		}
+		res /= 2;
+		one /= 4;
+	}
+	return res;
+}
+EXPORT_SYMBOL(int_sqrt);

lib/iomap.c

@@ -0,0 +1,257 @@
+/*
+ * Implement the default iomap interfaces
+ *
+ * (C) Copyright 2004 Linus Torvalds
+ */
+#include <linux/pci.h>
+#include <linux/io.h>
+
+#include <linux/module.h>
+
+/*
+ * Read/write from/to an (offsettable) iomem cookie. It might be a PIO
+ * access or a MMIO access, these functions don't care. The info is
+ * encoded in the hardware mapping set up by the mapping functions
+ * (or the cookie itself, depending on implementation and hw).
+ *
+ * The generic routines don't assume any hardware mappings, and just
+ * encode the PIO/MMIO as part of the cookie. They coldly assume that
+ * the MMIO IO mappings are not in the low address range.
+ *
+ * Architectures for which this is not true can't use this generic
+ * implementation and should do their own copy.
+ */
+
+#ifndef HAVE_ARCH_PIO_SIZE
+/*
+ * We encode the physical PIO addresses (0-0xffff) into the
+ * pointer by offsetting them with a constant (0x10000) and
+ * assuming that all the low addresses are always PIO. That means
+ * we can do some sanity checks on the low bits, and don't
+ * need to just take things for granted.
+ */
+#define PIO_OFFSET	0x10000UL
+#define PIO_MASK	0x0ffffUL
+#define PIO_RESERVED	0x40000UL
+#endif
+
+/*
+ * Ugly macros are a way of life.
+ */
+#define VERIFY_PIO(port) BUG_ON((port & ~PIO_MASK) != PIO_OFFSET)
+
+#define IO_COND(addr, is_pio, is_mmio) do {			\
+	unsigned long port = (unsigned long __force)addr;	\
+	if (port < PIO_RESERVED) {				\
+		VERIFY_PIO(port);				\
+		port &= PIO_MASK;				\
+		is_pio;						\
+	} else {						\
+		is_mmio;					\
+	}							\
+} while (0)
+
+#ifndef pio_read16be
+#define pio_read16be(port) swab16(inw(port))
+#define pio_read32be(port) swab32(inl(port))
+#endif
+
+#ifndef mmio_read16be
+#define mmio_read16be(addr) be16_to_cpu(__raw_readw(addr))
+#define mmio_read32be(addr) be32_to_cpu(__raw_readl(addr))
+#endif
+
+unsigned int fastcall ioread8(void __iomem *addr)
+{
+	IO_COND(addr, return inb(port), return readb(addr));
+}
+unsigned int fastcall ioread16(void __iomem *addr)
+{
+	IO_COND(addr, return inw(port), return readw(addr));
+}
+unsigned int fastcall ioread16be(void __iomem *addr)
+{
+	IO_COND(addr, return pio_read16be(port), return mmio_read16be(addr));
+}
+unsigned int fastcall ioread32(void __iomem *addr)
+{
+	IO_COND(addr, return inl(port), return readl(addr));
+}
+unsigned int fastcall ioread32be(void __iomem *addr)
+{
+	IO_COND(addr, return pio_read32be(port), return mmio_read32be(addr));
+}
+EXPORT_SYMBOL(ioread8);
+EXPORT_SYMBOL(ioread16);
+EXPORT_SYMBOL(ioread16be);
+EXPORT_SYMBOL(ioread32);
+EXPORT_SYMBOL(ioread32be);
+
+#ifndef pio_write16be
+#define pio_write16be(val,port) outw(swab16(val),port)
+#define pio_write32be(val,port) outl(swab32(val),port)
+#endif
+
+#ifndef mmio_write16be
+#define mmio_write16be(val,port) __raw_writew(be16_to_cpu(val),port)
+#define mmio_write32be(val,port) __raw_writel(be32_to_cpu(val),port)
+#endif
+
+void fastcall iowrite8(u8 val, void __iomem *addr)
+{
+	IO_COND(addr, outb(val,port), writeb(val, addr));
+}
+void fastcall iowrite16(u16 val, void __iomem *addr)
+{
+	IO_COND(addr, outw(val,port), writew(val, addr));
+}
+void fastcall iowrite16be(u16 val, void __iomem *addr)
+{
+	IO_COND(addr, pio_write16be(val,port), mmio_write16be(val, addr));
+}
+void fastcall iowrite32(u32 val, void __iomem *addr)
+{
+	IO_COND(addr, outl(val,port), writel(val, addr));
+}
+void fastcall iowrite32be(u32 val, void __iomem *addr)
+{
+	IO_COND(addr, pio_write32be(val,port), mmio_write32be(val, addr));
+}
+EXPORT_SYMBOL(iowrite8);
+EXPORT_SYMBOL(iowrite16);
+EXPORT_SYMBOL(iowrite16be);
+EXPORT_SYMBOL(iowrite32);
+EXPORT_SYMBOL(iowrite32be);
+
+/*
+ * These are the "repeat MMIO read/write" functions.
+ * Note the "__raw" accesses, since we don't want to
+ * convert to CPU byte order. We write in "IO byte
+ * order" (we also don't have IO barriers).
+ */
+#ifndef mmio_insb
+static inline void mmio_insb(void __iomem *addr, u8 *dst, int count)
+{
+	while (--count >= 0) {
+		u8 data = __raw_readb(addr);
+		*dst = data;
+		dst++;
+	}
+}
+static inline void mmio_insw(void __iomem *addr, u16 *dst, int count)
+{
+	while (--count >= 0) {
+		u16 data = __raw_readw(addr);
+		*dst = data;
+		dst++;
+	}
+}
+static inline void mmio_insl(void __iomem *addr, u32 *dst, int count)
+{
+	while (--count >= 0) {
+		u32 data = __raw_readl(addr);
+		*dst = data;
+		dst++;
+	}
+}
+#endif
+
+#ifndef mmio_outsb
+static inline void mmio_outsb(void __iomem *addr, const u8 *src, int count)
+{
+	while (--count >= 0) {
+		__raw_writeb(*src, addr);
+		src++;
+	}
+}
+static inline void mmio_outsw(void __iomem *addr, const u16 *src, int count)
+{
+	while (--count >= 0) {
+		__raw_writew(*src, addr);
+		src++;
+	}
+}
+static inline void mmio_outsl(void __iomem *addr, const u32 *src, int count)
+{
+	while (--count >= 0) {
+		__raw_writel(*src, addr);
+		src++;
+	}
+}
+#endif
+
+void fastcall ioread8_rep(void __iomem *addr, void *dst, unsigned long count)
+{
+	IO_COND(addr, insb(port,dst,count), mmio_insb(addr, dst, count));
+}
+void fastcall ioread16_rep(void __iomem *addr, void *dst, unsigned long count)
+{
+	IO_COND(addr, insw(port,dst,count), mmio_insw(addr, dst, count));
+}
+void fastcall ioread32_rep(void __iomem *addr, void *dst, unsigned long count)
+{
+	IO_COND(addr, insl(port,dst,count), mmio_insl(addr, dst, count));
+}
+EXPORT_SYMBOL(ioread8_rep);
+EXPORT_SYMBOL(ioread16_rep);
+EXPORT_SYMBOL(ioread32_rep);
+
+void fastcall iowrite8_rep(void __iomem *addr, const void *src, unsigned long count)
+{
+	IO_COND(addr, outsb(port, src, count), mmio_outsb(addr, src, count));
+}
+void fastcall iowrite16_rep(void __iomem *addr, const void *src, unsigned long count)
+{
+	IO_COND(addr, outsw(port, src, count), mmio_outsw(addr, src, count));
+}
+void fastcall iowrite32_rep(void __iomem *addr, const void *src, unsigned long count)
+{
+	IO_COND(addr, outsl(port, src,count), mmio_outsl(addr, src, count));
+}
+EXPORT_SYMBOL(iowrite8_rep);
+EXPORT_SYMBOL(iowrite16_rep);
+EXPORT_SYMBOL(iowrite32_rep);
+
+/* Create a virtual mapping cookie for an IO port range */
+void __iomem *ioport_map(unsigned long port, unsigned int nr)
+{
+	if (port > PIO_MASK)
+		return NULL;
+	return (void __iomem *) (unsigned long) (port + PIO_OFFSET);
+}
+
+void ioport_unmap(void __iomem *addr)
+{
+	/* Nothing to do */
+}
+EXPORT_SYMBOL(ioport_map);
+EXPORT_SYMBOL(ioport_unmap);
+
+/* Create a virtual mapping cookie for a PCI BAR (memory or IO) */
+void __iomem *pci_iomap(struct pci_dev *dev, int bar, unsigned long maxlen)
+{
+	unsigned long start = pci_resource_start(dev, bar);
+	unsigned long 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;
+}
+
+void pci_iounmap(struct pci_dev *dev, void __iomem * addr)
+{
+	IO_COND(addr, /* nothing */, iounmap(addr));
+}
+EXPORT_SYMBOL(pci_iomap);
+EXPORT_SYMBOL(pci_iounmap);

lib/iomap_copy.c

@@ -0,0 +1,70 @@
+/*
+ * Copyright 2006 PathScale, Inc.  All Rights Reserved.
+ *
+ * This file is free software; you can redistribute it and/or modify
+ * it under the terms of version 2 of the GNU General Public License
+ * as published by the Free Software Foundation.
+ *
+ * This program 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., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301, USA.
+ */
+
+#include <linux/module.h>
+#include <linux/io.h>
+
+/**
+ * __iowrite32_copy - copy data to MMIO space, in 32-bit units
+ * @to: destination, in MMIO space (must be 32-bit aligned)
+ * @from: source (must be 32-bit aligned)
+ * @count: number of 32-bit quantities to copy
+ *
+ * Copy data from kernel space to MMIO space, in units of 32 bits at a
+ * time.  Order of access is not guaranteed, nor is a memory barrier
+ * performed afterwards.
+ */
+void __attribute__((weak)) __iowrite32_copy(void __iomem *to,
+					    const void *from,
+					    size_t count)
+{
+	u32 __iomem *dst = to;
+	const u32 *src = from;
+	const u32 *end = src + count;
+
+	while (src < end)
+		__raw_writel(*src++, dst++);
+}
+EXPORT_SYMBOL_GPL(__iowrite32_copy);
+
+/**
+ * __iowrite64_copy - copy data to MMIO space, in 64-bit or 32-bit units
+ * @to: destination, in MMIO space (must be 64-bit aligned)
+ * @from: source (must be 64-bit aligned)
+ * @count: number of 64-bit quantities to copy
+ *
+ * Copy data from kernel space to MMIO space, in units of 32 or 64 bits at a
+ * time.  Order of access is not guaranteed, nor is a memory barrier
+ * performed afterwards.
+ */
+void __attribute__((weak)) __iowrite64_copy(void __iomem *to,
+					    const void *from,
+					    size_t count)
+{
+#ifdef CONFIG_64BIT
+	u64 __iomem *dst = to;
+	const u64 *src = from;
+	const u64 *end = src + count;
+
+	while (src < end)
+		__raw_writeq(*src++, dst++);
+#else
+	__iowrite32_copy(to, from, count * 2);
+#endif
+}
+
+EXPORT_SYMBOL_GPL(__iowrite64_copy);

lib/ioremap.c

@@ -0,0 +1,91 @@
+/*
+ * Re-map IO memory to kernel address space so that we can access it.
+ * This is needed for high PCI addresses that aren't mapped in the
+ * 640k-1MB IO memory area on PC's
+ *
+ * (C) Copyright 1995 1996 Linus Torvalds
+ */
+#include <linux/vmalloc.h>
+#include <linux/mm.h>
+
+#include <asm/cacheflush.h>
+#include <asm/pgtable.h>
+
+static int ioremap_pte_range(pmd_t *pmd, unsigned long addr,
+		unsigned long end, unsigned long phys_addr, pgprot_t prot)
+{
+	pte_t *pte;
+	unsigned long pfn;
+
+	pfn = phys_addr >> PAGE_SHIFT;
+	pte = pte_alloc_kernel(pmd, addr);
+	if (!pte)
+		return -ENOMEM;
+	do {
+		BUG_ON(!pte_none(*pte));
+		set_pte_at(&init_mm, addr, pte, pfn_pte(pfn, prot));
+		pfn++;
+	} while (pte++, addr += PAGE_SIZE, addr != end);
+	return 0;
+}
+
+static inline int ioremap_pmd_range(pud_t *pud, unsigned long addr,
+		unsigned long end, unsigned long phys_addr, pgprot_t prot)
+{
+	pmd_t *pmd;
+	unsigned long next;
+
+	phys_addr -= addr;
+	pmd = pmd_alloc(&init_mm, pud, addr);
+	if (!pmd)
+		return -ENOMEM;
+	do {
+		next = pmd_addr_end(addr, end);
+		if (ioremap_pte_range(pmd, addr, next, phys_addr + addr, prot))
+			return -ENOMEM;
+	} while (pmd++, addr = next, addr != end);
+	return 0;
+}
+
+static inline int ioremap_pud_range(pgd_t *pgd, unsigned long addr,
+		unsigned long end, unsigned long phys_addr, pgprot_t prot)
+{
+	pud_t *pud;
+	unsigned long next;
+
+	phys_addr -= addr;
+	pud = pud_alloc(&init_mm, pgd, addr);
+	if (!pud)
+		return -ENOMEM;
+	do {
+		next = pud_addr_end(addr, end);
+		if (ioremap_pmd_range(pud, addr, next, phys_addr + addr, prot))
+			return -ENOMEM;
+	} while (pud++, addr = next, addr != end);
+	return 0;
+}
+
+int ioremap_page_range(unsigned long addr,
+		       unsigned long end, unsigned long phys_addr, pgprot_t prot)
+{
+	pgd_t *pgd;
+	unsigned long start;
+	unsigned long next;
+	int err;
+
+	BUG_ON(addr >= end);
+
+	start = addr;
+	phys_addr -= addr;
+	pgd = pgd_offset_k(addr);
+	do {
+		next = pgd_addr_end(addr, end);
+		err = ioremap_pud_range(pgd, addr, next, phys_addr+addr, prot);
+		if (err)
+			break;
+	} while (pgd++, addr = next, addr != end);
+
+	flush_cache_vmap(start, end);
+
+	return err;
+}

lib/irq_regs.c

@@ -0,0 +1,17 @@
+/* saved per-CPU IRQ register pointer
+ *
+ * Copyright (C) 2006 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 License
+ * 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 <asm/irq_regs.h>
+
+#ifndef ARCH_HAS_OWN_IRQ_REGS
+DEFINE_PER_CPU(struct pt_regs *, __irq_regs);
+EXPORT_PER_CPU_SYMBOL(__irq_regs);
+#endif

lib/kernel_lock.c

@@ -0,0 +1,213 @@
+/*
+ * lib/kernel_lock.c
+ *
+ * This is the traditional BKL - big kernel lock. Largely
+ * relegated to obsolescense, but used by various less
+ * important (or lazy) subsystems.
+ */
+#include <linux/smp_lock.h>
+#include <linux/module.h>
+#include <linux/kallsyms.h>
+
+#ifdef CONFIG_PREEMPT_BKL
+/*
+ * The 'big kernel semaphore'
+ *
+ * This mutex is taken and released recursively by lock_kernel()
+ * and unlock_kernel().  It is transparently dropped and reacquired
+ * over schedule().  It is used to protect legacy code that hasn't
+ * been migrated to a proper locking design yet.
+ *
+ * Note: code locked by this semaphore will only be serialized against
+ * other code using the same locking facility. The code guarantees that
+ * the task remains on the same CPU.
+ *
+ * Don't use in new code.
+ */
+static DECLARE_MUTEX(kernel_sem);
+
+/*
+ * Re-acquire the kernel semaphore.
+ *
+ * This function is called with preemption off.
+ *
+ * We are executing in schedule() so the code must be extremely careful
+ * about recursion, both due to the down() and due to the enabling of
+ * preemption. schedule() will re-check the preemption flag after
+ * reacquiring the semaphore.
+ */
+int __lockfunc __reacquire_kernel_lock(void)
+{
+	struct task_struct *task = current;
+	int saved_lock_depth = task->lock_depth;
+
+	BUG_ON(saved_lock_depth < 0);
+
+	task->lock_depth = -1;
+	preempt_enable_no_resched();
+
+	down(&kernel_sem);
+
+	preempt_disable();
+	task->lock_depth = saved_lock_depth;
+
+	return 0;
+}
+
+void __lockfunc __release_kernel_lock(void)
+{
+	up(&kernel_sem);
+}
+
+/*
+ * Getting the big kernel semaphore.
+ */
+void __lockfunc lock_kernel(void)
+{
+	struct task_struct *task = current;
+	int depth = task->lock_depth + 1;
+
+	if (likely(!depth))
+		/*
+		 * No recursion worries - we set up lock_depth _after_
+		 */
+		down(&kernel_sem);
+
+	task->lock_depth = depth;
+}
+
+void __lockfunc unlock_kernel(void)
+{
+	struct task_struct *task = current;
+
+	BUG_ON(task->lock_depth < 0);
+
+	if (likely(--task->lock_depth < 0))
+		up(&kernel_sem);
+}
+
+#else
+
+/*
+ * The 'big kernel lock'
+ *
+ * This spinlock is taken and released recursively by lock_kernel()
+ * and unlock_kernel().  It is transparently dropped and reacquired
+ * over schedule().  It is used to protect legacy code that hasn't
+ * been migrated to a proper locking design yet.
+ *
+ * Don't use in new code.
+ */
+static  __cacheline_aligned_in_smp DEFINE_SPINLOCK(kernel_flag);
+
+
+/*
+ * Acquire/release the underlying lock from the scheduler.
+ *
+ * This is called with preemption disabled, and should
+ * return an error value if it cannot get the lock and
+ * TIF_NEED_RESCHED gets set.
+ *
+ * If it successfully gets the lock, it should increment
+ * the preemption count like any spinlock does.
+ *
+ * (This works on UP too - _raw_spin_trylock will never
+ * return false in that case)
+ */
+int __lockfunc __reacquire_kernel_lock(void)
+{
+	while (!_raw_spin_trylock(&kernel_flag)) {
+		if (test_thread_flag(TIF_NEED_RESCHED))
+			return -EAGAIN;
+		cpu_relax();
+	}
+	preempt_disable();
+	return 0;
+}
+
+void __lockfunc __release_kernel_lock(void)
+{
+	_raw_spin_unlock(&kernel_flag);
+	preempt_enable_no_resched();
+}
+
+/*
+ * These are the BKL spinlocks - we try to be polite about preemption. 
+ * If SMP is not on (ie UP preemption), this all goes away because the
+ * _raw_spin_trylock() will always succeed.
+ */
+#ifdef CONFIG_PREEMPT
+static inline void __lock_kernel(void)
+{
+	preempt_disable();
+	if (unlikely(!_raw_spin_trylock(&kernel_flag))) {
+		/*
+		 * If preemption was disabled even before this
+		 * was called, there's nothing we can be polite
+		 * about - just spin.
+		 */
+		if (preempt_count() > 1) {
+			_raw_spin_lock(&kernel_flag);
+			return;
+		}
+
+		/*
+		 * Otherwise, let's wait for the kernel lock
+		 * with preemption enabled..
+		 */
+		do {
+			preempt_enable();
+			while (spin_is_locked(&kernel_flag))
+				cpu_relax();
+			preempt_disable();
+		} while (!_raw_spin_trylock(&kernel_flag));
+	}
+}
+
+#else
+
+/*
+ * Non-preemption case - just get the spinlock
+ */
+static inline void __lock_kernel(void)
+{
+	_raw_spin_lock(&kernel_flag);
+}
+#endif
+
+static inline void __unlock_kernel(void)
+{
+	/*
+	 * the BKL is not covered by lockdep, so we open-code the
+	 * unlocking sequence (and thus avoid the dep-chain ops):
+	 */
+	_raw_spin_unlock(&kernel_flag);
+	preempt_enable();
+}
+
+/*
+ * Getting the big kernel lock.
+ *
+ * This cannot happen asynchronously, so we only need to
+ * worry about other CPU's.
+ */
+void __lockfunc lock_kernel(void)
+{
+	int depth = current->lock_depth+1;
+	if (likely(!depth))
+		__lock_kernel();
+	current->lock_depth = depth;
+}
+
+void __lockfunc unlock_kernel(void)
+{
+	BUG_ON(current->lock_depth < 0);
+	if (likely(--current->lock_depth < 0))
+		__unlock_kernel();
+}
+
+#endif
+
+EXPORT_SYMBOL(lock_kernel);
+EXPORT_SYMBOL(unlock_kernel);
+

lib/klist.c

@@ -0,0 +1,287 @@
+/*
+ *	klist.c - Routines for manipulating klists.
+ *
+ *
+ *	This klist interface provides a couple of structures that wrap around 
+ *	struct list_head to provide explicit list "head" (struct klist) and 
+ *	list "node" (struct klist_node) objects. For struct klist, a spinlock
+ *	is included that protects access to the actual list itself. struct 
+ *	klist_node provides a pointer to the klist that owns it and a kref
+ *	reference count that indicates the number of current users of that node
+ *	in the list.
+ *
+ *	The entire point is to provide an interface for iterating over a list
+ *	that is safe and allows for modification of the list during the
+ *	iteration (e.g. insertion and removal), including modification of the
+ *	current node on the list.
+ *
+ *	It works using a 3rd object type - struct klist_iter - that is declared
+ *	and initialized before an iteration. klist_next() is used to acquire the
+ *	next element in the list. It returns NULL if there are no more items.
+ *	Internally, that routine takes the klist's lock, decrements the reference
+ *	count of the previous klist_node and increments the count of the next
+ *	klist_node. It then drops the lock and returns.
+ *
+ *	There are primitives for adding and removing nodes to/from a klist. 
+ *	When deleting, klist_del() will simply decrement the reference count. 
+ *	Only when the count goes to 0 is the node removed from the list. 
+ *	klist_remove() will try to delete the node from the list and block
+ *	until it is actually removed. This is useful for objects (like devices)
+ *	that have been removed from the system and must be freed (but must wait
+ *	until all accessors have finished).
+ *
+ *	Copyright (C) 2005 Patrick Mochel
+ *
+ *	This file is released under the GPL v2.
+ */
+
+#include <linux/klist.h>
+#include <linux/module.h>
+
+
+/**
+ *	klist_init - Initialize a klist structure. 
+ *	@k:	The klist we're initializing.
+ *	@get:	The get function for the embedding object (NULL if none)
+ *	@put:	The put function for the embedding object (NULL if none)
+ *
+ * Initialises the klist structure.  If the klist_node structures are
+ * going to be embedded in refcounted objects (necessary for safe
+ * deletion) then the get/put arguments are used to initialise
+ * functions that take and release references on the embedding
+ * objects.
+ */
+
+void klist_init(struct klist * k, void (*get)(struct klist_node *),
+		void (*put)(struct klist_node *))
+{
+	INIT_LIST_HEAD(&k->k_list);
+	spin_lock_init(&k->k_lock);
+	k->get = get;
+	k->put = put;
+}
+
+EXPORT_SYMBOL_GPL(klist_init);
+
+
+static void add_head(struct klist * k, struct klist_node * n)
+{
+	spin_lock(&k->k_lock);
+	list_add(&n->n_node, &k->k_list);
+	spin_unlock(&k->k_lock);
+}
+
+static void add_tail(struct klist * k, struct klist_node * n)
+{
+	spin_lock(&k->k_lock);
+	list_add_tail(&n->n_node, &k->k_list);
+	spin_unlock(&k->k_lock);
+}
+
+
+static void klist_node_init(struct klist * k, struct klist_node * n)
+{
+	INIT_LIST_HEAD(&n->n_node);
+	init_completion(&n->n_removed);
+	kref_init(&n->n_ref);
+	n->n_klist = k;
+	if (k->get)
+		k->get(n);
+}
+
+
+/**
+ *	klist_add_head - Initialize a klist_node and add it to front.
+ *	@n:	node we're adding.
+ *	@k:	klist it's going on.
+ */
+
+void klist_add_head(struct klist_node * n, struct klist * k)
+{
+	klist_node_init(k, n);
+	add_head(k, n);
+}
+
+EXPORT_SYMBOL_GPL(klist_add_head);
+
+
+/**
+ *	klist_add_tail - Initialize a klist_node and add it to back.
+ *	@n:	node we're adding.
+ *	@k:	klist it's going on.
+ */
+
+void klist_add_tail(struct klist_node * n, struct klist * k)
+{
+	klist_node_init(k, n);
+	add_tail(k, n);
+}
+
+EXPORT_SYMBOL_GPL(klist_add_tail);
+
+
+static void klist_release(struct kref * kref)
+{
+	struct klist_node * n = container_of(kref, struct klist_node, n_ref);
+
+	list_del(&n->n_node);
+	complete(&n->n_removed);
+	n->n_klist = NULL;
+}
+
+static int klist_dec_and_del(struct klist_node * n)
+{
+	return kref_put(&n->n_ref, klist_release);
+}
+
+
+/**
+ *	klist_del - Decrement the reference count of node and try to remove.
+ *	@n:	node we're deleting.
+ */
+
+void klist_del(struct klist_node * n)
+{
+	struct klist * k = n->n_klist;
+	void (*put)(struct klist_node *) = k->put;
+
+	spin_lock(&k->k_lock);
+	if (!klist_dec_and_del(n))
+		put = NULL;
+	spin_unlock(&k->k_lock);
+	if (put)
+		put(n);
+}
+
+EXPORT_SYMBOL_GPL(klist_del);
+
+
+/**
+ *	klist_remove - Decrement the refcount of node and wait for it to go away.
+ *	@n:	node we're removing.
+ */
+
+void klist_remove(struct klist_node * n)
+{
+	klist_del(n);
+	wait_for_completion(&n->n_removed);
+}
+
+EXPORT_SYMBOL_GPL(klist_remove);
+
+
+/**
+ *	klist_node_attached - Say whether a node is bound to a list or not.
+ *	@n:	Node that we're testing.
+ */
+
+int klist_node_attached(struct klist_node * n)
+{
+	return (n->n_klist != NULL);
+}
+
+EXPORT_SYMBOL_GPL(klist_node_attached);
+
+
+/**
+ *	klist_iter_init_node - Initialize a klist_iter structure.
+ *	@k:	klist we're iterating.
+ *	@i:	klist_iter we're filling.
+ *	@n:	node to start with.
+ *
+ *	Similar to klist_iter_init(), but starts the action off with @n, 
+ *	instead of with the list head.
+ */
+
+void klist_iter_init_node(struct klist * k, struct klist_iter * i, struct klist_node * n)
+{
+	i->i_klist = k;
+	i->i_head = &k->k_list;
+	i->i_cur = n;
+	if (n)
+		kref_get(&n->n_ref);
+}
+
+EXPORT_SYMBOL_GPL(klist_iter_init_node);
+
+
+/**
+ *	klist_iter_init - Iniitalize a klist_iter structure.
+ *	@k:	klist we're iterating.
+ *	@i:	klist_iter structure we're filling.
+ *
+ *	Similar to klist_iter_init_node(), but start with the list head.
+ */
+
+void klist_iter_init(struct klist * k, struct klist_iter * i)
+{
+	klist_iter_init_node(k, i, NULL);
+}
+
+EXPORT_SYMBOL_GPL(klist_iter_init);
+
+
+/**
+ *	klist_iter_exit - Finish a list iteration.
+ *	@i:	Iterator structure.
+ *
+ *	Must be called when done iterating over list, as it decrements the 
+ *	refcount of the current node. Necessary in case iteration exited before
+ *	the end of the list was reached, and always good form.
+ */
+
+void klist_iter_exit(struct klist_iter * i)
+{
+	if (i->i_cur) {
+		klist_del(i->i_cur);
+		i->i_cur = NULL;
+	}
+}
+
+EXPORT_SYMBOL_GPL(klist_iter_exit);
+
+
+static struct klist_node * to_klist_node(struct list_head * n)
+{
+	return container_of(n, struct klist_node, n_node);
+}
+
+
+/**
+ *	klist_next - Ante up next node in list.
+ *	@i:	Iterator structure.
+ *
+ *	First grab list lock. Decrement the reference count of the previous
+ *	node, if there was one. Grab the next node, increment its reference 
+ *	count, drop the lock, and return that next node.
+ */
+
+struct klist_node * klist_next(struct klist_iter * i)
+{
+	struct list_head * next;
+	struct klist_node * lnode = i->i_cur;
+	struct klist_node * knode = NULL;
+	void (*put)(struct klist_node *) = i->i_klist->put;
+
+	spin_lock(&i->i_klist->k_lock);
+	if (lnode) {
+		next = lnode->n_node.next;
+		if (!klist_dec_and_del(lnode))
+			put = NULL;
+	} else
+		next = i->i_head->next;
+
+	if (next != i->i_head) {
+		knode = to_klist_node(next);
+		kref_get(&knode->n_ref);
+	}
+	i->i_cur = knode;
+	spin_unlock(&i->i_klist->k_lock);
+	if (put && lnode)
+		put(lnode);
+	return knode;
+}
+
+EXPORT_SYMBOL_GPL(klist_next);
+
+

lib/kobject.c

@@ -0,0 +1,704 @@
+/*
+ * kobject.c - library routines for handling generic kernel objects
+ *
+ * Copyright (c) 2002-2003 Patrick Mochel <mochel@osdl.org>
+ *
+ * This file is released under the GPLv2.
+ *
+ *
+ * Please see the file Documentation/kobject.txt for critical information
+ * about using the kobject interface.
+ */
+
+#include <linux/kobject.h>
+#include <linux/string.h>
+#include <linux/module.h>
+#include <linux/stat.h>
+#include <linux/slab.h>
+
+/**
+ *	populate_dir - populate directory with attributes.
+ *	@kobj:	object we're working on.
+ *
+ *	Most subsystems have a set of default attributes that 
+ *	are associated with an object that registers with them.
+ *	This is a helper called during object registration that 
+ *	loops through the default attributes of the subsystem 
+ *	and creates attributes files for them in sysfs.
+ *
+ */
+
+static int populate_dir(struct kobject * kobj)
+{
+	struct kobj_type * t = get_ktype(kobj);
+	struct attribute * attr;
+	int error = 0;
+	int i;
+	
+	if (t && t->default_attrs) {
+		for (i = 0; (attr = t->default_attrs[i]) != NULL; i++) {
+			if ((error = sysfs_create_file(kobj,attr)))
+				break;
+		}
+	}
+	return error;
+}
+
+static int create_dir(struct kobject * kobj, struct dentry *shadow_parent)
+{
+	int error = 0;
+	if (kobject_name(kobj)) {
+		error = sysfs_create_dir(kobj, shadow_parent);
+		if (!error) {
+			if ((error = populate_dir(kobj)))
+				sysfs_remove_dir(kobj);
+		}
+	}
+	return error;
+}
+
+static inline struct kobject * to_kobj(struct list_head * entry)
+{
+	return container_of(entry,struct kobject,entry);
+}
+
+static int get_kobj_path_length(struct kobject *kobj)
+{
+	int length = 1;
+	struct kobject * parent = kobj;
+
+	/* walk up the ancestors until we hit the one pointing to the 
+	 * root.
+	 * Add 1 to strlen for leading '/' of each level.
+	 */
+	do {
+		if (kobject_name(parent) == NULL)
+			return 0;
+		length += strlen(kobject_name(parent)) + 1;
+		parent = parent->parent;
+	} while (parent);
+	return length;
+}
+
+static void fill_kobj_path(struct kobject *kobj, char *path, int length)
+{
+	struct kobject * parent;
+
+	--length;
+	for (parent = kobj; parent; parent = parent->parent) {
+		int cur = strlen(kobject_name(parent));
+		/* back up enough to print this name with '/' */
+		length -= cur;
+		strncpy (path + length, kobject_name(parent), cur);
+		*(path + --length) = '/';
+	}
+
+	pr_debug("%s: path = '%s'\n",__FUNCTION__,path);
+}
+
+/**
+ * kobject_get_path - generate and return the path associated with a given kobj and kset pair.
+ *
+ * @kobj:	kobject in question, with which to build the path
+ * @gfp_mask:	the allocation type used to allocate the path
+ *
+ * The result must be freed by the caller with kfree().
+ */
+char *kobject_get_path(struct kobject *kobj, gfp_t gfp_mask)
+{
+	char *path;
+	int len;
+
+	len = get_kobj_path_length(kobj);
+	if (len == 0)
+		return NULL;
+	path = kzalloc(len, gfp_mask);
+	if (!path)
+		return NULL;
+	fill_kobj_path(kobj, path, len);
+
+	return path;
+}
+EXPORT_SYMBOL_GPL(kobject_get_path);
+
+/**
+ *	kobject_init - initialize object.
+ *	@kobj:	object in question.
+ */
+void kobject_init(struct kobject * kobj)
+{
+	if (!kobj)
+		return;
+	kref_init(&kobj->kref);
+	INIT_LIST_HEAD(&kobj->entry);
+	init_waitqueue_head(&kobj->poll);
+	kobj->kset = kset_get(kobj->kset);
+}
+
+
+/**
+ *	unlink - remove kobject from kset list.
+ *	@kobj:	kobject.
+ *
+ *	Remove the kobject from the kset list and decrement
+ *	its parent's refcount.
+ *	This is separated out, so we can use it in both 
+ *	kobject_del() and kobject_add() on error.
+ */
+
+static void unlink(struct kobject * kobj)
+{
+	if (kobj->kset) {
+		spin_lock(&kobj->kset->list_lock);
+		list_del_init(&kobj->entry);
+		spin_unlock(&kobj->kset->list_lock);
+	}
+	kobject_put(kobj);
+}
+
+/**
+ *	kobject_add - add an object to the hierarchy.
+ *	@kobj:	object.
+ *	@shadow_parent: sysfs directory to add to.
+ */
+
+int kobject_shadow_add(struct kobject * kobj, struct dentry *shadow_parent)
+{
+	int error = 0;
+	struct kobject * parent;
+
+	if (!(kobj = kobject_get(kobj)))
+		return -ENOENT;
+	if (!kobj->k_name)
+		kobj->k_name = kobj->name;
+	if (!*kobj->k_name) {
+		pr_debug("kobject attempted to be registered with no name!\n");
+		WARN_ON(1);
+		return -EINVAL;
+	}
+	parent = kobject_get(kobj->parent);
+
+	pr_debug("kobject %s: registering. parent: %s, set: %s\n",
+		 kobject_name(kobj), parent ? kobject_name(parent) : "<NULL>", 
+		 kobj->kset ? kobj->kset->kobj.name : "<NULL>" );
+
+	if (kobj->kset) {
+		spin_lock(&kobj->kset->list_lock);
+
+		if (!parent)
+			parent = kobject_get(&kobj->kset->kobj);
+
+		list_add_tail(&kobj->entry,&kobj->kset->list);
+		spin_unlock(&kobj->kset->list_lock);
+	}
+	kobj->parent = parent;
+
+	error = create_dir(kobj, shadow_parent);
+	if (error) {
+		/* unlink does the kobject_put() for us */
+		unlink(kobj);
+		kobject_put(parent);
+
+		/* be noisy on error issues */
+		if (error == -EEXIST)
+			printk("kobject_add failed for %s with -EEXIST, "
+			       "don't try to register things with the "
+			       "same name in the same directory.\n",
+			       kobject_name(kobj));
+		else
+			printk("kobject_add failed for %s (%d)\n",
+			       kobject_name(kobj), error);
+		 dump_stack();
+	}
+
+	return error;
+}
+
+/**
+ *	kobject_add - add an object to the hierarchy.
+ *	@kobj:	object.
+ */
+int kobject_add(struct kobject * kobj)
+{
+	return kobject_shadow_add(kobj, NULL);
+}
+
+
+/**
+ *	kobject_register - initialize and add an object.
+ *	@kobj:	object in question.
+ */
+
+int kobject_register(struct kobject * kobj)
+{
+	int error = -EINVAL;
+	if (kobj) {
+		kobject_init(kobj);
+		error = kobject_add(kobj);
+		if (!error)
+			kobject_uevent(kobj, KOBJ_ADD);
+	}
+	return error;
+}
+
+
+/**
+ *	kobject_set_name - Set the name of an object
+ *	@kobj:	object.
+ *	@fmt:	format string used to build the name
+ *
+ *	If strlen(name) >= KOBJ_NAME_LEN, then use a dynamically allocated
+ *	string that @kobj->k_name points to. Otherwise, use the static 
+ *	@kobj->name array.
+ */
+int kobject_set_name(struct kobject * kobj, const char * fmt, ...)
+{
+	int error = 0;
+	int limit = KOBJ_NAME_LEN;
+	int need;
+	va_list args;
+	char * name;
+
+	/* 
+	 * First, try the static array 
+	 */
+	va_start(args,fmt);
+	need = vsnprintf(kobj->name,limit,fmt,args);
+	va_end(args);
+	if (need < limit) 
+		name = kobj->name;
+	else {
+		/* 
+		 * Need more space? Allocate it and try again 
+		 */
+		limit = need + 1;
+		name = kmalloc(limit,GFP_KERNEL);
+		if (!name) {
+			error = -ENOMEM;
+			goto Done;
+		}
+		va_start(args,fmt);
+		need = vsnprintf(name,limit,fmt,args);
+		va_end(args);
+
+		/* Still? Give up. */
+		if (need >= limit) {
+			kfree(name);
+			error = -EFAULT;
+			goto Done;
+		}
+	}
+
+	/* Free the old name, if necessary. */
+	if (kobj->k_name && kobj->k_name != kobj->name)
+		kfree(kobj->k_name);
+
+	/* Now, set the new name */
+	kobj->k_name = name;
+ Done:
+	return error;
+}
+
+EXPORT_SYMBOL(kobject_set_name);
+
+
+/**
+ *	kobject_rename - change the name of an object
+ *	@kobj:	object in question.
+ *	@new_name: object's new name
+ */
+
+int kobject_rename(struct kobject * kobj, const char *new_name)
+{
+	int error = 0;
+
+	kobj = kobject_get(kobj);
+	if (!kobj)
+		return -EINVAL;
+	if (!kobj->parent)
+		return -EINVAL;
+	error = sysfs_rename_dir(kobj, kobj->parent->dentry, new_name);
+	kobject_put(kobj);
+
+	return error;
+}
+
+/**
+ *	kobject_rename - change the name of an object
+ *	@kobj:	object in question.
+ *	@new_parent: object's new parent
+ *	@new_name: object's new name
+ */
+
+int kobject_shadow_rename(struct kobject * kobj, struct dentry *new_parent,
+			  const char *new_name)
+{
+	int error = 0;
+
+	kobj = kobject_get(kobj);
+	if (!kobj)
+		return -EINVAL;
+	error = sysfs_rename_dir(kobj, new_parent, new_name);
+	kobject_put(kobj);
+
+	return error;
+}
+
+/**
+ *	kobject_move - move object to another parent
+ *	@kobj:	object in question.
+ *	@new_parent: object's new parent (can be NULL)
+ */
+
+int kobject_move(struct kobject *kobj, struct kobject *new_parent)
+{
+	int error;
+	struct kobject *old_parent;
+	const char *devpath = NULL;
+	char *devpath_string = NULL;
+	char *envp[2];
+
+	kobj = kobject_get(kobj);
+	if (!kobj)
+		return -EINVAL;
+	new_parent = kobject_get(new_parent);
+	if (!new_parent) {
+		if (kobj->kset)
+			new_parent = kobject_get(&kobj->kset->kobj);
+	}
+	/* old object path */
+	devpath = kobject_get_path(kobj, GFP_KERNEL);
+	if (!devpath) {
+		error = -ENOMEM;
+		goto out;
+	}
+	devpath_string = kmalloc(strlen(devpath) + 15, GFP_KERNEL);
+	if (!devpath_string) {
+		error = -ENOMEM;
+		goto out;
+	}
+	sprintf(devpath_string, "DEVPATH_OLD=%s", devpath);
+	envp[0] = devpath_string;
+	envp[1] = NULL;
+	error = sysfs_move_dir(kobj, new_parent);
+	if (error)
+		goto out;
+	old_parent = kobj->parent;
+	kobj->parent = new_parent;
+	new_parent = NULL;
+	kobject_put(old_parent);
+	kobject_uevent_env(kobj, KOBJ_MOVE, envp);
+out:
+	kobject_put(new_parent);
+	kobject_put(kobj);
+	kfree(devpath_string);
+	kfree(devpath);
+	return error;
+}
+
+/**
+ *	kobject_del - unlink kobject from hierarchy.
+ * 	@kobj:	object.
+ */
+
+void kobject_del(struct kobject * kobj)
+{
+	if (!kobj)
+		return;
+	sysfs_remove_dir(kobj);
+	unlink(kobj);
+}
+
+/**
+ *	kobject_unregister - remove object from hierarchy and decrement refcount.
+ *	@kobj:	object going away.
+ */
+
+void kobject_unregister(struct kobject * kobj)
+{
+	if (!kobj)
+		return;
+	pr_debug("kobject %s: unregistering\n",kobject_name(kobj));
+	kobject_uevent(kobj, KOBJ_REMOVE);
+	kobject_del(kobj);
+	kobject_put(kobj);
+}
+
+/**
+ *	kobject_get - increment refcount for object.
+ *	@kobj:	object.
+ */
+
+struct kobject * kobject_get(struct kobject * kobj)
+{
+	if (kobj)
+		kref_get(&kobj->kref);
+	return kobj;
+}
+
+/**
+ *	kobject_cleanup - free kobject resources. 
+ *	@kobj:	object.
+ */
+
+void kobject_cleanup(struct kobject * kobj)
+{
+	struct kobj_type * t = get_ktype(kobj);
+	struct kset * s = kobj->kset;
+	struct kobject * parent = kobj->parent;
+
+	pr_debug("kobject %s: cleaning up\n",kobject_name(kobj));
+	if (kobj->k_name != kobj->name)
+		kfree(kobj->k_name);
+	kobj->k_name = NULL;
+	if (t && t->release)
+		t->release(kobj);
+	if (s)
+		kset_put(s);
+	kobject_put(parent);
+}
+
+static void kobject_release(struct kref *kref)
+{
+	kobject_cleanup(container_of(kref, struct kobject, kref));
+}
+
+/**
+ *	kobject_put - decrement refcount for object.
+ *	@kobj:	object.
+ *
+ *	Decrement the refcount, and if 0, call kobject_cleanup().
+ */
+void kobject_put(struct kobject * kobj)
+{
+	if (kobj)
+		kref_put(&kobj->kref, kobject_release);
+}
+
+
+static void dir_release(struct kobject *kobj)
+{
+	kfree(kobj);
+}
+
+static struct kobj_type dir_ktype = {
+	.release	= dir_release,
+	.sysfs_ops	= NULL,
+	.default_attrs	= NULL,
+};
+
+/**
+ *	kobject_add_dir - add sub directory of object.
+ *	@parent:	object in which a directory is created.
+ *	@name:	directory name.
+ *
+ *	Add a plain directory object as child of given object.
+ */
+struct kobject *kobject_add_dir(struct kobject *parent, const char *name)
+{
+	struct kobject *k;
+	int ret;
+
+	if (!parent)
+		return NULL;
+
+	k = kzalloc(sizeof(*k), GFP_KERNEL);
+	if (!k)
+		return NULL;
+
+	k->parent = parent;
+	k->ktype = &dir_ktype;
+	kobject_set_name(k, name);
+	ret = kobject_register(k);
+	if (ret < 0) {
+		printk(KERN_WARNING "kobject_add_dir: "
+			"kobject_register error: %d\n", ret);
+		kobject_del(k);
+		return NULL;
+	}
+
+	return k;
+}
+
+/**
+ *	kset_init - initialize a kset for use
+ *	@k:	kset 
+ */
+
+void kset_init(struct kset * k)
+{
+	kobject_init(&k->kobj);
+	INIT_LIST_HEAD(&k->list);
+	spin_lock_init(&k->list_lock);
+}
+
+
+/**
+ *	kset_add - add a kset object to the hierarchy.
+ *	@k:	kset.
+ *
+ *	Simply, this adds the kset's embedded kobject to the 
+ *	hierarchy. 
+ *	We also try to make sure that the kset's embedded kobject
+ *	has a parent before it is added. We only care if the embedded
+ *	kobject is not part of a kset itself, since kobject_add()
+ *	assigns a parent in that case. 
+ *	If that is the case, and the kset has a controlling subsystem,
+ *	then we set the kset's parent to be said subsystem. 
+ */
+
+int kset_add(struct kset * k)
+{
+	if (!k->kobj.parent && !k->kobj.kset && k->subsys)
+		k->kobj.parent = &k->subsys->kset.kobj;
+
+	return kobject_add(&k->kobj);
+}
+
+
+/**
+ *	kset_register - initialize and add a kset.
+ *	@k:	kset.
+ */
+
+int kset_register(struct kset * k)
+{
+	if (!k)
+		return -EINVAL;
+	kset_init(k);
+	return kset_add(k);
+}
+
+
+/**
+ *	kset_unregister - remove a kset.
+ *	@k:	kset.
+ */
+
+void kset_unregister(struct kset * k)
+{
+	if (!k)
+		return;
+	kobject_unregister(&k->kobj);
+}
+
+
+/**
+ *	kset_find_obj - search for object in kset.
+ *	@kset:	kset we're looking in.
+ *	@name:	object's name.
+ *
+ *	Lock kset via @kset->subsys, and iterate over @kset->list,
+ *	looking for a matching kobject. If matching object is found
+ *	take a reference and return the object.
+ */
+
+struct kobject * kset_find_obj(struct kset * kset, const char * name)
+{
+	struct list_head * entry;
+	struct kobject * ret = NULL;
+
+	spin_lock(&kset->list_lock);
+	list_for_each(entry,&kset->list) {
+		struct kobject * k = to_kobj(entry);
+		if (kobject_name(k) && !strcmp(kobject_name(k),name)) {
+			ret = kobject_get(k);
+			break;
+		}
+	}
+	spin_unlock(&kset->list_lock);
+	return ret;
+}
+
+
+void subsystem_init(struct subsystem * s)
+{
+	init_rwsem(&s->rwsem);
+	kset_init(&s->kset);
+}
+
+/**
+ *	subsystem_register - register a subsystem.
+ *	@s:	the subsystem we're registering.
+ *
+ *	Once we register the subsystem, we want to make sure that 
+ *	the kset points back to this subsystem for correct usage of 
+ *	the rwsem. 
+ */
+
+int subsystem_register(struct subsystem * s)
+{
+	int error;
+
+	if (!s)
+		return -EINVAL;
+
+	subsystem_init(s);
+	pr_debug("subsystem %s: registering\n",s->kset.kobj.name);
+
+	if (!(error = kset_add(&s->kset))) {
+		if (!s->kset.subsys)
+			s->kset.subsys = s;
+	}
+	return error;
+}
+
+void subsystem_unregister(struct subsystem * s)
+{
+	if (!s)
+		return;
+	pr_debug("subsystem %s: unregistering\n",s->kset.kobj.name);
+	kset_unregister(&s->kset);
+}
+
+
+/**
+ *	subsystem_create_file - export sysfs attribute file.
+ *	@s:	subsystem.
+ *	@a:	subsystem attribute descriptor.
+ */
+
+int subsys_create_file(struct subsystem * s, struct subsys_attribute * a)
+{
+	int error = 0;
+
+	if (!s || !a)
+		return -EINVAL;
+
+	if (subsys_get(s)) {
+		error = sysfs_create_file(&s->kset.kobj,&a->attr);
+		subsys_put(s);
+	}
+	return error;
+}
+
+
+/**
+ *	subsystem_remove_file - remove sysfs attribute file.
+ *	@s:	subsystem.
+ *	@a:	attribute desciptor.
+ */
+#if 0
+void subsys_remove_file(struct subsystem * s, struct subsys_attribute * a)
+{
+	if (subsys_get(s)) {
+		sysfs_remove_file(&s->kset.kobj,&a->attr);
+		subsys_put(s);
+	}
+}
+#endif  /*  0  */
+
+EXPORT_SYMBOL(kobject_init);
+EXPORT_SYMBOL(kobject_register);
+EXPORT_SYMBOL(kobject_unregister);
+EXPORT_SYMBOL(kobject_get);
+EXPORT_SYMBOL(kobject_put);
+EXPORT_SYMBOL(kobject_add);
+EXPORT_SYMBOL(kobject_del);
+
+EXPORT_SYMBOL(kset_register);
+EXPORT_SYMBOL(kset_unregister);
+
+EXPORT_SYMBOL(subsystem_register);
+EXPORT_SYMBOL(subsystem_unregister);
+EXPORT_SYMBOL(subsys_create_file);

lib/kobject_uevent.c

@@ -0,0 +1,310 @@
+/*
+ * kernel userspace event delivery
+ *
+ * Copyright (C) 2004 Red Hat, Inc.  All rights reserved.
+ * Copyright (C) 2004 Novell, Inc.  All rights reserved.
+ * Copyright (C) 2004 IBM, Inc. All rights reserved.
+ *
+ * Licensed under the GNU GPL v2.
+ *
+ * Authors:
+ *	Robert Love		<rml@novell.com>
+ *	Kay Sievers		<kay.sievers@vrfy.org>
+ *	Arjan van de Ven	<arjanv@redhat.com>
+ *	Greg Kroah-Hartman	<greg@kroah.com>
+ */
+
+#include <linux/spinlock.h>
+#include <linux/socket.h>
+#include <linux/skbuff.h>
+#include <linux/netlink.h>
+#include <linux/string.h>
+#include <linux/kobject.h>
+#include <net/sock.h>
+
+#define BUFFER_SIZE	2048	/* buffer for the variables */
+#define NUM_ENVP	32	/* number of env pointers */
+
+#if defined(CONFIG_HOTPLUG)
+u64 uevent_seqnum;
+char uevent_helper[UEVENT_HELPER_PATH_LEN] = "/sbin/hotplug";
+static DEFINE_SPINLOCK(sequence_lock);
+#if defined(CONFIG_NET)
+static struct sock *uevent_sock;
+#endif
+
+static char *action_to_string(enum kobject_action action)
+{
+	switch (action) {
+	case KOBJ_ADD:
+		return "add";
+	case KOBJ_REMOVE:
+		return "remove";
+	case KOBJ_CHANGE:
+		return "change";
+	case KOBJ_MOUNT:
+		return "mount";
+	case KOBJ_UMOUNT:
+		return "umount";
+	case KOBJ_OFFLINE:
+		return "offline";
+	case KOBJ_ONLINE:
+		return "online";
+	case KOBJ_MOVE:
+		return "move";
+	default:
+		return NULL;
+	}
+}
+
+/**
+ * kobject_uevent_env - send an uevent with environmental data
+ *
+ * @action: action that is happening (usually KOBJ_MOVE)
+ * @kobj: struct kobject that the action is happening to
+ * @envp_ext: pointer to environmental data
+ *
+ * Returns 0 if kobject_uevent() is completed with success or the
+ * corresponding error when it fails.
+ */
+int kobject_uevent_env(struct kobject *kobj, enum kobject_action action,
+			char *envp_ext[])
+{
+	char **envp;
+	char *buffer;
+	char *scratch;
+	const char *action_string;
+	const char *devpath = NULL;
+	const char *subsystem;
+	struct kobject *top_kobj;
+	struct kset *kset;
+	struct kset_uevent_ops *uevent_ops;
+	u64 seq;
+	char *seq_buff;
+	int i = 0;
+	int retval = 0;
+	int j;
+
+	pr_debug("%s\n", __FUNCTION__);
+
+	action_string = action_to_string(action);
+	if (!action_string) {
+		pr_debug("kobject attempted to send uevent without action_string!\n");
+		return -EINVAL;
+	}
+
+	/* search the kset we belong to */
+	top_kobj = kobj;
+	if (!top_kobj->kset && top_kobj->parent) {
+		do {
+			top_kobj = top_kobj->parent;
+		} while (!top_kobj->kset && top_kobj->parent);
+	}
+	if (!top_kobj->kset) {
+		pr_debug("kobject attempted to send uevent without kset!\n");
+		return -EINVAL;
+	}
+
+	kset = top_kobj->kset;
+	uevent_ops = kset->uevent_ops;
+
+	/*  skip the event, if the filter returns zero. */
+	if (uevent_ops && uevent_ops->filter)
+		if (!uevent_ops->filter(kset, kobj)) {
+			pr_debug("kobject filter function caused the event to drop!\n");
+			return 0;
+		}
+
+	/* environment index */
+	envp = kzalloc(NUM_ENVP * sizeof (char *), GFP_KERNEL);
+	if (!envp)
+		return -ENOMEM;
+
+	/* environment values */
+	buffer = kmalloc(BUFFER_SIZE, GFP_KERNEL);
+	if (!buffer) {
+		retval = -ENOMEM;
+		goto exit;
+	}
+
+	/* complete object path */
+	devpath = kobject_get_path(kobj, GFP_KERNEL);
+	if (!devpath) {
+		retval = -ENOENT;
+		goto exit;
+	}
+
+	/* originating subsystem */
+	if (uevent_ops && uevent_ops->name)
+		subsystem = uevent_ops->name(kset, kobj);
+	else
+		subsystem = kobject_name(&kset->kobj);
+
+	/* event environemnt for helper process only */
+	envp[i++] = "HOME=/";
+	envp[i++] = "PATH=/sbin:/bin:/usr/sbin:/usr/bin";
+
+	/* default keys */
+	scratch = buffer;
+	envp [i++] = scratch;
+	scratch += sprintf(scratch, "ACTION=%s", action_string) + 1;
+	envp [i++] = scratch;
+	scratch += sprintf (scratch, "DEVPATH=%s", devpath) + 1;
+	envp [i++] = scratch;
+	scratch += sprintf(scratch, "SUBSYSTEM=%s", subsystem) + 1;
+	for (j = 0; envp_ext && envp_ext[j]; j++)
+		envp[i++] = envp_ext[j];
+	/* just reserve the space, overwrite it after kset call has returned */
+	envp[i++] = seq_buff = scratch;
+	scratch += strlen("SEQNUM=18446744073709551616") + 1;
+
+	/* let the kset specific function add its stuff */
+	if (uevent_ops && uevent_ops->uevent) {
+		retval = uevent_ops->uevent(kset, kobj,
+				  &envp[i], NUM_ENVP - i, scratch,
+				  BUFFER_SIZE - (scratch - buffer));
+		if (retval) {
+			pr_debug ("%s - uevent() returned %d\n",
+				  __FUNCTION__, retval);
+			goto exit;
+		}
+	}
+
+	/* we will send an event, request a new sequence number */
+	spin_lock(&sequence_lock);
+	seq = ++uevent_seqnum;
+	spin_unlock(&sequence_lock);
+	sprintf(seq_buff, "SEQNUM=%llu", (unsigned long long)seq);
+
+#if defined(CONFIG_NET)
+	/* send netlink message */
+	if (uevent_sock) {
+		struct sk_buff *skb;
+		size_t len;
+
+		/* allocate message with the maximum possible size */
+		len = strlen(action_string) + strlen(devpath) + 2;
+		skb = alloc_skb(len + BUFFER_SIZE, GFP_KERNEL);
+		if (skb) {
+			/* add header */
+			scratch = skb_put(skb, len);
+			sprintf(scratch, "%s@%s", action_string, devpath);
+
+			/* copy keys to our continuous event payload buffer */
+			for (i = 2; envp[i]; i++) {
+				len = strlen(envp[i]) + 1;
+				scratch = skb_put(skb, len);
+				strcpy(scratch, envp[i]);
+			}
+
+			NETLINK_CB(skb).dst_group = 1;
+			netlink_broadcast(uevent_sock, skb, 0, 1, GFP_KERNEL);
+		}
+	}
+#endif
+
+	/* call uevent_helper, usually only enabled during early boot */
+	if (uevent_helper[0]) {
+		char *argv [3];
+
+		argv [0] = uevent_helper;
+		argv [1] = (char *)subsystem;
+		argv [2] = NULL;
+		call_usermodehelper (argv[0], argv, envp, 0);
+	}
+
+exit:
+	kfree(devpath);
+	kfree(buffer);
+	kfree(envp);
+	return retval;
+}
+
+EXPORT_SYMBOL_GPL(kobject_uevent_env);
+
+/**
+ * kobject_uevent - notify userspace by ending an uevent
+ *
+ * @action: action that is happening (usually KOBJ_ADD and KOBJ_REMOVE)
+ * @kobj: struct kobject that the action is happening to
+ *
+ * Returns 0 if kobject_uevent() is completed with success or the
+ * corresponding error when it fails.
+ */
+int kobject_uevent(struct kobject *kobj, enum kobject_action action)
+{
+	return kobject_uevent_env(kobj, action, NULL);
+}
+
+EXPORT_SYMBOL_GPL(kobject_uevent);
+
+/**
+ * add_uevent_var - helper for creating event variables
+ * @envp: Pointer to table of environment variables, as passed into
+ * uevent() method.
+ * @num_envp: Number of environment variable slots available, as
+ * passed into uevent() method.
+ * @cur_index: Pointer to current index into @envp.  It should be
+ * initialized to 0 before the first call to add_uevent_var(),
+ * and will be incremented on success.
+ * @buffer: Pointer to buffer for environment variables, as passed
+ * into uevent() method.
+ * @buffer_size: Length of @buffer, as passed into uevent() method.
+ * @cur_len: Pointer to current length of space used in @buffer.
+ * Should be initialized to 0 before the first call to
+ * add_uevent_var(), and will be incremented on success.
+ * @format: Format for creating environment variable (of the form
+ * "XXX=%x") for snprintf().
+ *
+ * Returns 0 if environment variable was added successfully or -ENOMEM
+ * if no space was available.
+ */
+int add_uevent_var(char **envp, int num_envp, int *cur_index,
+		   char *buffer, int buffer_size, int *cur_len,
+		   const char *format, ...)
+{
+	va_list args;
+
+	/*
+	 * We check against num_envp - 1 to make sure there is at
+	 * least one slot left after we return, since kobject_uevent()
+	 * needs to set the last slot to NULL.
+	 */
+	if (*cur_index >= num_envp - 1)
+		return -ENOMEM;
+
+	envp[*cur_index] = buffer + *cur_len;
+
+	va_start(args, format);
+	*cur_len += vsnprintf(envp[*cur_index],
+			      max(buffer_size - *cur_len, 0),
+			      format, args) + 1;
+	va_end(args);
+
+	if (*cur_len > buffer_size)
+		return -ENOMEM;
+
+	(*cur_index)++;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(add_uevent_var);
+
+#if defined(CONFIG_NET)
+static int __init kobject_uevent_init(void)
+{
+	uevent_sock = netlink_kernel_create(NETLINK_KOBJECT_UEVENT, 1, NULL,
+					    THIS_MODULE);
+
+	if (!uevent_sock) {
+		printk(KERN_ERR
+		       "kobject_uevent: unable to create netlink socket!\n");
+		return -ENODEV;
+	}
+
+	return 0;
+}
+
+postcore_initcall(kobject_uevent_init);
+#endif
+
+#endif /* CONFIG_HOTPLUG */

lib/kref.c

@@ -0,0 +1,64 @@
+/*
+ * 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>
+
+/**
+ * kref_init - initialize object.
+ * @kref: object in question.
+ */
+void kref_init(struct kref *kref)
+{
+	atomic_set(&kref->refcount,1);
+}
+
+/**
+ * kref_get - increment refcount for object.
+ * @kref: object.
+ */
+void kref_get(struct kref *kref)
+{
+	WARN_ON(!atomic_read(&kref->refcount));
+	atomic_inc(&kref->refcount);
+}
+
+/**
+ * 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;
+}
+
+EXPORT_SYMBOL(kref_init);
+EXPORT_SYMBOL(kref_get);
+EXPORT_SYMBOL(kref_put);

lib/libcrc32c.c

@@ -0,0 +1,200 @@
+/* 
+ * CRC32C
+ *@Article{castagnoli-crc,
+ * author =       { Guy Castagnoli and Stefan Braeuer and Martin Herrman},
+ * title =        {{Optimization of Cyclic Redundancy-Check Codes with 24
+ *                 and 32 Parity Bits}},
+ * journal =      IEEE Transactions on Communication,
+ * year =         {1993},
+ * volume =       {41},
+ * number =       {6},
+ * pages =        {},
+ * month =        {June},
+ *}
+ * Used by the iSCSI driver, possibly others, and derived from the
+ * the iscsi-crc.c module of the linux-iscsi driver at
+ * http://linux-iscsi.sourceforge.net.
+ *
+ * Following the example of lib/crc32, this function is intended to be
+ * flexible and useful for all users.  Modules that currently have their
+ * own crc32c, but hopefully may be able to use this one are:
+ *  net/sctp (please add all your doco to here if you change to
+ *            use this one!)
+ *  <endoflist>
+ *
+ * Copyright (c) 2004 Cisco Systems, Inc.
+ * 
+ * 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/crc32c.h>
+#include <linux/compiler.h>
+#include <linux/module.h>
+#include <asm/byteorder.h>
+
+MODULE_AUTHOR("Clay Haapala <chaapala@cisco.com>");
+MODULE_DESCRIPTION("CRC32c (Castagnoli) calculations");
+MODULE_LICENSE("GPL");
+
+#define CRC32C_POLY_BE 0x1EDC6F41
+#define CRC32C_POLY_LE 0x82F63B78
+
+#ifndef CRC_LE_BITS 
+# define CRC_LE_BITS 8
+#endif
+
+
+/*
+ * Haven't generated a big-endian table yet, but the bit-wise version
+ * should at least work.
+ */
+#if defined CRC_BE_BITS && CRC_BE_BITS != 1
+#undef CRC_BE_BITS
+#endif
+#ifndef CRC_BE_BITS
+# define CRC_BE_BITS 1
+#endif
+
+EXPORT_SYMBOL(crc32c_le);
+
+#if CRC_LE_BITS == 1
+/*
+ * Compute things bit-wise, as done in crc32.c.  We could share the tight 
+ * loop below with crc32 and vary the POLY if we don't find value in terms
+ * of space and maintainability in keeping the two modules separate.
+ */
+u32 __attribute_pure__
+crc32c_le(u32 crc, unsigned char const *p, size_t len)
+{
+	int i;
+	while (len--) {
+		crc ^= *p++;
+		for (i = 0; i < 8; i++)
+			crc = (crc >> 1) ^ ((crc & 1) ? CRC32C_POLY_LE : 0);
+	}
+	return crc;
+}
+#else
+
+/*
+ * This is the CRC-32C table
+ * Generated with:
+ * width = 32 bits
+ * poly = 0x1EDC6F41
+ * reflect input bytes = true
+ * reflect output bytes = true
+ */
+
+static const u32 crc32c_table[256] = {
+	0x00000000L, 0xF26B8303L, 0xE13B70F7L, 0x1350F3F4L,
+	0xC79A971FL, 0x35F1141CL, 0x26A1E7E8L, 0xD4CA64EBL,
+	0x8AD958CFL, 0x78B2DBCCL, 0x6BE22838L, 0x9989AB3BL,
+	0x4D43CFD0L, 0xBF284CD3L, 0xAC78BF27L, 0x5E133C24L,
+	0x105EC76FL, 0xE235446CL, 0xF165B798L, 0x030E349BL,
+	0xD7C45070L, 0x25AFD373L, 0x36FF2087L, 0xC494A384L,
+	0x9A879FA0L, 0x68EC1CA3L, 0x7BBCEF57L, 0x89D76C54L,
+	0x5D1D08BFL, 0xAF768BBCL, 0xBC267848L, 0x4E4DFB4BL,
+	0x20BD8EDEL, 0xD2D60DDDL, 0xC186FE29L, 0x33ED7D2AL,
+	0xE72719C1L, 0x154C9AC2L, 0x061C6936L, 0xF477EA35L,
+	0xAA64D611L, 0x580F5512L, 0x4B5FA6E6L, 0xB93425E5L,
+	0x6DFE410EL, 0x9F95C20DL, 0x8CC531F9L, 0x7EAEB2FAL,
+	0x30E349B1L, 0xC288CAB2L, 0xD1D83946L, 0x23B3BA45L,
+	0xF779DEAEL, 0x05125DADL, 0x1642AE59L, 0xE4292D5AL,
+	0xBA3A117EL, 0x4851927DL, 0x5B016189L, 0xA96AE28AL,
+	0x7DA08661L, 0x8FCB0562L, 0x9C9BF696L, 0x6EF07595L,
+	0x417B1DBCL, 0xB3109EBFL, 0xA0406D4BL, 0x522BEE48L,
+	0x86E18AA3L, 0x748A09A0L, 0x67DAFA54L, 0x95B17957L,
+	0xCBA24573L, 0x39C9C670L, 0x2A993584L, 0xD8F2B687L,
+	0x0C38D26CL, 0xFE53516FL, 0xED03A29BL, 0x1F682198L,
+	0x5125DAD3L, 0xA34E59D0L, 0xB01EAA24L, 0x42752927L,
+	0x96BF4DCCL, 0x64D4CECFL, 0x77843D3BL, 0x85EFBE38L,
+	0xDBFC821CL, 0x2997011FL, 0x3AC7F2EBL, 0xC8AC71E8L,
+	0x1C661503L, 0xEE0D9600L, 0xFD5D65F4L, 0x0F36E6F7L,
+	0x61C69362L, 0x93AD1061L, 0x80FDE395L, 0x72966096L,
+	0xA65C047DL, 0x5437877EL, 0x4767748AL, 0xB50CF789L,
+	0xEB1FCBADL, 0x197448AEL, 0x0A24BB5AL, 0xF84F3859L,
+	0x2C855CB2L, 0xDEEEDFB1L, 0xCDBE2C45L, 0x3FD5AF46L,
+	0x7198540DL, 0x83F3D70EL, 0x90A324FAL, 0x62C8A7F9L,
+	0xB602C312L, 0x44694011L, 0x5739B3E5L, 0xA55230E6L,
+	0xFB410CC2L, 0x092A8FC1L, 0x1A7A7C35L, 0xE811FF36L,
+	0x3CDB9BDDL, 0xCEB018DEL, 0xDDE0EB2AL, 0x2F8B6829L,
+	0x82F63B78L, 0x709DB87BL, 0x63CD4B8FL, 0x91A6C88CL,
+	0x456CAC67L, 0xB7072F64L, 0xA457DC90L, 0x563C5F93L,
+	0x082F63B7L, 0xFA44E0B4L, 0xE9141340L, 0x1B7F9043L,
+	0xCFB5F4A8L, 0x3DDE77ABL, 0x2E8E845FL, 0xDCE5075CL,
+	0x92A8FC17L, 0x60C37F14L, 0x73938CE0L, 0x81F80FE3L,
+	0x55326B08L, 0xA759E80BL, 0xB4091BFFL, 0x466298FCL,
+	0x1871A4D8L, 0xEA1A27DBL, 0xF94AD42FL, 0x0B21572CL,
+	0xDFEB33C7L, 0x2D80B0C4L, 0x3ED04330L, 0xCCBBC033L,
+	0xA24BB5A6L, 0x502036A5L, 0x4370C551L, 0xB11B4652L,
+	0x65D122B9L, 0x97BAA1BAL, 0x84EA524EL, 0x7681D14DL,
+	0x2892ED69L, 0xDAF96E6AL, 0xC9A99D9EL, 0x3BC21E9DL,
+	0xEF087A76L, 0x1D63F975L, 0x0E330A81L, 0xFC588982L,
+	0xB21572C9L, 0x407EF1CAL, 0x532E023EL, 0xA145813DL,
+	0x758FE5D6L, 0x87E466D5L, 0x94B49521L, 0x66DF1622L,
+	0x38CC2A06L, 0xCAA7A905L, 0xD9F75AF1L, 0x2B9CD9F2L,
+	0xFF56BD19L, 0x0D3D3E1AL, 0x1E6DCDEEL, 0xEC064EEDL,
+	0xC38D26C4L, 0x31E6A5C7L, 0x22B65633L, 0xD0DDD530L,
+	0x0417B1DBL, 0xF67C32D8L, 0xE52CC12CL, 0x1747422FL,
+	0x49547E0BL, 0xBB3FFD08L, 0xA86F0EFCL, 0x5A048DFFL,
+	0x8ECEE914L, 0x7CA56A17L, 0x6FF599E3L, 0x9D9E1AE0L,
+	0xD3D3E1ABL, 0x21B862A8L, 0x32E8915CL, 0xC083125FL,
+	0x144976B4L, 0xE622F5B7L, 0xF5720643L, 0x07198540L,
+	0x590AB964L, 0xAB613A67L, 0xB831C993L, 0x4A5A4A90L,
+	0x9E902E7BL, 0x6CFBAD78L, 0x7FAB5E8CL, 0x8DC0DD8FL,
+	0xE330A81AL, 0x115B2B19L, 0x020BD8EDL, 0xF0605BEEL,
+	0x24AA3F05L, 0xD6C1BC06L, 0xC5914FF2L, 0x37FACCF1L,
+	0x69E9F0D5L, 0x9B8273D6L, 0x88D28022L, 0x7AB90321L,
+	0xAE7367CAL, 0x5C18E4C9L, 0x4F48173DL, 0xBD23943EL,
+	0xF36E6F75L, 0x0105EC76L, 0x12551F82L, 0xE03E9C81L,
+	0x34F4F86AL, 0xC69F7B69L, 0xD5CF889DL, 0x27A40B9EL,
+	0x79B737BAL, 0x8BDCB4B9L, 0x988C474DL, 0x6AE7C44EL,
+	0xBE2DA0A5L, 0x4C4623A6L, 0x5F16D052L, 0xAD7D5351L
+};
+
+/*
+ * Steps through buffer one byte at at time, calculates reflected 
+ * crc using table.
+ */
+
+u32 __attribute_pure__
+crc32c_le(u32 seed, unsigned char const *data, size_t length)
+{
+	u32 crc = __cpu_to_le32(seed);
+	
+	while (length--)
+		crc =
+		    crc32c_table[(crc ^ *data++) & 0xFFL] ^ (crc >> 8);
+
+	return __le32_to_cpu(crc);
+}
+
+#endif	/* CRC_LE_BITS == 8 */
+
+EXPORT_SYMBOL(crc32c_be);
+
+#if CRC_BE_BITS == 1
+u32 __attribute_pure__
+crc32c_be(u32 crc, unsigned char const *p, size_t len)
+{
+	int i;
+	while (len--) {
+		crc ^= *p++ << 24;
+		for (i = 0; i < 8; i++)
+			crc =
+			    (crc << 1) ^ ((crc & 0x80000000) ? CRC32C_POLY_BE :
+					  0);
+	}
+	return crc;
+}
+#endif
+
+/*
+ * Unit test
+ *
+ * A small unit test suite is implemented as part of the crypto suite.
+ * Select CRYPTO_CRC32C and use the tcrypt module to run the tests.
+ */

lib/list_debug.c

@@ -0,0 +1,78 @@
+/*
+ * Copyright 2006, Red Hat, Inc., Dave Jones
+ * Released under the General Public License (GPL).
+ *
+ * This file contains the linked list implementations for
+ * DEBUG_LIST.
+ */
+
+#include <linux/module.h>
+#include <linux/list.h>
+
+/*
+ * Insert a new entry between two known consecutive entries.
+ *
+ * This is only for internal list manipulation where we know
+ * the prev/next entries already!
+ */
+
+void __list_add(struct list_head *new,
+			      struct list_head *prev,
+			      struct list_head *next)
+{
+	if (unlikely(next->prev != prev)) {
+		printk(KERN_ERR "list_add corruption. next->prev should be "
+			"prev (%p), but was %p. (next=%p).\n",
+			prev, next->prev, next);
+		BUG();
+	}
+	if (unlikely(prev->next != next)) {
+		printk(KERN_ERR "list_add corruption. prev->next should be "
+			"next (%p), but was %p. (prev=%p).\n",
+			next, prev->next, prev);
+		BUG();
+	}
+	next->prev = new;
+	new->next = next;
+	new->prev = prev;
+	prev->next = new;
+}
+EXPORT_SYMBOL(__list_add);
+
+/**
+ * list_add - add a new entry
+ * @new: new entry to be added
+ * @head: list head to add it after
+ *
+ * Insert a new entry after the specified head.
+ * This is good for implementing stacks.
+ */
+void list_add(struct list_head *new, struct list_head *head)
+{
+	__list_add(new, head, head->next);
+}
+EXPORT_SYMBOL(list_add);
+
+/**
+ * list_del - deletes entry from list.
+ * @entry: the element to delete from the list.
+ * Note: list_empty on entry does not return true after this, the entry is
+ * in an undefined state.
+ */
+void list_del(struct list_head *entry)
+{
+	if (unlikely(entry->prev->next != entry)) {
+		printk(KERN_ERR "list_del corruption. prev->next should be %p, "
+				"but was %p\n", entry, entry->prev->next);
+		BUG();
+	}
+	if (unlikely(entry->next->prev != entry)) {
+		printk(KERN_ERR "list_del corruption. next->prev should be %p, "
+				"but was %p\n", entry, entry->next->prev);
+		BUG();
+	}
+	__list_del(entry->prev, entry->next);
+	entry->next = LIST_POISON1;
+	entry->prev = LIST_POISON2;
+}
+EXPORT_SYMBOL(list_del);

lib/locking-selftest-hardirq.h

@@ -0,0 +1,9 @@
+#undef IRQ_DISABLE
+#undef IRQ_ENABLE
+#undef IRQ_ENTER
+#undef IRQ_EXIT
+
+#define IRQ_ENABLE		HARDIRQ_ENABLE
+#define IRQ_DISABLE		HARDIRQ_DISABLE
+#define IRQ_ENTER		HARDIRQ_ENTER
+#define IRQ_EXIT		HARDIRQ_EXIT

lib/locking-selftest-mutex.h

@@ -0,0 +1,11 @@
+#undef LOCK
+#define LOCK		ML
+
+#undef UNLOCK
+#define UNLOCK		MU
+
+#undef RLOCK
+#undef WLOCK
+
+#undef INIT
+#define INIT		MI

lib/locking-selftest-rlock-hardirq.h

@@ -0,0 +1,2 @@
+#include "locking-selftest-rlock.h"
+#include "locking-selftest-hardirq.h"

lib/locking-selftest-rlock-softirq.h

@@ -0,0 +1,2 @@
+#include "locking-selftest-rlock.h"
+#include "locking-selftest-softirq.h"

lib/locking-selftest-rlock.h

@@ -0,0 +1,14 @@
+#undef LOCK
+#define LOCK		RL
+
+#undef UNLOCK
+#define UNLOCK		RU
+
+#undef RLOCK
+#define RLOCK		RL
+
+#undef WLOCK
+#define WLOCK		WL
+
+#undef INIT
+#define INIT		RWI

lib/locking-selftest-rsem.h

@@ -0,0 +1,14 @@
+#undef LOCK
+#define LOCK		RSL
+
+#undef UNLOCK
+#define UNLOCK		RSU
+
+#undef RLOCK
+#define RLOCK		RSL
+
+#undef WLOCK
+#define WLOCK		WSL
+
+#undef INIT
+#define INIT		RWSI

lib/locking-selftest-softirq.h

@@ -0,0 +1,9 @@
+#undef IRQ_DISABLE
+#undef IRQ_ENABLE
+#undef IRQ_ENTER
+#undef IRQ_EXIT
+
+#define IRQ_DISABLE		SOFTIRQ_DISABLE
+#define IRQ_ENABLE		SOFTIRQ_ENABLE
+#define IRQ_ENTER		SOFTIRQ_ENTER
+#define IRQ_EXIT		SOFTIRQ_EXIT

lib/locking-selftest-spin-hardirq.h

@@ -0,0 +1,2 @@
+#include "locking-selftest-spin.h"
+#include "locking-selftest-hardirq.h"

lib/locking-selftest-spin-softirq.h

@@ -0,0 +1,2 @@
+#include "locking-selftest-spin.h"
+#include "locking-selftest-softirq.h"

lib/locking-selftest-spin.h

@@ -0,0 +1,11 @@
+#undef LOCK
+#define LOCK		L
+
+#undef UNLOCK
+#define UNLOCK		U
+
+#undef RLOCK
+#undef WLOCK
+
+#undef INIT
+#define INIT		SI

lib/locking-selftest-wlock-hardirq.h

@@ -0,0 +1,2 @@
+#include "locking-selftest-wlock.h"
+#include "locking-selftest-hardirq.h"

lib/locking-selftest-wlock-softirq.h

@@ -0,0 +1,2 @@
+#include "locking-selftest-wlock.h"
+#include "locking-selftest-softirq.h"

lib/locking-selftest-wlock.h

@@ -0,0 +1,14 @@
+#undef LOCK
+#define LOCK		WL
+
+#undef UNLOCK
+#define UNLOCK		WU
+
+#undef RLOCK
+#define RLOCK		RL
+
+#undef WLOCK
+#define WLOCK		WL
+
+#undef INIT
+#define INIT		RWI

lib/locking-selftest-wsem.h

@@ -0,0 +1,14 @@
+#undef LOCK
+#define LOCK		WSL
+
+#undef UNLOCK
+#define UNLOCK		WSU
+
+#undef RLOCK
+#define RLOCK		RSL
+
+#undef WLOCK
+#define WLOCK		WSL
+
+#undef INIT
+#define INIT		RWSI

lib/parser.c

@@ -0,0 +1,220 @@
+/*
+ * lib/parser.c - simple parser for mount, etc. options.
+ *
+ * This source code is licensed under the GNU General Public License,
+ * Version 2.  See the file COPYING for more details.
+ */
+
+#include <linux/ctype.h>
+#include <linux/module.h>
+#include <linux/parser.h>
+#include <linux/slab.h>
+#include <linux/string.h>
+
+/**
+ * match_one: - Determines if a string matches a simple pattern
+ * @s: the string to examine for presense of the pattern
+ * @p: the string containing the pattern
+ * @args: array of %MAX_OPT_ARGS &substring_t elements. Used to return match
+ * locations.
+ *
+ * Description: Determines if the pattern @p is present in string @s. Can only
+ * match extremely simple token=arg style patterns. If the pattern is found,
+ * the location(s) of the arguments will be returned in the @args array.
+ */
+static int match_one(char *s, char *p, substring_t args[])
+{
+	char *meta;
+	int argc = 0;
+
+	if (!p)
+		return 1;
+
+	while(1) {
+		int len = -1;
+		meta = strchr(p, '%');
+		if (!meta)
+			return strcmp(p, s) == 0;
+
+		if (strncmp(p, s, meta-p))
+			return 0;
+
+		s += meta - p;
+		p = meta + 1;
+
+		if (isdigit(*p))
+			len = simple_strtoul(p, &p, 10);
+		else if (*p == '%') {
+			if (*s++ != '%')
+				return 0;
+			p++;
+			continue;
+		}
+
+		if (argc >= MAX_OPT_ARGS)
+			return 0;
+
+		args[argc].from = s;
+		switch (*p++) {
+		case 's':
+			if (strlen(s) == 0)
+				return 0;
+			else if (len == -1 || len > strlen(s))
+				len = strlen(s);
+			args[argc].to = s + len;
+			break;
+		case 'd':
+			simple_strtol(s, &args[argc].to, 0);
+			goto num;
+		case 'u':
+			simple_strtoul(s, &args[argc].to, 0);
+			goto num;
+		case 'o':
+			simple_strtoul(s, &args[argc].to, 8);
+			goto num;
+		case 'x':
+			simple_strtoul(s, &args[argc].to, 16);
+		num:
+			if (args[argc].to == args[argc].from)
+				return 0;
+			break;
+		default:
+			return 0;
+		}
+		s = args[argc].to;
+		argc++;
+	}
+}
+
+/**
+ * match_token: - Find a token (and optional args) in a string
+ * @s: the string to examine for token/argument pairs
+ * @table: match_table_t describing the set of allowed option tokens and the
+ * arguments that may be associated with them. Must be terminated with a
+ * &struct match_token whose pattern is set to the NULL pointer.
+ * @args: array of %MAX_OPT_ARGS &substring_t elements. Used to return match
+ * locations.
+ *
+ * Description: Detects which if any of a set of token strings has been passed
+ * to it. Tokens can include up to MAX_OPT_ARGS instances of basic c-style
+ * format identifiers which will be taken into account when matching the
+ * tokens, and whose locations will be returned in the @args array.
+ */
+int match_token(char *s, match_table_t table, substring_t args[])
+{
+	struct match_token *p;
+
+	for (p = table; !match_one(s, p->pattern, args) ; p++)
+		;
+
+	return p->token;
+}
+
+/**
+ * match_number: scan a number in the given base from a substring_t
+ * @s: substring to be scanned
+ * @result: resulting integer on success
+ * @base: base to use when converting string
+ *
+ * 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.
+ */
+static int match_number(substring_t *s, int *result, int base)
+{
+	char *endp;
+	char *buf;
+	int ret;
+
+	buf = kmalloc(s->to - s->from + 1, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+	memcpy(buf, s->from, s->to - s->from);
+	buf[s->to - s->from] = '\0';
+	*result = simple_strtol(buf, &endp, base);
+	ret = 0;
+	if (endp == buf)
+		ret = -EINVAL;
+	kfree(buf);
+	return ret;
+}
+
+/**
+ * match_int: - scan a decimal representation of an integer from a substring_t
+ * @s: substring_t to be scanned
+ * @result: resulting integer on success
+ *
+ * Description: Attempts to parse the &substring_t @s as a decimal integer. On
+ * success, sets @result to the integer represented by the string and returns 0.
+ * Returns either -ENOMEM or -EINVAL on failure.
+ */
+int match_int(substring_t *s, int *result)
+{
+	return match_number(s, result, 0);
+}
+
+/**
+ * match_octal: - scan an octal representation of an integer from a substring_t
+ * @s: substring_t to be scanned
+ * @result: resulting integer on success
+ *
+ * Description: Attempts to parse the &substring_t @s as an octal integer. On
+ * success, sets @result to the integer represented by the string and returns
+ * 0. Returns either -ENOMEM or -EINVAL on failure.
+ */
+int match_octal(substring_t *s, int *result)
+{
+	return match_number(s, result, 8);
+}
+
+/**
+ * match_hex: - scan a hex representation of an integer from a substring_t
+ * @s: substring_t to be scanned
+ * @result: resulting integer on success
+ *
+ * Description: Attempts to parse the &substring_t @s as a hexadecimal integer.
+ * On success, sets @result to the integer represented by the string and
+ * returns 0. Returns either -ENOMEM or -EINVAL on failure.
+ */
+int match_hex(substring_t *s, int *result)
+{
+	return match_number(s, result, 16);
+}
+
+/**
+ * match_strcpy: - copies the characters from a substring_t to a string
+ * @to: string to copy characters to.
+ * @s: &substring_t to copy
+ *
+ * Description: Copies the set of characters represented by the given
+ * &substring_t @s to the c-style string @to. Caller guarantees that @to is
+ * large enough to hold the characters of @s.
+ */
+void match_strcpy(char *to, substring_t *s)
+{
+	memcpy(to, s->from, s->to - s->from);
+	to[s->to - s->from] = '\0';
+}
+
+/**
+ * match_strdup: - allocate a new string with the contents of a substring_t
+ * @s: &substring_t to copy
+ *
+ * Description: Allocates and returns a string filled with the contents of
+ * the &substring_t @s. The caller is responsible for freeing the returned
+ * string with kfree().
+ */
+char *match_strdup(substring_t *s)
+{
+	char *p = kmalloc(s->to - s->from + 1, GFP_KERNEL);
+	if (p)
+		match_strcpy(p, s);
+	return p;
+}
+
+EXPORT_SYMBOL(match_token);
+EXPORT_SYMBOL(match_int);
+EXPORT_SYMBOL(match_octal);
+EXPORT_SYMBOL(match_hex);
+EXPORT_SYMBOL(match_strcpy);
+EXPORT_SYMBOL(match_strdup);

lib/percpu_counter.c

@@ -0,0 +1,46 @@
+/*
+ * Fast batching percpu counters.
+ */
+
+#include <linux/percpu_counter.h>
+#include <linux/module.h>
+
+void percpu_counter_mod(struct percpu_counter *fbc, s32 amount)
+{
+	long count;
+	s32 *pcount;
+	int cpu = get_cpu();
+
+	pcount = per_cpu_ptr(fbc->counters, cpu);
+	count = *pcount + amount;
+	if (count >= FBC_BATCH || count <= -FBC_BATCH) {
+		spin_lock(&fbc->lock);
+		fbc->count += count;
+		*pcount = 0;
+		spin_unlock(&fbc->lock);
+	} else {
+		*pcount = count;
+	}
+	put_cpu();
+}
+EXPORT_SYMBOL(percpu_counter_mod);
+
+/*
+ * Add up all the per-cpu counts, return the result.  This is a more accurate
+ * but much slower version of percpu_counter_read_positive()
+ */
+s64 percpu_counter_sum(struct percpu_counter *fbc)
+{
+	s64 ret;
+	int cpu;
+
+	spin_lock(&fbc->lock);
+	ret = fbc->count;
+	for_each_possible_cpu(cpu) {
+		s32 *pcount = per_cpu_ptr(fbc->counters, cpu);
+		ret += *pcount;
+	}
+	spin_unlock(&fbc->lock);
+	return ret < 0 ? 0 : ret;
+}
+EXPORT_SYMBOL(percpu_counter_sum);

lib/plist.c

@@ -0,0 +1,118 @@
+/*
+ * lib/plist.c
+ *
+ * Descending-priority-sorted double-linked list
+ *
+ * (C) 2002-2003 Intel Corp
+ * Inaky Perez-Gonzalez <inaky.perez-gonzalez@intel.com>.
+ *
+ * 2001-2005 (c) MontaVista Software, Inc.
+ * Daniel Walker <dwalker@mvista.com>
+ *
+ * (C) 2005 Thomas Gleixner <tglx@linutronix.de>
+ *
+ * Simplifications of the original code by
+ * Oleg Nesterov <oleg@tv-sign.ru>
+ *
+ * Licensed under the FSF's GNU Public License v2 or later.
+ *
+ * Based on simple lists (include/linux/list.h).
+ *
+ * This file contains the add / del functions which are considered to
+ * be too large to inline. See include/linux/plist.h for further
+ * information.
+ */
+
+#include <linux/plist.h>
+#include <linux/spinlock.h>
+
+#ifdef CONFIG_DEBUG_PI_LIST
+
+static void plist_check_prev_next(struct list_head *t, struct list_head *p,
+				  struct list_head *n)
+{
+	if (n->prev != p || p->next != n) {
+		printk("top: %p, n: %p, p: %p\n", t, t->next, t->prev);
+		printk("prev: %p, n: %p, p: %p\n", p, p->next, p->prev);
+		printk("next: %p, n: %p, p: %p\n", n, n->next, n->prev);
+		WARN_ON(1);
+	}
+}
+
+static void plist_check_list(struct list_head *top)
+{
+	struct list_head *prev = top, *next = top->next;
+
+	plist_check_prev_next(top, prev, next);
+	while (next != top) {
+		prev = next;
+		next = prev->next;
+		plist_check_prev_next(top, prev, next);
+	}
+}
+
+static void plist_check_head(struct plist_head *head)
+{
+	WARN_ON(!head->lock);
+	if (head->lock)
+		WARN_ON_SMP(!spin_is_locked(head->lock));
+	plist_check_list(&head->prio_list);
+	plist_check_list(&head->node_list);
+}
+
+#else
+# define plist_check_head(h)	do { } while (0)
+#endif
+
+/**
+ * plist_add - add @node to @head
+ *
+ * @node:	&struct plist_node pointer
+ * @head:	&struct plist_head pointer
+ */
+void plist_add(struct plist_node *node, struct plist_head *head)
+{
+	struct plist_node *iter;
+
+	plist_check_head(head);
+	WARN_ON(!plist_node_empty(node));
+
+	list_for_each_entry(iter, &head->prio_list, plist.prio_list) {
+		if (node->prio < iter->prio)
+			goto lt_prio;
+		else if (node->prio == iter->prio) {
+			iter = list_entry(iter->plist.prio_list.next,
+					struct plist_node, plist.prio_list);
+			goto eq_prio;
+		}
+	}
+
+lt_prio:
+	list_add_tail(&node->plist.prio_list, &iter->plist.prio_list);
+eq_prio:
+	list_add_tail(&node->plist.node_list, &iter->plist.node_list);
+
+	plist_check_head(head);
+}
+
+/**
+ * plist_del - Remove a @node from plist.
+ *
+ * @node:	&struct plist_node pointer - entry to be removed
+ * @head:	&struct plist_head pointer - list head
+ */
+void plist_del(struct plist_node *node, struct plist_head *head)
+{
+	plist_check_head(head);
+
+	if (!list_empty(&node->plist.prio_list)) {
+		struct plist_node *next = plist_first(&node->plist);
+
+		list_move_tail(&next->plist.prio_list, &node->plist.prio_list);
+		list_del_init(&node->plist.prio_list);
+	}
+
+	list_del_init(&node->plist.node_list);
+
+	plist_check_head(head);
+}

lib/prio_tree.c

@@ -0,0 +1,484 @@
+/*
+ * 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;
+}

lib/random32.c

@@ -0,0 +1,143 @@
+/*
+  This is a maximally equidistributed combined Tausworthe generator
+  based on code from GNU Scientific Library 1.5 (30 Jun 2004)
+
+   x_n = (s1_n ^ s2_n ^ s3_n)
+
+   s1_{n+1} = (((s1_n & 4294967294) <<12) ^ (((s1_n <<13) ^ s1_n) >>19))
+   s2_{n+1} = (((s2_n & 4294967288) << 4) ^ (((s2_n << 2) ^ s2_n) >>25))
+   s3_{n+1} = (((s3_n & 4294967280) <<17) ^ (((s3_n << 3) ^ s3_n) >>11))
+
+   The period of this generator is about 2^88.
+
+   From: P. L'Ecuyer, "Maximally Equidistributed Combined Tausworthe
+   Generators", Mathematics of Computation, 65, 213 (1996), 203--213.
+
+   This is available on the net from L'Ecuyer's home page,
+
+   http://www.iro.umontreal.ca/~lecuyer/myftp/papers/tausme.ps
+   ftp://ftp.iro.umontreal.ca/pub/simulation/lecuyer/papers/tausme.ps
+
+   There is an erratum in the paper "Tables of Maximally
+   Equidistributed Combined LFSR Generators", Mathematics of
+   Computation, 68, 225 (1999), 261--269:
+   http://www.iro.umontreal.ca/~lecuyer/myftp/papers/tausme2.ps
+
+        ... the k_j most significant bits of z_j must be non-
+        zero, for each j. (Note: this restriction also applies to the
+        computer code given in [4], but was mistakenly not mentioned in
+        that paper.)
+
+   This affects the seeding procedure by imposing the requirement
+   s1 > 1, s2 > 7, s3 > 15.
+
+*/
+
+#include <linux/types.h>
+#include <linux/percpu.h>
+#include <linux/module.h>
+#include <linux/jiffies.h>
+#include <linux/random.h>
+
+struct rnd_state {
+	u32 s1, s2, s3;
+};
+
+static DEFINE_PER_CPU(struct rnd_state, net_rand_state);
+
+static u32 __random32(struct rnd_state *state)
+{
+#define TAUSWORTHE(s,a,b,c,d) ((s&c)<<d) ^ (((s <<a) ^ s)>>b)
+
+	state->s1 = TAUSWORTHE(state->s1, 13, 19, 4294967294UL, 12);
+	state->s2 = TAUSWORTHE(state->s2, 2, 25, 4294967288UL, 4);
+	state->s3 = TAUSWORTHE(state->s3, 3, 11, 4294967280UL, 17);
+
+	return (state->s1 ^ state->s2 ^ state->s3);
+}
+
+static void __set_random32(struct rnd_state *state, unsigned long s)
+{
+	if (s == 0)
+		s = 1;      /* default seed is 1 */
+
+#define LCG(n) (69069 * n)
+	state->s1 = LCG(s);
+	state->s2 = LCG(state->s1);
+	state->s3 = LCG(state->s2);
+
+	/* "warm it up" */
+	__random32(state);
+	__random32(state);
+	__random32(state);
+	__random32(state);
+	__random32(state);
+	__random32(state);
+}
+
+/**
+ *	random32 - pseudo random number generator
+ *
+ *	A 32 bit pseudo-random number is generated using a fast
+ *	algorithm suitable for simulation. This algorithm is NOT
+ *	considered safe for cryptographic use.
+ */
+u32 random32(void)
+{
+	unsigned long r;
+	struct rnd_state *state = &get_cpu_var(net_rand_state);
+	r = __random32(state);
+	put_cpu_var(state);
+	return r;
+}
+EXPORT_SYMBOL(random32);
+
+/**
+ *	srandom32 - add entropy to pseudo random number generator
+ *	@seed: seed value
+ *
+ *	Add some additional seeding to the random32() pool.
+ *	Note: this pool is per cpu so it only affects current CPU.
+ */
+void srandom32(u32 entropy)
+{
+	struct rnd_state *state = &get_cpu_var(net_rand_state);
+	__set_random32(state, state->s1 ^ entropy);
+	put_cpu_var(state);
+}
+EXPORT_SYMBOL(srandom32);
+
+/*
+ *	Generate some initially weak seeding values to allow
+ *	to start the random32() engine.
+ */
+static int __init random32_init(void)
+{
+	int i;
+
+	for_each_possible_cpu(i) {
+		struct rnd_state *state = &per_cpu(net_rand_state,i);
+		__set_random32(state, i + jiffies);
+	}
+	return 0;
+}
+core_initcall(random32_init);
+
+/*
+ *	Generate better values after random number generator
+ *	is fully initalized.
+ */
+static int __init random32_reseed(void)
+{
+	int i;
+	unsigned long seed;
+
+	for_each_possible_cpu(i) {
+		struct rnd_state *state = &per_cpu(net_rand_state,i);
+
+		get_random_bytes(&seed, sizeof(seed));
+		__set_random32(state, seed);
+	}
+	return 0;
+}
+late_initcall(random32_reseed);

lib/rbtree.c

@@ -0,0 +1,397 @@
+/*
+  Red Black Trees
+  (C) 1999  Andrea Arcangeli <andrea@suse.de>
+  (C) 2002  David Woodhouse <dwmw2@infradead.org>
+  
+  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.
+
+  This program 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
+
+  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;
+
+	rb_set_parent(right, parent);
+
+	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 void __rb_rotate_right(struct rb_node *node, struct rb_root *root)
+{
+	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);
+
+	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);
+}
+
+void rb_insert_color(struct rb_node *node, struct rb_root *root)
+{
+	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;
+				}
+			}
+
+			if (parent->rb_right == node)
+			{
+				register struct rb_node *tmp;
+				__rb_rotate_left(parent, root);
+				tmp = parent;
+				parent = node;
+				node = tmp;
+			}
+
+			rb_set_black(parent);
+			rb_set_red(gparent);
+			__rb_rotate_right(gparent, root);
+		} 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;
+				}
+			}
+
+			if (parent->rb_left == node)
+			{
+				register struct rb_node *tmp;
+				__rb_rotate_right(parent, root);
+				tmp = parent;
+				parent = node;
+				node = tmp;
+			}
+
+			rb_set_black(parent);
+			rb_set_red(gparent);
+			__rb_rotate_left(gparent, root);
+		}
+	}
+
+	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)
+{
+	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;
+			}
+			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))
+				{
+					struct rb_node *o_left;
+					if ((o_left = other->rb_left))
+						rb_set_black(o_left);
+					rb_set_red(other);
+					__rb_rotate_right(other, root);
+					other = parent->rb_right;
+				}
+				rb_set_color(other, rb_color(parent));
+				rb_set_black(parent);
+				if (other->rb_right)
+					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;
+			}
+			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_left || rb_is_black(other->rb_left))
+				{
+					register struct rb_node *o_right;
+					if ((o_right = other->rb_right))
+						rb_set_black(o_right);
+					rb_set_red(other);
+					__rb_rotate_left(other, root);
+					other = parent->rb_left;
+				}
+				rb_set_color(other, rb_color(parent));
+				rb_set_black(parent);
+				if (other->rb_left)
+					rb_set_black(other->rb_left);
+				__rb_rotate_right(parent, root);
+				node = root->rb_node;
+				break;
+			}
+		}
+	}
+	if (node)
+		rb_set_black(node);
+}
+
+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;
+		child = node->rb_right;
+		parent = rb_parent(node);
+		color = rb_color(node);
+
+		if (child)
+			rb_set_parent(child, parent);
+		if (parent == old) {
+			parent->rb_right = child;
+			parent = node;
+		} else
+			parent->rb_left = child;
+
+		node->rb_parent_color = old->rb_parent_color;
+		node->rb_right = old->rb_right;
+		node->rb_left = old->rb_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;
+
+		rb_set_parent(old->rb_left, node);
+		if (old->rb_right)
+			rb_set_parent(old->rb_right, node);
+		goto color;
+	}
+
+	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;
+
+ color:
+	if (color == RB_BLACK)
+		__rb_erase_color(child, parent, root);
+}
+EXPORT_SYMBOL(rb_erase);
+
+/*
+ * This function returns the first node (in sort order) of the tree.
+ */
+struct rb_node *rb_first(struct rb_root *root)
+{
+	struct rb_node	*n;
+
+	n = root->rb_node;
+	if (!n)
+		return NULL;
+	while (n->rb_left)
+		n = n->rb_left;
+	return n;
+}
+EXPORT_SYMBOL(rb_first);
+
+struct rb_node *rb_last(struct rb_root *root)
+{
+	struct rb_node	*n;
+
+	n = root->rb_node;
+	if (!n)
+		return NULL;
+	while (n->rb_right)
+		n = n->rb_right;
+	return n;
+}
+EXPORT_SYMBOL(rb_last);
+
+struct rb_node *rb_next(struct rb_node *node)
+{
+	struct rb_node *parent;
+
+	if (rb_parent(node) == node)
+		return NULL;
+
+	/* 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)
+			node=node->rb_left;
+		return 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;
+
+	return parent;
+}
+EXPORT_SYMBOL(rb_next);
+
+struct rb_node *rb_prev(struct rb_node *node)
+{
+	struct rb_node *parent;
+
+	if (rb_parent(node) == node)
+		return NULL;
+
+	/* 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)
+			node=node->rb_right;
+		return node;
+	}
+
+	/* 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;
+
+	return parent;
+}
+EXPORT_SYMBOL(rb_prev);
+
+void rb_replace_node(struct rb_node *victim, struct rb_node *new,
+		     struct rb_root *root)
+{
+	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;
+	}
+	if (victim->rb_left)
+		rb_set_parent(victim->rb_left, new);
+	if (victim->rb_right)
+		rb_set_parent(victim->rb_right, new);
+
+	/* Copy the pointers/colour from the victim to the replacement */
+	*new = *victim;
+}
+EXPORT_SYMBOL(rb_replace_node);

lib/reciprocal_div.c

@@ -0,0 +1,9 @@
+#include <asm/div64.h>
+#include <linux/reciprocal_div.h>
+
+u32 reciprocal_value(u32 k)
+{
+	u64 val = (1LL << 32) + (k - 1);
+	do_div(val, k);
+	return (u32)val;
+}

lib/reed_solomon/Makefile

@@ -0,0 +1,6 @@
+#
+# This is a modified version of reed solomon lib,
+#
+
+obj-$(CONFIG_REED_SOLOMON) += reed_solomon.o
+

lib/reed_solomon/decode_rs.c

@@ -0,0 +1,272 @@
+/*
+ * lib/reed_solomon/decode_rs.c
+ *
+ * Overview:
+ *   Generic Reed Solomon encoder / decoder library
+ *
+ * Copyright 2002, Phil Karn, KA9Q
+ * May be used under the terms of the GNU General Public License (GPL)
+ *
+ * Adaption to the kernel by Thomas Gleixner (tglx@linutronix.de)
+ *
+ * $Id: decode_rs.c,v 1.1.1.1 2007/06/12 07:27:13 eyryu Exp $
+ *
+ */
+
+/* Generic data width independent code which is included by the
+ * wrappers.
+ */
+{
+	int deg_lambda, el, deg_omega;
+	int i, j, r, k, pad;
+	int nn = rs->nn;
+	int nroots = rs->nroots;
+	int fcr = rs->fcr;
+	int prim = rs->prim;
+	int iprim = rs->iprim;
+	uint16_t *alpha_to = rs->alpha_to;
+	uint16_t *index_of = rs->index_of;
+	uint16_t u, q, tmp, num1, num2, den, discr_r, syn_error;
+	/* Err+Eras Locator poly and syndrome poly The maximum value
+	 * of nroots is 8. So the necessary stack size will be about
+	 * 220 bytes max.
+	 */
+	uint16_t lambda[nroots + 1], syn[nroots];
+	uint16_t b[nroots + 1], t[nroots + 1], omega[nroots + 1];
+	uint16_t root[nroots], reg[nroots + 1], loc[nroots];
+	int count = 0;
+	uint16_t msk = (uint16_t) rs->nn;
+
+	/* Check length parameter for validity */
+	pad = nn - nroots - len;
+	if (pad < 0 || pad >= nn)
+		return -ERANGE;
+
+	/* Does the caller provide the syndrome ? */
+	if (s != NULL)
+		goto decode;
+
+	/* form the syndromes; i.e., evaluate data(x) at roots of
+	 * g(x) */
+	for (i = 0; i < nroots; i++)
+		syn[i] = (((uint16_t) data[0]) ^ invmsk) & msk;
+
+	for (j = 1; j < len; j++) {
+		for (i = 0; i < nroots; i++) {
+			if (syn[i] == 0) {
+				syn[i] = (((uint16_t) data[j]) ^
+					  invmsk) & msk;
+			} else {
+				syn[i] = ((((uint16_t) data[j]) ^
+					   invmsk) & msk) ^
+					alpha_to[rs_modnn(rs, index_of[syn[i]] +
+						       (fcr + i) * prim)];
+			}
+		}
+	}
+
+	for (j = 0; j < nroots; j++) {
+		for (i = 0; i < nroots; i++) {
+			if (syn[i] == 0) {
+				syn[i] = ((uint16_t) par[j]) & msk;
+			} else {
+				syn[i] = (((uint16_t) par[j]) & msk) ^
+					alpha_to[rs_modnn(rs, index_of[syn[i]] +
+						       (fcr+i)*prim)];
+			}
+		}
+	}
+	s = syn;
+
+	/* Convert syndromes to index form, checking for nonzero condition */
+	syn_error = 0;
+	for (i = 0; i < nroots; i++) {
+		syn_error |= s[i];
+		s[i] = index_of[s[i]];
+	}
+
+	if (!syn_error) {
+		/* if syndrome is zero, data[] is a codeword and there are no
+		 * errors to correct. So return data[] unmodified
+		 */
+		count = 0;
+		goto finish;
+	}
+
+ decode:
+	memset(&lambda[1], 0, nroots * sizeof(lambda[0]));
+	lambda[0] = 1;
+
+	if (no_eras > 0) {
+		/* Init lambda to be the erasure locator polynomial */
+		lambda[1] = alpha_to[rs_modnn(rs,
+					      prim * (nn - 1 - eras_pos[0]))];
+		for (i = 1; i < no_eras; i++) {
+			u = rs_modnn(rs, prim * (nn - 1 - eras_pos[i]));
+			for (j = i + 1; j > 0; j--) {
+				tmp = index_of[lambda[j - 1]];
+				if (tmp != nn) {
+					lambda[j] ^=
+						alpha_to[rs_modnn(rs, u + tmp)];
+				}
+			}
+		}
+	}
+
+	for (i = 0; i < nroots + 1; i++)
+		b[i] = index_of[lambda[i]];
+
+	/*
+	 * Begin Berlekamp-Massey algorithm to determine error+erasure
+	 * locator polynomial
+	 */
+	r = no_eras;
+	el = no_eras;
+	while (++r <= nroots) {	/* r is the step number */
+		/* Compute discrepancy at the r-th step in poly-form */
+		discr_r = 0;
+		for (i = 0; i < r; i++) {
+			if ((lambda[i] != 0) && (s[r - i - 1] != nn)) {
+				discr_r ^=
+					alpha_to[rs_modnn(rs,
+							  index_of[lambda[i]] +
+							  s[r - i - 1])];
+			}
+		}
+		discr_r = index_of[discr_r];	/* Index form */
+		if (discr_r == nn) {
+			/* 2 lines below: B(x) <-- x*B(x) */
+			memmove (&b[1], b, nroots * sizeof (b[0]));
+			b[0] = nn;
+		} else {
+			/* 7 lines below: T(x) <-- lambda(x)-discr_r*x*b(x) */
+			t[0] = lambda[0];
+			for (i = 0; i < nroots; i++) {
+				if (b[i] != nn) {
+					t[i + 1] = lambda[i + 1] ^
+						alpha_to[rs_modnn(rs, discr_r +
+								  b[i])];
+				} else
+					t[i + 1] = lambda[i + 1];
+			}
+			if (2 * el <= r + no_eras - 1) {
+				el = r + no_eras - el;
+				/*
+				 * 2 lines below: B(x) <-- inv(discr_r) *
+				 * lambda(x)
+				 */
+				for (i = 0; i <= nroots; i++) {
+					b[i] = (lambda[i] == 0) ? nn :
+						rs_modnn(rs, index_of[lambda[i]]
+							 - discr_r + nn);
+				}
+			} else {
+				/* 2 lines below: B(x) <-- x*B(x) */
+				memmove(&b[1], b, nroots * sizeof(b[0]));
+				b[0] = nn;
+			}
+			memcpy(lambda, t, (nroots + 1) * sizeof(t[0]));
+		}
+	}
+
+	/* Convert lambda to index form and compute deg(lambda(x)) */
+	deg_lambda = 0;
+	for (i = 0; i < nroots + 1; i++) {
+		lambda[i] = index_of[lambda[i]];
+		if (lambda[i] != nn)
+			deg_lambda = i;
+	}
+	/* Find roots of error+erasure locator polynomial by Chien search */
+	memcpy(&reg[1], &lambda[1], nroots * sizeof(reg[0]));
+	count = 0;		/* Number of roots of lambda(x) */
+	for (i = 1, k = iprim - 1; i <= nn; i++, k = rs_modnn(rs, k + iprim)) {
+		q = 1;		/* lambda[0] is always 0 */
+		for (j = deg_lambda; j > 0; j--) {
+			if (reg[j] != nn) {
+				reg[j] = rs_modnn(rs, reg[j] + j);
+				q ^= alpha_to[reg[j]];
+			}
+		}
+		if (q != 0)
+			continue;	/* Not a root */
+		/* store root (index-form) and error location number */
+		root[count] = i;
+		loc[count] = k;
+		/* If we've already found max possible roots,
+		 * abort the search to save time
+		 */
+		if (++count == deg_lambda)
+			break;
+	}
+	if (deg_lambda != count) {
+		/*
+		 * deg(lambda) unequal to number of roots => uncorrectable
+		 * error detected
+		 */
+		count = -1;
+		goto finish;
+	}
+	/*
+	 * Compute err+eras evaluator poly omega(x) = s(x)*lambda(x) (modulo
+	 * x**nroots). in index form. Also find deg(omega).
+	 */
+	deg_omega = deg_lambda - 1;
+	for (i = 0; i <= deg_omega; i++) {
+		tmp = 0;
+		for (j = i; j >= 0; j--) {
+			if ((s[i - j] != nn) && (lambda[j] != nn))
+				tmp ^=
+				    alpha_to[rs_modnn(rs, s[i - j] + lambda[j])];
+		}
+		omega[i] = index_of[tmp];
+	}
+
+	/*
+	 * Compute error values in poly-form. num1 = omega(inv(X(l))), num2 =
+	 * inv(X(l))**(fcr-1) and den = lambda_pr(inv(X(l))) all in poly-form
+	 */
+	for (j = count - 1; j >= 0; j--) {
+		num1 = 0;
+		for (i = deg_omega; i >= 0; i--) {
+			if (omega[i] != nn)
+				num1 ^= alpha_to[rs_modnn(rs, omega[i] +
+							i * root[j])];
+		}
+		num2 = alpha_to[rs_modnn(rs, root[j] * (fcr - 1) + nn)];
+		den = 0;
+
+		/* lambda[i+1] for i even is the formal derivative
+		 * lambda_pr of lambda[i] */
+		for (i = min(deg_lambda, nroots - 1) & ~1; i >= 0; i -= 2) {
+			if (lambda[i + 1] != nn) {
+				den ^= alpha_to[rs_modnn(rs, lambda[i + 1] +
+						       i * root[j])];
+			}
+		}
+		/* Apply error to data */
+		if (num1 != 0 && loc[j] >= pad) {
+			uint16_t cor = alpha_to[rs_modnn(rs,index_of[num1] +
+						       index_of[num2] +
+						       nn - index_of[den])];
+			/* Store the error correction pattern, if a
+			 * correction buffer is available */
+			if (corr) {
+				corr[j] = cor;
+			} else {
+				/* If a data buffer is given and the
+				 * error is inside the message,
+				 * correct it */
+				if (data && (loc[j] < (nn - nroots)))
+					data[loc[j] - pad] ^= cor;
+			}
+		}
+	}
+
+finish:
+	if (eras_pos != NULL) {
+		for (i = 0; i < count; i++)
+			eras_pos[i] = loc[i] - pad;
+	}
+	return count;
+
+}

lib/reed_solomon/encode_rs.c

@@ -0,0 +1,54 @@
+/*
+ * lib/reed_solomon/encode_rs.c
+ *
+ * Overview:
+ *   Generic Reed Solomon encoder / decoder library
+ *
+ * Copyright 2002, Phil Karn, KA9Q
+ * May be used under the terms of the GNU General Public License (GPL)
+ *
+ * Adaption to the kernel by Thomas Gleixner (tglx@linutronix.de)
+ *
+ * $Id: encode_rs.c,v 1.1.1.1 2007/06/12 07:27:13 eyryu Exp $
+ *
+ */
+
+/* Generic data width independent code which is included by the
+ * wrappers.
+ * int encode_rsX (struct rs_control *rs, uintX_t *data, int len, uintY_t *par)
+ */
+{
+	int i, j, pad;
+	int nn = rs->nn;
+	int nroots = rs->nroots;
+	uint16_t *alpha_to = rs->alpha_to;
+	uint16_t *index_of = rs->index_of;
+	uint16_t *genpoly = rs->genpoly;
+	uint16_t fb;
+	uint16_t msk = (uint16_t) rs->nn;
+
+	/* Check length parameter for validity */
+	pad = nn - nroots - len;
+	if (pad < 0 || pad >= nn)
+		return -ERANGE;
+
+	for (i = 0; i < len; i++) {
+		fb = index_of[((((uint16_t) data[i])^invmsk) & msk) ^ par[0]];
+		/* feedback term is non-zero */
+		if (fb != nn) {
+			for (j = 1; j < nroots; j++) {
+				par[j] ^= alpha_to[rs_modnn(rs, fb +
+							 genpoly[nroots - j])];
+			}
+		}
+		/* Shift */
+		memmove(&par[0], &par[1], sizeof(uint16_t) * (nroots - 1));
+		if (fb != nn) {
+			par[nroots - 1] = alpha_to[rs_modnn(rs,
+							    fb + genpoly[0])];
+		} else {
+			par[nroots - 1] = 0;
+		}
+	}
+	return 0;
+}

lib/reed_solomon/reed_solomon.c

@@ -0,0 +1,329 @@
+/*
+ * lib/reed_solomon/reed_solomon.c
+ *
+ * Overview:
+ *   Generic Reed Solomon encoder / decoder library
+ *
+ * Copyright (C) 2004 Thomas Gleixner (tglx@linutronix.de)
+ *
+ * Reed Solomon code lifted from reed solomon library written by Phil Karn
+ * Copyright 2002 Phil Karn, KA9Q
+ *
+ * $Id: reed_solomon.c,v 1.1.1.1 2007/06/12 07:27:13 eyryu Exp $
+ *
+ * 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.
+ *
+ * Description:
+ *
+ * The generic Reed Solomon library provides runtime configurable
+ * encoding / decoding of RS codes.
+ * Each user must call init_rs to get a pointer to a rs_control
+ * structure for the given rs parameters. This structure is either
+ * generated or a already available matching control structure is used.
+ * If a structure is generated then the polynomial arrays for
+ * fast encoding / decoding are built. This can take some time so
+ * make sure not to call this function from a time critical path.
+ * Usually a module / driver should initialize the necessary
+ * rs_control structure on module / driver init and release it
+ * on exit.
+ * The encoding puts the calculated syndrome into a given syndrome
+ * buffer.
+ * The decoding is a two step process. The first step calculates
+ * the syndrome over the received (data + syndrome) and calls the
+ * second stage, which does the decoding / error correction itself.
+ * Many hw encoders provide a syndrome calculation over the received
+ * data + syndrome and can call the second stage directly.
+ *
+ */
+
+#include <linux/errno.h>
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/rslib.h>
+#include <linux/slab.h>
+#include <linux/mutex.h>
+#include <asm/semaphore.h>
+
+/* This list holds all currently allocated rs control structures */
+static LIST_HEAD (rslist);
+/* Protection for the list */
+static DEFINE_MUTEX(rslistlock);
+
+/**
+ * rs_init - Initialize a Reed-Solomon codec
+ * @symsize:	symbol size, bits (1-8)
+ * @gfpoly:	Field generator polynomial coefficients
+ * @fcr:	first root of RS code generator polynomial, index form
+ * @prim:	primitive element to generate polynomial roots
+ * @nroots:	RS code generator polynomial degree (number of roots)
+ *
+ * Allocate a control structure and the polynom arrays for faster
+ * en/decoding. Fill the arrays according to the given parameters.
+ */
+static struct rs_control *rs_init(int symsize, int gfpoly, int fcr,
+				   int prim, int nroots)
+{
+	struct rs_control *rs;
+	int i, j, sr, root, iprim;
+
+	/* Allocate the control structure */
+	rs = kmalloc(sizeof (struct rs_control), GFP_KERNEL);
+	if (rs == NULL)
+		return NULL;
+
+	INIT_LIST_HEAD(&rs->list);
+
+	rs->mm = symsize;
+	rs->nn = (1 << symsize) - 1;
+	rs->fcr = fcr;
+	rs->prim = prim;
+	rs->nroots = nroots;
+	rs->gfpoly = gfpoly;
+
+	/* Allocate the arrays */
+	rs->alpha_to = kmalloc(sizeof(uint16_t) * (rs->nn + 1), GFP_KERNEL);
+	if (rs->alpha_to == NULL)
+		goto errrs;
+
+	rs->index_of = kmalloc(sizeof(uint16_t) * (rs->nn + 1), GFP_KERNEL);
+	if (rs->index_of == NULL)
+		goto erralp;
+
+	rs->genpoly = kmalloc(sizeof(uint16_t) * (rs->nroots + 1), GFP_KERNEL);
+	if(rs->genpoly == NULL)
+		goto erridx;
+
+	/* Generate Galois field lookup tables */
+	rs->index_of[0] = rs->nn;	/* log(zero) = -inf */
+	rs->alpha_to[rs->nn] = 0;	/* alpha**-inf = 0 */
+	sr = 1;
+	for (i = 0; i < rs->nn; i++) {
+		rs->index_of[sr] = i;
+		rs->alpha_to[i] = sr;
+		sr <<= 1;
+		if (sr & (1 << symsize))
+			sr ^= gfpoly;
+		sr &= rs->nn;
+	}
+	/* If it's not primitive, exit */
+	if(sr != 1)
+		goto errpol;
+
+	/* Find prim-th root of 1, used in decoding */
+	for(iprim = 1; (iprim % prim) != 0; iprim += rs->nn);
+	/* prim-th root of 1, index form */
+	rs->iprim = iprim / prim;
+
+	/* Form RS code generator polynomial from its roots */
+	rs->genpoly[0] = 1;
+	for (i = 0, root = fcr * prim; i < nroots; i++, root += prim) {
+		rs->genpoly[i + 1] = 1;
+		/* Multiply rs->genpoly[] by  @**(root + x) */
+		for (j = i; j > 0; j--) {
+			if (rs->genpoly[j] != 0) {
+				rs->genpoly[j] = rs->genpoly[j -1] ^
+					rs->alpha_to[rs_modnn(rs,
+					rs->index_of[rs->genpoly[j]] + root)];
+			} else
+				rs->genpoly[j] = rs->genpoly[j - 1];
+		}
+		/* rs->genpoly[0] can never be zero */
+		rs->genpoly[0] =
+			rs->alpha_to[rs_modnn(rs,
+				rs->index_of[rs->genpoly[0]] + root)];
+	}
+	/* convert rs->genpoly[] to index form for quicker encoding */
+	for (i = 0; i <= nroots; i++)
+		rs->genpoly[i] = rs->index_of[rs->genpoly[i]];
+	return rs;
+
+	/* Error exit */
+errpol:
+	kfree(rs->genpoly);
+erridx:
+	kfree(rs->index_of);
+erralp:
+	kfree(rs->alpha_to);
+errrs:
+	kfree(rs);
+	return NULL;
+}
+
+
+/**
+ *  free_rs - Free the rs control structure, if it is no longer used
+ *  @rs:	the control structure which is not longer used by the
+ *		caller
+ */
+void free_rs(struct rs_control *rs)
+{
+	mutex_lock(&rslistlock);
+	rs->users--;
+	if(!rs->users) {
+		list_del(&rs->list);
+		kfree(rs->alpha_to);
+		kfree(rs->index_of);
+		kfree(rs->genpoly);
+		kfree(rs);
+	}
+	mutex_unlock(&rslistlock);
+}
+
+/**
+ * init_rs - Find a matching or allocate a new rs control structure
+ *  @symsize:	the symbol size (number of bits)
+ *  @gfpoly:	the extended Galois field generator polynomial coefficients,
+ *		with the 0th coefficient in the low order bit. The polynomial
+ *		must be primitive;
+ *  @fcr:  	the first consecutive root of the rs code generator polynomial
+ *		in index form
+ *  @prim:	primitive element to generate polynomial roots
+ *  @nroots:	RS code generator polynomial degree (number of roots)
+ */
+struct rs_control *init_rs(int symsize, int gfpoly, int fcr, int prim,
+			   int nroots)
+{
+	struct list_head	*tmp;
+	struct rs_control	*rs;
+
+	/* Sanity checks */
+	if (symsize < 1)
+		return NULL;
+	if (fcr < 0 || fcr >= (1<<symsize))
+    		return NULL;
+	if (prim <= 0 || prim >= (1<<symsize))
+    		return NULL;
+	if (nroots < 0 || nroots >= (1<<symsize))
+		return NULL;
+
+	mutex_lock(&rslistlock);
+
+	/* Walk through the list and look for a matching entry */
+	list_for_each(tmp, &rslist) {
+		rs = list_entry(tmp, struct rs_control, list);
+		if (symsize != rs->mm)
+			continue;
+		if (gfpoly != rs->gfpoly)
+			continue;
+		if (fcr != rs->fcr)
+			continue;
+		if (prim != rs->prim)
+			continue;
+		if (nroots != rs->nroots)
+			continue;
+		/* We have a matching one already */
+		rs->users++;
+		goto out;
+	}
+
+	/* Create a new one */
+	rs = rs_init(symsize, gfpoly, fcr, prim, nroots);
+	if (rs) {
+		rs->users = 1;
+		list_add(&rs->list, &rslist);
+	}
+out:
+	mutex_unlock(&rslistlock);
+	return rs;
+}
+
+#ifdef CONFIG_REED_SOLOMON_ENC8
+/**
+ *  encode_rs8 - Calculate the parity for data values (8bit data width)
+ *  @rs:	the rs control structure
+ *  @data:	data field of a given type
+ *  @len:	data length
+ *  @par:	parity data, must be initialized by caller (usually all 0)
+ *  @invmsk:	invert data mask (will be xored on data)
+ *
+ *  The parity uses a uint16_t data type to enable
+ *  symbol size > 8. The calling code must take care of encoding of the
+ *  syndrome result for storage itself.
+ */
+int encode_rs8(struct rs_control *rs, uint8_t *data, int len, uint16_t *par,
+	       uint16_t invmsk)
+{
+#include "encode_rs.c"
+}
+EXPORT_SYMBOL_GPL(encode_rs8);
+#endif
+
+#ifdef CONFIG_REED_SOLOMON_DEC8
+/**
+ *  decode_rs8 - Decode codeword (8bit data width)
+ *  @rs:	the rs control structure
+ *  @data:	data field of a given type
+ *  @par:	received parity data field
+ *  @len:	data length
+ *  @s:		syndrome data field (if NULL, syndrome is calculated)
+ *  @no_eras:	number of erasures
+ *  @eras_pos:	position of erasures, can be NULL
+ *  @invmsk:	invert data mask (will be xored on data, not on parity!)
+ *  @corr:	buffer to store correction bitmask on eras_pos
+ *
+ *  The syndrome and parity uses a uint16_t data type to enable
+ *  symbol size > 8. The calling code must take care of decoding of the
+ *  syndrome result and the received parity before calling this code.
+ */
+int decode_rs8(struct rs_control *rs, uint8_t *data, uint16_t *par, int len,
+	       uint16_t *s, int no_eras, int *eras_pos, uint16_t invmsk,
+	       uint16_t *corr)
+{
+#include "decode_rs.c"
+}
+EXPORT_SYMBOL_GPL(decode_rs8);
+#endif
+
+#ifdef CONFIG_REED_SOLOMON_ENC16
+/**
+ *  encode_rs16 - Calculate the parity for data values (16bit data width)
+ *  @rs:	the rs control structure
+ *  @data:	data field of a given type
+ *  @len:	data length
+ *  @par:	parity data, must be initialized by caller (usually all 0)
+ *  @invmsk:	invert data mask (will be xored on data, not on parity!)
+ *
+ *  Each field in the data array contains up to symbol size bits of valid data.
+ */
+int encode_rs16(struct rs_control *rs, uint16_t *data, int len, uint16_t *par,
+	uint16_t invmsk)
+{
+#include "encode_rs.c"
+}
+EXPORT_SYMBOL_GPL(encode_rs16);
+#endif
+
+#ifdef CONFIG_REED_SOLOMON_DEC16
+/**
+ *  decode_rs16 - Decode codeword (16bit data width)
+ *  @rs:	the rs control structure
+ *  @data:	data field of a given type
+ *  @par:	received parity data field
+ *  @len:	data length
+ *  @s:		syndrome data field (if NULL, syndrome is calculated)
+ *  @no_eras:	number of erasures
+ *  @eras_pos:	position of erasures, can be NULL
+ *  @invmsk:	invert data mask (will be xored on data, not on parity!)
+ *  @corr:	buffer to store correction bitmask on eras_pos
+ *
+ *  Each field in the data array contains up to symbol size bits of valid data.
+ */
+int decode_rs16(struct rs_control *rs, uint16_t *data, uint16_t *par, int len,
+		uint16_t *s, int no_eras, int *eras_pos, uint16_t invmsk,
+		uint16_t *corr)
+{
+#include "decode_rs.c"
+}
+EXPORT_SYMBOL_GPL(decode_rs16);
+#endif
+
+EXPORT_SYMBOL_GPL(init_rs);
+EXPORT_SYMBOL_GPL(free_rs);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Reed Solomon encoder/decoder");
+MODULE_AUTHOR("Phil Karn, Thomas Gleixner");
+

lib/rwsem-spinlock.c

@@ -0,0 +1,316 @@
+/* rwsem-spinlock.c: R/W semaphores: contention handling functions for
+ * generic spinlock implementation
+ *
+ * Copyright (c) 2001   David Howells (dhowells@redhat.com).
+ * - Derived partially from idea by Andrea Arcangeli <andrea@suse.de>
+ * - Derived also from comments by Linus
+ */
+#include <linux/rwsem.h>
+#include <linux/sched.h>
+#include <linux/module.h>
+
+struct rwsem_waiter {
+	struct list_head list;
+	struct task_struct *task;
+	unsigned int flags;
+#define RWSEM_WAITING_FOR_READ	0x00000001
+#define RWSEM_WAITING_FOR_WRITE	0x00000002
+};
+
+/*
+ * initialise the semaphore
+ */
+void __init_rwsem(struct rw_semaphore *sem, const char *name,
+		  struct lock_class_key *key)
+{
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+	/*
+	 * Make sure we are not reinitializing a held semaphore:
+	 */
+	debug_check_no_locks_freed((void *)sem, sizeof(*sem));
+	lockdep_init_map(&sem->dep_map, name, key, 0);
+#endif
+	sem->activity = 0;
+	spin_lock_init(&sem->wait_lock);
+	INIT_LIST_HEAD(&sem->wait_list);
+}
+
+/*
+ * handle the lock release when processes blocked on it that can now run
+ * - if we come here, then:
+ *   - the 'active count' _reached_ zero
+ *   - the 'waiting count' is non-zero
+ * - the spinlock must be held by the caller
+ * - woken process blocks are discarded from the list after having task zeroed
+ * - writers are only woken if wakewrite is non-zero
+ */
+static inline struct rw_semaphore *
+__rwsem_do_wake(struct rw_semaphore *sem, int wakewrite)
+{
+	struct rwsem_waiter *waiter;
+	struct task_struct *tsk;
+	int woken;
+
+	waiter = list_entry(sem->wait_list.next, struct rwsem_waiter, list);
+
+	if (!wakewrite) {
+		if (waiter->flags & RWSEM_WAITING_FOR_WRITE)
+			goto out;
+		goto dont_wake_writers;
+	}
+
+	/* if we are allowed to wake writers try to grant a single write lock
+	 * if there's a writer at the front of the queue
+	 * - we leave the 'waiting count' incremented to signify potential
+	 *   contention
+	 */
+	if (waiter->flags & RWSEM_WAITING_FOR_WRITE) {
+		sem->activity = -1;
+		list_del(&waiter->list);
+		tsk = waiter->task;
+		/* Don't touch waiter after ->task has been NULLed */
+		smp_mb();
+		waiter->task = NULL;
+		wake_up_process(tsk);
+		put_task_struct(tsk);
+		goto out;
+	}
+
+	/* grant an infinite number of read locks to the front of the queue */
+ dont_wake_writers:
+	woken = 0;
+	while (waiter->flags & RWSEM_WAITING_FOR_READ) {
+		struct list_head *next = waiter->list.next;
+
+		list_del(&waiter->list);
+		tsk = waiter->task;
+		smp_mb();
+		waiter->task = NULL;
+		wake_up_process(tsk);
+		put_task_struct(tsk);
+		woken++;
+		if (list_empty(&sem->wait_list))
+			break;
+		waiter = list_entry(next, struct rwsem_waiter, list);
+	}
+
+	sem->activity += woken;
+
+ out:
+	return sem;
+}
+
+/*
+ * wake a single writer
+ */
+static inline struct rw_semaphore *
+__rwsem_wake_one_writer(struct rw_semaphore *sem)
+{
+	struct rwsem_waiter *waiter;
+	struct task_struct *tsk;
+
+	sem->activity = -1;
+
+	waiter = list_entry(sem->wait_list.next, struct rwsem_waiter, list);
+	list_del(&waiter->list);
+
+	tsk = waiter->task;
+	smp_mb();
+	waiter->task = NULL;
+	wake_up_process(tsk);
+	put_task_struct(tsk);
+	return sem;
+}
+
+/*
+ * get a read lock on the semaphore
+ */
+void fastcall __sched __down_read(struct rw_semaphore *sem)
+{
+	struct rwsem_waiter waiter;
+	struct task_struct *tsk;
+
+	spin_lock_irq(&sem->wait_lock);
+
+	if (sem->activity >= 0 && list_empty(&sem->wait_list)) {
+		/* granted */
+		sem->activity++;
+		spin_unlock_irq(&sem->wait_lock);
+		goto out;
+	}
+
+	tsk = current;
+	set_task_state(tsk, TASK_UNINTERRUPTIBLE);
+
+	/* set up my own style of waitqueue */
+	waiter.task = tsk;
+	waiter.flags = RWSEM_WAITING_FOR_READ;
+	get_task_struct(tsk);
+
+	list_add_tail(&waiter.list, &sem->wait_list);
+
+	/* we don't need to touch the semaphore struct anymore */
+	spin_unlock_irq(&sem->wait_lock);
+
+	/* wait to be given the lock */
+	for (;;) {
+		if (!waiter.task)
+			break;
+		schedule();
+		set_task_state(tsk, TASK_UNINTERRUPTIBLE);
+	}
+
+	tsk->state = TASK_RUNNING;
+ out:
+	;
+}
+
+/*
+ * trylock for reading -- returns 1 if successful, 0 if contention
+ */
+int fastcall __down_read_trylock(struct rw_semaphore *sem)
+{
+	unsigned long flags;
+	int ret = 0;
+
+
+	spin_lock_irqsave(&sem->wait_lock, flags);
+
+	if (sem->activity >= 0 && list_empty(&sem->wait_list)) {
+		/* granted */
+		sem->activity++;
+		ret = 1;
+	}
+
+	spin_unlock_irqrestore(&sem->wait_lock, flags);
+
+	return ret;
+}
+
+/*
+ * get a write lock on the semaphore
+ * - we increment the waiting count anyway to indicate an exclusive lock
+ */
+void fastcall __sched __down_write_nested(struct rw_semaphore *sem, int subclass)
+{
+	struct rwsem_waiter waiter;
+	struct task_struct *tsk;
+
+	spin_lock_irq(&sem->wait_lock);
+
+	if (sem->activity == 0 && list_empty(&sem->wait_list)) {
+		/* granted */
+		sem->activity = -1;
+		spin_unlock_irq(&sem->wait_lock);
+		goto out;
+	}
+
+	tsk = current;
+	set_task_state(tsk, TASK_UNINTERRUPTIBLE);
+
+	/* set up my own style of waitqueue */
+	waiter.task = tsk;
+	waiter.flags = RWSEM_WAITING_FOR_WRITE;
+	get_task_struct(tsk);
+
+	list_add_tail(&waiter.list, &sem->wait_list);
+
+	/* we don't need to touch the semaphore struct anymore */
+	spin_unlock_irq(&sem->wait_lock);
+
+	/* wait to be given the lock */
+	for (;;) {
+		if (!waiter.task)
+			break;
+		schedule();
+		set_task_state(tsk, TASK_UNINTERRUPTIBLE);
+	}
+
+	tsk->state = TASK_RUNNING;
+ out:
+	;
+}
+
+void fastcall __sched __down_write(struct rw_semaphore *sem)
+{
+	__down_write_nested(sem, 0);
+}
+
+/*
+ * trylock for writing -- returns 1 if successful, 0 if contention
+ */
+int fastcall __down_write_trylock(struct rw_semaphore *sem)
+{
+	unsigned long flags;
+	int ret = 0;
+
+	spin_lock_irqsave(&sem->wait_lock, flags);
+
+	if (sem->activity == 0 && list_empty(&sem->wait_list)) {
+		/* granted */
+		sem->activity = -1;
+		ret = 1;
+	}
+
+	spin_unlock_irqrestore(&sem->wait_lock, flags);
+
+	return ret;
+}
+
+/*
+ * release a read lock on the semaphore
+ */
+void fastcall __up_read(struct rw_semaphore *sem)
+{
+	unsigned long flags;
+
+	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);
+}
+
+/*
+ * release a write lock on the semaphore
+ */
+void fastcall __up_write(struct rw_semaphore *sem)
+{
+	unsigned long flags;
+
+	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);
+}
+
+/*
+ * downgrade a write lock into a read lock
+ * - just wake up any readers at the front of the queue
+ */
+void fastcall __downgrade_write(struct rw_semaphore *sem)
+{
+	unsigned long flags;
+
+	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);
+}
+
+EXPORT_SYMBOL(__init_rwsem);
+EXPORT_SYMBOL(__down_read);
+EXPORT_SYMBOL(__down_read_trylock);
+EXPORT_SYMBOL(__down_write_nested);
+EXPORT_SYMBOL(__down_write);
+EXPORT_SYMBOL(__down_write_trylock);
+EXPORT_SYMBOL(__up_read);
+EXPORT_SYMBOL(__up_write);
+EXPORT_SYMBOL(__downgrade_write);

lib/rwsem.c

@@ -0,0 +1,257 @@
+/* rwsem.c: R/W semaphores: contention handling functions
+ *
+ * Written by David Howells (dhowells@redhat.com).
+ * Derived from arch/i386/kernel/semaphore.c
+ */
+#include <linux/rwsem.h>
+#include <linux/sched.h>
+#include <linux/init.h>
+#include <linux/module.h>
+
+/*
+ * Initialize an rwsem:
+ */
+void __init_rwsem(struct rw_semaphore *sem, const char *name,
+		  struct lock_class_key *key)
+{
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+	/*
+	 * Make sure we are not reinitializing a held semaphore:
+	 */
+	debug_check_no_locks_freed((void *)sem, sizeof(*sem));
+	lockdep_init_map(&sem->dep_map, name, key, 0);
+#endif
+	sem->count = RWSEM_UNLOCKED_VALUE;
+	spin_lock_init(&sem->wait_lock);
+	INIT_LIST_HEAD(&sem->wait_list);
+}
+
+EXPORT_SYMBOL(__init_rwsem);
+
+struct rwsem_waiter {
+	struct list_head list;
+	struct task_struct *task;
+	unsigned int flags;
+#define RWSEM_WAITING_FOR_READ	0x00000001
+#define RWSEM_WAITING_FOR_WRITE	0x00000002
+};
+
+/*
+ * handle the lock release when processes blocked on it that can now run
+ * - if we come here from up_xxxx(), then:
+ *   - the 'active part' of count (&0x0000ffff) reached 0 (but may have changed)
+ *   - the 'waiting part' of count (&0xffff0000) is -ve (and will still be so)
+ *   - there must be someone on the queue
+ * - the spinlock must be held by the caller
+ * - woken process blocks are discarded from the list after having task zeroed
+ * - writers are only woken if downgrading is false
+ */
+static inline struct rw_semaphore *
+__rwsem_do_wake(struct rw_semaphore *sem, int downgrading)
+{
+	struct rwsem_waiter *waiter;
+	struct task_struct *tsk;
+	struct list_head *next;
+	signed long oldcount, woken, loop;
+
+	if (downgrading)
+		goto dont_wake_writers;
+
+	/* if we came through an up_xxxx() call, we only only wake someone up
+	 * if we can transition the active part of the count from 0 -> 1
+	 */
+ try_again:
+	oldcount = rwsem_atomic_update(RWSEM_ACTIVE_BIAS, sem)
+						- RWSEM_ACTIVE_BIAS;
+	if (oldcount & RWSEM_ACTIVE_MASK)
+		goto undo;
+
+	waiter = list_entry(sem->wait_list.next, struct rwsem_waiter, list);
+
+	/* try to grant a single write lock if there's a writer at the front
+	 * of the queue - note we leave the 'active part' of the count
+	 * incremented by 1 and the waiting part incremented by 0x00010000
+	 */
+	if (!(waiter->flags & RWSEM_WAITING_FOR_WRITE))
+		goto readers_only;
+
+	/* We must be careful not to touch 'waiter' after we set ->task = NULL.
+	 * It is an allocated on the waiter's stack and may become invalid at
+	 * any time after that point (due to a wakeup from another source).
+	 */
+	list_del(&waiter->list);
+	tsk = waiter->task;
+	smp_mb();
+	waiter->task = NULL;
+	wake_up_process(tsk);
+	put_task_struct(tsk);
+	goto out;
+
+	/* don't want to wake any writers */
+ dont_wake_writers:
+	waiter = list_entry(sem->wait_list.next, struct rwsem_waiter, list);
+	if (waiter->flags & RWSEM_WAITING_FOR_WRITE)
+		goto out;
+
+	/* grant an infinite number of read locks to the readers at the front
+	 * of the queue
+	 * - note we increment the 'active part' of the count by the number of
+	 *   readers before waking any processes up
+	 */
+ readers_only:
+	woken = 0;
+	do {
+		woken++;
+
+		if (waiter->list.next == &sem->wait_list)
+			break;
+
+		waiter = list_entry(waiter->list.next,
+					struct rwsem_waiter, list);
+
+	} while (waiter->flags & RWSEM_WAITING_FOR_READ);
+
+	loop = woken;
+	woken *= RWSEM_ACTIVE_BIAS - RWSEM_WAITING_BIAS;
+	if (!downgrading)
+		/* we'd already done one increment earlier */
+		woken -= RWSEM_ACTIVE_BIAS;
+
+	rwsem_atomic_add(woken, sem);
+
+	next = sem->wait_list.next;
+	for (; loop > 0; loop--) {
+		waiter = list_entry(next, struct rwsem_waiter, list);
+		next = waiter->list.next;
+		tsk = waiter->task;
+		smp_mb();
+		waiter->task = NULL;
+		wake_up_process(tsk);
+		put_task_struct(tsk);
+	}
+
+	sem->wait_list.next = next;
+	next->prev = &sem->wait_list;
+
+ out:
+	return sem;
+
+	/* undo the change to count, but check for a transition 1->0 */
+ undo:
+	if (rwsem_atomic_update(-RWSEM_ACTIVE_BIAS, sem) != 0)
+		goto out;
+	goto try_again;
+}
+
+/*
+ * wait for a lock to be granted
+ */
+static struct rw_semaphore *
+rwsem_down_failed_common(struct rw_semaphore *sem,
+			struct rwsem_waiter *waiter, signed long adjustment)
+{
+	struct task_struct *tsk = current;
+	signed long count;
+
+	set_task_state(tsk, TASK_UNINTERRUPTIBLE);
+
+	/* set up my own style of waitqueue */
+	spin_lock_irq(&sem->wait_lock);
+	waiter->task = tsk;
+	get_task_struct(tsk);
+
+	list_add_tail(&waiter->list, &sem->wait_list);
+
+	/* we're now waiting on the lock, but no longer actively read-locking */
+	count = rwsem_atomic_update(adjustment, sem);
+
+	/* if there are no active locks, wake the front queued process(es) up */
+	if (!(count & RWSEM_ACTIVE_MASK))
+		sem = __rwsem_do_wake(sem, 0);
+
+	spin_unlock_irq(&sem->wait_lock);
+
+	/* wait to be given the lock */
+	for (;;) {
+		if (!waiter->task)
+			break;
+		schedule();
+		set_task_state(tsk, TASK_UNINTERRUPTIBLE);
+	}
+
+	tsk->state = TASK_RUNNING;
+
+	return sem;
+}
+
+/*
+ * wait for the read lock to be granted
+ */
+struct rw_semaphore fastcall __sched *
+rwsem_down_read_failed(struct rw_semaphore *sem)
+{
+	struct rwsem_waiter waiter;
+
+	waiter.flags = RWSEM_WAITING_FOR_READ;
+	rwsem_down_failed_common(sem, &waiter,
+				RWSEM_WAITING_BIAS - RWSEM_ACTIVE_BIAS);
+	return sem;
+}
+
+/*
+ * wait for the write lock to be granted
+ */
+struct rw_semaphore fastcall __sched *
+rwsem_down_write_failed(struct rw_semaphore *sem)
+{
+	struct rwsem_waiter waiter;
+
+	waiter.flags = RWSEM_WAITING_FOR_WRITE;
+	rwsem_down_failed_common(sem, &waiter, -RWSEM_ACTIVE_BIAS);
+
+	return sem;
+}
+
+/*
+ * handle waking up a waiter on the semaphore
+ * - up_read/up_write has decremented the active part of count if we come here
+ */
+struct rw_semaphore fastcall *rwsem_wake(struct rw_semaphore *sem)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&sem->wait_lock, flags);
+
+	/* do nothing if list empty */
+	if (!list_empty(&sem->wait_list))
+		sem = __rwsem_do_wake(sem, 0);
+
+	spin_unlock_irqrestore(&sem->wait_lock, flags);
+
+	return sem;
+}
+
+/*
+ * downgrade a write lock into a read lock
+ * - caller incremented waiting part of count and discovered it still negative
+ * - just wake up any readers at the front of the queue
+ */
+struct rw_semaphore fastcall *rwsem_downgrade_wake(struct rw_semaphore *sem)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&sem->wait_lock, flags);
+
+	/* do nothing if list empty */
+	if (!list_empty(&sem->wait_list))
+		sem = __rwsem_do_wake(sem, 1);
+
+	spin_unlock_irqrestore(&sem->wait_lock, flags);
+
+	return sem;
+}
+
+EXPORT_SYMBOL(rwsem_down_read_failed);
+EXPORT_SYMBOL(rwsem_down_write_failed);
+EXPORT_SYMBOL(rwsem_wake);
+EXPORT_SYMBOL(rwsem_downgrade_wake);

lib/semaphore-sleepers.c

@@ -0,0 +1,176 @@
+/*
+ * i386 and x86-64 semaphore implementation.
+ *
+ * (C) Copyright 1999 Linus Torvalds
+ *
+ * Portions Copyright 1999 Red Hat, Inc.
+ *
+ *	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.
+ *
+ * rw semaphores implemented November 1999 by Benjamin LaHaise <bcrl@kvack.org>
+ */
+#include <linux/sched.h>
+#include <linux/err.h>
+#include <linux/init.h>
+#include <asm/semaphore.h>
+
+/*
+ * Semaphores are implemented using a two-way counter:
+ * The "count" variable is decremented for each process
+ * that tries to acquire the semaphore, while the "sleeping"
+ * variable is a count of such acquires.
+ *
+ * Notably, the inline "up()" and "down()" functions can
+ * efficiently test if they need to do any extra work (up
+ * needs to do something only if count was negative before
+ * the increment operation.
+ *
+ * "sleeping" and the contention routine ordering is protected
+ * by the spinlock in the semaphore's waitqueue head.
+ *
+ * Note that these functions are only called when there is
+ * contention on the lock, and as such all this is the
+ * "non-critical" part of the whole semaphore business. The
+ * critical part is the inline stuff in <asm/semaphore.h>
+ * where we want to avoid any extra jumps and calls.
+ */
+
+/*
+ * Logic:
+ *  - only on a boundary condition do we need to care. When we go
+ *    from a negative count to a non-negative, we wake people up.
+ *  - when we go from a non-negative count to a negative do we
+ *    (a) synchronize with the "sleeper" count and (b) make sure
+ *    that we're on the wakeup list before we synchronize so that
+ *    we cannot lose wakeup events.
+ */
+
+fastcall void __up(struct semaphore *sem)
+{
+	wake_up(&sem->wait);
+}
+
+fastcall void __sched __down(struct semaphore * sem)
+{
+	struct task_struct *tsk = current;
+	DECLARE_WAITQUEUE(wait, tsk);
+	unsigned long flags;
+
+	tsk->state = TASK_UNINTERRUPTIBLE;
+	spin_lock_irqsave(&sem->wait.lock, flags);
+	add_wait_queue_exclusive_locked(&sem->wait, &wait);
+
+	sem->sleepers++;
+	for (;;) {
+		int sleepers = sem->sleepers;
+
+		/*
+		 * Add "everybody else" into it. They aren't
+		 * playing, because we own the spinlock in
+		 * the wait_queue_head.
+		 */
+		if (!atomic_add_negative(sleepers - 1, &sem->count)) {
+			sem->sleepers = 0;
+			break;
+		}
+		sem->sleepers = 1;	/* us - see -1 above */
+		spin_unlock_irqrestore(&sem->wait.lock, flags);
+
+		schedule();
+
+		spin_lock_irqsave(&sem->wait.lock, flags);
+		tsk->state = TASK_UNINTERRUPTIBLE;
+	}
+	remove_wait_queue_locked(&sem->wait, &wait);
+	wake_up_locked(&sem->wait);
+	spin_unlock_irqrestore(&sem->wait.lock, flags);
+	tsk->state = TASK_RUNNING;
+}
+
+fastcall int __sched __down_interruptible(struct semaphore * sem)
+{
+	int retval = 0;
+	struct task_struct *tsk = current;
+	DECLARE_WAITQUEUE(wait, tsk);
+	unsigned long flags;
+
+	tsk->state = TASK_INTERRUPTIBLE;
+	spin_lock_irqsave(&sem->wait.lock, flags);
+	add_wait_queue_exclusive_locked(&sem->wait, &wait);
+
+	sem->sleepers++;
+	for (;;) {
+		int sleepers = sem->sleepers;
+
+		/*
+		 * With signals pending, this turns into
+		 * the trylock failure case - we won't be
+		 * sleeping, and we* can't get the lock as
+		 * it has contention. Just correct the count
+		 * and exit.
+		 */
+		if (signal_pending(current)) {
+			retval = -EINTR;
+			sem->sleepers = 0;
+			atomic_add(sleepers, &sem->count);
+			break;
+		}
+
+		/*
+		 * Add "everybody else" into it. They aren't
+		 * playing, because we own the spinlock in
+		 * wait_queue_head. The "-1" is because we're
+		 * still hoping to get the semaphore.
+		 */
+		if (!atomic_add_negative(sleepers - 1, &sem->count)) {
+			sem->sleepers = 0;
+			break;
+		}
+		sem->sleepers = 1;	/* us - see -1 above */
+		spin_unlock_irqrestore(&sem->wait.lock, flags);
+
+		schedule();
+
+		spin_lock_irqsave(&sem->wait.lock, flags);
+		tsk->state = TASK_INTERRUPTIBLE;
+	}
+	remove_wait_queue_locked(&sem->wait, &wait);
+	wake_up_locked(&sem->wait);
+	spin_unlock_irqrestore(&sem->wait.lock, flags);
+
+	tsk->state = TASK_RUNNING;
+	return retval;
+}
+
+/*
+ * Trylock failed - make sure we correct for
+ * having decremented the count.
+ *
+ * We could have done the trylock with a
+ * single "cmpxchg" without failure cases,
+ * but then it wouldn't work on a 386.
+ */
+fastcall int __down_trylock(struct semaphore * sem)
+{
+	int sleepers;
+	unsigned long flags;
+
+	spin_lock_irqsave(&sem->wait.lock, flags);
+	sleepers = sem->sleepers + 1;
+	sem->sleepers = 0;
+
+	/*
+	 * Add "everybody else" and us into it. They aren't
+	 * playing, because we own the spinlock in the
+	 * wait_queue_head.
+	 */
+	if (!atomic_add_negative(sleepers, &sem->count)) {
+		wake_up_locked(&sem->wait);
+	}
+
+	spin_unlock_irqrestore(&sem->wait.lock, flags);
+	return 1;
+}

lib/sha1.c

@@ -0,0 +1,95 @@
+/*
+ * SHA transform algorithm, originally taken from code written by
+ * Peter Gutmann, and placed in the public domain.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/cryptohash.h>
+
+/* The SHA f()-functions.  */
+
+#define f1(x,y,z)   (z ^ (x & (y ^ z)))		/* x ? y : z */
+#define f2(x,y,z)   (x ^ y ^ z)			/* XOR */
+#define f3(x,y,z)   ((x & y) + (z & (x ^ y)))	/* majority */
+
+/* The SHA Mysterious Constants */
+
+#define K1  0x5A827999L			/* Rounds  0-19: sqrt(2) * 2^30 */
+#define K2  0x6ED9EBA1L			/* Rounds 20-39: sqrt(3) * 2^30 */
+#define K3  0x8F1BBCDCL			/* Rounds 40-59: sqrt(5) * 2^30 */
+#define K4  0xCA62C1D6L			/* Rounds 60-79: sqrt(10) * 2^30 */
+
+/**
+ * sha_transform - single block SHA1 transform
+ *
+ * @digest: 160 bit digest to update
+ * @data:   512 bits of data to hash
+ * @W:      80 words of workspace (see note)
+ *
+ * This function generates a SHA1 digest for a single 512-bit block.
+ * Be warned, it does not handle padding and message digest, do not
+ * confuse it with the full FIPS 180-1 digest algorithm for variable
+ * length messages.
+ *
+ * Note: If the hash is security sensitive, the caller should be sure
+ * to clear the workspace. This is left to the caller to avoid
+ * unnecessary clears between chained hashing operations.
+ */
+void sha_transform(__u32 *digest, const char *in, __u32 *W)
+{
+	__u32 a, b, c, d, e, t, i;
+
+	for (i = 0; i < 16; i++)
+		W[i] = be32_to_cpu(((const __be32 *)in)[i]);
+
+	for (i = 0; i < 64; i++)
+		W[i+16] = rol32(W[i+13] ^ W[i+8] ^ W[i+2] ^ W[i], 1);
+
+	a = digest[0];
+	b = digest[1];
+	c = digest[2];
+	d = digest[3];
+	e = digest[4];
+
+	for (i = 0; i < 20; i++) {
+		t = f1(b, c, d) + K1 + rol32(a, 5) + e + W[i];
+		e = d; d = c; c = rol32(b, 30); b = a; a = t;
+	}
+
+	for (; i < 40; i ++) {
+		t = f2(b, c, d) + K2 + rol32(a, 5) + e + W[i];
+		e = d; d = c; c = rol32(b, 30); b = a; a = t;
+	}
+
+	for (; i < 60; i ++) {
+		t = f3(b, c, d) + K3 + rol32(a, 5) + e + W[i];
+		e = d; d = c; c = rol32(b, 30); b = a; a = t;
+	}
+
+	for (; i < 80; i ++) {
+		t = f2(b, c, d) + K4 + rol32(a, 5) + e + W[i];
+		e = d; d = c; c = rol32(b, 30); b = a; a = t;
+	}
+
+	digest[0] += a;
+	digest[1] += b;
+	digest[2] += c;
+	digest[3] += d;
+	digest[4] += e;
+}
+EXPORT_SYMBOL(sha_transform);
+
+/**
+ * sha_init - initialize the vectors for a SHA1 digest
+ * @buf: vector to initialize
+ */
+void sha_init(__u32 *buf)
+{
+	buf[0] = 0x67452301;
+	buf[1] = 0xefcdab89;
+	buf[2] = 0x98badcfe;
+	buf[3] = 0x10325476;
+	buf[4] = 0xc3d2e1f0;
+}
+

lib/smp_processor_id.c

@@ -0,0 +1,56 @@
+/*
+ * lib/smp_processor_id.c
+ *
+ * DEBUG_PREEMPT variant of smp_processor_id().
+ */
+#include <linux/module.h>
+#include <linux/kallsyms.h>
+#include <linux/sched.h>
+
+unsigned int debug_smp_processor_id(void)
+{
+	unsigned long preempt_count = preempt_count();
+	int this_cpu = raw_smp_processor_id();
+	cpumask_t this_mask;
+
+	if (likely(preempt_count))
+		goto out;
+
+	if (irqs_disabled())
+		goto out;
+
+	/*
+	 * Kernel threads bound to a single CPU can safely use
+	 * smp_processor_id():
+	 */
+	this_mask = cpumask_of_cpu(this_cpu);
+
+	if (cpus_equal(current->cpus_allowed, this_mask))
+		goto out;
+
+	/*
+	 * It is valid to assume CPU-locality during early bootup:
+	 */
+	if (system_state != SYSTEM_RUNNING)
+		goto out;
+
+	/*
+	 * Avoid recursion:
+	 */
+	preempt_disable();
+
+	if (!printk_ratelimit())
+		goto out_enable;
+
+	printk(KERN_ERR "BUG: using smp_processor_id() in preemptible [%08x] code: %s/%d\n", preempt_count(), current->comm, current->pid);
+	print_symbol("caller is %s\n", (long)__builtin_return_address(0));
+	dump_stack();
+
+out_enable:
+	preempt_enable_no_resched();
+out:
+	return this_cpu;
+}
+
+EXPORT_SYMBOL(debug_smp_processor_id);
+

lib/sort.c

@@ -0,0 +1,121 @@
+/*
+ * A fast, small, non-recursive O(nlog n) sort for the Linux kernel
+ *
+ * Jan 23 2005  Matt Mackall <mpm@selenic.com>
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/sort.h>
+#include <linux/slab.h>
+
+static void u32_swap(void *a, void *b, int size)
+{
+	u32 t = *(u32 *)a;
+	*(u32 *)a = *(u32 *)b;
+	*(u32 *)b = t;
+}
+
+static void generic_swap(void *a, void *b, int size)
+{
+	char t;
+
+	do {
+		t = *(char *)a;
+		*(char *)a++ = *(char *)b;
+		*(char *)b++ = t;
+	} while (--size > 0);
+}
+
+/**
+ * sort - sort an array of elements
+ * @base: pointer to data to sort
+ * @num: number of elements
+ * @size: size of each element
+ * @cmp: pointer to comparison function
+ * @swap: pointer to swap function or NULL
+ *
+ * This function does a heapsort on the given array. You may provide a
+ * swap function optimized to your element type.
+ *
+ * Sorting time is O(n log n) both on average and worst-case. While
+ * qsort is about 20% faster on average, it suffers from exploitable
+ * O(n*n) worst-case behavior and extra memory requirements that make
+ * it less suitable for kernel use.
+ */
+
+void sort(void *base, size_t num, size_t size,
+	  int (*cmp)(const void *, const void *),
+	  void (*swap)(void *, void *, int size))
+{
+	/* pre-scale counters for performance */
+	int i = (num/2 - 1) * size, n = num * size, c, r;
+
+	if (!swap)
+		swap = (size == 4 ? u32_swap : generic_swap);
+
+	/* heapify */
+	for ( ; i >= 0; i -= size) {
+		for (r = i; r * 2 + size < n; r  = c) {
+			c = r * 2 + size;
+			if (c < n - size && cmp(base + c, base + c + size) < 0)
+				c += size;
+			if (cmp(base + r, base + c) >= 0)
+				break;
+			swap(base + r, base + c, size);
+		}
+	}
+
+	/* sort */
+	for (i = n - size; i >= 0; i -= size) {
+		swap(base, base + i, size);
+		for (r = 0; r * 2 + size < i; r = c) {
+			c = r * 2 + size;
+			if (c < i - size && cmp(base + c, base + c + size) < 0)
+				c += size;
+			if (cmp(base + r, base + c) >= 0)
+				break;
+			swap(base + r, base + c, size);
+		}
+	}
+}
+
+EXPORT_SYMBOL(sort);
+
+#if 0
+/* a simple boot-time regression test */
+
+int cmpint(const void *a, const void *b)
+{
+	return *(int *)a - *(int *)b;
+}
+
+static int sort_test(void)
+{
+	int *a, i, r = 1;
+
+	a = kmalloc(1000 * sizeof(int), GFP_KERNEL);
+	BUG_ON(!a);
+
+	printk("testing sort()\n");
+
+	for (i = 0; i < 1000; i++) {
+		r = (r * 725861) % 6599;
+		a[i] = r;
+	}
+
+	sort(a, 1000, sizeof(int), cmpint, NULL);
+
+	for (i = 0; i < 999; i++)
+		if (a[i] > a[i+1]) {
+			printk("sort() failed!\n");
+			break;
+		}
+
+	kfree(a);
+
+	return 0;
+}
+
+module_init(sort_test);
+#endif

lib/spinlock_debug.c

@@ -0,0 +1,297 @@
+/*
+ * Copyright 2005, Red Hat, Inc., Ingo Molnar
+ * Released under the General Public License (GPL).
+ *
+ * This file contains the spinlock/rwlock implementations for
+ * DEBUG_SPINLOCK.
+ */
+
+#include <linux/spinlock.h>
+#include <linux/nmi.h>
+#include <linux/interrupt.h>
+#include <linux/debug_locks.h>
+#include <linux/delay.h>
+#include <linux/module.h>
+
+void __spin_lock_init(spinlock_t *lock, const char *name,
+		      struct lock_class_key *key)
+{
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+	/*
+	 * Make sure we are not reinitializing a held lock:
+	 */
+	debug_check_no_locks_freed((void *)lock, sizeof(*lock));
+	lockdep_init_map(&lock->dep_map, name, key, 0);
+#endif
+	lock->raw_lock = (raw_spinlock_t)__RAW_SPIN_LOCK_UNLOCKED;
+	lock->magic = SPINLOCK_MAGIC;
+	lock->owner = SPINLOCK_OWNER_INIT;
+	lock->owner_cpu = -1;
+}
+
+EXPORT_SYMBOL(__spin_lock_init);
+
+void __rwlock_init(rwlock_t *lock, const char *name,
+		   struct lock_class_key *key)
+{
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+	/*
+	 * Make sure we are not reinitializing a held lock:
+	 */
+	debug_check_no_locks_freed((void *)lock, sizeof(*lock));
+	lockdep_init_map(&lock->dep_map, name, key, 0);
+#endif
+	lock->raw_lock = (raw_rwlock_t) __RAW_RW_LOCK_UNLOCKED;
+	lock->magic = RWLOCK_MAGIC;
+	lock->owner = SPINLOCK_OWNER_INIT;
+	lock->owner_cpu = -1;
+}
+
+EXPORT_SYMBOL(__rwlock_init);
+
+static void spin_bug(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, current->pid);
+	printk(KERN_EMERG " lock: %p, .magic: %08x, .owner: %s/%d, "
+			".owner_cpu: %d\n",
+		lock, lock->magic,
+		owner ? owner->comm : "<none>",
+		owner ? owner->pid : -1,
+		lock->owner_cpu);
+	dump_stack();
+}
+
+#define SPIN_BUG_ON(cond, lock, msg) if (unlikely(cond)) spin_bug(lock, msg)
+
+static inline void
+debug_spin_lock_before(spinlock_t *lock)
+{
+	SPIN_BUG_ON(lock->magic != SPINLOCK_MAGIC, lock, "bad magic");
+	SPIN_BUG_ON(lock->owner == current, lock, "recursion");
+	SPIN_BUG_ON(lock->owner_cpu == raw_smp_processor_id(),
+							lock, "cpu recursion");
+}
+
+static inline void debug_spin_lock_after(spinlock_t *lock)
+{
+	lock->owner_cpu = raw_smp_processor_id();
+	lock->owner = current;
+}
+
+static inline void debug_spin_unlock(spinlock_t *lock)
+{
+	SPIN_BUG_ON(lock->magic != SPINLOCK_MAGIC, lock, "bad magic");
+	SPIN_BUG_ON(!spin_is_locked(lock), lock, "already unlocked");
+	SPIN_BUG_ON(lock->owner != current, lock, "wrong owner");
+	SPIN_BUG_ON(lock->owner_cpu != raw_smp_processor_id(),
+							lock, "wrong CPU");
+	lock->owner = SPINLOCK_OWNER_INIT;
+	lock->owner_cpu = -1;
+}
+
+static void __spin_lock_debug(spinlock_t *lock)
+{
+	u64 i;
+	u64 loops = loops_per_jiffy * HZ;
+	int print_once = 1;
+
+	for (;;) {
+		for (i = 0; i < loops; i++) {
+			if (__raw_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,
+				current->pid, lock);
+			dump_stack();
+#ifdef CONFIG_SMP
+			trigger_all_cpu_backtrace();
+#endif
+		}
+	}
+}
+
+void _raw_spin_lock(spinlock_t *lock)
+{
+	debug_spin_lock_before(lock);
+	if (unlikely(!__raw_spin_trylock(&lock->raw_lock)))
+		__spin_lock_debug(lock);
+	debug_spin_lock_after(lock);
+}
+
+int _raw_spin_trylock(spinlock_t *lock)
+{
+	int ret = __raw_spin_trylock(&lock->raw_lock);
+
+	if (ret)
+		debug_spin_lock_after(lock);
+#ifndef CONFIG_SMP
+	/*
+	 * Must not happen on UP:
+	 */
+	SPIN_BUG_ON(!ret, lock, "trylock failure on UP");
+#endif
+	return ret;
+}
+
+void _raw_spin_unlock(spinlock_t *lock)
+{
+	debug_spin_unlock(lock);
+	__raw_spin_unlock(&lock->raw_lock);
+}
+
+static void rwlock_bug(rwlock_t *lock, const char *msg)
+{
+	if (!debug_locks_off())
+		return;
+
+	printk(KERN_EMERG "BUG: rwlock %s on CPU#%d, %s/%d, %p\n",
+		msg, raw_smp_processor_id(), current->comm,
+		current->pid, lock);
+	dump_stack();
+}
+
+#define RWLOCK_BUG_ON(cond, lock, msg) if (unlikely(cond)) rwlock_bug(lock, msg)
+
+#if 0		/* __write_lock_debug() can lock up - maybe this can too? */
+static void __read_lock_debug(rwlock_t *lock)
+{
+	u64 i;
+	u64 loops = loops_per_jiffy * HZ;
+	int print_once = 1;
+
+	for (;;) {
+		for (i = 0; i < loops; i++) {
+			if (__raw_read_trylock(&lock->raw_lock))
+				return;
+			__delay(1);
+		}
+		/* lockup suspected: */
+		if (print_once) {
+			print_once = 0;
+			printk(KERN_EMERG "BUG: read-lock lockup on CPU#%d, "
+					"%s/%d, %p\n",
+				raw_smp_processor_id(), current->comm,
+				current->pid, lock);
+			dump_stack();
+		}
+	}
+}
+#endif
+
+void _raw_read_lock(rwlock_t *lock)
+{
+	RWLOCK_BUG_ON(lock->magic != RWLOCK_MAGIC, lock, "bad magic");
+	__raw_read_lock(&lock->raw_lock);
+}
+
+int _raw_read_trylock(rwlock_t *lock)
+{
+	int ret = __raw_read_trylock(&lock->raw_lock);
+
+#ifndef CONFIG_SMP
+	/*
+	 * Must not happen on UP:
+	 */
+	RWLOCK_BUG_ON(!ret, lock, "trylock failure on UP");
+#endif
+	return ret;
+}
+
+void _raw_read_unlock(rwlock_t *lock)
+{
+	RWLOCK_BUG_ON(lock->magic != RWLOCK_MAGIC, lock, "bad magic");
+	__raw_read_unlock(&lock->raw_lock);
+}
+
+static inline void debug_write_lock_before(rwlock_t *lock)
+{
+	RWLOCK_BUG_ON(lock->magic != RWLOCK_MAGIC, lock, "bad magic");
+	RWLOCK_BUG_ON(lock->owner == current, lock, "recursion");
+	RWLOCK_BUG_ON(lock->owner_cpu == raw_smp_processor_id(),
+							lock, "cpu recursion");
+}
+
+static inline void debug_write_lock_after(rwlock_t *lock)
+{
+	lock->owner_cpu = raw_smp_processor_id();
+	lock->owner = current;
+}
+
+static inline void debug_write_unlock(rwlock_t *lock)
+{
+	RWLOCK_BUG_ON(lock->magic != RWLOCK_MAGIC, lock, "bad magic");
+	RWLOCK_BUG_ON(lock->owner != current, lock, "wrong owner");
+	RWLOCK_BUG_ON(lock->owner_cpu != raw_smp_processor_id(),
+							lock, "wrong CPU");
+	lock->owner = SPINLOCK_OWNER_INIT;
+	lock->owner_cpu = -1;
+}
+
+#if 0		/* This can cause lockups */
+static void __write_lock_debug(rwlock_t *lock)
+{
+	u64 i;
+	u64 loops = loops_per_jiffy * HZ;
+	int print_once = 1;
+
+	for (;;) {
+		for (i = 0; i < loops; i++) {
+			if (__raw_write_trylock(&lock->raw_lock))
+				return;
+			__delay(1);
+		}
+		/* lockup suspected: */
+		if (print_once) {
+			print_once = 0;
+			printk(KERN_EMERG "BUG: write-lock lockup on CPU#%d, "
+					"%s/%d, %p\n",
+				raw_smp_processor_id(), current->comm,
+				current->pid, lock);
+			dump_stack();
+		}
+	}
+}
+#endif
+
+void _raw_write_lock(rwlock_t *lock)
+{
+	debug_write_lock_before(lock);
+	__raw_write_lock(&lock->raw_lock);
+	debug_write_lock_after(lock);
+}
+
+int _raw_write_trylock(rwlock_t *lock)
+{
+	int ret = __raw_write_trylock(&lock->raw_lock);
+
+	if (ret)
+		debug_write_lock_after(lock);
+#ifndef CONFIG_SMP
+	/*
+	 * Must not happen on UP:
+	 */
+	RWLOCK_BUG_ON(!ret, lock, "trylock failure on UP");
+#endif
+	return ret;
+}
+
+void _raw_write_unlock(rwlock_t *lock)
+{
+	debug_write_unlock(lock);
+	__raw_write_unlock(&lock->raw_lock);
+}

lib/string.c

@@ -0,0 +1,634 @@
+/*
+ *  linux/lib/string.c
+ *
+ *  Copyright (C) 1991, 1992  Linus Torvalds
+ */
+
+/*
+ * stupid library routines.. The optimized versions should generally be found
+ * as inline code in <asm-xx/string.h>
+ *
+ * These are buggy as well..
+ *
+ * * Fri Jun 25 1999, Ingo Oeser <ioe@informatik.tu-chemnitz.de>
+ * -  Added strsep() which will replace strtok() soon (because strsep() is
+ *    reentrant and should be faster). Use only strsep() in new code, please.
+ *
+ * * Sat Feb 09 2002, Jason Thomas <jason@topic.com.au>,
+ *                    Matthew Hawkins <matt@mh.dropbear.id.au>
+ * -  Kissed strtok() goodbye
+ */
+
+#include <linux/types.h>
+#include <linux/string.h>
+#include <linux/ctype.h>
+#include <linux/module.h>
+
+#ifndef __HAVE_ARCH_STRNICMP
+/**
+ * strnicmp - Case insensitive, length-limited string comparison
+ * @s1: One string
+ * @s2: The other string
+ * @len: the maximum number of characters to compare
+ */
+int strnicmp(const char *s1, const char *s2, size_t len)
+{
+	/* Yes, Virginia, it had better be unsigned */
+	unsigned char c1, c2;
+
+	c1 = c2 = 0;
+	if (len) {
+		do {
+			c1 = *s1;
+			c2 = *s2;
+			s1++;
+			s2++;
+			if (!c1)
+				break;
+			if (!c2)
+				break;
+			if (c1 == c2)
+				continue;
+			c1 = tolower(c1);
+			c2 = tolower(c2);
+			if (c1 != c2)
+				break;
+		} while (--len);
+	}
+	return (int)c1 - (int)c2;
+}
+EXPORT_SYMBOL(strnicmp);
+#endif
+
+#ifndef __HAVE_ARCH_STRCPY
+/**
+ * strcpy - Copy a %NUL terminated string
+ * @dest: Where to copy the string to
+ * @src: Where to copy the string from
+ */
+#undef strcpy
+char *strcpy(char *dest, const char *src)
+{
+	char *tmp = dest;
+
+	while ((*dest++ = *src++) != '\0')
+		/* nothing */;
+	return tmp;
+}
+EXPORT_SYMBOL(strcpy);
+#endif
+
+#ifndef __HAVE_ARCH_STRNCPY
+/**
+ * strncpy - Copy a length-limited, %NUL-terminated string
+ * @dest: Where to copy the string to
+ * @src: Where to copy the string from
+ * @count: The maximum number of bytes to copy
+ *
+ * The result is not %NUL-terminated if the source exceeds
+ * @count bytes.
+ *
+ * In the case where the length of @src is less than  that  of
+ * count, the remainder of @dest will be padded with %NUL.
+ *
+ */
+char *strncpy(char *dest, const char *src, size_t count)
+{
+	char *tmp = dest;
+
+	while (count) {
+		if ((*tmp = *src) != 0)
+			src++;
+		tmp++;
+		count--;
+	}
+	return dest;
+}
+EXPORT_SYMBOL(strncpy);
+#endif
+
+#ifndef __HAVE_ARCH_STRLCPY
+/**
+ * strlcpy - Copy a %NUL terminated string into a sized buffer
+ * @dest: Where to copy the string to
+ * @src: Where to copy the string from
+ * @size: size of destination buffer
+ *
+ * Compatible with *BSD: the result is always a valid
+ * NUL-terminated string that fits in the buffer (unless,
+ * of course, the buffer size is zero). It does not pad
+ * out the result like strncpy() does.
+ */
+size_t strlcpy(char *dest, const char *src, size_t size)
+{
+	size_t ret = strlen(src);
+
+	if (size) {
+		size_t len = (ret >= size) ? size - 1 : ret;
+		memcpy(dest, src, len);
+		dest[len] = '\0';
+	}
+	return ret;
+}
+EXPORT_SYMBOL(strlcpy);
+#endif
+
+#ifndef __HAVE_ARCH_STRCAT
+/**
+ * strcat - Append one %NUL-terminated string to another
+ * @dest: The string to be appended to
+ * @src: The string to append to it
+ */
+#undef strcat
+char *strcat(char *dest, const char *src)
+{
+	char *tmp = dest;
+
+	while (*dest)
+		dest++;
+	while ((*dest++ = *src++) != '\0')
+		;
+	return tmp;
+}
+EXPORT_SYMBOL(strcat);
+#endif
+
+#ifndef __HAVE_ARCH_STRNCAT
+/**
+ * strncat - Append a length-limited, %NUL-terminated string to another
+ * @dest: The string to be appended to
+ * @src: The string to append to it
+ * @count: The maximum numbers of bytes to copy
+ *
+ * Note that in contrast to strncpy(), strncat() ensures the result is
+ * terminated.
+ */
+char *strncat(char *dest, const char *src, size_t count)
+{
+	char *tmp = dest;
+
+	if (count) {
+		while (*dest)
+			dest++;
+		while ((*dest++ = *src++) != 0) {
+			if (--count == 0) {
+				*dest = '\0';
+				break;
+			}
+		}
+	}
+	return tmp;
+}
+EXPORT_SYMBOL(strncat);
+#endif
+
+#ifndef __HAVE_ARCH_STRLCAT
+/**
+ * strlcat - Append a length-limited, %NUL-terminated string to another
+ * @dest: The string to be appended to
+ * @src: The string to append to it
+ * @count: The size of the destination buffer.
+ */
+size_t strlcat(char *dest, const char *src, size_t count)
+{
+	size_t dsize = strlen(dest);
+	size_t len = strlen(src);
+	size_t res = dsize + len;
+
+	/* This would be a bug */
+	BUG_ON(dsize >= count);
+
+	dest += dsize;
+	count -= dsize;
+	if (len >= count)
+		len = count-1;
+	memcpy(dest, src, len);
+	dest[len] = 0;
+	return res;
+}
+EXPORT_SYMBOL(strlcat);
+#endif
+
+#ifndef __HAVE_ARCH_STRCMP
+/**
+ * strcmp - Compare two strings
+ * @cs: One string
+ * @ct: Another string
+ */
+#undef strcmp
+int strcmp(const char *cs, const char *ct)
+{
+	signed char __res;
+
+	while (1) {
+		if ((__res = *cs - *ct++) != 0 || !*cs++)
+			break;
+	}
+	return __res;
+}
+EXPORT_SYMBOL(strcmp);
+#endif
+
+#ifndef __HAVE_ARCH_STRNCMP
+/**
+ * strncmp - Compare two length-limited strings
+ * @cs: One string
+ * @ct: Another string
+ * @count: The maximum number of bytes to compare
+ */
+int strncmp(const char *cs, const char *ct, size_t count)
+{
+	signed char __res = 0;
+
+	while (count) {
+		if ((__res = *cs - *ct++) != 0 || !*cs++)
+			break;
+		count--;
+	}
+	return __res;
+}
+EXPORT_SYMBOL(strncmp);
+#endif
+
+#ifndef __HAVE_ARCH_STRCHR
+/**
+ * strchr - Find the first occurrence of a character in a string
+ * @s: The string to be searched
+ * @c: The character to search for
+ */
+char *strchr(const char *s, int c)
+{
+	for (; *s != (char)c; ++s)
+		if (*s == '\0')
+			return NULL;
+	return (char *)s;
+}
+EXPORT_SYMBOL(strchr);
+#endif
+
+#ifndef __HAVE_ARCH_STRRCHR
+/**
+ * strrchr - Find the last occurrence of a character in a string
+ * @s: The string to be searched
+ * @c: The character to search for
+ */
+char *strrchr(const char *s, int c)
+{
+       const char *p = s + strlen(s);
+       do {
+           if (*p == (char)c)
+               return (char *)p;
+       } while (--p >= s);
+       return NULL;
+}
+EXPORT_SYMBOL(strrchr);
+#endif
+
+#ifndef __HAVE_ARCH_STRNCHR
+/**
+ * strnchr - Find a character in a length limited string
+ * @s: The string to be searched
+ * @count: The number of characters to be searched
+ * @c: The character to search for
+ */
+char *strnchr(const char *s, size_t count, int c)
+{
+	for (; count-- && *s != '\0'; ++s)
+		if (*s == (char)c)
+			return (char *)s;
+	return NULL;
+}
+EXPORT_SYMBOL(strnchr);
+#endif
+
+/**
+ * strstrip - Removes leading and trailing whitespace from @s.
+ * @s: The string to be stripped.
+ *
+ * Note that the first trailing whitespace is replaced with a %NUL-terminator
+ * in the given string @s. Returns a pointer to the first non-whitespace
+ * character in @s.
+ */
+char *strstrip(char *s)
+{
+	size_t size;
+	char *end;
+
+	size = strlen(s);
+
+	if (!size)
+		return s;
+
+	end = s + size - 1;
+	while (end >= s && isspace(*end))
+		end--;
+	*(end + 1) = '\0';
+
+	while (*s && isspace(*s))
+		s++;
+
+	return s;
+}
+EXPORT_SYMBOL(strstrip);
+
+#ifndef __HAVE_ARCH_STRLEN
+/**
+ * strlen - Find the length of a string
+ * @s: The string to be sized
+ */
+size_t strlen(const char *s)
+{
+	const char *sc;
+
+	for (sc = s; *sc != '\0'; ++sc)
+		/* nothing */;
+	return sc - s;
+}
+EXPORT_SYMBOL(strlen);
+#endif
+
+#ifndef __HAVE_ARCH_STRNLEN
+/**
+ * strnlen - Find the length of a length-limited string
+ * @s: The string to be sized
+ * @count: The maximum number of bytes to search
+ */
+size_t strnlen(const char *s, size_t count)
+{
+	const char *sc;
+
+	for (sc = s; count-- && *sc != '\0'; ++sc)
+		/* nothing */;
+	return sc - s;
+}
+EXPORT_SYMBOL(strnlen);
+#endif
+
+#ifndef __HAVE_ARCH_STRSPN
+/**
+ * strspn - Calculate the length of the initial substring of @s which only contain letters in @accept
+ * @s: The string to be searched
+ * @accept: The string to search for
+ */
+size_t strspn(const char *s, const char *accept)
+{
+	const char *p;
+	const char *a;
+	size_t count = 0;
+
+	for (p = s; *p != '\0'; ++p) {
+		for (a = accept; *a != '\0'; ++a) {
+			if (*p == *a)
+				break;
+		}
+		if (*a == '\0')
+			return count;
+		++count;
+	}
+	return count;
+}
+
+EXPORT_SYMBOL(strspn);
+#endif
+
+#ifndef __HAVE_ARCH_STRCSPN
+/**
+ * strcspn - Calculate the length of the initial substring of @s which does not contain letters in @reject
+ * @s: The string to be searched
+ * @reject: The string to avoid
+ */
+size_t strcspn(const char *s, const char *reject)
+{
+	const char *p;
+	const char *r;
+	size_t count = 0;
+
+	for (p = s; *p != '\0'; ++p) {
+		for (r = reject; *r != '\0'; ++r) {
+			if (*p == *r)
+				return count;
+		}
+		++count;
+	}
+	return count;
+}
+EXPORT_SYMBOL(strcspn);
+#endif
+
+#ifndef __HAVE_ARCH_STRPBRK
+/**
+ * strpbrk - Find the first occurrence of a set of characters
+ * @cs: The string to be searched
+ * @ct: The characters to search for
+ */
+char *strpbrk(const char *cs, const char *ct)
+{
+	const char *sc1, *sc2;
+
+	for (sc1 = cs; *sc1 != '\0'; ++sc1) {
+		for (sc2 = ct; *sc2 != '\0'; ++sc2) {
+			if (*sc1 == *sc2)
+				return (char *)sc1;
+		}
+	}
+	return NULL;
+}
+EXPORT_SYMBOL(strpbrk);
+#endif
+
+#ifndef __HAVE_ARCH_STRSEP
+/**
+ * strsep - Split a string into tokens
+ * @s: The string to be searched
+ * @ct: The characters to search for
+ *
+ * strsep() updates @s to point after the token, ready for the next call.
+ *
+ * It returns empty tokens, too, behaving exactly like the libc function
+ * of that name. In fact, it was stolen from glibc2 and de-fancy-fied.
+ * Same semantics, slimmer shape. ;)
+ */
+char *strsep(char **s, const char *ct)
+{
+	char *sbegin = *s;
+	char *end;
+
+	if (sbegin == NULL)
+		return NULL;
+
+	end = strpbrk(sbegin, ct);
+	if (end)
+		*end++ = '\0';
+	*s = end;
+	return sbegin;
+}
+EXPORT_SYMBOL(strsep);
+#endif
+
+#ifndef __HAVE_ARCH_MEMSET
+/**
+ * memset - Fill a region of memory with the given value
+ * @s: Pointer to the start of the area.
+ * @c: The byte to fill the area with
+ * @count: The size of the area.
+ *
+ * Do not use memset() to access IO space, use memset_io() instead.
+ */
+void *memset(void *s, int c, size_t count)
+{
+	char *xs = s;
+
+	while (count--)
+		*xs++ = c;
+	return s;
+}
+EXPORT_SYMBOL(memset);
+#endif
+
+#ifndef __HAVE_ARCH_MEMCPY
+/**
+ * memcpy - Copy one area of memory to another
+ * @dest: Where to copy to
+ * @src: Where to copy from
+ * @count: The size of the area.
+ *
+ * You should not use this function to access IO space, use memcpy_toio()
+ * or memcpy_fromio() instead.
+ */
+void *memcpy(void *dest, const void *src, size_t count)
+{
+	char *tmp = dest;
+	const char *s = src;
+
+	while (count--)
+		*tmp++ = *s++;
+	return dest;
+}
+EXPORT_SYMBOL(memcpy);
+#endif
+
+#ifndef __HAVE_ARCH_MEMMOVE
+/**
+ * memmove - Copy one area of memory to another
+ * @dest: Where to copy to
+ * @src: Where to copy from
+ * @count: The size of the area.
+ *
+ * Unlike memcpy(), memmove() copes with overlapping areas.
+ */
+void *memmove(void *dest, const void *src, size_t count)
+{
+	char *tmp;
+	const char *s;
+
+	if (dest <= src) {
+		tmp = dest;
+		s = src;
+		while (count--)
+			*tmp++ = *s++;
+	} else {
+		tmp = dest;
+		tmp += count;
+		s = src;
+		s += count;
+		while (count--)
+			*--tmp = *--s;
+	}
+	return dest;
+}
+EXPORT_SYMBOL(memmove);
+#endif
+
+#ifndef __HAVE_ARCH_MEMCMP
+/**
+ * memcmp - Compare two areas of memory
+ * @cs: One area of memory
+ * @ct: Another area of memory
+ * @count: The size of the area.
+ */
+#undef memcmp
+int memcmp(const void *cs, const void *ct, size_t count)
+{
+	const unsigned char *su1, *su2;
+	int res = 0;
+
+	for (su1 = cs, su2 = ct; 0 < count; ++su1, ++su2, count--)
+		if ((res = *su1 - *su2) != 0)
+			break;
+	return res;
+}
+EXPORT_SYMBOL(memcmp);
+#endif
+
+#ifndef __HAVE_ARCH_MEMSCAN
+/**
+ * memscan - Find a character in an area of memory.
+ * @addr: The memory area
+ * @c: The byte to search for
+ * @size: The size of the area.
+ *
+ * returns the address of the first occurrence of @c, or 1 byte past
+ * the area if @c is not found
+ */
+void *memscan(void *addr, int c, size_t size)
+{
+	unsigned char *p = addr;
+
+	while (size) {
+		if (*p == c)
+			return (void *)p;
+		p++;
+		size--;
+	}
+  	return (void *)p;
+}
+EXPORT_SYMBOL(memscan);
+#endif
+
+#ifndef __HAVE_ARCH_STRSTR
+/**
+ * strstr - Find the first substring in a %NUL terminated string
+ * @s1: The string to be searched
+ * @s2: The string to search for
+ */
+char *strstr(const char *s1, const char *s2)
+{
+	int l1, l2;
+
+	l2 = strlen(s2);
+	if (!l2)
+		return (char *)s1;
+	l1 = strlen(s1);
+	while (l1 >= l2) {
+		l1--;
+		if (!memcmp(s1, s2, l2))
+			return (char *)s1;
+		s1++;
+	}
+	return NULL;
+}
+EXPORT_SYMBOL(strstr);
+#endif
+
+#ifndef __HAVE_ARCH_MEMCHR
+/**
+ * memchr - Find a character in an area of memory.
+ * @s: The memory area
+ * @c: The byte to search for
+ * @n: The size of the area.
+ *
+ * returns the address of the first occurrence of @c, or %NULL
+ * if @c is not found
+ */
+void *memchr(const void *s, int c, size_t n)
+{
+	const unsigned char *p = s;
+	while (n-- != 0) {
+        	if ((unsigned char)c == *p++) {
+			return (void *)(p - 1);
+		}
+	}
+	return NULL;
+}
+EXPORT_SYMBOL(memchr);
+#endif

lib/swiotlb.c

@@ -0,0 +1,795 @@
+/*
+ * Dynamic DMA mapping support.
+ *
+ * This implementation is a fallback for platforms that do not support
+ * I/O TLBs (aka DMA address translation hardware).
+ * Copyright (C) 2000 Asit Mallick <Asit.K.Mallick@intel.com>
+ * Copyright (C) 2000 Goutham Rao <goutham.rao@intel.com>
+ * Copyright (C) 2000, 2003 Hewlett-Packard Co
+ *	David Mosberger-Tang <davidm@hpl.hp.com>
+ *
+ * 03/05/07 davidm	Switch from PCI-DMA to generic device DMA API.
+ * 00/12/13 davidm	Rename to swiotlb.c and add mark_clean() to avoid
+ *			unnecessary i-cache flushing.
+ * 04/07/.. ak		Better overflow handling. Assorted fixes.
+ * 05/09/10 linville	Add support for syncing ranges, support syncing for
+ *			DMA_BIDIRECTIONAL mappings, miscellaneous cleanup.
+ */
+
+#include <linux/cache.h>
+#include <linux/dma-mapping.h>
+#include <linux/mm.h>
+#include <linux/module.h>
+#include <linux/spinlock.h>
+#include <linux/string.h>
+#include <linux/types.h>
+#include <linux/ctype.h>
+
+#include <asm/io.h>
+#include <asm/dma.h>
+#include <asm/scatterlist.h>
+
+#include <linux/init.h>
+#include <linux/bootmem.h>
+
+#define OFFSET(val,align) ((unsigned long)	\
+	                   ( (val) & ( (align) - 1)))
+
+#define SG_ENT_VIRT_ADDRESS(sg)	(page_address((sg)->page) + (sg)->offset)
+#define SG_ENT_PHYS_ADDRESS(sg)	virt_to_bus(SG_ENT_VIRT_ADDRESS(sg))
+
+/*
+ * Maximum allowable number of contiguous slabs to map,
+ * must be a power of 2.  What is the appropriate value ?
+ * The complexity of {map,unmap}_single is linearly dependent on this value.
+ */
+#define IO_TLB_SEGSIZE	128
+
+/*
+ * log of the size of each IO TLB slab.  The number of slabs is command line
+ * controllable.
+ */
+#define IO_TLB_SHIFT 11
+
+#define SLABS_PER_PAGE (1 << (PAGE_SHIFT - IO_TLB_SHIFT))
+
+/*
+ * Minimum IO TLB size to bother booting with.  Systems with mainly
+ * 64bit capable cards will only lightly use the swiotlb.  If we can't
+ * allocate a contiguous 1MB, we're probably in trouble anyway.
+ */
+#define IO_TLB_MIN_SLABS ((1<<20) >> IO_TLB_SHIFT)
+
+/*
+ * Enumeration for sync targets
+ */
+enum dma_sync_target {
+	SYNC_FOR_CPU = 0,
+	SYNC_FOR_DEVICE = 1,
+};
+
+int swiotlb_force;
+
+/*
+ * Used to do a quick range check in swiotlb_unmap_single and
+ * swiotlb_sync_single_*, to see if the memory was in fact allocated by this
+ * API.
+ */
+static char *io_tlb_start, *io_tlb_end;
+
+/*
+ * The number of IO TLB blocks (in groups of 64) betweeen io_tlb_start and
+ * io_tlb_end.  This is command line adjustable via setup_io_tlb_npages.
+ */
+static unsigned long io_tlb_nslabs;
+
+/*
+ * When the IOMMU overflows we return a fallback buffer. This sets the size.
+ */
+static unsigned long io_tlb_overflow = 32*1024;
+
+void *io_tlb_overflow_buffer;
+
+/*
+ * This is a free list describing the number of free entries available from
+ * each index
+ */
+static unsigned int *io_tlb_list;
+static unsigned int io_tlb_index;
+
+/*
+ * We need to save away the original address corresponding to a mapped entry
+ * for the sync operations.
+ */
+static unsigned char **io_tlb_orig_addr;
+
+/*
+ * Protect the above data structures in the map and unmap calls
+ */
+static DEFINE_SPINLOCK(io_tlb_lock);
+
+static int __init
+setup_io_tlb_npages(char *str)
+{
+	if (isdigit(*str)) {
+		io_tlb_nslabs = simple_strtoul(str, &str, 0);
+		/* avoid tail segment of size < IO_TLB_SEGSIZE */
+		io_tlb_nslabs = ALIGN(io_tlb_nslabs, IO_TLB_SEGSIZE);
+	}
+	if (*str == ',')
+		++str;
+	if (!strcmp(str, "force"))
+		swiotlb_force = 1;
+	return 1;
+}
+__setup("swiotlb=", setup_io_tlb_npages);
+/* make io_tlb_overflow tunable too? */
+
+/*
+ * Statically reserve bounce buffer space and initialize bounce buffer data
+ * structures for the software IO TLB used to implement the DMA API.
+ */
+void __init
+swiotlb_init_with_default_size(size_t default_size)
+{
+	unsigned long i, bytes;
+
+	if (!io_tlb_nslabs) {
+		io_tlb_nslabs = (default_size >> IO_TLB_SHIFT);
+		io_tlb_nslabs = ALIGN(io_tlb_nslabs, IO_TLB_SEGSIZE);
+	}
+
+	bytes = io_tlb_nslabs << IO_TLB_SHIFT;
+
+	/*
+	 * Get IO TLB memory from the low pages
+	 */
+	io_tlb_start = alloc_bootmem_low_pages(bytes);
+	if (!io_tlb_start)
+		panic("Cannot allocate SWIOTLB buffer");
+	io_tlb_end = io_tlb_start + bytes;
+
+	/*
+	 * Allocate and initialize the free list array.  This array is used
+	 * to find contiguous free memory regions of size up to IO_TLB_SEGSIZE
+	 * between io_tlb_start and io_tlb_end.
+	 */
+	io_tlb_list = alloc_bootmem(io_tlb_nslabs * sizeof(int));
+	for (i = 0; i < io_tlb_nslabs; i++)
+ 		io_tlb_list[i] = IO_TLB_SEGSIZE - OFFSET(i, IO_TLB_SEGSIZE);
+	io_tlb_index = 0;
+	io_tlb_orig_addr = alloc_bootmem(io_tlb_nslabs * sizeof(char *));
+
+	/*
+	 * Get the overflow emergency buffer
+	 */
+	io_tlb_overflow_buffer = alloc_bootmem_low(io_tlb_overflow);
+	if (!io_tlb_overflow_buffer)
+		panic("Cannot allocate SWIOTLB overflow buffer!\n");
+
+	printk(KERN_INFO "Placing software IO TLB between 0x%lx - 0x%lx\n",
+	       virt_to_bus(io_tlb_start), virt_to_bus(io_tlb_end));
+}
+
+void __init
+swiotlb_init(void)
+{
+	swiotlb_init_with_default_size(64 * (1<<20));	/* default to 64MB */
+}
+
+/*
+ * Systems with larger DMA zones (those that don't support ISA) can
+ * initialize the swiotlb later using the slab allocator if needed.
+ * This should be just like above, but with some error catching.
+ */
+int
+swiotlb_late_init_with_default_size(size_t default_size)
+{
+	unsigned long i, bytes, req_nslabs = io_tlb_nslabs;
+	unsigned int order;
+
+	if (!io_tlb_nslabs) {
+		io_tlb_nslabs = (default_size >> IO_TLB_SHIFT);
+		io_tlb_nslabs = ALIGN(io_tlb_nslabs, IO_TLB_SEGSIZE);
+	}
+
+	/*
+	 * Get IO TLB memory from the low pages
+	 */
+	order = get_order(io_tlb_nslabs << IO_TLB_SHIFT);
+	io_tlb_nslabs = SLABS_PER_PAGE << order;
+	bytes = io_tlb_nslabs << IO_TLB_SHIFT;
+
+	while ((SLABS_PER_PAGE << order) > IO_TLB_MIN_SLABS) {
+		io_tlb_start = (char *)__get_free_pages(GFP_DMA | __GFP_NOWARN,
+		                                        order);
+		if (io_tlb_start)
+			break;
+		order--;
+	}
+
+	if (!io_tlb_start)
+		goto cleanup1;
+
+	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;
+	}
+	io_tlb_end = io_tlb_start + bytes;
+	memset(io_tlb_start, 0, bytes);
+
+	/*
+	 * Allocate and initialize the free list array.  This array is used
+	 * to find contiguous free memory regions of size up to IO_TLB_SEGSIZE
+	 * between io_tlb_start and io_tlb_end.
+	 */
+	io_tlb_list = (unsigned int *)__get_free_pages(GFP_KERNEL,
+	                              get_order(io_tlb_nslabs * sizeof(int)));
+	if (!io_tlb_list)
+		goto cleanup2;
+
+	for (i = 0; i < io_tlb_nslabs; i++)
+ 		io_tlb_list[i] = IO_TLB_SEGSIZE - OFFSET(i, IO_TLB_SEGSIZE);
+	io_tlb_index = 0;
+
+	io_tlb_orig_addr = (unsigned char **)__get_free_pages(GFP_KERNEL,
+	                           get_order(io_tlb_nslabs * sizeof(char *)));
+	if (!io_tlb_orig_addr)
+		goto cleanup3;
+
+	memset(io_tlb_orig_addr, 0, io_tlb_nslabs * sizeof(char *));
+
+	/*
+	 * Get the overflow emergency buffer
+	 */
+	io_tlb_overflow_buffer = (void *)__get_free_pages(GFP_DMA,
+	                                          get_order(io_tlb_overflow));
+	if (!io_tlb_overflow_buffer)
+		goto cleanup4;
+
+	printk(KERN_INFO "Placing %luMB software IO TLB between 0x%lx - "
+	       "0x%lx\n", bytes >> 20,
+	       virt_to_bus(io_tlb_start), virt_to_bus(io_tlb_end));
+
+	return 0;
+
+cleanup4:
+	free_pages((unsigned long)io_tlb_orig_addr, get_order(io_tlb_nslabs *
+	                                                      sizeof(char *)));
+	io_tlb_orig_addr = NULL;
+cleanup3:
+	free_pages((unsigned long)io_tlb_list, get_order(io_tlb_nslabs *
+	                                                 sizeof(int)));
+	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;
+	return -ENOMEM;
+}
+
+static int
+address_needs_mapping(struct device *hwdev, dma_addr_t addr)
+{
+	dma_addr_t mask = 0xffffffff;
+	/* If the device has a mask, use it, otherwise default to 32 bits */
+	if (hwdev && hwdev->dma_mask)
+		mask = *hwdev->dma_mask;
+	return (addr & ~mask) != 0;
+}
+
+/*
+ * Allocates bounce buffer and returns its kernel virtual address.
+ */
+static void *
+map_single(struct device *hwdev, char *buffer, size_t size, int dir)
+{
+	unsigned long flags;
+	char *dma_addr;
+	unsigned int nslots, stride, index, wrap;
+	int i;
+
+	/*
+	 * For mappings greater than a page, we limit the stride (and
+	 * hence alignment) to a page size.
+	 */
+	nslots = ALIGN(size, 1 << IO_TLB_SHIFT) >> IO_TLB_SHIFT;
+	if (size > PAGE_SIZE)
+		stride = (1 << (PAGE_SHIFT - IO_TLB_SHIFT));
+	else
+		stride = 1;
+
+	BUG_ON(!nslots);
+
+	/*
+	 * Find suitable number of IO TLB entries size that will fit this
+	 * request and allocate a buffer from that IO TLB pool.
+	 */
+	spin_lock_irqsave(&io_tlb_lock, flags);
+	{
+		wrap = index = ALIGN(io_tlb_index, stride);
+
+		if (index >= io_tlb_nslabs)
+			wrap = index = 0;
+
+		do {
+			/*
+			 * If we find a slot that indicates we have 'nslots'
+			 * number of contiguous buffers, we allocate the
+			 * buffers from that slot and mark the entries as '0'
+			 * indicating unavailable.
+			 */
+			if (io_tlb_list[index] >= nslots) {
+				int count = 0;
+
+				for (i = index; i < (int) (index + nslots); i++)
+					io_tlb_list[i] = 0;
+				for (i = index - 1; (OFFSET(i, IO_TLB_SEGSIZE) != IO_TLB_SEGSIZE -1) && io_tlb_list[i]; i--)
+					io_tlb_list[i] = ++count;
+				dma_addr = io_tlb_start + (index << IO_TLB_SHIFT);
+
+				/*
+				 * Update the indices to avoid searching in
+				 * the next round.
+				 */
+				io_tlb_index = ((index + nslots) < io_tlb_nslabs
+						? (index + nslots) : 0);
+
+				goto found;
+			}
+			index += stride;
+			if (index >= io_tlb_nslabs)
+				index = 0;
+		} while (index != wrap);
+
+		spin_unlock_irqrestore(&io_tlb_lock, flags);
+		return NULL;
+	}
+  found:
+	spin_unlock_irqrestore(&io_tlb_lock, flags);
+
+	/*
+	 * Save away the mapping from the original address to the DMA address.
+	 * This is needed when we sync the memory.  Then we sync the buffer if
+	 * needed.
+	 */
+	io_tlb_orig_addr[index] = buffer;
+	if (dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL)
+		memcpy(dma_addr, buffer, size);
+
+	return dma_addr;
+}
+
+/*
+ * dma_addr is the kernel virtual address of the bounce buffer to unmap.
+ */
+static void
+unmap_single(struct device *hwdev, char *dma_addr, size_t size, int dir)
+{
+	unsigned long flags;
+	int i, count, nslots = ALIGN(size, 1 << IO_TLB_SHIFT) >> IO_TLB_SHIFT;
+	int index = (dma_addr - io_tlb_start) >> IO_TLB_SHIFT;
+	char *buffer = io_tlb_orig_addr[index];
+
+	/*
+	 * First, sync the memory before unmapping the entry
+	 */
+	if (buffer && ((dir == DMA_FROM_DEVICE) || (dir == DMA_BIDIRECTIONAL)))
+		/*
+		 * bounce... copy the data back into the original buffer * and
+		 * delete the bounce buffer.
+		 */
+		memcpy(buffer, dma_addr, size);
+
+	/*
+	 * Return the buffer to the free list by setting the corresponding
+	 * entries to indicate the number of contigous entries available.
+	 * While returning the entries to the free list, we merge the entries
+	 * with slots below and above the pool being returned.
+	 */
+	spin_lock_irqsave(&io_tlb_lock, flags);
+	{
+		count = ((index + nslots) < ALIGN(index + 1, IO_TLB_SEGSIZE) ?
+			 io_tlb_list[index + nslots] : 0);
+		/*
+		 * Step 1: return the slots to the free list, merging the
+		 * slots with superceeding slots
+		 */
+		for (i = index + nslots - 1; i >= index; i--)
+			io_tlb_list[i] = ++count;
+		/*
+		 * Step 2: merge the returned slots with the preceding slots,
+		 * if available (non zero)
+		 */
+		for (i = index - 1; (OFFSET(i, IO_TLB_SEGSIZE) != IO_TLB_SEGSIZE -1) && io_tlb_list[i]; i--)
+			io_tlb_list[i] = ++count;
+	}
+	spin_unlock_irqrestore(&io_tlb_lock, flags);
+}
+
+static void
+sync_single(struct device *hwdev, char *dma_addr, size_t size,
+	    int dir, int target)
+{
+	int index = (dma_addr - io_tlb_start) >> IO_TLB_SHIFT;
+	char *buffer = io_tlb_orig_addr[index];
+
+	switch (target) {
+	case SYNC_FOR_CPU:
+		if (likely(dir == DMA_FROM_DEVICE || dir == DMA_BIDIRECTIONAL))
+			memcpy(buffer, dma_addr, size);
+		else
+			BUG_ON(dir != DMA_TO_DEVICE);
+		break;
+	case SYNC_FOR_DEVICE:
+		if (likely(dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL))
+			memcpy(dma_addr, buffer, size);
+		else
+			BUG_ON(dir != DMA_FROM_DEVICE);
+		break;
+	default:
+		BUG();
+	}
+}
+
+void *
+swiotlb_alloc_coherent(struct device *hwdev, size_t size,
+		       dma_addr_t *dma_handle, gfp_t flags)
+{
+	dma_addr_t dev_addr;
+	void *ret;
+	int order = get_order(size);
+
+	/*
+	 * XXX fix me: the DMA API should pass us an explicit DMA mask
+	 * instead, or use ZONE_DMA32 (ia64 overloads ZONE_DMA to be a ~32
+	 * bit range instead of a 16MB one).
+	 */
+	flags |= GFP_DMA;
+
+	ret = (void *)__get_free_pages(flags, order);
+	if (ret && address_needs_mapping(hwdev, virt_to_bus(ret))) {
+		/*
+		 * The allocated memory isn't reachable by the device.
+		 * Fall back on swiotlb_map_single().
+		 */
+		free_pages((unsigned long) ret, order);
+		ret = NULL;
+	}
+	if (!ret) {
+		/*
+		 * We are either out of memory or the device can't DMA
+		 * to GFP_DMA memory; fall back on
+		 * swiotlb_map_single(), which will grab memory from
+		 * the lowest available address range.
+		 */
+		dma_addr_t handle;
+		handle = swiotlb_map_single(NULL, NULL, size, DMA_FROM_DEVICE);
+		if (swiotlb_dma_mapping_error(handle))
+			return NULL;
+
+		ret = bus_to_virt(handle);
+	}
+
+	memset(ret, 0, size);
+	dev_addr = virt_to_bus(ret);
+
+	/* Confirm address can be DMA'd by device */
+	if (address_needs_mapping(hwdev, dev_addr)) {
+		printk("hwdev DMA mask = 0x%016Lx, dev_addr = 0x%016Lx\n",
+		       (unsigned long long)*hwdev->dma_mask,
+		       (unsigned long long)dev_addr);
+		panic("swiotlb_alloc_coherent: allocated memory is out of "
+		      "range for device");
+	}
+	*dma_handle = dev_addr;
+	return ret;
+}
+
+void
+swiotlb_free_coherent(struct device *hwdev, size_t size, void *vaddr,
+		      dma_addr_t dma_handle)
+{
+	if (!(vaddr >= (void *)io_tlb_start
+                    && vaddr < (void *)io_tlb_end))
+		free_pages((unsigned long) vaddr, get_order(size));
+	else
+		/* DMA_TO_DEVICE to avoid memcpy in unmap_single */
+		swiotlb_unmap_single (hwdev, dma_handle, size, DMA_TO_DEVICE);
+}
+
+static void
+swiotlb_full(struct device *dev, size_t size, int dir, int do_panic)
+{
+	/*
+	 * Ran out of IOMMU space for this operation. This is very bad.
+	 * Unfortunately the drivers cannot handle this operation properly.
+	 * unless they check for dma_mapping_error (most don't)
+	 * When the mapping is small enough return a static buffer to limit
+	 * the damage, or panic when the transfer is too big.
+	 */
+	printk(KERN_ERR "DMA: Out of SW-IOMMU space for %zu bytes at "
+	       "device %s\n", size, dev ? dev->bus_id : "?");
+
+	if (size > io_tlb_overflow && do_panic) {
+		if (dir == DMA_FROM_DEVICE || dir == DMA_BIDIRECTIONAL)
+			panic("DMA: Memory would be corrupted\n");
+		if (dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL)
+			panic("DMA: Random memory would be DMAed\n");
+	}
+}
+
+/*
+ * Map a single buffer of the indicated size for DMA in streaming mode.  The
+ * physical address to use is returned.
+ *
+ * Once the device is given the dma address, the device owns this memory until
+ * either swiotlb_unmap_single or swiotlb_dma_sync_single is performed.
+ */
+dma_addr_t
+swiotlb_map_single(struct device *hwdev, void *ptr, size_t size, int dir)
+{
+	dma_addr_t dev_addr = virt_to_bus(ptr);
+	void *map;
+
+	BUG_ON(dir == DMA_NONE);
+	/*
+	 * If the pointer passed in happens to be in the device's DMA window,
+	 * we can safely return the device addr and not worry about bounce
+	 * buffering it.
+	 */
+	if (!address_needs_mapping(hwdev, dev_addr) && !swiotlb_force)
+		return dev_addr;
+
+	/*
+	 * Oh well, have to allocate and map a bounce buffer.
+	 */
+	map = map_single(hwdev, ptr, size, dir);
+	if (!map) {
+		swiotlb_full(hwdev, size, dir, 1);
+		map = io_tlb_overflow_buffer;
+	}
+
+	dev_addr = virt_to_bus(map);
+
+	/*
+	 * Ensure that the address returned is DMA'ble
+	 */
+	if (address_needs_mapping(hwdev, dev_addr))
+		panic("map_single: bounce buffer is not DMA'ble");
+
+	return dev_addr;
+}
+
+/*
+ * Unmap a single streaming mode DMA translation.  The dma_addr and size must
+ * match what was provided for in a previous swiotlb_map_single call.  All
+ * other usages are undefined.
+ *
+ * After this call, reads by the cpu to the buffer are guaranteed to see
+ * whatever the device wrote there.
+ */
+void
+swiotlb_unmap_single(struct device *hwdev, dma_addr_t dev_addr, size_t size,
+		     int dir)
+{
+	char *dma_addr = bus_to_virt(dev_addr);
+
+	BUG_ON(dir == DMA_NONE);
+	if (dma_addr >= io_tlb_start && dma_addr < io_tlb_end)
+		unmap_single(hwdev, dma_addr, size, dir);
+	else if (dir == DMA_FROM_DEVICE)
+		dma_mark_clean(dma_addr, size);
+}
+
+/*
+ * Make physical memory consistent for a single streaming mode DMA translation
+ * after a transfer.
+ *
+ * If you perform a swiotlb_map_single() but wish to interrogate the buffer
+ * using the cpu, yet do not wish to teardown the dma mapping, you must
+ * call this function before doing so.  At the next point you give the dma
+ * address back to the card, you must first perform a
+ * swiotlb_dma_sync_for_device, and then the device again owns the buffer
+ */
+static void
+swiotlb_sync_single(struct device *hwdev, dma_addr_t dev_addr,
+		    size_t size, int dir, int target)
+{
+	char *dma_addr = bus_to_virt(dev_addr);
+
+	BUG_ON(dir == DMA_NONE);
+	if (dma_addr >= io_tlb_start && dma_addr < io_tlb_end)
+		sync_single(hwdev, dma_addr, size, dir, target);
+	else if (dir == DMA_FROM_DEVICE)
+		dma_mark_clean(dma_addr, size);
+}
+
+void
+swiotlb_sync_single_for_cpu(struct device *hwdev, dma_addr_t dev_addr,
+			    size_t size, int dir)
+{
+	swiotlb_sync_single(hwdev, dev_addr, size, dir, SYNC_FOR_CPU);
+}
+
+void
+swiotlb_sync_single_for_device(struct device *hwdev, dma_addr_t dev_addr,
+			       size_t size, int dir)
+{
+	swiotlb_sync_single(hwdev, dev_addr, size, dir, SYNC_FOR_DEVICE);
+}
+
+/*
+ * Same as above, but for a sub-range of the mapping.
+ */
+static void
+swiotlb_sync_single_range(struct device *hwdev, dma_addr_t dev_addr,
+			  unsigned long offset, size_t size,
+			  int dir, int target)
+{
+	char *dma_addr = bus_to_virt(dev_addr) + offset;
+
+	BUG_ON(dir == DMA_NONE);
+	if (dma_addr >= io_tlb_start && dma_addr < io_tlb_end)
+		sync_single(hwdev, dma_addr, size, dir, target);
+	else if (dir == DMA_FROM_DEVICE)
+		dma_mark_clean(dma_addr, size);
+}
+
+void
+swiotlb_sync_single_range_for_cpu(struct device *hwdev, dma_addr_t dev_addr,
+				  unsigned long offset, size_t size, int dir)
+{
+	swiotlb_sync_single_range(hwdev, dev_addr, offset, size, dir,
+				  SYNC_FOR_CPU);
+}
+
+void
+swiotlb_sync_single_range_for_device(struct device *hwdev, dma_addr_t dev_addr,
+				     unsigned long offset, size_t size, int dir)
+{
+	swiotlb_sync_single_range(hwdev, dev_addr, offset, size, dir,
+				  SYNC_FOR_DEVICE);
+}
+
+/*
+ * Map a set of buffers described by scatterlist in streaming mode for DMA.
+ * This is the scatter-gather version of the above swiotlb_map_single
+ * interface.  Here the scatter gather list elements are each tagged with the
+ * appropriate dma address and length.  They are obtained via
+ * sg_dma_{address,length}(SG).
+ *
+ * NOTE: An implementation may be able to use a smaller number of
+ *       DMA address/length pairs than there are SG table elements.
+ *       (for example via virtual mapping capabilities)
+ *       The routine returns the number of addr/length pairs actually
+ *       used, at most nents.
+ *
+ * Device ownership issues as mentioned above for swiotlb_map_single are the
+ * same here.
+ */
+int
+swiotlb_map_sg(struct device *hwdev, struct scatterlist *sg, int nelems,
+	       int dir)
+{
+	void *addr;
+	dma_addr_t dev_addr;
+	int i;
+
+	BUG_ON(dir == DMA_NONE);
+
+	for (i = 0; i < nelems; i++, sg++) {
+		addr = SG_ENT_VIRT_ADDRESS(sg);
+		dev_addr = virt_to_bus(addr);
+		if (swiotlb_force || address_needs_mapping(hwdev, dev_addr)) {
+			void *map = map_single(hwdev, addr, sg->length, dir);
+			if (!map) {
+				/* Don't panic here, we expect map_sg users
+				   to do proper error handling. */
+				swiotlb_full(hwdev, sg->length, dir, 0);
+				swiotlb_unmap_sg(hwdev, sg - i, i, dir);
+				sg[0].dma_length = 0;
+				return 0;
+			}
+			sg->dma_address = virt_to_bus(map);
+		} else
+			sg->dma_address = dev_addr;
+		sg->dma_length = sg->length;
+	}
+	return nelems;
+}
+
+/*
+ * Unmap a set of streaming mode DMA translations.  Again, cpu read rules
+ * concerning calls here are the same as for swiotlb_unmap_single() above.
+ */
+void
+swiotlb_unmap_sg(struct device *hwdev, struct scatterlist *sg, int nelems,
+		 int dir)
+{
+	int i;
+
+	BUG_ON(dir == DMA_NONE);
+
+	for (i = 0; i < nelems; i++, sg++)
+		if (sg->dma_address != SG_ENT_PHYS_ADDRESS(sg))
+			unmap_single(hwdev, bus_to_virt(sg->dma_address),
+				     sg->dma_length, dir);
+		else if (dir == DMA_FROM_DEVICE)
+			dma_mark_clean(SG_ENT_VIRT_ADDRESS(sg), sg->dma_length);
+}
+
+/*
+ * Make physical memory consistent for a set of streaming mode DMA translations
+ * after a transfer.
+ *
+ * The same as swiotlb_sync_single_* but for a scatter-gather list, same rules
+ * and usage.
+ */
+static void
+swiotlb_sync_sg(struct device *hwdev, struct scatterlist *sg,
+		int nelems, int dir, int target)
+{
+	int i;
+
+	BUG_ON(dir == DMA_NONE);
+
+	for (i = 0; i < nelems; i++, sg++)
+		if (sg->dma_address != SG_ENT_PHYS_ADDRESS(sg))
+			sync_single(hwdev, bus_to_virt(sg->dma_address),
+				    sg->dma_length, dir, target);
+		else if (dir == DMA_FROM_DEVICE)
+			dma_mark_clean(SG_ENT_VIRT_ADDRESS(sg), sg->dma_length);
+}
+
+void
+swiotlb_sync_sg_for_cpu(struct device *hwdev, struct scatterlist *sg,
+			int nelems, int dir)
+{
+	swiotlb_sync_sg(hwdev, sg, nelems, dir, SYNC_FOR_CPU);
+}
+
+void
+swiotlb_sync_sg_for_device(struct device *hwdev, struct scatterlist *sg,
+			   int nelems, int dir)
+{
+	swiotlb_sync_sg(hwdev, sg, nelems, dir, SYNC_FOR_DEVICE);
+}
+
+int
+swiotlb_dma_mapping_error(dma_addr_t dma_addr)
+{
+	return (dma_addr == virt_to_bus(io_tlb_overflow_buffer));
+}
+
+/*
+ * Return whether the given device DMA address mask can be supported
+ * properly.  For example, if your device can only drive the low 24-bits
+ * during bus mastering, then you would pass 0x00ffffff as the mask to
+ * this function.
+ */
+int
+swiotlb_dma_supported(struct device *hwdev, u64 mask)
+{
+	return virt_to_bus(io_tlb_end - 1) <= mask;
+}
+
+EXPORT_SYMBOL(swiotlb_init);
+EXPORT_SYMBOL(swiotlb_map_single);
+EXPORT_SYMBOL(swiotlb_unmap_single);
+EXPORT_SYMBOL(swiotlb_map_sg);
+EXPORT_SYMBOL(swiotlb_unmap_sg);
+EXPORT_SYMBOL(swiotlb_sync_single_for_cpu);
+EXPORT_SYMBOL(swiotlb_sync_single_for_device);
+EXPORT_SYMBOL_GPL(swiotlb_sync_single_range_for_cpu);
+EXPORT_SYMBOL_GPL(swiotlb_sync_single_range_for_device);
+EXPORT_SYMBOL(swiotlb_sync_sg_for_cpu);
+EXPORT_SYMBOL(swiotlb_sync_sg_for_device);
+EXPORT_SYMBOL(swiotlb_dma_mapping_error);
+EXPORT_SYMBOL(swiotlb_alloc_coherent);
+EXPORT_SYMBOL(swiotlb_free_coherent);
+EXPORT_SYMBOL(swiotlb_dma_supported);

lib/textsearch.c

@@ -0,0 +1,316 @@
+/*
+ * lib/textsearch.c	Generic text search interface
+ *
+ *		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.
+ *
+ * Authors:	Thomas Graf <tgraf@suug.ch>
+ * 		Pablo Neira Ayuso <pablo@eurodev.net>
+ *
+ * ==========================================================================
+ *
+ * INTRODUCTION
+ *
+ *   The textsearch infrastructure provides text searching facitilies for
+ *   both linear and non-linear data. Individual search algorithms are
+ *   implemented in modules and chosen by the user.
+ *
+ * ARCHITECTURE
+ *
+ *      User
+ *     +----------------+
+ *     |        finish()|<--------------(6)-----------------+
+ *     |get_next_block()|<--------------(5)---------------+ |
+ *     |                |                     Algorithm   | |
+ *     |                |                    +------------------------------+
+ *     |                |                    |  init()   find()   destroy() |
+ *     |                |                    +------------------------------+
+ *     |                |       Core API           ^       ^          ^
+ *     |                |      +---------------+  (2)     (4)        (8)
+ *     |             (1)|----->| prepare()     |---+       |          |
+ *     |             (3)|----->| find()/next() |-----------+          |
+ *     |             (7)|----->| destroy()     |----------------------+
+ *     +----------------+      +---------------+
+ *  
+ *   (1) User configures a search by calling _prepare() specifying the
+ *       search parameters such as the pattern and algorithm name.
+ *   (2) Core requests the algorithm to allocate and initialize a search
+ *       configuration according to the specified parameters.
+ *   (3) User starts the search(es) by calling _find() or _next() to
+ *       fetch subsequent occurrences. A state variable is provided
+ *       to the algorithm to store persistent variables.
+ *   (4) Core eventually resets the search offset and forwards the find()
+ *       request to the algorithm.
+ *   (5) Algorithm calls get_next_block() provided by the user continously
+ *       to fetch the data to be searched in block by block.
+ *   (6) Algorithm invokes finish() after the last call to get_next_block
+ *       to clean up any leftovers from get_next_block. (Optional)
+ *   (7) User destroys the configuration by calling _destroy().
+ *   (8) Core notifies the algorithm to destroy algorithm specific
+ *       allocations. (Optional)
+ *
+ * USAGE
+ *
+ *   Before a search can be performed, a configuration must be created
+ *   by calling textsearch_prepare() specyfing the searching algorithm and
+ *   the pattern to look for. The returned configuration may then be used
+ *   for an arbitary amount of times and even in parallel as long as a
+ *   separate struct ts_state variable is provided to every instance.
+ *
+ *   The actual search is performed by either calling textsearch_find_-
+ *   continuous() for linear data or by providing an own get_next_block()
+ *   implementation and calling textsearch_find(). Both functions return
+ *   the position of the first occurrence of the patern or UINT_MAX if
+ *   no match was found. Subsequent occurences can be found by calling
+ *   textsearch_next() regardless of the linearity of the data.
+ *
+ *   Once you're done using a configuration it must be given back via
+ *   textsearch_destroy.
+ *
+ * EXAMPLE
+ *
+ *   int pos;
+ *   struct ts_config *conf;
+ *   struct ts_state state;
+ *   const char *pattern = "chicken";
+ *   const char *example = "We dance the funky chicken";
+ *
+ *   conf = textsearch_prepare("kmp", pattern, strlen(pattern),
+ *                             GFP_KERNEL, TS_AUTOLOAD);
+ *   if (IS_ERR(conf)) {
+ *       err = PTR_ERR(conf);
+ *       goto errout;
+ *   }
+ *
+ *   pos = textsearch_find_continuous(conf, &state, example, strlen(example));
+ *   if (pos != UINT_MAX)
+ *       panic("Oh my god, dancing chickens at %d\n", pos);
+ *
+ *   textsearch_destroy(conf);
+ *
+ * ==========================================================================
+ */
+
+#include <linux/module.h>
+#include <linux/types.h>
+#include <linux/string.h>
+#include <linux/init.h>
+#include <linux/rcupdate.h>
+#include <linux/err.h>
+#include <linux/textsearch.h>
+
+static LIST_HEAD(ts_ops);
+static DEFINE_SPINLOCK(ts_mod_lock);
+
+static inline struct ts_ops *lookup_ts_algo(const char *name)
+{
+	struct ts_ops *o;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(o, &ts_ops, list) {
+		if (!strcmp(name, o->name)) {
+			if (!try_module_get(o->owner))
+				o = NULL;
+			rcu_read_unlock();
+			return o;
+		}
+	}
+	rcu_read_unlock();
+
+	return NULL;
+}
+
+/**
+ * textsearch_register - register a textsearch module
+ * @ops: operations lookup table
+ *
+ * This function must be called by textsearch modules to announce
+ * their presence. The specified &@ops must have %name set to a
+ * unique identifier and the callbacks find(), init(), get_pattern(),
+ * and get_pattern_len() must be implemented.
+ *
+ * Returns 0 or -EEXISTS if another module has already registered
+ * with same name.
+ */
+int textsearch_register(struct ts_ops *ops)
+{
+	int err = -EEXIST;
+	struct ts_ops *o;
+
+	if (ops->name == NULL || ops->find == NULL || ops->init == NULL ||
+	    ops->get_pattern == NULL || ops->get_pattern_len == NULL)
+		return -EINVAL;
+
+	spin_lock(&ts_mod_lock);
+	list_for_each_entry(o, &ts_ops, list) {
+		if (!strcmp(ops->name, o->name))
+			goto errout;
+	}
+
+	list_add_tail_rcu(&ops->list, &ts_ops);
+	err = 0;
+errout:
+	spin_unlock(&ts_mod_lock);
+	return err;
+}
+
+/**
+ * textsearch_unregister - unregister a textsearch module
+ * @ops: operations lookup table
+ *
+ * This function must be called by textsearch modules to announce
+ * their disappearance for examples when the module gets unloaded.
+ * The &ops parameter must be the same as the one during the
+ * registration.
+ *
+ * Returns 0 on success or -ENOENT if no matching textsearch
+ * registration was found.
+ */
+int textsearch_unregister(struct ts_ops *ops)
+{
+	int err = 0;
+	struct ts_ops *o;
+
+	spin_lock(&ts_mod_lock);
+	list_for_each_entry(o, &ts_ops, list) {
+		if (o == ops) {
+			list_del_rcu(&o->list);
+			goto out;
+		}
+	}
+
+	err = -ENOENT;
+out:
+	spin_unlock(&ts_mod_lock);
+	return err;
+}
+
+struct ts_linear_state
+{
+	unsigned int	len;
+	const void	*data;
+};
+
+static unsigned int get_linear_data(unsigned int consumed, const u8 **dst,
+				    struct ts_config *conf,
+				    struct ts_state *state)
+{
+	struct ts_linear_state *st = (struct ts_linear_state *) state->cb;
+
+	if (likely(consumed < st->len)) {
+		*dst = st->data + consumed;
+		return st->len - consumed;
+	}
+
+	return 0;
+}
+
+/**
+ * textsearch_find_continuous - search a pattern in continuous/linear data
+ * @conf: search configuration
+ * @state: search state
+ * @data: data to search in
+ * @len: length of data
+ *
+ * A simplified version of textsearch_find() for continuous/linear data.
+ * Call textsearch_next() to retrieve subsequent matches.
+ *
+ * Returns the position of first occurrence of the pattern or
+ * %UINT_MAX if no occurrence was found.
+ */ 
+unsigned int textsearch_find_continuous(struct ts_config *conf,
+					struct ts_state *state,
+					const void *data, unsigned int len)
+{
+	struct ts_linear_state *st = (struct ts_linear_state *) state->cb;
+
+	conf->get_next_block = get_linear_data;
+	st->data = data;
+	st->len = len;
+
+	return textsearch_find(conf, state);
+}
+
+/**
+ * textsearch_prepare - Prepare a search
+ * @algo: name of search algorithm
+ * @pattern: pattern data
+ * @len: length of pattern
+ * @gfp_mask: allocation mask
+ * @flags: search flags
+ *
+ * Looks up the search algorithm module and creates a new textsearch
+ * configuration for the specified pattern. Upon completion all
+ * necessary refcnts are held and the configuration must be put back
+ * using textsearch_put() after usage.
+ *
+ * Note: The format of the pattern may not be compatible between
+ *       the various search algorithms.
+ *
+ * Returns a new textsearch configuration according to the specified
+ *         parameters or a ERR_PTR().
+ */
+struct ts_config *textsearch_prepare(const char *algo, const void *pattern,
+				     unsigned int len, gfp_t gfp_mask, int flags)
+{
+	int err = -ENOENT;
+	struct ts_config *conf;
+	struct ts_ops *ops;
+	
+	ops = lookup_ts_algo(algo);
+#ifdef CONFIG_KMOD
+	/*
+	 * Why not always autoload you may ask. Some users are
+	 * in a situation where requesting a module may deadlock,
+	 * especially when the module is located on a NFS mount.
+	 */
+	if (ops == NULL && flags & TS_AUTOLOAD) {
+		request_module("ts_%s", algo);
+		ops = lookup_ts_algo(algo);
+	}
+#endif
+
+	if (ops == NULL)
+		goto errout;
+
+	conf = ops->init(pattern, len, gfp_mask);
+	if (IS_ERR(conf)) {
+		err = PTR_ERR(conf);
+		goto errout;
+	}
+
+	conf->ops = ops;
+	return conf;
+
+errout:
+	if (ops)
+		module_put(ops->owner);
+		
+	return ERR_PTR(err);
+}
+
+/**
+ * textsearch_destroy - destroy a search configuration
+ * @conf: search configuration
+ *
+ * Releases all references of the configuration and frees
+ * up the memory.
+ */
+void textsearch_destroy(struct ts_config *conf)
+{
+	if (conf->ops) {
+		if (conf->ops->destroy)
+			conf->ops->destroy(conf);
+		module_put(conf->ops->owner);
+	}
+
+	kfree(conf);
+}
+
+EXPORT_SYMBOL(textsearch_register);
+EXPORT_SYMBOL(textsearch_unregister);
+EXPORT_SYMBOL(textsearch_prepare);
+EXPORT_SYMBOL(textsearch_find_continuous);
+EXPORT_SYMBOL(textsearch_destroy);

lib/ts_bm.c

@@ -0,0 +1,193 @@
+/*
+ * lib/ts_bm.c		Boyer-Moore text search implementation
+ *
+ *		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.
+ *
+ * Authors:	Pablo Neira Ayuso <pablo@eurodev.net>
+ *
+ * ==========================================================================
+ * 
+ *   Implements Boyer-Moore string matching algorithm:
+ *
+ *   [1] A Fast String Searching Algorithm, R.S. Boyer and Moore.
+ *       Communications of the Association for Computing Machinery, 
+ *       20(10), 1977, pp. 762-772.
+ *       http://www.cs.utexas.edu/users/moore/publications/fstrpos.pdf
+ *
+ *   [2] Handbook of Exact String Matching Algorithms, Thierry Lecroq, 2004
+ *       http://www-igm.univ-mlv.fr/~lecroq/string/string.pdf
+ *
+ *   Note: Since Boyer-Moore (BM) performs searches for matchings from right 
+ *   to left, it's still possible that a matching could be spread over 
+ *   multiple blocks, in that case this algorithm won't find any coincidence.
+ *   
+ *   If you're willing to ensure that such thing won't ever happen, use the
+ *   Knuth-Pratt-Morris (KMP) implementation instead. In conclusion, choose 
+ *   the proper string search algorithm depending on your setting. 
+ *
+ *   Say you're using the textsearch infrastructure for filtering, NIDS or 
+ *   any similar security focused purpose, then go KMP. Otherwise, if you 
+ *   really care about performance, say you're classifying packets to apply
+ *   Quality of Service (QoS) policies, and you don't mind about possible
+ *   matchings spread over multiple fragments, then go BM.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/types.h>
+#include <linux/string.h>
+#include <linux/textsearch.h>
+
+/* Alphabet size, use ASCII */
+#define ASIZE 256
+
+#if 0
+#define DEBUGP printk
+#else
+#define DEBUGP(args, format...)
+#endif
+
+struct ts_bm
+{
+	u8 *		pattern;
+	unsigned int	patlen;
+	unsigned int 	bad_shift[ASIZE];
+	unsigned int	good_shift[0];
+};
+
+static unsigned int bm_find(struct ts_config *conf, struct ts_state *state)
+{
+	struct ts_bm *bm = ts_config_priv(conf);
+	unsigned int i, text_len, consumed = state->offset;
+	const u8 *text;
+	int shift = bm->patlen, bs;
+
+	for (;;) {
+		text_len = conf->get_next_block(consumed, &text, conf, state);
+
+		if (unlikely(text_len == 0))
+			break;
+
+		while (shift < text_len) {
+			DEBUGP("Searching in position %d (%c)\n", 
+				shift, text[shift]);
+			for (i = 0; i < bm->patlen; i++) 
+			     if (text[shift-i] != bm->pattern[bm->patlen-1-i])
+				     goto next;
+
+			/* London calling... */
+			DEBUGP("found!\n");
+			return consumed += (shift-(bm->patlen-1));
+
+next:			bs = bm->bad_shift[text[shift-i]];
+
+			/* Now jumping to... */
+			shift = max_t(int, shift-i+bs, shift+bm->good_shift[i]);
+		}
+		consumed += text_len;
+	}
+
+	return UINT_MAX;
+}
+
+static int subpattern(u8 *pattern, int i, int j, int g)
+{
+	int x = i+g-1, y = j+g-1, ret = 0;
+
+	while(pattern[x--] == pattern[y--]) {
+		if (y < 0) {
+			ret = 1;
+			break;
+		}
+		if (--g == 0) {
+			ret = pattern[i-1] != pattern[j-1];
+			break;
+		}
+	}
+
+	return ret;
+}
+
+static void compute_prefix_tbl(struct ts_bm *bm)
+{
+	int i, j, g;
+
+	for (i = 0; i < ASIZE; i++)
+		bm->bad_shift[i] = bm->patlen;
+	for (i = 0; i < bm->patlen - 1; i++)
+		bm->bad_shift[bm->pattern[i]] = bm->patlen - 1 - i;
+
+	/* Compute the good shift array, used to match reocurrences 
+	 * of a subpattern */
+	bm->good_shift[0] = 1;
+	for (i = 1; i < bm->patlen; i++)
+		bm->good_shift[i] = bm->patlen;
+        for (i = bm->patlen-1, g = 1; i > 0; g++, i--) {
+		for (j = i-1; j >= 1-g ; j--)
+			if (subpattern(bm->pattern, i, j, g)) {
+				bm->good_shift[g] = bm->patlen-j-g;
+				break;
+			}
+	}
+}
+
+static struct ts_config *bm_init(const void *pattern, unsigned int len,
+				 gfp_t gfp_mask)
+{
+	struct ts_config *conf;
+	struct ts_bm *bm;
+	unsigned int prefix_tbl_len = len * sizeof(unsigned int);
+	size_t priv_size = sizeof(*bm) + len + prefix_tbl_len;
+
+	conf = alloc_ts_config(priv_size, gfp_mask);
+	if (IS_ERR(conf))
+		return conf;
+
+	bm = ts_config_priv(conf);
+	bm->patlen = len;
+	bm->pattern = (u8 *) bm->good_shift + prefix_tbl_len;
+	memcpy(bm->pattern, pattern, len);
+	compute_prefix_tbl(bm);
+
+	return conf;
+}
+
+static void *bm_get_pattern(struct ts_config *conf)
+{
+	struct ts_bm *bm = ts_config_priv(conf);
+	return bm->pattern;
+}
+
+static unsigned int bm_get_pattern_len(struct ts_config *conf)
+{
+	struct ts_bm *bm = ts_config_priv(conf);
+	return bm->patlen;
+}
+
+static struct ts_ops bm_ops = {
+	.name		  = "bm",
+	.find		  = bm_find,
+	.init		  = bm_init,
+	.get_pattern	  = bm_get_pattern,
+	.get_pattern_len  = bm_get_pattern_len,
+	.owner		  = THIS_MODULE,
+	.list		  = LIST_HEAD_INIT(bm_ops.list)
+};
+
+static int __init init_bm(void)
+{
+	return textsearch_register(&bm_ops);
+}
+
+static void __exit exit_bm(void)
+{
+	textsearch_unregister(&bm_ops);
+}
+
+MODULE_LICENSE("GPL");
+
+module_init(init_bm);
+module_exit(exit_bm);

lib/ts_fsm.c

@@ -0,0 +1,337 @@
+/*
+ * lib/ts_fsm.c	   A naive finite state machine text search approach
+ *
+ *		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.
+ *
+ * Authors:	Thomas Graf <tgraf@suug.ch>
+ *
+ * ==========================================================================
+ *
+ *   A finite state machine consists of n states (struct ts_fsm_token)
+ *   representing the pattern as a finite automation. The data is read
+ *   sequentially on an octet basis. Every state token specifies the number
+ *   of recurrences and the type of value accepted which can be either a
+ *   specific character or ctype based set of characters. The available
+ *   type of recurrences include 1, (0|1), [0 n], and [1 n].
+ *
+ *   The algorithm differs between strict/non-strict mode specifying
+ *   whether the pattern has to start at the first octet. Strict mode
+ *   is enabled by default and can be disabled by inserting
+ *   TS_FSM_HEAD_IGNORE as the first token in the chain.
+ *
+ *   The runtime performance of the algorithm should be around O(n),
+ *   however while in strict mode the average runtime can be better.
+ */
+
+#include <linux/module.h>
+#include <linux/types.h>
+#include <linux/string.h>
+#include <linux/ctype.h>
+#include <linux/textsearch.h>
+#include <linux/textsearch_fsm.h>
+
+struct ts_fsm
+{
+	unsigned int		ntokens;
+	struct ts_fsm_token	tokens[0];
+};
+
+/* other values derived from ctype.h */
+#define _A		0x100 /* ascii */
+#define _W		0x200 /* wildcard */
+
+/* Map to _ctype flags and some magic numbers */
+static const u16 token_map[TS_FSM_TYPE_MAX+1] = {
+	[TS_FSM_SPECIFIC] = 0,
+	[TS_FSM_WILDCARD] = _W,
+	[TS_FSM_CNTRL]	  = _C,
+	[TS_FSM_LOWER]	  = _L,
+	[TS_FSM_UPPER]	  = _U,
+	[TS_FSM_PUNCT]	  = _P,
+	[TS_FSM_SPACE]	  = _S,
+	[TS_FSM_DIGIT]	  = _D,
+	[TS_FSM_XDIGIT]	  = _D | _X,
+	[TS_FSM_ALPHA]	  = _U | _L,
+	[TS_FSM_ALNUM]	  = _U | _L | _D,
+	[TS_FSM_PRINT]	  = _P | _U | _L | _D | _SP,
+	[TS_FSM_GRAPH]	  = _P | _U | _L | _D,
+	[TS_FSM_ASCII]	  = _A,
+};
+
+static const u16 token_lookup_tbl[256] = {
+_W|_A|_C,      _W|_A|_C,     _W|_A|_C,     _W|_A|_C,		/*   0-  3 */
+_W|_A|_C,      _W|_A|_C,     _W|_A|_C,     _W|_A|_C,		/*   4-  7 */
+_W|_A|_C,      _W|_A|_C|_S,  _W|_A|_C|_S,  _W|_A|_C|_S,		/*   8- 11 */
+_W|_A|_C|_S,   _W|_A|_C|_S,  _W|_A|_C,     _W|_A|_C,		/*  12- 15 */
+_W|_A|_C,      _W|_A|_C,     _W|_A|_C,     _W|_A|_C,		/*  16- 19 */
+_W|_A|_C,      _W|_A|_C,     _W|_A|_C,     _W|_A|_C,		/*  20- 23 */
+_W|_A|_C,      _W|_A|_C,     _W|_A|_C,     _W|_A|_C,		/*  24- 27 */
+_W|_A|_C,      _W|_A|_C,     _W|_A|_C,     _W|_A|_C,		/*  28- 31 */
+_W|_A|_S|_SP,  _W|_A|_P,     _W|_A|_P,     _W|_A|_P,		/*  32- 35 */
+_W|_A|_P,      _W|_A|_P,     _W|_A|_P,     _W|_A|_P,		/*  36- 39 */
+_W|_A|_P,      _W|_A|_P,     _W|_A|_P,     _W|_A|_P,		/*  40- 43 */
+_W|_A|_P,      _W|_A|_P,     _W|_A|_P,     _W|_A|_P,		/*  44- 47 */
+_W|_A|_D,      _W|_A|_D,     _W|_A|_D,     _W|_A|_D,		/*  48- 51 */
+_W|_A|_D,      _W|_A|_D,     _W|_A|_D,     _W|_A|_D,		/*  52- 55 */
+_W|_A|_D,      _W|_A|_D,     _W|_A|_P,     _W|_A|_P,		/*  56- 59 */
+_W|_A|_P,      _W|_A|_P,     _W|_A|_P,     _W|_A|_P,		/*  60- 63 */
+_W|_A|_P,      _W|_A|_U|_X,  _W|_A|_U|_X,  _W|_A|_U|_X,		/*  64- 67 */
+_W|_A|_U|_X,   _W|_A|_U|_X,  _W|_A|_U|_X,  _W|_A|_U,		/*  68- 71 */
+_W|_A|_U,      _W|_A|_U,     _W|_A|_U,     _W|_A|_U,		/*  72- 75 */
+_W|_A|_U,      _W|_A|_U,     _W|_A|_U,     _W|_A|_U,		/*  76- 79 */
+_W|_A|_U,      _W|_A|_U,     _W|_A|_U,     _W|_A|_U,		/*  80- 83 */
+_W|_A|_U,      _W|_A|_U,     _W|_A|_U,     _W|_A|_U,		/*  84- 87 */
+_W|_A|_U,      _W|_A|_U,     _W|_A|_U,     _W|_A|_P,		/*  88- 91 */
+_W|_A|_P,      _W|_A|_P,     _W|_A|_P,     _W|_A|_P,		/*  92- 95 */
+_W|_A|_P,      _W|_A|_L|_X,  _W|_A|_L|_X,  _W|_A|_L|_X,		/*  96- 99 */
+_W|_A|_L|_X,   _W|_A|_L|_X,  _W|_A|_L|_X,  _W|_A|_L,		/* 100-103 */
+_W|_A|_L,      _W|_A|_L,     _W|_A|_L,     _W|_A|_L,		/* 104-107 */
+_W|_A|_L,      _W|_A|_L,     _W|_A|_L,     _W|_A|_L,		/* 108-111 */
+_W|_A|_L,      _W|_A|_L,     _W|_A|_L,     _W|_A|_L,		/* 112-115 */
+_W|_A|_L,      _W|_A|_L,     _W|_A|_L,     _W|_A|_L,		/* 116-119 */
+_W|_A|_L,      _W|_A|_L,     _W|_A|_L,     _W|_A|_P,		/* 120-123 */
+_W|_A|_P,      _W|_A|_P,     _W|_A|_P,     _W|_A|_C,		/* 124-127 */
+_W,            _W,           _W,           _W,			/* 128-131 */
+_W,            _W,           _W,           _W,			/* 132-135 */
+_W,            _W,           _W,           _W,			/* 136-139 */
+_W,            _W,           _W,           _W,			/* 140-143 */
+_W,            _W,           _W,           _W,			/* 144-147 */
+_W,            _W,           _W,           _W,			/* 148-151 */
+_W,            _W,           _W,           _W,			/* 152-155 */
+_W,            _W,           _W,           _W,			/* 156-159 */
+_W|_S|_SP,     _W|_P,        _W|_P,        _W|_P,		/* 160-163 */
+_W|_P,         _W|_P,        _W|_P,        _W|_P,		/* 164-167 */
+_W|_P,         _W|_P,        _W|_P,        _W|_P,		/* 168-171 */
+_W|_P,         _W|_P,        _W|_P,        _W|_P,		/* 172-175 */
+_W|_P,         _W|_P,        _W|_P,        _W|_P,		/* 176-179 */
+_W|_P,         _W|_P,        _W|_P,        _W|_P,		/* 180-183 */
+_W|_P,         _W|_P,        _W|_P,        _W|_P,		/* 184-187 */
+_W|_P,         _W|_P,        _W|_P,        _W|_P,		/* 188-191 */
+_W|_U,         _W|_U,        _W|_U,        _W|_U,		/* 192-195 */
+_W|_U,         _W|_U,        _W|_U,        _W|_U,		/* 196-199 */
+_W|_U,         _W|_U,        _W|_U,        _W|_U,		/* 200-203 */
+_W|_U,         _W|_U,        _W|_U,        _W|_U,		/* 204-207 */
+_W|_U,         _W|_U,        _W|_U,        _W|_U,		/* 208-211 */
+_W|_U,         _W|_U,        _W|_U,        _W|_P,		/* 212-215 */
+_W|_U,         _W|_U,        _W|_U,        _W|_U,		/* 216-219 */
+_W|_U,         _W|_U,        _W|_U,        _W|_L,		/* 220-223 */
+_W|_L,         _W|_L,        _W|_L,        _W|_L,		/* 224-227 */
+_W|_L,         _W|_L,        _W|_L,        _W|_L,		/* 228-231 */
+_W|_L,         _W|_L,        _W|_L,        _W|_L,		/* 232-235 */
+_W|_L,         _W|_L,        _W|_L,        _W|_L,		/* 236-239 */
+_W|_L,         _W|_L,        _W|_L,        _W|_L,		/* 240-243 */
+_W|_L,         _W|_L,        _W|_L,        _W|_P,		/* 244-247 */
+_W|_L,         _W|_L,        _W|_L,        _W|_L,		/* 248-251 */
+_W|_L,         _W|_L,        _W|_L,        _W|_L};		/* 252-255 */
+
+static inline int match_token(struct ts_fsm_token *t, u8 d)
+{
+	if (t->type)
+		return (token_lookup_tbl[d] & t->type) != 0;
+	else
+		return t->value == d;
+}
+
+static unsigned int fsm_find(struct ts_config *conf, struct ts_state *state)
+{
+	struct ts_fsm *fsm = ts_config_priv(conf);
+	struct ts_fsm_token *cur = NULL, *next;
+	unsigned int match_start, block_idx = 0, tok_idx;
+	unsigned block_len = 0, strict, consumed = state->offset;
+	const u8 *data;
+
+#define GET_NEXT_BLOCK()		\
+({	consumed += block_idx;		\
+	block_idx = 0;			\
+	block_len = conf->get_next_block(consumed, &data, conf, state); })
+
+#define TOKEN_MISMATCH()		\
+	do {				\
+		if (strict)		\
+			goto no_match;	\
+		block_idx++;		\
+		goto startover;		\
+	} while(0)
+
+#define end_of_data() unlikely(block_idx >= block_len && !GET_NEXT_BLOCK())
+
+	if (end_of_data())
+		goto no_match;
+
+	strict = fsm->tokens[0].recur != TS_FSM_HEAD_IGNORE;
+
+startover:
+	match_start = consumed + block_idx;
+
+	for (tok_idx = 0; tok_idx < fsm->ntokens; tok_idx++) {
+		cur = &fsm->tokens[tok_idx];
+
+		if (likely(tok_idx < (fsm->ntokens - 1)))
+			next = &fsm->tokens[tok_idx + 1];
+		else
+			next = NULL;
+
+		switch (cur->recur) {
+		case TS_FSM_SINGLE:
+			if (end_of_data())
+				goto no_match;
+
+			if (!match_token(cur, data[block_idx]))
+				TOKEN_MISMATCH();
+			break;
+
+		case TS_FSM_PERHAPS:
+			if (end_of_data() ||
+			    !match_token(cur, data[block_idx]))
+				continue;
+			break;
+
+		case TS_FSM_MULTI:
+			if (end_of_data())
+				goto no_match;
+
+			if (!match_token(cur, data[block_idx]))
+				TOKEN_MISMATCH();
+
+			block_idx++;
+			/* fall through */
+
+		case TS_FSM_ANY:
+			if (next == NULL)
+				goto found_match;
+
+			if (end_of_data())
+				continue;
+
+			while (!match_token(next, data[block_idx])) {
+				if (!match_token(cur, data[block_idx]))
+					TOKEN_MISMATCH();
+				block_idx++;
+				if (end_of_data())
+					goto no_match;
+			}
+			continue;
+
+		/*
+		 * Optimization: Prefer small local loop over jumping
+		 * back and forth until garbage at head is munched.
+		 */
+		case TS_FSM_HEAD_IGNORE:
+			if (end_of_data())
+				continue;
+
+			while (!match_token(next, data[block_idx])) {
+				/*
+				 * Special case, don't start over upon
+				 * a mismatch, give the user the
+				 * chance to specify the type of data
+				 * allowed to be ignored.
+				 */
+				if (!match_token(cur, data[block_idx]))
+					goto no_match;
+
+				block_idx++;
+				if (end_of_data())
+					goto no_match;
+			}
+
+			match_start = consumed + block_idx;
+			continue;
+		}
+
+		block_idx++;
+	}
+
+	if (end_of_data())
+		goto found_match;
+
+no_match:
+	return UINT_MAX;
+
+found_match:
+	state->offset = consumed + block_idx;
+	return match_start;
+}
+
+static struct ts_config *fsm_init(const void *pattern, unsigned int len,
+				     gfp_t gfp_mask)
+{
+	int i, err = -EINVAL;
+	struct ts_config *conf;
+	struct ts_fsm *fsm;
+	struct ts_fsm_token *tokens = (struct ts_fsm_token *) pattern;
+	unsigned int ntokens = len / sizeof(*tokens);
+	size_t priv_size = sizeof(*fsm) + len;
+
+	if (len  % sizeof(struct ts_fsm_token) || ntokens < 1)
+		goto errout;
+
+	for (i = 0; i < ntokens; i++) {
+		struct ts_fsm_token *t = &tokens[i];
+
+		if (t->type > TS_FSM_TYPE_MAX || t->recur > TS_FSM_RECUR_MAX)
+			goto errout;
+
+		if (t->recur == TS_FSM_HEAD_IGNORE &&
+		    (i != 0 || i == (ntokens - 1)))
+			goto errout;
+	}
+
+	conf = alloc_ts_config(priv_size, gfp_mask);
+	if (IS_ERR(conf))
+		return conf;
+
+	fsm = ts_config_priv(conf);
+	fsm->ntokens = ntokens;
+	memcpy(fsm->tokens, pattern, len);
+
+	for (i = 0; i < fsm->ntokens; i++) {
+		struct ts_fsm_token *t = &fsm->tokens[i];
+		t->type = token_map[t->type];
+	}
+
+	return conf;
+
+errout:
+	return ERR_PTR(err);
+}
+
+static void *fsm_get_pattern(struct ts_config *conf)
+{
+	struct ts_fsm *fsm = ts_config_priv(conf);
+	return fsm->tokens;
+}
+
+static unsigned int fsm_get_pattern_len(struct ts_config *conf)
+{
+	struct ts_fsm *fsm = ts_config_priv(conf);
+	return fsm->ntokens * sizeof(struct ts_fsm_token);
+}
+
+static struct ts_ops fsm_ops = {
+	.name		  = "fsm",
+	.find		  = fsm_find,
+	.init		  = fsm_init,
+	.get_pattern	  = fsm_get_pattern,
+	.get_pattern_len  = fsm_get_pattern_len,
+	.owner		  = THIS_MODULE,
+	.list		  = LIST_HEAD_INIT(fsm_ops.list)
+};
+
+static int __init init_fsm(void)
+{
+	return textsearch_register(&fsm_ops);
+}
+
+static void __exit exit_fsm(void)
+{
+	textsearch_unregister(&fsm_ops);
+}
+
+MODULE_LICENSE("GPL");
+
+module_init(init_fsm);
+module_exit(exit_fsm);

lib/ts_kmp.c

@@ -0,0 +1,144 @@
+/*
+ * lib/ts_kmp.c		Knuth-Morris-Pratt text search implementation
+ *
+ *		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.
+ *
+ * Authors:	Thomas Graf <tgraf@suug.ch>
+ *
+ * ==========================================================================
+ * 
+ *   Implements a linear-time string-matching algorithm due to Knuth,
+ *   Morris, and Pratt [1]. Their algorithm avoids the explicit
+ *   computation of the transition function DELTA altogether. Its
+ *   matching time is O(n), for n being length(text), using just an
+ *   auxiliary function PI[1..m], for m being length(pattern),
+ *   precomputed from the pattern in time O(m). The array PI allows
+ *   the transition function DELTA to be computed efficiently
+ *   "on the fly" as needed. Roughly speaking, for any state
+ *   "q" = 0,1,...,m and any character "a" in SIGMA, the value
+ *   PI["q"] contains the information that is independent of "a" and
+ *   is needed to compute DELTA("q", "a") [2]. Since the array PI
+ *   has only m entries, whereas DELTA has O(m|SIGMA|) entries, we
+ *   save a factor of |SIGMA| in the preprocessing time by computing
+ *   PI rather than DELTA.
+ *
+ *   [1] Cormen, Leiserson, Rivest, Stein
+ *       Introdcution to Algorithms, 2nd Edition, MIT Press
+ *   [2] See finite automation theory
+ */
+
+#include <linux/module.h>
+#include <linux/types.h>
+#include <linux/string.h>
+#include <linux/textsearch.h>
+
+struct ts_kmp
+{
+	u8 *		pattern;
+	unsigned int	pattern_len;
+	unsigned int 	prefix_tbl[0];
+};
+
+static unsigned int kmp_find(struct ts_config *conf, struct ts_state *state)
+{
+	struct ts_kmp *kmp = ts_config_priv(conf);
+	unsigned int i, q = 0, text_len, consumed = state->offset;
+	const u8 *text;
+
+	for (;;) {
+		text_len = conf->get_next_block(consumed, &text, conf, state);
+
+		if (unlikely(text_len == 0))
+			break;
+
+		for (i = 0; i < text_len; i++) {
+			while (q > 0 && kmp->pattern[q] != text[i])
+				q = kmp->prefix_tbl[q - 1];
+			if (kmp->pattern[q] == text[i])
+				q++;
+			if (unlikely(q == kmp->pattern_len)) {
+				state->offset = consumed + i + 1;
+				return state->offset - kmp->pattern_len;
+			}
+		}
+
+		consumed += text_len;
+	}
+
+	return UINT_MAX;
+}
+
+static inline void compute_prefix_tbl(const u8 *pattern, unsigned int len,
+				      unsigned int *prefix_tbl)
+{
+	unsigned int k, q;
+
+	for (k = 0, q = 1; q < len; q++) {
+		while (k > 0 && pattern[k] != pattern[q])
+			k = prefix_tbl[k-1];
+		if (pattern[k] == pattern[q])
+			k++;
+		prefix_tbl[q] = k;
+	}
+}
+
+static struct ts_config *kmp_init(const void *pattern, unsigned int len,
+				  gfp_t gfp_mask)
+{
+	struct ts_config *conf;
+	struct ts_kmp *kmp;
+	unsigned int prefix_tbl_len = len * sizeof(unsigned int);
+	size_t priv_size = sizeof(*kmp) + len + prefix_tbl_len;
+
+	conf = alloc_ts_config(priv_size, gfp_mask);
+	if (IS_ERR(conf))
+		return conf;
+
+	kmp = ts_config_priv(conf);
+	kmp->pattern_len = len;
+	compute_prefix_tbl(pattern, len, kmp->prefix_tbl);
+	kmp->pattern = (u8 *) kmp->prefix_tbl + prefix_tbl_len;
+	memcpy(kmp->pattern, pattern, len);
+
+	return conf;
+}
+
+static void *kmp_get_pattern(struct ts_config *conf)
+{
+	struct ts_kmp *kmp = ts_config_priv(conf);
+	return kmp->pattern;
+}
+
+static unsigned int kmp_get_pattern_len(struct ts_config *conf)
+{
+	struct ts_kmp *kmp = ts_config_priv(conf);
+	return kmp->pattern_len;
+}
+
+static struct ts_ops kmp_ops = {
+	.name		  = "kmp",
+	.find		  = kmp_find,
+	.init		  = kmp_init,
+	.get_pattern	  = kmp_get_pattern,
+	.get_pattern_len  = kmp_get_pattern_len,
+	.owner		  = THIS_MODULE,
+	.list		  = LIST_HEAD_INIT(kmp_ops.list)
+};
+
+static int __init init_kmp(void)
+{
+	return textsearch_register(&kmp_ops);
+}
+
+static void __exit exit_kmp(void)
+{
+	textsearch_unregister(&kmp_ops);
+}
+
+MODULE_LICENSE("GPL");
+
+module_init(init_kmp);
+module_exit(exit_kmp);

lib/vsprintf.c

@@ -0,0 +1,873 @@
+/*
+ *  linux/lib/vsprintf.c
+ *
+ *  Copyright (C) 1991, 1992  Linus Torvalds
+ */
+
+/* vsprintf.c -- Lars Wirzenius & Linus Torvalds. */
+/*
+ * Wirzenius wrote this portably, Torvalds fucked it up :-)
+ */
+
+/* 
+ * Fri Jul 13 2001 Crutcher Dunnavant <crutcher+kernel@datastacks.com>
+ * - changed to provide snprintf and vsnprintf functions
+ * So Feb  1 16:51:32 CET 2004 Juergen Quade <quade@hsnr.de>
+ * - scnprintf and vscnprintf
+ */
+
+#include <stdarg.h>
+#include <linux/module.h>
+#include <linux/types.h>
+#include <linux/string.h>
+#include <linux/ctype.h>
+#include <linux/kernel.h>
+
+#include <asm/page.h>		/* for PAGE_SIZE */
+#include <asm/div64.h>
+
+/**
+ * simple_strtoul - convert a string to an unsigned long
+ * @cp: The start of the string
+ * @endp: A pointer to the end of the parsed string will be placed here
+ * @base: The number base to use
+ */
+unsigned long simple_strtoul(const char *cp,char **endp,unsigned int base)
+{
+	unsigned long result = 0,value;
+
+	if (!base) {
+		base = 10;
+		if (*cp == '0') {
+			base = 8;
+			cp++;
+			if ((toupper(*cp) == 'X') && isxdigit(cp[1])) {
+				cp++;
+				base = 16;
+			}
+		}
+	} else if (base == 16) {
+		if (cp[0] == '0' && toupper(cp[1]) == 'X')
+			cp += 2;
+	}
+	while (isxdigit(*cp) &&
+	       (value = isdigit(*cp) ? *cp-'0' : toupper(*cp)-'A'+10) < base) {
+		result = result*base + value;
+		cp++;
+	}
+	if (endp)
+		*endp = (char *)cp;
+	return result;
+}
+
+EXPORT_SYMBOL(simple_strtoul);
+
+/**
+ * simple_strtol - convert a string to a signed long
+ * @cp: The start of the string
+ * @endp: A pointer to the end of the parsed string will be placed here
+ * @base: The number base to use
+ */
+long simple_strtol(const char *cp,char **endp,unsigned int base)
+{
+	if(*cp=='-')
+		return -simple_strtoul(cp+1,endp,base);
+	return simple_strtoul(cp,endp,base);
+}
+
+EXPORT_SYMBOL(simple_strtol);
+
+/**
+ * simple_strtoull - convert a string to an unsigned long long
+ * @cp: The start of the string
+ * @endp: A pointer to the end of the parsed string will be placed here
+ * @base: The number base to use
+ */
+unsigned long long simple_strtoull(const char *cp,char **endp,unsigned int base)
+{
+	unsigned long long result = 0,value;
+
+	if (!base) {
+		base = 10;
+		if (*cp == '0') {
+			base = 8;
+			cp++;
+			if ((toupper(*cp) == 'X') && isxdigit(cp[1])) {
+				cp++;
+				base = 16;
+			}
+		}
+	} else if (base == 16) {
+		if (cp[0] == '0' && toupper(cp[1]) == 'X')
+			cp += 2;
+	}
+	while (isxdigit(*cp) && (value = isdigit(*cp) ? *cp-'0' : (islower(*cp)
+	    ? toupper(*cp) : *cp)-'A'+10) < base) {
+		result = result*base + value;
+		cp++;
+	}
+	if (endp)
+		*endp = (char *)cp;
+	return result;
+}
+
+EXPORT_SYMBOL(simple_strtoull);
+
+/**
+ * simple_strtoll - convert a string to a signed long long
+ * @cp: The start of the string
+ * @endp: A pointer to the end of the parsed string will be placed here
+ * @base: The number base to use
+ */
+long long simple_strtoll(const char *cp,char **endp,unsigned int base)
+{
+	if(*cp=='-')
+		return -simple_strtoull(cp+1,endp,base);
+	return simple_strtoull(cp,endp,base);
+}
+
+static int skip_atoi(const char **s)
+{
+	int i=0;
+
+	while (isdigit(**s))
+		i = i*10 + *((*s)++) - '0';
+	return i;
+}
+
+#define ZEROPAD	1		/* pad with zero */
+#define SIGN	2		/* unsigned/signed long */
+#define PLUS	4		/* show plus */
+#define SPACE	8		/* space if plus */
+#define LEFT	16		/* left justified */
+#define SPECIAL	32		/* 0x */
+#define LARGE	64		/* use 'ABCDEF' instead of 'abcdef' */
+
+static char * number(char * buf, char * end, unsigned long long num, int base, int size, int precision, int type)
+{
+	char c,sign,tmp[66];
+	const char *digits;
+	static const char small_digits[] = "0123456789abcdefghijklmnopqrstuvwxyz";
+	static const char large_digits[] = "0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZ";
+	int i;
+
+	digits = (type & LARGE) ? large_digits : small_digits;
+	if (type & LEFT)
+		type &= ~ZEROPAD;
+	if (base < 2 || base > 36)
+		return NULL;
+	c = (type & ZEROPAD) ? '0' : ' ';
+	sign = 0;
+	if (type & SIGN) {
+		if ((signed long long) num < 0) {
+			sign = '-';
+			num = - (signed long long) num;
+			size--;
+		} else if (type & PLUS) {
+			sign = '+';
+			size--;
+		} else if (type & SPACE) {
+			sign = ' ';
+			size--;
+		}
+	}
+	if (type & SPECIAL) {
+		if (base == 16)
+			size -= 2;
+		else if (base == 8)
+			size--;
+	}
+	i = 0;
+	if (num == 0)
+		tmp[i++]='0';
+	else while (num != 0)
+		tmp[i++] = digits[do_div(num,base)];
+	if (i > precision)
+		precision = i;
+	size -= precision;
+	if (!(type&(ZEROPAD+LEFT))) {
+		while(size-->0) {
+			if (buf < end)
+				*buf = ' ';
+			++buf;
+		}
+	}
+	if (sign) {
+		if (buf < end)
+			*buf = sign;
+		++buf;
+	}
+	if (type & SPECIAL) {
+		if (base==8) {
+			if (buf < end)
+				*buf = '0';
+			++buf;
+		} else if (base==16) {
+			if (buf < end)
+				*buf = '0';
+			++buf;
+			if (buf < end)
+				*buf = digits[33];
+			++buf;
+		}
+	}
+	if (!(type & LEFT)) {
+		while (size-- > 0) {
+			if (buf < end)
+				*buf = c;
+			++buf;
+		}
+	}
+	while (i < precision--) {
+		if (buf < end)
+			*buf = '0';
+		++buf;
+	}
+	while (i-- > 0) {
+		if (buf < end)
+			*buf = tmp[i];
+		++buf;
+	}
+	while (size-- > 0) {
+		if (buf < end)
+			*buf = ' ';
+		++buf;
+	}
+	return buf;
+}
+
+/**
+ * vsnprintf - Format a string and place it in a buffer
+ * @buf: The buffer to place the result into
+ * @size: The size of the buffer, including the trailing null space
+ * @fmt: The format string to use
+ * @args: Arguments for the format string
+ *
+ * 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
+ * number of characters written into @buf as return value
+ * (not including the trailing '\0'), use vscnprintf(). If the
+ * return is greater than or equal to @size, the resulting
+ * string is truncated.
+ *
+ * Call this function if you are already dealing with a va_list.
+ * You probably want snprintf() instead.
+ */
+int vsnprintf(char *buf, size_t size, const char *fmt, va_list args)
+{
+	int len;
+	unsigned long long num;
+	int i, base;
+	char *str, *end, c;
+	const char *s;
+
+	int flags;		/* flags to number() */
+
+	int field_width;	/* width of output field */
+	int precision;		/* min. # of digits for integers; max
+				   number of chars for from string */
+	int qualifier;		/* 'h', 'l', or 'L' for integer fields */
+				/* 'z' support added 23/7/1999 S.H.    */
+				/* 'z' changed to 'Z' --davidm 1/25/99 */
+				/* 't' added for ptrdiff_t */
+
+	/* Reject out-of-range values early.  Large positive sizes are
+	   used for unknown buffer sizes. */
+	if (unlikely((int) size < 0)) {
+		/* There can be only one.. */
+		static int warn = 1;
+		WARN_ON(warn);
+		warn = 0;
+		return 0;
+	}
+
+	str = buf;
+	end = buf + size;
+
+	/* Make sure end is always >= buf */
+	if (end < buf) {
+		end = ((void *)-1);
+		size = end - buf;
+	}
+
+	for (; *fmt ; ++fmt) {
+		if (*fmt != '%') {
+			if (str < end)
+				*str = *fmt;
+			++str;
+			continue;
+		}
+
+		/* process flags */
+		flags = 0;
+		repeat:
+			++fmt;		/* this also skips first '%' */
+			switch (*fmt) {
+				case '-': flags |= LEFT; goto repeat;
+				case '+': flags |= PLUS; goto repeat;
+				case ' ': flags |= SPACE; goto repeat;
+				case '#': flags |= SPECIAL; goto repeat;
+				case '0': flags |= ZEROPAD; goto repeat;
+			}
+
+		/* get field width */
+		field_width = -1;
+		if (isdigit(*fmt))
+			field_width = skip_atoi(&fmt);
+		else if (*fmt == '*') {
+			++fmt;
+			/* it's the next argument */
+			field_width = va_arg(args, int);
+			if (field_width < 0) {
+				field_width = -field_width;
+				flags |= LEFT;
+			}
+		}
+
+		/* get the precision */
+		precision = -1;
+		if (*fmt == '.') {
+			++fmt;	
+			if (isdigit(*fmt))
+				precision = skip_atoi(&fmt);
+			else if (*fmt == '*') {
+				++fmt;
+				/* it's the next argument */
+				precision = va_arg(args, int);
+			}
+			if (precision < 0)
+				precision = 0;
+		}
+
+		/* get the conversion qualifier */
+		qualifier = -1;
+		if (*fmt == 'h' || *fmt == 'l' || *fmt == 'L' ||
+		    *fmt =='Z' || *fmt == 'z' || *fmt == 't') {
+			qualifier = *fmt;
+			++fmt;
+			if (qualifier == 'l' && *fmt == 'l') {
+				qualifier = 'L';
+				++fmt;
+			}
+		}
+
+		/* default base */
+		base = 10;
+
+		switch (*fmt) {
+			case 'c':
+				if (!(flags & LEFT)) {
+					while (--field_width > 0) {
+						if (str < end)
+							*str = ' ';
+						++str;
+					}
+				}
+				c = (unsigned char) va_arg(args, int);
+				if (str < end)
+					*str = c;
+				++str;
+				while (--field_width > 0) {
+					if (str < end)
+						*str = ' ';
+					++str;
+				}
+				continue;
+
+			case 's':
+				s = va_arg(args, char *);
+				if ((unsigned long)s < PAGE_SIZE)
+					s = "<NULL>";
+
+				len = strnlen(s, precision);
+
+				if (!(flags & LEFT)) {
+					while (len < field_width--) {
+						if (str < end)
+							*str = ' ';
+						++str;
+					}
+				}
+				for (i = 0; i < len; ++i) {
+					if (str < end)
+						*str = *s;
+					++str; ++s;
+				}
+				while (len < field_width--) {
+					if (str < end)
+						*str = ' ';
+					++str;
+				}
+				continue;
+
+			case 'p':
+				if (field_width == -1) {
+					field_width = 2*sizeof(void *);
+					flags |= ZEROPAD;
+				}
+				str = number(str, end,
+						(unsigned long) va_arg(args, void *),
+						16, field_width, precision, flags);
+				continue;
+
+
+			case 'n':
+				/* FIXME:
+				* What does C99 say about the overflow case here? */
+				if (qualifier == 'l') {
+					long * ip = va_arg(args, long *);
+					*ip = (str - buf);
+				} else if (qualifier == 'Z' || qualifier == 'z') {
+					size_t * ip = va_arg(args, size_t *);
+					*ip = (str - buf);
+				} else {
+					int * ip = va_arg(args, int *);
+					*ip = (str - buf);
+				}
+				continue;
+
+			case '%':
+				if (str < end)
+					*str = '%';
+				++str;
+				continue;
+
+				/* integer number formats - set up the flags and "break" */
+			case 'o':
+				base = 8;
+				break;
+
+			case 'X':
+				flags |= LARGE;
+			case 'x':
+				base = 16;
+				break;
+
+			case 'd':
+			case 'i':
+				flags |= SIGN;
+			case 'u':
+				break;
+
+			default:
+				if (str < end)
+					*str = '%';
+				++str;
+				if (*fmt) {
+					if (str < end)
+						*str = *fmt;
+					++str;
+				} else {
+					--fmt;
+				}
+				continue;
+		}
+		if (qualifier == 'L')
+			num = va_arg(args, long long);
+		else if (qualifier == 'l') {
+			num = va_arg(args, unsigned long);
+			if (flags & SIGN)
+				num = (signed long) num;
+		} else if (qualifier == 'Z' || qualifier == 'z') {
+			num = va_arg(args, size_t);
+		} else if (qualifier == 't') {
+			num = va_arg(args, ptrdiff_t);
+		} else if (qualifier == 'h') {
+			num = (unsigned short) va_arg(args, int);
+			if (flags & SIGN)
+				num = (signed short) num;
+		} else {
+			num = va_arg(args, unsigned int);
+			if (flags & SIGN)
+				num = (signed int) num;
+		}
+		str = number(str, end, num, base,
+				field_width, precision, flags);
+	}
+	if (size > 0) {
+		if (str < end)
+			*str = '\0';
+		else
+			end[-1] = '\0';
+	}
+	/* the trailing null byte doesn't count towards the total */
+	return str-buf;
+}
+
+EXPORT_SYMBOL(vsnprintf);
+
+/**
+ * vscnprintf - Format a string and place it in a buffer
+ * @buf: The buffer to place the result into
+ * @size: The size of the buffer, including the trailing null space
+ * @fmt: The format string to use
+ * @args: Arguments for the format string
+ *
+ * The return value is the number of characters which have been written into
+ * the @buf not including the trailing '\0'. If @size is <= 0 the function
+ * returns 0.
+ *
+ * Call this function if you are already dealing with a va_list.
+ * You probably want scnprintf() instead.
+ */
+int vscnprintf(char *buf, size_t size, const char *fmt, va_list args)
+{
+	int i;
+
+	i=vsnprintf(buf,size,fmt,args);
+	return (i >= size) ? (size - 1) : i;
+}
+
+EXPORT_SYMBOL(vscnprintf);
+
+/**
+ * snprintf - Format a string and place it in a buffer
+ * @buf: The buffer to place the result into
+ * @size: The size of the buffer, including the trailing null space
+ * @fmt: The format string to use
+ * @...: Arguments for the format string
+ *
+ * The return value is the number of characters which would be
+ * generated for the given input, excluding the trailing null,
+ * as per ISO C99.  If the return is greater than or equal to
+ * @size, the resulting string is truncated.
+ */
+int snprintf(char * buf, size_t size, const char *fmt, ...)
+{
+	va_list args;
+	int i;
+
+	va_start(args, fmt);
+	i=vsnprintf(buf,size,fmt,args);
+	va_end(args);
+	return i;
+}
+
+EXPORT_SYMBOL(snprintf);
+
+/**
+ * scnprintf - Format a string and place it in a buffer
+ * @buf: The buffer to place the result into
+ * @size: The size of the buffer, including the trailing null space
+ * @fmt: The format string to use
+ * @...: Arguments for the format string
+ *
+ * The return value is the number of characters written into @buf not including
+ * the trailing '\0'. If @size is <= 0 the function returns 0.
+ */
+
+int scnprintf(char * buf, size_t size, const char *fmt, ...)
+{
+	va_list args;
+	int i;
+
+	va_start(args, fmt);
+	i = vsnprintf(buf, size, fmt, args);
+	va_end(args);
+	return (i >= size) ? (size - 1) : i;
+}
+EXPORT_SYMBOL(scnprintf);
+
+/**
+ * vsprintf - Format a string and place it in a buffer
+ * @buf: The buffer to place the result into
+ * @fmt: The format string to use
+ * @args: Arguments for the format string
+ *
+ * The function returns the number of characters written
+ * into @buf. Use vsnprintf() or vscnprintf() in order to avoid
+ * buffer overflows.
+ *
+ * Call this function if you are already dealing with a va_list.
+ * You probably want sprintf() instead.
+ */
+int vsprintf(char *buf, const char *fmt, va_list args)
+{
+	return vsnprintf(buf, INT_MAX, fmt, args);
+}
+
+EXPORT_SYMBOL(vsprintf);
+
+/**
+ * sprintf - Format a string and place it in a buffer
+ * @buf: The buffer to place the result into
+ * @fmt: The format string to use
+ * @...: Arguments for the format string
+ *
+ * The function returns the number of characters written
+ * into @buf. Use snprintf() or scnprintf() in order to avoid
+ * buffer overflows.
+ */
+int sprintf(char * buf, const char *fmt, ...)
+{
+	va_list args;
+	int i;
+
+	va_start(args, fmt);
+	i=vsnprintf(buf, INT_MAX, fmt, args);
+	va_end(args);
+	return i;
+}
+
+EXPORT_SYMBOL(sprintf);
+
+/**
+ * vsscanf - Unformat a buffer into a list of arguments
+ * @buf:	input buffer
+ * @fmt:	format of buffer
+ * @args:	arguments
+ */
+int vsscanf(const char * buf, const char * fmt, va_list args)
+{
+	const char *str = buf;
+	char *next;
+	char digit;
+	int num = 0;
+	int qualifier;
+	int base;
+	int field_width;
+	int is_sign = 0;
+
+	while(*fmt && *str) {
+		/* skip any white space in format */
+		/* white space in format matchs any amount of
+		 * white space, including none, in the input.
+		 */
+		if (isspace(*fmt)) {
+			while (isspace(*fmt))
+				++fmt;
+			while (isspace(*str))
+				++str;
+		}
+
+		/* anything that is not a conversion must match exactly */
+		if (*fmt != '%' && *fmt) {
+			if (*fmt++ != *str++)
+				break;
+			continue;
+		}
+
+		if (!*fmt)
+			break;
+		++fmt;
+		
+		/* skip this conversion.
+		 * advance both strings to next white space
+		 */
+		if (*fmt == '*') {
+			while (!isspace(*fmt) && *fmt)
+				fmt++;
+			while (!isspace(*str) && *str)
+				str++;
+			continue;
+		}
+
+		/* get field width */
+		field_width = -1;
+		if (isdigit(*fmt))
+			field_width = skip_atoi(&fmt);
+
+		/* get conversion qualifier */
+		qualifier = -1;
+		if (*fmt == 'h' || *fmt == 'l' || *fmt == 'L' ||
+		    *fmt == 'Z' || *fmt == 'z') {
+			qualifier = *fmt++;
+			if (unlikely(qualifier == *fmt)) {
+				if (qualifier == 'h') {
+					qualifier = 'H';
+					fmt++;
+				} else if (qualifier == 'l') {
+					qualifier = 'L';
+					fmt++;
+				}
+			}
+		}
+		base = 10;
+		is_sign = 0;
+
+		if (!*fmt || !*str)
+			break;
+
+		switch(*fmt++) {
+		case 'c':
+		{
+			char *s = (char *) va_arg(args,char*);
+			if (field_width == -1)
+				field_width = 1;
+			do {
+				*s++ = *str++;
+			} while (--field_width > 0 && *str);
+			num++;
+		}
+		continue;
+		case 's':
+		{
+			char *s = (char *) va_arg(args, char *);
+			if(field_width == -1)
+				field_width = INT_MAX;
+			/* first, skip leading white space in buffer */
+			while (isspace(*str))
+				str++;
+
+			/* now copy until next white space */
+			while (*str && !isspace(*str) && field_width--) {
+				*s++ = *str++;
+			}
+			*s = '\0';
+			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;
+		case 'x':
+		case 'X':
+			base = 16;
+			break;
+		case 'i':
+                        base = 0;
+		case 'd':
+			is_sign = 1;
+		case 'u':
+			break;
+		case '%':
+			/* looking for '%' in str */
+			if (*str++ != '%') 
+				return num;
+			continue;
+		default:
+			/* invalid format; stop here */
+			return num;
+		}
+
+		/* have some sort of integer conversion.
+		 * first, skip white space in buffer.
+		 */
+		while (isspace(*str))
+			str++;
+
+		digit = *str;
+		if (is_sign && digit == '-')
+			digit = *(str + 1);
+
+		if (!digit
+                    || (base == 16 && !isxdigit(digit))
+                    || (base == 10 && !isdigit(digit))
+                    || (base == 8 && (!isdigit(digit) || digit > '7'))
+                    || (base == 0 && !isdigit(digit)))
+				break;
+
+		switch(qualifier) {
+		case 'H':	/* that's 'hh' in format */
+			if (is_sign) {
+				signed char *s = (signed char *) va_arg(args,signed char *);
+				*s = (signed char) simple_strtol(str,&next,base);
+			} else {
+				unsigned char *s = (unsigned char *) va_arg(args, unsigned char *);
+				*s = (unsigned char) simple_strtoul(str, &next, base);
+			}
+			break;
+		case 'h':
+			if (is_sign) {
+				short *s = (short *) va_arg(args,short *);
+				*s = (short) simple_strtol(str,&next,base);
+			} else {
+				unsigned short *s = (unsigned short *) va_arg(args, unsigned short *);
+				*s = (unsigned short) simple_strtoul(str, &next, base);
+			}
+			break;
+		case 'l':
+			if (is_sign) {
+				long *l = (long *) va_arg(args,long *);
+				*l = simple_strtol(str,&next,base);
+			} else {
+				unsigned long *l = (unsigned long*) va_arg(args,unsigned long*);
+				*l = simple_strtoul(str,&next,base);
+			}
+			break;
+		case 'L':
+			if (is_sign) {
+				long long *l = (long long*) va_arg(args,long long *);
+				*l = simple_strtoll(str,&next,base);
+			} else {
+				unsigned long long *l = (unsigned long long*) va_arg(args,unsigned long long*);
+				*l = simple_strtoull(str,&next,base);
+			}
+			break;
+		case 'Z':
+		case 'z':
+		{
+			size_t *s = (size_t*) va_arg(args,size_t*);
+			*s = (size_t) simple_strtoul(str,&next,base);
+		}
+		break;
+		default:
+			if (is_sign) {
+				int *i = (int *) va_arg(args, int*);
+				*i = (int) simple_strtol(str,&next,base);
+			} else {
+				unsigned int *i = (unsigned int*) va_arg(args, unsigned int*);
+				*i = (unsigned int) simple_strtoul(str,&next,base);
+			}
+			break;
+		}
+		num++;
+
+		if (!next)
+			break;
+		str = next;
+	}
+	return num;
+}
+
+EXPORT_SYMBOL(vsscanf);
+
+/**
+ * sscanf - Unformat a buffer into a list of arguments
+ * @buf:	input buffer
+ * @fmt:	formatting of buffer
+ * @...:	resulting arguments
+ */
+int sscanf(const char * buf, const char * fmt, ...)
+{
+	va_list args;
+	int i;
+
+	va_start(args,fmt);
+	i = vsscanf(buf,fmt,args);
+	va_end(args);
+	return i;
+}
+
+EXPORT_SYMBOL(sscanf);
+
+
+/* Simplified asprintf. */
+char *kasprintf(gfp_t gfp, const char *fmt, ...)
+{
+	va_list ap;
+	unsigned int len;
+	char *p;
+
+	va_start(ap, fmt);
+	len = vsnprintf(NULL, 0, fmt, ap);
+	va_end(ap);
+
+	p = kmalloc(len+1, gfp);
+	if (!p)
+		return NULL;
+	va_start(ap, fmt);
+	vsnprintf(p, len+1, fmt, ap);
+	va_end(ap);
+	return p;
+}
+
+EXPORT_SYMBOL(kasprintf);

lib/zlib_deflate/Makefile

@@ -0,0 +1,11 @@
+#
+# This is a modified version of zlib, which does all memory
+# allocation ahead of time.
+#
+# This is the compression code, see zlib_inflate for the
+# decompression code.
+#
+
+obj-$(CONFIG_ZLIB_DEFLATE) += zlib_deflate.o
+
+zlib_deflate-objs := deflate.o deftree.o deflate_syms.o

lib/zlib_deflate/deflate_syms.c

@@ -0,0 +1,18 @@
+/*
+ * linux/lib/zlib_deflate/deflate_syms.c
+ *
+ * Exported symbols for the deflate functionality.
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/init.h>
+
+#include <linux/zlib.h>
+
+EXPORT_SYMBOL(zlib_deflate_workspacesize);
+EXPORT_SYMBOL(zlib_deflate);
+EXPORT_SYMBOL(zlib_deflateInit2);
+EXPORT_SYMBOL(zlib_deflateEnd);
+EXPORT_SYMBOL(zlib_deflateReset);
+MODULE_LICENSE("GPL");

lib/zlib_deflate/defutil.h

@@ -0,0 +1,334 @@
+
+
+
+#define Assert(err, str) 
+#define Trace(dummy) 
+#define Tracev(dummy) 
+#define Tracecv(err, dummy) 
+#define Tracevv(dummy) 
+
+
+
+#define LENGTH_CODES 29
+/* number of length codes, not counting the special END_BLOCK code */
+
+#define LITERALS  256
+/* number of literal bytes 0..255 */
+
+#define L_CODES (LITERALS+1+LENGTH_CODES)
+/* number of Literal or Length codes, including the END_BLOCK code */
+
+#define D_CODES   30
+/* number of distance codes */
+
+#define BL_CODES  19
+/* number of codes used to transfer the bit lengths */
+
+#define HEAP_SIZE (2*L_CODES+1)
+/* maximum heap size */
+
+#define MAX_BITS 15
+/* All codes must not exceed MAX_BITS bits */
+
+#define INIT_STATE    42
+#define BUSY_STATE   113
+#define FINISH_STATE 666
+/* Stream status */
+
+
+/* Data structure describing a single value and its code string. */
+typedef struct ct_data_s {
+    union {
+        ush  freq;       /* frequency count */
+        ush  code;       /* bit string */
+    } fc;
+    union {
+        ush  dad;        /* father node in Huffman tree */
+        ush  len;        /* length of bit string */
+    } dl;
+} ct_data;
+
+#define Freq fc.freq
+#define Code fc.code
+#define Dad  dl.dad
+#define Len  dl.len
+
+typedef struct static_tree_desc_s  static_tree_desc;
+
+typedef struct tree_desc_s {
+    ct_data *dyn_tree;           /* the dynamic tree */
+    int     max_code;            /* largest code with non zero frequency */
+    static_tree_desc *stat_desc; /* the corresponding static tree */
+} tree_desc;
+
+typedef ush Pos;
+typedef unsigned IPos;
+
+/* A Pos is an index in the character window. We use short instead of int to
+ * save space in the various tables. IPos is used only for parameter passing.
+ */
+
+typedef struct deflate_state {
+    z_streamp strm;      /* pointer back to this zlib stream */
+    int   status;        /* as the name implies */
+    Byte *pending_buf;   /* output still pending */
+    ulg   pending_buf_size; /* size of pending_buf */
+    Byte *pending_out;   /* next pending byte to output to the stream */
+    int   pending;       /* nb of bytes in the pending buffer */
+    int   noheader;      /* suppress zlib header and adler32 */
+    Byte  data_type;     /* UNKNOWN, BINARY or ASCII */
+    Byte  method;        /* STORED (for zip only) or DEFLATED */
+    int   last_flush;    /* value of flush param for previous deflate call */
+
+                /* used by deflate.c: */
+
+    uInt  w_size;        /* LZ77 window size (32K by default) */
+    uInt  w_bits;        /* log2(w_size)  (8..16) */
+    uInt  w_mask;        /* w_size - 1 */
+
+    Byte *window;
+    /* Sliding window. Input bytes are read into the second half of the window,
+     * and move to the first half later to keep a dictionary of at least wSize
+     * bytes. With this organization, matches are limited to a distance of
+     * wSize-MAX_MATCH bytes, but this ensures that IO is always
+     * performed with a length multiple of the block size. Also, it limits
+     * the window size to 64K, which is quite useful on MSDOS.
+     * To do: use the user input buffer as sliding window.
+     */
+
+    ulg window_size;
+    /* Actual size of window: 2*wSize, except when the user input buffer
+     * is directly used as sliding window.
+     */
+
+    Pos *prev;
+    /* Link to older string with same hash index. To limit the size of this
+     * array to 64K, this link is maintained only for the last 32K strings.
+     * An index in this array is thus a window index modulo 32K.
+     */
+
+    Pos *head; /* Heads of the hash chains or NIL. */
+
+    uInt  ins_h;          /* hash index of string to be inserted */
+    uInt  hash_size;      /* number of elements in hash table */
+    uInt  hash_bits;      /* log2(hash_size) */
+    uInt  hash_mask;      /* hash_size-1 */
+
+    uInt  hash_shift;
+    /* Number of bits by which ins_h must be shifted at each input
+     * step. It must be such that after MIN_MATCH steps, the oldest
+     * byte no longer takes part in the hash key, that is:
+     *   hash_shift * MIN_MATCH >= hash_bits
+     */
+
+    long block_start;
+    /* Window position at the beginning of the current output block. Gets
+     * negative when the window is moved backwards.
+     */
+
+    uInt match_length;           /* length of best match */
+    IPos prev_match;             /* previous match */
+    int match_available;         /* set if previous match exists */
+    uInt strstart;               /* start of string to insert */
+    uInt match_start;            /* start of matching string */
+    uInt lookahead;              /* number of valid bytes ahead in window */
+
+    uInt prev_length;
+    /* Length of the best match at previous step. Matches not greater than this
+     * are discarded. This is used in the lazy match evaluation.
+     */
+
+    uInt max_chain_length;
+    /* To speed up deflation, hash chains are never searched beyond this
+     * length.  A higher limit improves compression ratio but degrades the
+     * speed.
+     */
+
+    uInt max_lazy_match;
+    /* Attempt to find a better match only when the current match is strictly
+     * smaller than this value. This mechanism is used only for compression
+     * levels >= 4.
+     */
+#   define max_insert_length  max_lazy_match
+    /* Insert new strings in the hash table only if the match length is not
+     * greater than this length. This saves time but degrades compression.
+     * max_insert_length is used only for compression levels <= 3.
+     */
+
+    int level;    /* compression level (1..9) */
+    int strategy; /* favor or force Huffman coding*/
+
+    uInt good_match;
+    /* Use a faster search when the previous match is longer than this */
+
+    int nice_match; /* Stop searching when current match exceeds this */
+
+                /* used by trees.c: */
+    /* Didn't use ct_data typedef below to supress compiler warning */
+    struct ct_data_s dyn_ltree[HEAP_SIZE];   /* literal and length tree */
+    struct ct_data_s dyn_dtree[2*D_CODES+1]; /* distance tree */
+    struct ct_data_s bl_tree[2*BL_CODES+1];  /* Huffman tree for bit lengths */
+
+    struct tree_desc_s l_desc;               /* desc. for literal tree */
+    struct tree_desc_s d_desc;               /* desc. for distance tree */
+    struct tree_desc_s bl_desc;              /* desc. for bit length tree */
+
+    ush bl_count[MAX_BITS+1];
+    /* number of codes at each bit length for an optimal tree */
+
+    int heap[2*L_CODES+1];      /* heap used to build the Huffman trees */
+    int heap_len;               /* number of elements in the heap */
+    int heap_max;               /* element of largest frequency */
+    /* The sons of heap[n] are heap[2*n] and heap[2*n+1]. heap[0] is not used.
+     * The same heap array is used to build all trees.
+     */
+
+    uch depth[2*L_CODES+1];
+    /* Depth of each subtree used as tie breaker for trees of equal frequency
+     */
+
+    uch *l_buf;          /* buffer for literals or lengths */
+
+    uInt  lit_bufsize;
+    /* Size of match buffer for literals/lengths.  There are 4 reasons for
+     * limiting lit_bufsize to 64K:
+     *   - frequencies can be kept in 16 bit counters
+     *   - if compression is not successful for the first block, all input
+     *     data is still in the window so we can still emit a stored block even
+     *     when input comes from standard input.  (This can also be done for
+     *     all blocks if lit_bufsize is not greater than 32K.)
+     *   - if compression is not successful for a file smaller than 64K, we can
+     *     even emit a stored file instead of a stored block (saving 5 bytes).
+     *     This is applicable only for zip (not gzip or zlib).
+     *   - creating new Huffman trees less frequently may not provide fast
+     *     adaptation to changes in the input data statistics. (Take for
+     *     example a binary file with poorly compressible code followed by
+     *     a highly compressible string table.) Smaller buffer sizes give
+     *     fast adaptation but have of course the overhead of transmitting
+     *     trees more frequently.
+     *   - I can't count above 4
+     */
+
+    uInt last_lit;      /* running index in l_buf */
+
+    ush *d_buf;
+    /* Buffer for distances. To simplify the code, d_buf and l_buf have
+     * the same number of elements. To use different lengths, an extra flag
+     * array would be necessary.
+     */
+
+    ulg opt_len;        /* bit length of current block with optimal trees */
+    ulg static_len;     /* bit length of current block with static trees */
+    ulg compressed_len; /* total bit length of compressed file */
+    uInt matches;       /* number of string matches in current block */
+    int last_eob_len;   /* bit length of EOB code for last block */
+
+#ifdef DEBUG_ZLIB
+    ulg bits_sent;      /* bit length of the compressed data */
+#endif
+
+    ush bi_buf;
+    /* Output buffer. bits are inserted starting at the bottom (least
+     * significant bits).
+     */
+    int bi_valid;
+    /* Number of valid bits in bi_buf.  All bits above the last valid bit
+     * are always zero.
+     */
+
+} deflate_state;
+
+typedef struct deflate_workspace {
+    /* State memory for the deflator */
+    deflate_state deflate_memory;
+    Byte window_memory[2 * (1 << MAX_WBITS)];
+    Pos prev_memory[1 << MAX_WBITS];
+    Pos head_memory[1 << (MAX_MEM_LEVEL + 7)];
+    char overlay_memory[(1 << (MAX_MEM_LEVEL + 6)) * (sizeof(ush)+2)];
+} deflate_workspace;
+
+/* Output a byte on the stream.
+ * IN assertion: there is enough room in pending_buf.
+ */
+#define put_byte(s, c) {s->pending_buf[s->pending++] = (c);}
+
+
+#define MIN_LOOKAHEAD (MAX_MATCH+MIN_MATCH+1)
+/* Minimum amount of lookahead, except at the end of the input file.
+ * See deflate.c for comments about the MIN_MATCH+1.
+ */
+
+#define MAX_DIST(s)  ((s)->w_size-MIN_LOOKAHEAD)
+/* In order to simplify the code, particularly on 16 bit machines, match
+ * distances are limited to MAX_DIST instead of WSIZE.
+ */
+
+        /* in trees.c */
+void zlib_tr_init         (deflate_state *s);
+int  zlib_tr_tally        (deflate_state *s, unsigned dist, unsigned lc);
+ulg  zlib_tr_flush_block  (deflate_state *s, char *buf, ulg stored_len,
+			   int eof);
+void zlib_tr_align        (deflate_state *s);
+void zlib_tr_stored_block (deflate_state *s, char *buf, ulg stored_len,
+			   int eof);
+void zlib_tr_stored_type_only (deflate_state *);
+
+
+/* ===========================================================================
+ * Output a short LSB first on the stream.
+ * IN assertion: there is enough room in pendingBuf.
+ */
+#define put_short(s, w) { \
+    put_byte(s, (uch)((w) & 0xff)); \
+    put_byte(s, (uch)((ush)(w) >> 8)); \
+}
+
+/* ===========================================================================
+ * Reverse the first len bits of a code, using straightforward code (a faster
+ * method would use a table)
+ * IN assertion: 1 <= len <= 15
+ */
+static inline unsigned bi_reverse(unsigned code, /* the value to invert */
+				  int len)       /* its bit length */
+{
+    register unsigned res = 0;
+    do {
+        res |= code & 1;
+        code >>= 1, res <<= 1;
+    } while (--len > 0);
+    return res >> 1;
+}
+
+/* ===========================================================================
+ * Flush the bit buffer, keeping at most 7 bits in it.
+ */
+static inline void bi_flush(deflate_state *s)
+{
+    if (s->bi_valid == 16) {
+        put_short(s, s->bi_buf);
+        s->bi_buf = 0;
+        s->bi_valid = 0;
+    } else if (s->bi_valid >= 8) {
+        put_byte(s, (Byte)s->bi_buf);
+        s->bi_buf >>= 8;
+        s->bi_valid -= 8;
+    }
+}
+
+/* ===========================================================================
+ * Flush the bit buffer and align the output on a byte boundary
+ */
+static inline void bi_windup(deflate_state *s)
+{
+    if (s->bi_valid > 8) {
+        put_short(s, s->bi_buf);
+    } else if (s->bi_valid > 0) {
+        put_byte(s, (Byte)s->bi_buf);
+    }
+    s->bi_buf = 0;
+    s->bi_valid = 0;
+#ifdef DEBUG_ZLIB
+    s->bits_sent = (s->bits_sent+7) & ~7;
+#endif
+}
+

lib/zlib_inflate/Makefile

@@ -0,0 +1,19 @@
+#
+# This is a modified version of zlib, which does all memory
+# allocation ahead of time.
+#
+# This is only the decompression, see zlib_deflate for the
+# the compression
+#
+# Decompression needs to be serialized for each memory
+# allocation.
+#
+# (The upsides of the simplification is that you can't get in
+# any nasty situations wrt memory management, and that the
+# uncompression can be done without blocking on allocation).
+#
+
+obj-$(CONFIG_ZLIB_INFLATE) += zlib_inflate.o
+
+zlib_inflate-objs := inffast.o inflate.o \
+		     inftrees.o inflate_syms.o

lib/zlib_inflate/inffast.c

@@ -0,0 +1,312 @@
+/* inffast.c -- fast decoding
+ * Copyright (C) 1995-2004 Mark Adler
+ * For conditions of distribution and use, see copyright notice in zlib.h
+ */
+
+#include <linux/zutil.h>
+#include "inftrees.h"
+#include "inflate.h"
+#include "inffast.h"
+
+#ifndef ASMINF
+
+/* Allow machine dependent optimization for post-increment or pre-increment.
+   Based on testing to date,
+   Pre-increment preferred for:
+   - PowerPC G3 (Adler)
+   - MIPS R5000 (Randers-Pehrson)
+   Post-increment preferred for:
+   - none
+   No measurable difference:
+   - Pentium III (Anderson)
+   - M68060 (Nikl)
+ */
+#ifdef POSTINC
+#  define OFF 0
+#  define PUP(a) *(a)++
+#else
+#  define OFF 1
+#  define PUP(a) *++(a)
+#endif
+
+/*
+   Decode literal, length, and distance codes and write out the resulting
+   literal and match bytes until either not enough input or output is
+   available, an end-of-block is encountered, or a data error is encountered.
+   When large enough input and output buffers are supplied to inflate(), for
+   example, a 16K input buffer and a 64K output buffer, more than 95% of the
+   inflate execution time is spent in this routine.
+
+   Entry assumptions:
+
+        state->mode == LEN
+        strm->avail_in >= 6
+        strm->avail_out >= 258
+        start >= strm->avail_out
+        state->bits < 8
+
+   On return, state->mode is one of:
+
+        LEN -- ran out of enough output space or enough available input
+        TYPE -- reached end of block code, inflate() to interpret next block
+        BAD -- error in block data
+
+   Notes:
+
+    - The maximum input bits used by a length/distance pair is 15 bits for the
+      length code, 5 bits for the length extra, 15 bits for the distance code,
+      and 13 bits for the distance extra.  This totals 48 bits, or six bytes.
+      Therefore if strm->avail_in >= 6, then there is enough input to avoid
+      checking for available input while decoding.
+
+    - The maximum bytes that a single length/distance pair can output is 258
+      bytes, which is the maximum length that can be coded.  inflate_fast()
+      requires strm->avail_out >= 258 for each loop to avoid checking for
+      output space.
+
+    - @start:	inflate()'s starting value for strm->avail_out
+ */
+void inflate_fast(z_streamp strm, unsigned start)
+{
+    struct inflate_state *state;
+    unsigned char *in;      /* local strm->next_in */
+    unsigned char *last;    /* while in < last, enough input available */
+    unsigned char *out;     /* local strm->next_out */
+    unsigned char *beg;     /* inflate()'s initial strm->next_out */
+    unsigned char *end;     /* while out < end, enough space available */
+#ifdef INFLATE_STRICT
+    unsigned dmax;              /* maximum distance from zlib header */
+#endif
+    unsigned wsize;             /* window size or zero if not using window */
+    unsigned whave;             /* valid bytes in the window */
+    unsigned write;             /* window write index */
+    unsigned char *window;  /* allocated sliding window, if wsize != 0 */
+    unsigned long hold;         /* local strm->hold */
+    unsigned bits;              /* local strm->bits */
+    code const *lcode;      /* local strm->lencode */
+    code const *dcode;      /* local strm->distcode */
+    unsigned lmask;             /* mask for first level of length codes */
+    unsigned dmask;             /* mask for first level of distance codes */
+    code this;                  /* retrieved table entry */
+    unsigned op;                /* code bits, operation, extra bits, or */
+                                /*  window position, window bytes to copy */
+    unsigned len;               /* match length, unused bytes */
+    unsigned dist;              /* match distance */
+    unsigned char *from;    /* where to copy match from */
+
+    /* copy state to local variables */
+    state = (struct inflate_state *)strm->state;
+    in = strm->next_in - OFF;
+    last = in + (strm->avail_in - 5);
+    out = strm->next_out - OFF;
+    beg = out - (start - strm->avail_out);
+    end = out + (strm->avail_out - 257);
+#ifdef INFLATE_STRICT
+    dmax = state->dmax;
+#endif
+    wsize = state->wsize;
+    whave = state->whave;
+    write = state->write;
+    window = state->window;
+    hold = state->hold;
+    bits = state->bits;
+    lcode = state->lencode;
+    dcode = state->distcode;
+    lmask = (1U << state->lenbits) - 1;
+    dmask = (1U << state->distbits) - 1;
+
+    /* decode literals and length/distances until end-of-block or not enough
+       input data or output space */
+    do {
+        if (bits < 15) {
+            hold += (unsigned long)(PUP(in)) << bits;
+            bits += 8;
+            hold += (unsigned long)(PUP(in)) << bits;
+            bits += 8;
+        }
+        this = lcode[hold & lmask];
+      dolen:
+        op = (unsigned)(this.bits);
+        hold >>= op;
+        bits -= op;
+        op = (unsigned)(this.op);
+        if (op == 0) {                          /* literal */
+            PUP(out) = (unsigned char)(this.val);
+        }
+        else if (op & 16) {                     /* length base */
+            len = (unsigned)(this.val);
+            op &= 15;                           /* number of extra bits */
+            if (op) {
+                if (bits < op) {
+                    hold += (unsigned long)(PUP(in)) << bits;
+                    bits += 8;
+                }
+                len += (unsigned)hold & ((1U << op) - 1);
+                hold >>= op;
+                bits -= op;
+            }
+            if (bits < 15) {
+                hold += (unsigned long)(PUP(in)) << bits;
+                bits += 8;
+                hold += (unsigned long)(PUP(in)) << bits;
+                bits += 8;
+            }
+            this = dcode[hold & dmask];
+          dodist:
+            op = (unsigned)(this.bits);
+            hold >>= op;
+            bits -= op;
+            op = (unsigned)(this.op);
+            if (op & 16) {                      /* distance base */
+                dist = (unsigned)(this.val);
+                op &= 15;                       /* number of extra bits */
+                if (bits < op) {
+                    hold += (unsigned long)(PUP(in)) << bits;
+                    bits += 8;
+                    if (bits < op) {
+                        hold += (unsigned long)(PUP(in)) << bits;
+                        bits += 8;
+                    }
+                }
+                dist += (unsigned)hold & ((1U << op) - 1);
+#ifdef INFLATE_STRICT
+                if (dist > dmax) {
+                    strm->msg = (char *)"invalid distance too far back";
+                    state->mode = BAD;
+                    break;
+                }
+#endif
+                hold >>= op;
+                bits -= op;
+                op = (unsigned)(out - beg);     /* max distance in output */
+                if (dist > op) {                /* see if copy from window */
+                    op = dist - op;             /* distance back in window */
+                    if (op > whave) {
+                        strm->msg = (char *)"invalid distance too far back";
+                        state->mode = BAD;
+                        break;
+                    }
+                    from = window - OFF;
+                    if (write == 0) {           /* very common case */
+                        from += wsize - op;
+                        if (op < len) {         /* some from window */
+                            len -= op;
+                            do {
+                                PUP(out) = PUP(from);
+                            } while (--op);
+                            from = out - dist;  /* rest from output */
+                        }
+                    }
+                    else if (write < op) {      /* wrap around window */
+                        from += wsize + write - op;
+                        op -= write;
+                        if (op < len) {         /* some from end of window */
+                            len -= op;
+                            do {
+                                PUP(out) = PUP(from);
+                            } while (--op);
+                            from = window - OFF;
+                            if (write < len) {  /* some from start of window */
+                                op = write;
+                                len -= op;
+                                do {
+                                    PUP(out) = PUP(from);
+                                } while (--op);
+                                from = out - dist;      /* rest from output */
+                            }
+                        }
+                    }
+                    else {                      /* contiguous in window */
+                        from += write - op;
+                        if (op < len) {         /* some from window */
+                            len -= op;
+                            do {
+                                PUP(out) = PUP(from);
+                            } while (--op);
+                            from = out - dist;  /* rest from output */
+                        }
+                    }
+                    while (len > 2) {
+                        PUP(out) = PUP(from);
+                        PUP(out) = PUP(from);
+                        PUP(out) = PUP(from);
+                        len -= 3;
+                    }
+                    if (len) {
+                        PUP(out) = PUP(from);
+                        if (len > 1)
+                            PUP(out) = PUP(from);
+                    }
+                }
+                else {
+                    from = out - dist;          /* copy direct from output */
+                    do {                        /* minimum length is three */
+                        PUP(out) = PUP(from);
+                        PUP(out) = PUP(from);
+                        PUP(out) = PUP(from);
+                        len -= 3;
+                    } while (len > 2);
+                    if (len) {
+                        PUP(out) = PUP(from);
+                        if (len > 1)
+                            PUP(out) = PUP(from);
+                    }
+                }
+            }
+            else if ((op & 64) == 0) {          /* 2nd level distance code */
+                this = dcode[this.val + (hold & ((1U << op) - 1))];
+                goto dodist;
+            }
+            else {
+                strm->msg = (char *)"invalid distance code";
+                state->mode = BAD;
+                break;
+            }
+        }
+        else if ((op & 64) == 0) {              /* 2nd level length code */
+            this = lcode[this.val + (hold & ((1U << op) - 1))];
+            goto dolen;
+        }
+        else if (op & 32) {                     /* end-of-block */
+            state->mode = TYPE;
+            break;
+        }
+        else {
+            strm->msg = (char *)"invalid literal/length code";
+            state->mode = BAD;
+            break;
+        }
+    } while (in < last && out < end);
+
+    /* return unused bytes (on entry, bits < 8, so in won't go too far back) */
+    len = bits >> 3;
+    in -= len;
+    bits -= len << 3;
+    hold &= (1U << bits) - 1;
+
+    /* update state and return */
+    strm->next_in = in + OFF;
+    strm->next_out = out + OFF;
+    strm->avail_in = (unsigned)(in < last ? 5 + (last - in) : 5 - (in - last));
+    strm->avail_out = (unsigned)(out < end ?
+                                 257 + (end - out) : 257 - (out - end));
+    state->hold = hold;
+    state->bits = bits;
+    return;
+}
+
+/*
+   inflate_fast() speedups that turned out slower (on a PowerPC G3 750CXe):
+   - Using bit fields for code structure
+   - Different op definition to avoid & for extra bits (do & for table bits)
+   - Three separate decoding do-loops for direct, window, and write == 0
+   - Special case for distance > 1 copies to do overlapped load and store copy
+   - Explicit branch predictions (based on measured branch probabilities)
+   - Deferring match copy and interspersed it with decoding subsequent codes
+   - Swapping literal/length else
+   - Swapping window/direct else
+   - Larger unrolled copy loops (three is about right)
+   - Moving len -= 3 statement into middle of loop
+ */
+
+#endif /* !ASMINF */

lib/zlib_inflate/inffast.h

@@ -0,0 +1,11 @@
+/* inffast.h -- header to use inffast.c
+ * Copyright (C) 1995-2003 Mark Adler
+ * For conditions of distribution and use, see copyright notice in zlib.h
+ */
+
+/* WARNING: this file should *not* be used by applications. It is
+   part of the implementation of the compression library and is
+   subject to change. Applications should only use zlib.h.
+ */
+
+void inflate_fast (z_streamp strm, unsigned start);

lib/zlib_inflate/inffixed.h

@@ -0,0 +1,94 @@
+    /* inffixed.h -- table for decoding fixed codes
+     * Generated automatically by makefixed().
+     */
+
+    /* WARNING: this file should *not* be used by applications. It
+       is part of the implementation of the compression library and
+       is subject to change. Applications should only use zlib.h.
+     */
+
+    static const code lenfix[512] = {
+        {96,7,0},{0,8,80},{0,8,16},{20,8,115},{18,7,31},{0,8,112},{0,8,48},
+        {0,9,192},{16,7,10},{0,8,96},{0,8,32},{0,9,160},{0,8,0},{0,8,128},
+        {0,8,64},{0,9,224},{16,7,6},{0,8,88},{0,8,24},{0,9,144},{19,7,59},
+        {0,8,120},{0,8,56},{0,9,208},{17,7,17},{0,8,104},{0,8,40},{0,9,176},
+        {0,8,8},{0,8,136},{0,8,72},{0,9,240},{16,7,4},{0,8,84},{0,8,20},
+        {21,8,227},{19,7,43},{0,8,116},{0,8,52},{0,9,200},{17,7,13},{0,8,100},
+        {0,8,36},{0,9,168},{0,8,4},{0,8,132},{0,8,68},{0,9,232},{16,7,8},
+        {0,8,92},{0,8,28},{0,9,152},{20,7,83},{0,8,124},{0,8,60},{0,9,216},
+        {18,7,23},{0,8,108},{0,8,44},{0,9,184},{0,8,12},{0,8,140},{0,8,76},
+        {0,9,248},{16,7,3},{0,8,82},{0,8,18},{21,8,163},{19,7,35},{0,8,114},
+        {0,8,50},{0,9,196},{17,7,11},{0,8,98},{0,8,34},{0,9,164},{0,8,2},
+        {0,8,130},{0,8,66},{0,9,228},{16,7,7},{0,8,90},{0,8,26},{0,9,148},
+        {20,7,67},{0,8,122},{0,8,58},{0,9,212},{18,7,19},{0,8,106},{0,8,42},
+        {0,9,180},{0,8,10},{0,8,138},{0,8,74},{0,9,244},{16,7,5},{0,8,86},
+        {0,8,22},{64,8,0},{19,7,51},{0,8,118},{0,8,54},{0,9,204},{17,7,15},
+        {0,8,102},{0,8,38},{0,9,172},{0,8,6},{0,8,134},{0,8,70},{0,9,236},
+        {16,7,9},{0,8,94},{0,8,30},{0,9,156},{20,7,99},{0,8,126},{0,8,62},
+        {0,9,220},{18,7,27},{0,8,110},{0,8,46},{0,9,188},{0,8,14},{0,8,142},
+        {0,8,78},{0,9,252},{96,7,0},{0,8,81},{0,8,17},{21,8,131},{18,7,31},
+        {0,8,113},{0,8,49},{0,9,194},{16,7,10},{0,8,97},{0,8,33},{0,9,162},
+        {0,8,1},{0,8,129},{0,8,65},{0,9,226},{16,7,6},{0,8,89},{0,8,25},
+        {0,9,146},{19,7,59},{0,8,121},{0,8,57},{0,9,210},{17,7,17},{0,8,105},
+        {0,8,41},{0,9,178},{0,8,9},{0,8,137},{0,8,73},{0,9,242},{16,7,4},
+        {0,8,85},{0,8,21},{16,8,258},{19,7,43},{0,8,117},{0,8,53},{0,9,202},
+        {17,7,13},{0,8,101},{0,8,37},{0,9,170},{0,8,5},{0,8,133},{0,8,69},
+        {0,9,234},{16,7,8},{0,8,93},{0,8,29},{0,9,154},{20,7,83},{0,8,125},
+        {0,8,61},{0,9,218},{18,7,23},{0,8,109},{0,8,45},{0,9,186},{0,8,13},
+        {0,8,141},{0,8,77},{0,9,250},{16,7,3},{0,8,83},{0,8,19},{21,8,195},
+        {19,7,35},{0,8,115},{0,8,51},{0,9,198},{17,7,11},{0,8,99},{0,8,35},
+        {0,9,166},{0,8,3},{0,8,131},{0,8,67},{0,9,230},{16,7,7},{0,8,91},
+        {0,8,27},{0,9,150},{20,7,67},{0,8,123},{0,8,59},{0,9,214},{18,7,19},
+        {0,8,107},{0,8,43},{0,9,182},{0,8,11},{0,8,139},{0,8,75},{0,9,246},
+        {16,7,5},{0,8,87},{0,8,23},{64,8,0},{19,7,51},{0,8,119},{0,8,55},
+        {0,9,206},{17,7,15},{0,8,103},{0,8,39},{0,9,174},{0,8,7},{0,8,135},
+        {0,8,71},{0,9,238},{16,7,9},{0,8,95},{0,8,31},{0,9,158},{20,7,99},
+        {0,8,127},{0,8,63},{0,9,222},{18,7,27},{0,8,111},{0,8,47},{0,9,190},
+        {0,8,15},{0,8,143},{0,8,79},{0,9,254},{96,7,0},{0,8,80},{0,8,16},
+        {20,8,115},{18,7,31},{0,8,112},{0,8,48},{0,9,193},{16,7,10},{0,8,96},
+        {0,8,32},{0,9,161},{0,8,0},{0,8,128},{0,8,64},{0,9,225},{16,7,6},
+        {0,8,88},{0,8,24},{0,9,145},{19,7,59},{0,8,120},{0,8,56},{0,9,209},
+        {17,7,17},{0,8,104},{0,8,40},{0,9,177},{0,8,8},{0,8,136},{0,8,72},
+        {0,9,241},{16,7,4},{0,8,84},{0,8,20},{21,8,227},{19,7,43},{0,8,116},
+        {0,8,52},{0,9,201},{17,7,13},{0,8,100},{0,8,36},{0,9,169},{0,8,4},
+        {0,8,132},{0,8,68},{0,9,233},{16,7,8},{0,8,92},{0,8,28},{0,9,153},
+        {20,7,83},{0,8,124},{0,8,60},{0,9,217},{18,7,23},{0,8,108},{0,8,44},
+        {0,9,185},{0,8,12},{0,8,140},{0,8,76},{0,9,249},{16,7,3},{0,8,82},
+        {0,8,18},{21,8,163},{19,7,35},{0,8,114},{0,8,50},{0,9,197},{17,7,11},
+        {0,8,98},{0,8,34},{0,9,165},{0,8,2},{0,8,130},{0,8,66},{0,9,229},
+        {16,7,7},{0,8,90},{0,8,26},{0,9,149},{20,7,67},{0,8,122},{0,8,58},
+        {0,9,213},{18,7,19},{0,8,106},{0,8,42},{0,9,181},{0,8,10},{0,8,138},
+        {0,8,74},{0,9,245},{16,7,5},{0,8,86},{0,8,22},{64,8,0},{19,7,51},
+        {0,8,118},{0,8,54},{0,9,205},{17,7,15},{0,8,102},{0,8,38},{0,9,173},
+        {0,8,6},{0,8,134},{0,8,70},{0,9,237},{16,7,9},{0,8,94},{0,8,30},
+        {0,9,157},{20,7,99},{0,8,126},{0,8,62},{0,9,221},{18,7,27},{0,8,110},
+        {0,8,46},{0,9,189},{0,8,14},{0,8,142},{0,8,78},{0,9,253},{96,7,0},
+        {0,8,81},{0,8,17},{21,8,131},{18,7,31},{0,8,113},{0,8,49},{0,9,195},
+        {16,7,10},{0,8,97},{0,8,33},{0,9,163},{0,8,1},{0,8,129},{0,8,65},
+        {0,9,227},{16,7,6},{0,8,89},{0,8,25},{0,9,147},{19,7,59},{0,8,121},
+        {0,8,57},{0,9,211},{17,7,17},{0,8,105},{0,8,41},{0,9,179},{0,8,9},
+        {0,8,137},{0,8,73},{0,9,243},{16,7,4},{0,8,85},{0,8,21},{16,8,258},
+        {19,7,43},{0,8,117},{0,8,53},{0,9,203},{17,7,13},{0,8,101},{0,8,37},
+        {0,9,171},{0,8,5},{0,8,133},{0,8,69},{0,9,235},{16,7,8},{0,8,93},
+        {0,8,29},{0,9,155},{20,7,83},{0,8,125},{0,8,61},{0,9,219},{18,7,23},
+        {0,8,109},{0,8,45},{0,9,187},{0,8,13},{0,8,141},{0,8,77},{0,9,251},
+        {16,7,3},{0,8,83},{0,8,19},{21,8,195},{19,7,35},{0,8,115},{0,8,51},
+        {0,9,199},{17,7,11},{0,8,99},{0,8,35},{0,9,167},{0,8,3},{0,8,131},
+        {0,8,67},{0,9,231},{16,7,7},{0,8,91},{0,8,27},{0,9,151},{20,7,67},
+        {0,8,123},{0,8,59},{0,9,215},{18,7,19},{0,8,107},{0,8,43},{0,9,183},
+        {0,8,11},{0,8,139},{0,8,75},{0,9,247},{16,7,5},{0,8,87},{0,8,23},
+        {64,8,0},{19,7,51},{0,8,119},{0,8,55},{0,9,207},{17,7,15},{0,8,103},
+        {0,8,39},{0,9,175},{0,8,7},{0,8,135},{0,8,71},{0,9,239},{16,7,9},
+        {0,8,95},{0,8,31},{0,9,159},{20,7,99},{0,8,127},{0,8,63},{0,9,223},
+        {18,7,27},{0,8,111},{0,8,47},{0,9,191},{0,8,15},{0,8,143},{0,8,79},
+        {0,9,255}
+    };
+
+    static const code distfix[32] = {
+        {16,5,1},{23,5,257},{19,5,17},{27,5,4097},{17,5,5},{25,5,1025},
+        {21,5,65},{29,5,16385},{16,5,3},{24,5,513},{20,5,33},{28,5,8193},
+        {18,5,9},{26,5,2049},{22,5,129},{64,5,0},{16,5,2},{23,5,385},
+        {19,5,25},{27,5,6145},{17,5,7},{25,5,1537},{21,5,97},{29,5,24577},
+        {16,5,4},{24,5,769},{20,5,49},{28,5,12289},{18,5,13},{26,5,3073},
+        {22,5,193},{64,5,0}
+    };

lib/zlib_inflate/inflate.c

@@ -0,0 +1,918 @@
+/* inflate.c -- zlib decompression
+ * Copyright (C) 1995-2005 Mark Adler
+ * For conditions of distribution and use, see copyright notice in zlib.h
+ *
+ * Based on zlib 1.2.3 but modified for the Linux Kernel by
+ * Richard Purdie <richard@openedhand.com>
+ *
+ * Changes mainly for static instead of dynamic memory allocation
+ *
+ */
+
+#include <linux/zutil.h>
+#include "inftrees.h"
+#include "inflate.h"
+#include "inffast.h"
+#include "infutil.h"
+
+int zlib_inflate_workspacesize(void)
+{
+    return sizeof(struct inflate_workspace);
+}
+
+int zlib_inflateReset(z_streamp strm)
+{
+    struct inflate_state *state;
+
+    if (strm == NULL || strm->state == NULL) return Z_STREAM_ERROR;
+    state = (struct inflate_state *)strm->state;
+    strm->total_in = strm->total_out = state->total = 0;
+    strm->msg = NULL;
+    strm->adler = 1;        /* to support ill-conceived Java test suite */
+    state->mode = HEAD;
+    state->last = 0;
+    state->havedict = 0;
+    state->dmax = 32768U;
+    state->hold = 0;
+    state->bits = 0;
+    state->lencode = state->distcode = state->next = state->codes;
+
+    /* Initialise Window */
+    state->wsize = 1U << state->wbits;
+    state->write = 0;
+    state->whave = 0;
+
+    return Z_OK;
+}
+
+#if 0
+int zlib_inflatePrime(z_streamp strm, int bits, int value)
+{
+    struct inflate_state *state;
+
+    if (strm == NULL || strm->state == NULL) return Z_STREAM_ERROR;
+    state = (struct inflate_state *)strm->state;
+    if (bits > 16 || state->bits + bits > 32) return Z_STREAM_ERROR;
+    value &= (1L << bits) - 1;
+    state->hold += value << state->bits;
+    state->bits += bits;
+    return Z_OK;
+}
+#endif
+
+int zlib_inflateInit2(z_streamp strm, int windowBits)
+{
+    struct inflate_state *state;
+
+    if (strm == NULL) return Z_STREAM_ERROR;
+    strm->msg = NULL;                 /* in case we return an error */
+
+    state = &WS(strm)->inflate_state;
+    strm->state = (struct internal_state *)state;
+
+    if (windowBits < 0) {
+        state->wrap = 0;
+        windowBits = -windowBits;
+    }
+    else {
+        state->wrap = (windowBits >> 4) + 1;
+    }
+    if (windowBits < 8 || windowBits > 15) {
+        return Z_STREAM_ERROR;
+    }
+    state->wbits = (unsigned)windowBits;
+    state->window = &WS(strm)->working_window[0];
+
+    return zlib_inflateReset(strm);
+}
+
+/*
+   Return state with length and distance decoding tables and index sizes set to
+   fixed code decoding.  This returns fixed tables from inffixed.h.
+ */
+static void zlib_fixedtables(struct inflate_state *state)
+{
+#   include "inffixed.h"
+    state->lencode = lenfix;
+    state->lenbits = 9;
+    state->distcode = distfix;
+    state->distbits = 5;
+}
+
+
+/*
+   Update the window with the last wsize (normally 32K) bytes written before
+   returning. This is only called when a window is already in use, or when
+   output has been written during this inflate call, but the end of the deflate
+   stream has not been reached yet. It is also called to window dictionary data
+   when a dictionary is loaded.
+
+   Providing output buffers larger than 32K to inflate() should provide a speed
+   advantage, since only the last 32K of output is copied to the sliding window
+   upon return from inflate(), and since all distances after the first 32K of
+   output will fall in the output data, making match copies simpler and faster.
+   The advantage may be dependent on the size of the processor's data caches.
+ */
+static void zlib_updatewindow(z_streamp strm, unsigned out)
+{
+    struct inflate_state *state;
+    unsigned copy, dist;
+
+    state = (struct inflate_state *)strm->state;
+
+    /* copy state->wsize or less output bytes into the circular window */
+    copy = out - strm->avail_out;
+    if (copy >= state->wsize) {
+        memcpy(state->window, strm->next_out - state->wsize, state->wsize);
+        state->write = 0;
+        state->whave = state->wsize;
+    }
+    else {
+        dist = state->wsize - state->write;
+        if (dist > copy) dist = copy;
+        memcpy(state->window + state->write, strm->next_out - copy, dist);
+        copy -= dist;
+        if (copy) {
+            memcpy(state->window, strm->next_out - copy, copy);
+            state->write = copy;
+            state->whave = state->wsize;
+        }
+        else {
+            state->write += dist;
+            if (state->write == state->wsize) state->write = 0;
+            if (state->whave < state->wsize) state->whave += dist;
+        }
+    }
+}
+
+
+/*
+ * At the end of a Deflate-compressed PPP packet, we expect to have seen
+ * a `stored' block type value but not the (zero) length bytes.
+ */
+/*
+   Returns true if inflate is currently at the end of a block generated by
+   Z_SYNC_FLUSH or Z_FULL_FLUSH. This function is used by one PPP
+   implementation to provide an additional safety check. PPP uses
+   Z_SYNC_FLUSH but removes the length bytes of the resulting empty stored
+   block. When decompressing, PPP checks that at the end of input packet,
+   inflate is waiting for these length bytes.
+ */
+static int zlib_inflateSyncPacket(z_streamp strm)
+{
+    struct inflate_state *state;
+
+    if (strm == NULL || strm->state == NULL) return Z_STREAM_ERROR;
+    state = (struct inflate_state *)strm->state;
+
+    if (state->mode == STORED && state->bits == 0) {
+	state->mode = TYPE;
+        return Z_OK;
+    }
+    return Z_DATA_ERROR;
+}
+
+/* Macros for inflate(): */
+
+/* check function to use adler32() for zlib or crc32() for gzip */
+#define UPDATE(check, buf, len) zlib_adler32(check, buf, len)
+
+/* Load registers with state in inflate() for speed */
+#define LOAD() \
+    do { \
+        put = strm->next_out; \
+        left = strm->avail_out; \
+        next = strm->next_in; \
+        have = strm->avail_in; \
+        hold = state->hold; \
+        bits = state->bits; \
+    } while (0)
+
+/* Restore state from registers in inflate() */
+#define RESTORE() \
+    do { \
+        strm->next_out = put; \
+        strm->avail_out = left; \
+        strm->next_in = next; \
+        strm->avail_in = have; \
+        state->hold = hold; \
+        state->bits = bits; \
+    } while (0)
+
+/* Clear the input bit accumulator */
+#define INITBITS() \
+    do { \
+        hold = 0; \
+        bits = 0; \
+    } while (0)
+
+/* Get a byte of input into the bit accumulator, or return from inflate()
+   if there is no input available. */
+#define PULLBYTE() \
+    do { \
+        if (have == 0) goto inf_leave; \
+        have--; \
+        hold += (unsigned long)(*next++) << bits; \
+        bits += 8; \
+    } while (0)
+
+/* Assure that there are at least n bits in the bit accumulator.  If there is
+   not enough available input to do that, then return from inflate(). */
+#define NEEDBITS(n) \
+    do { \
+        while (bits < (unsigned)(n)) \
+            PULLBYTE(); \
+    } while (0)
+
+/* Return the low n bits of the bit accumulator (n < 16) */
+#define BITS(n) \
+    ((unsigned)hold & ((1U << (n)) - 1))
+
+/* Remove n bits from the bit accumulator */
+#define DROPBITS(n) \
+    do { \
+        hold >>= (n); \
+        bits -= (unsigned)(n); \
+    } while (0)
+
+/* Remove zero to seven bits as needed to go to a byte boundary */
+#define BYTEBITS() \
+    do { \
+        hold >>= bits & 7; \
+        bits -= bits & 7; \
+    } while (0)
+
+/* Reverse the bytes in a 32-bit value */
+#define REVERSE(q) \
+    ((((q) >> 24) & 0xff) + (((q) >> 8) & 0xff00) + \
+     (((q) & 0xff00) << 8) + (((q) & 0xff) << 24))
+
+/*
+   inflate() uses a state machine to process as much input data and generate as
+   much output data as possible before returning.  The state machine is
+   structured roughly as follows:
+
+    for (;;) switch (state) {
+    ...
+    case STATEn:
+        if (not enough input data or output space to make progress)
+            return;
+        ... make progress ...
+        state = STATEm;
+        break;
+    ...
+    }
+
+   so when inflate() is called again, the same case is attempted again, and
+   if the appropriate resources are provided, the machine proceeds to the
+   next state.  The NEEDBITS() macro is usually the way the state evaluates
+   whether it can proceed or should return.  NEEDBITS() does the return if
+   the requested bits are not available.  The typical use of the BITS macros
+   is:
+
+        NEEDBITS(n);
+        ... do something with BITS(n) ...
+        DROPBITS(n);
+
+   where NEEDBITS(n) either returns from inflate() if there isn't enough
+   input left to load n bits into the accumulator, or it continues.  BITS(n)
+   gives the low n bits in the accumulator.  When done, DROPBITS(n) drops
+   the low n bits off the accumulator.  INITBITS() clears the accumulator
+   and sets the number of available bits to zero.  BYTEBITS() discards just
+   enough bits to put the accumulator on a byte boundary.  After BYTEBITS()
+   and a NEEDBITS(8), then BITS(8) would return the next byte in the stream.
+
+   NEEDBITS(n) uses PULLBYTE() to get an available byte of input, or to return
+   if there is no input available.  The decoding of variable length codes uses
+   PULLBYTE() directly in order to pull just enough bytes to decode the next
+   code, and no more.
+
+   Some states loop until they get enough input, making sure that enough
+   state information is maintained to continue the loop where it left off
+   if NEEDBITS() returns in the loop.  For example, want, need, and keep
+   would all have to actually be part of the saved state in case NEEDBITS()
+   returns:
+
+    case STATEw:
+        while (want < need) {
+            NEEDBITS(n);
+            keep[want++] = BITS(n);
+            DROPBITS(n);
+        }
+        state = STATEx;
+    case STATEx:
+
+   As shown above, if the next state is also the next case, then the break
+   is omitted.
+
+   A state may also return if there is not enough output space available to
+   complete that state.  Those states are copying stored data, writing a
+   literal byte, and copying a matching string.
+
+   When returning, a "goto inf_leave" is used to update the total counters,
+   update the check value, and determine whether any progress has been made
+   during that inflate() call in order to return the proper return code.
+   Progress is defined as a change in either strm->avail_in or strm->avail_out.
+   When there is a window, goto inf_leave will update the window with the last
+   output written.  If a goto inf_leave occurs in the middle of decompression
+   and there is no window currently, goto inf_leave will create one and copy
+   output to the window for the next call of inflate().
+
+   In this implementation, the flush parameter of inflate() only affects the
+   return code (per zlib.h).  inflate() always writes as much as possible to
+   strm->next_out, given the space available and the provided input--the effect
+   documented in zlib.h of Z_SYNC_FLUSH.  Furthermore, inflate() always defers
+   the allocation of and copying into a sliding window until necessary, which
+   provides the effect documented in zlib.h for Z_FINISH when the entire input
+   stream available.  So the only thing the flush parameter actually does is:
+   when flush is set to Z_FINISH, inflate() cannot return Z_OK.  Instead it
+   will return Z_BUF_ERROR if it has not reached the end of the stream.
+ */
+
+int zlib_inflate(z_streamp strm, int flush)
+{
+    struct inflate_state *state;
+    unsigned char *next;    /* next input */
+    unsigned char *put;     /* next output */
+    unsigned have, left;        /* available input and output */
+    unsigned long hold;         /* bit buffer */
+    unsigned bits;              /* bits in bit buffer */
+    unsigned in, out;           /* save starting available input and output */
+    unsigned copy;              /* number of stored or match bytes to copy */
+    unsigned char *from;    /* where to copy match bytes from */
+    code this;                  /* current decoding table entry */
+    code last;                  /* parent table entry */
+    unsigned len;               /* length to copy for repeats, bits to drop */
+    int ret;                    /* return code */
+    static const unsigned short order[19] = /* permutation of code lengths */
+        {16, 17, 18, 0, 8, 7, 9, 6, 10, 5, 11, 4, 12, 3, 13, 2, 14, 1, 15};
+
+    /* Do not check for strm->next_out == NULL here as ppc zImage
+       inflates to strm->next_out = 0 */
+
+    if (strm == NULL || strm->state == NULL ||
+        (strm->next_in == NULL && strm->avail_in != 0))
+        return Z_STREAM_ERROR;
+
+    state = (struct inflate_state *)strm->state;
+
+    if (state->mode == TYPE) state->mode = TYPEDO;      /* skip check */
+    LOAD();
+    in = have;
+    out = left;
+    ret = Z_OK;
+    for (;;)
+        switch (state->mode) {
+        case HEAD:
+            if (state->wrap == 0) {
+                state->mode = TYPEDO;
+                break;
+            }
+            NEEDBITS(16);
+            if (
+                ((BITS(8) << 8) + (hold >> 8)) % 31) {
+                strm->msg = (char *)"incorrect header check";
+                state->mode = BAD;
+                break;
+            }
+            if (BITS(4) != Z_DEFLATED) {
+                strm->msg = (char *)"unknown compression method";
+                state->mode = BAD;
+                break;
+            }
+            DROPBITS(4);
+            len = BITS(4) + 8;
+            if (len > state->wbits) {
+                strm->msg = (char *)"invalid window size";
+                state->mode = BAD;
+                break;
+            }
+            state->dmax = 1U << len;
+            strm->adler = state->check = zlib_adler32(0L, NULL, 0);
+            state->mode = hold & 0x200 ? DICTID : TYPE;
+            INITBITS();
+            break;
+        case DICTID:
+            NEEDBITS(32);
+            strm->adler = state->check = REVERSE(hold);
+            INITBITS();
+            state->mode = DICT;
+        case DICT:
+            if (state->havedict == 0) {
+                RESTORE();
+                return Z_NEED_DICT;
+            }
+            strm->adler = state->check = zlib_adler32(0L, NULL, 0);
+            state->mode = TYPE;
+        case TYPE:
+            if (flush == Z_BLOCK) goto inf_leave;
+        case TYPEDO:
+            if (state->last) {
+                BYTEBITS();
+                state->mode = CHECK;
+                break;
+            }
+            NEEDBITS(3);
+            state->last = BITS(1);
+            DROPBITS(1);
+            switch (BITS(2)) {
+            case 0:                             /* stored block */
+                state->mode = STORED;
+                break;
+            case 1:                             /* fixed block */
+                zlib_fixedtables(state);
+                state->mode = LEN;              /* decode codes */
+                break;
+            case 2:                             /* dynamic block */
+                state->mode = TABLE;
+                break;
+            case 3:
+                strm->msg = (char *)"invalid block type";
+                state->mode = BAD;
+            }
+            DROPBITS(2);
+            break;
+        case STORED:
+            BYTEBITS();                         /* go to byte boundary */
+            NEEDBITS(32);
+            if ((hold & 0xffff) != ((hold >> 16) ^ 0xffff)) {
+                strm->msg = (char *)"invalid stored block lengths";
+                state->mode = BAD;
+                break;
+            }
+            state->length = (unsigned)hold & 0xffff;
+            INITBITS();
+            state->mode = COPY;
+        case COPY:
+            copy = state->length;
+            if (copy) {
+                if (copy > have) copy = have;
+                if (copy > left) copy = left;
+                if (copy == 0) goto inf_leave;
+                memcpy(put, next, copy);
+                have -= copy;
+                next += copy;
+                left -= copy;
+                put += copy;
+                state->length -= copy;
+                break;
+            }
+            state->mode = TYPE;
+            break;
+        case TABLE:
+            NEEDBITS(14);
+            state->nlen = BITS(5) + 257;
+            DROPBITS(5);
+            state->ndist = BITS(5) + 1;
+            DROPBITS(5);
+            state->ncode = BITS(4) + 4;
+            DROPBITS(4);
+#ifndef PKZIP_BUG_WORKAROUND
+            if (state->nlen > 286 || state->ndist > 30) {
+                strm->msg = (char *)"too many length or distance symbols";
+                state->mode = BAD;
+                break;
+            }
+#endif
+            state->have = 0;
+            state->mode = LENLENS;
+        case LENLENS:
+            while (state->have < state->ncode) {
+                NEEDBITS(3);
+                state->lens[order[state->have++]] = (unsigned short)BITS(3);
+                DROPBITS(3);
+            }
+            while (state->have < 19)
+                state->lens[order[state->have++]] = 0;
+            state->next = state->codes;
+            state->lencode = (code const *)(state->next);
+            state->lenbits = 7;
+            ret = zlib_inflate_table(CODES, state->lens, 19, &(state->next),
+                                &(state->lenbits), state->work);
+            if (ret) {
+                strm->msg = (char *)"invalid code lengths set";
+                state->mode = BAD;
+                break;
+            }
+            state->have = 0;
+            state->mode = CODELENS;
+        case CODELENS:
+            while (state->have < state->nlen + state->ndist) {
+                for (;;) {
+                    this = state->lencode[BITS(state->lenbits)];
+                    if ((unsigned)(this.bits) <= bits) break;
+                    PULLBYTE();
+                }
+                if (this.val < 16) {
+                    NEEDBITS(this.bits);
+                    DROPBITS(this.bits);
+                    state->lens[state->have++] = this.val;
+                }
+                else {
+                    if (this.val == 16) {
+                        NEEDBITS(this.bits + 2);
+                        DROPBITS(this.bits);
+                        if (state->have == 0) {
+                            strm->msg = (char *)"invalid bit length repeat";
+                            state->mode = BAD;
+                            break;
+                        }
+                        len = state->lens[state->have - 1];
+                        copy = 3 + BITS(2);
+                        DROPBITS(2);
+                    }
+                    else if (this.val == 17) {
+                        NEEDBITS(this.bits + 3);
+                        DROPBITS(this.bits);
+                        len = 0;
+                        copy = 3 + BITS(3);
+                        DROPBITS(3);
+                    }
+                    else {
+                        NEEDBITS(this.bits + 7);
+                        DROPBITS(this.bits);
+                        len = 0;
+                        copy = 11 + BITS(7);
+                        DROPBITS(7);
+                    }
+                    if (state->have + copy > state->nlen + state->ndist) {
+                        strm->msg = (char *)"invalid bit length repeat";
+                        state->mode = BAD;
+                        break;
+                    }
+                    while (copy--)
+                        state->lens[state->have++] = (unsigned short)len;
+                }
+            }
+
+            /* handle error breaks in while */
+            if (state->mode == BAD) break;
+
+            /* build code tables */
+            state->next = state->codes;
+            state->lencode = (code const *)(state->next);
+            state->lenbits = 9;
+            ret = zlib_inflate_table(LENS, state->lens, state->nlen, &(state->next),
+                                &(state->lenbits), state->work);
+            if (ret) {
+                strm->msg = (char *)"invalid literal/lengths set";
+                state->mode = BAD;
+                break;
+            }
+            state->distcode = (code const *)(state->next);
+            state->distbits = 6;
+            ret = zlib_inflate_table(DISTS, state->lens + state->nlen, state->ndist,
+                            &(state->next), &(state->distbits), state->work);
+            if (ret) {
+                strm->msg = (char *)"invalid distances set";
+                state->mode = BAD;
+                break;
+            }
+            state->mode = LEN;
+        case LEN:
+            if (have >= 6 && left >= 258) {
+                RESTORE();
+                inflate_fast(strm, out);
+                LOAD();
+                break;
+            }
+            for (;;) {
+                this = state->lencode[BITS(state->lenbits)];
+                if ((unsigned)(this.bits) <= bits) break;
+                PULLBYTE();
+            }
+            if (this.op && (this.op & 0xf0) == 0) {
+                last = this;
+                for (;;) {
+                    this = state->lencode[last.val +
+                            (BITS(last.bits + last.op) >> last.bits)];
+                    if ((unsigned)(last.bits + this.bits) <= bits) break;
+                    PULLBYTE();
+                }
+                DROPBITS(last.bits);
+            }
+            DROPBITS(this.bits);
+            state->length = (unsigned)this.val;
+            if ((int)(this.op) == 0) {
+                state->mode = LIT;
+                break;
+            }
+            if (this.op & 32) {
+                state->mode = TYPE;
+                break;
+            }
+            if (this.op & 64) {
+                strm->msg = (char *)"invalid literal/length code";
+                state->mode = BAD;
+                break;
+            }
+            state->extra = (unsigned)(this.op) & 15;
+            state->mode = LENEXT;
+        case LENEXT:
+            if (state->extra) {
+                NEEDBITS(state->extra);
+                state->length += BITS(state->extra);
+                DROPBITS(state->extra);
+            }
+            state->mode = DIST;
+        case DIST:
+            for (;;) {
+                this = state->distcode[BITS(state->distbits)];
+                if ((unsigned)(this.bits) <= bits) break;
+                PULLBYTE();
+            }
+            if ((this.op & 0xf0) == 0) {
+                last = this;
+                for (;;) {
+                    this = state->distcode[last.val +
+                            (BITS(last.bits + last.op) >> last.bits)];
+                    if ((unsigned)(last.bits + this.bits) <= bits) break;
+                    PULLBYTE();
+                }
+                DROPBITS(last.bits);
+            }
+            DROPBITS(this.bits);
+            if (this.op & 64) {
+                strm->msg = (char *)"invalid distance code";
+                state->mode = BAD;
+                break;
+            }
+            state->offset = (unsigned)this.val;
+            state->extra = (unsigned)(this.op) & 15;
+            state->mode = DISTEXT;
+        case DISTEXT:
+            if (state->extra) {
+                NEEDBITS(state->extra);
+                state->offset += BITS(state->extra);
+                DROPBITS(state->extra);
+            }
+#ifdef INFLATE_STRICT
+            if (state->offset > state->dmax) {
+                strm->msg = (char *)"invalid distance too far back";
+                state->mode = BAD;
+                break;
+            }
+#endif
+            if (state->offset > state->whave + out - left) {
+                strm->msg = (char *)"invalid distance too far back";
+                state->mode = BAD;
+                break;
+            }
+            state->mode = MATCH;
+        case MATCH:
+            if (left == 0) goto inf_leave;
+            copy = out - left;
+            if (state->offset > copy) {         /* copy from window */
+                copy = state->offset - copy;
+                if (copy > state->write) {
+                    copy -= state->write;
+                    from = state->window + (state->wsize - copy);
+                }
+                else
+                    from = state->window + (state->write - copy);
+                if (copy > state->length) copy = state->length;
+            }
+            else {                              /* copy from output */
+                from = put - state->offset;
+                copy = state->length;
+            }
+            if (copy > left) copy = left;
+            left -= copy;
+            state->length -= copy;
+            do {
+                *put++ = *from++;
+            } while (--copy);
+            if (state->length == 0) state->mode = LEN;
+            break;
+        case LIT:
+            if (left == 0) goto inf_leave;
+            *put++ = (unsigned char)(state->length);
+            left--;
+            state->mode = LEN;
+            break;
+        case CHECK:
+            if (state->wrap) {
+                NEEDBITS(32);
+                out -= left;
+                strm->total_out += out;
+                state->total += out;
+                if (out)
+                    strm->adler = state->check =
+                        UPDATE(state->check, put - out, out);
+                out = left;
+                if ((
+                     REVERSE(hold)) != state->check) {
+                    strm->msg = (char *)"incorrect data check";
+                    state->mode = BAD;
+                    break;
+                }
+                INITBITS();
+            }
+            state->mode = DONE;
+        case DONE:
+            ret = Z_STREAM_END;
+            goto inf_leave;
+        case BAD:
+            ret = Z_DATA_ERROR;
+            goto inf_leave;
+        case MEM:
+            return Z_MEM_ERROR;
+        case SYNC:
+        default:
+            return Z_STREAM_ERROR;
+        }
+
+    /*
+       Return from inflate(), updating the total counts and the check value.
+       If there was no progress during the inflate() call, return a buffer
+       error.  Call zlib_updatewindow() to create and/or update the window state.
+     */
+  inf_leave:
+    RESTORE();
+    if (state->wsize || (state->mode < CHECK && out != strm->avail_out))
+        zlib_updatewindow(strm, out);
+
+    in -= strm->avail_in;
+    out -= strm->avail_out;
+    strm->total_in += in;
+    strm->total_out += out;
+    state->total += out;
+    if (state->wrap && out)
+        strm->adler = state->check =
+            UPDATE(state->check, strm->next_out - out, out);
+
+    strm->data_type = state->bits + (state->last ? 64 : 0) +
+                      (state->mode == TYPE ? 128 : 0);
+
+    if (flush == Z_PACKET_FLUSH && ret == Z_OK &&
+            strm->avail_out != 0 && strm->avail_in == 0)
+		return zlib_inflateSyncPacket(strm);
+
+    if (((in == 0 && out == 0) || flush == Z_FINISH) && ret == Z_OK)
+        ret = Z_BUF_ERROR;
+
+    return ret;
+}
+
+int zlib_inflateEnd(z_streamp strm)
+{
+    if (strm == NULL || strm->state == NULL)
+        return Z_STREAM_ERROR;
+    return Z_OK;
+}
+
+#if 0
+int zlib_inflateSetDictionary(z_streamp strm, const Byte *dictionary,
+        uInt dictLength)
+{
+    struct inflate_state *state;
+    unsigned long id;
+
+    /* check state */
+    if (strm == NULL || strm->state == NULL) return Z_STREAM_ERROR;
+    state = (struct inflate_state *)strm->state;
+    if (state->wrap != 0 && state->mode != DICT)
+        return Z_STREAM_ERROR;
+
+    /* check for correct dictionary id */
+    if (state->mode == DICT) {
+        id = zlib_adler32(0L, NULL, 0);
+        id = zlib_adler32(id, dictionary, dictLength);
+        if (id != state->check)
+            return Z_DATA_ERROR;
+    }
+
+    /* copy dictionary to window */
+    zlib_updatewindow(strm, strm->avail_out);
+
+    if (dictLength > state->wsize) {
+        memcpy(state->window, dictionary + dictLength - state->wsize,
+                state->wsize);
+        state->whave = state->wsize;
+    }
+    else {
+        memcpy(state->window + state->wsize - dictLength, dictionary,
+                dictLength);
+        state->whave = dictLength;
+    }
+    state->havedict = 1;
+    return Z_OK;
+}
+#endif
+
+#if 0
+/*
+   Search buf[0..len-1] for the pattern: 0, 0, 0xff, 0xff.  Return when found
+   or when out of input.  When called, *have is the number of pattern bytes
+   found in order so far, in 0..3.  On return *have is updated to the new
+   state.  If on return *have equals four, then the pattern was found and the
+   return value is how many bytes were read including the last byte of the
+   pattern.  If *have is less than four, then the pattern has not been found
+   yet and the return value is len.  In the latter case, zlib_syncsearch() can be
+   called again with more data and the *have state.  *have is initialized to
+   zero for the first call.
+ */
+static unsigned zlib_syncsearch(unsigned *have, unsigned char *buf,
+        unsigned len)
+{
+    unsigned got;
+    unsigned next;
+
+    got = *have;
+    next = 0;
+    while (next < len && got < 4) {
+        if ((int)(buf[next]) == (got < 2 ? 0 : 0xff))
+            got++;
+        else if (buf[next])
+            got = 0;
+        else
+            got = 4 - got;
+        next++;
+    }
+    *have = got;
+    return next;
+}
+#endif
+
+#if 0
+int zlib_inflateSync(z_streamp strm)
+{
+    unsigned len;               /* number of bytes to look at or looked at */
+    unsigned long in, out;      /* temporary to save total_in and total_out */
+    unsigned char buf[4];       /* to restore bit buffer to byte string */
+    struct inflate_state *state;
+
+    /* check parameters */
+    if (strm == NULL || strm->state == NULL) return Z_STREAM_ERROR;
+    state = (struct inflate_state *)strm->state;
+    if (strm->avail_in == 0 && state->bits < 8) return Z_BUF_ERROR;
+
+    /* if first time, start search in bit buffer */
+    if (state->mode != SYNC) {
+        state->mode = SYNC;
+        state->hold <<= state->bits & 7;
+        state->bits -= state->bits & 7;
+        len = 0;
+        while (state->bits >= 8) {
+            buf[len++] = (unsigned char)(state->hold);
+            state->hold >>= 8;
+            state->bits -= 8;
+        }
+        state->have = 0;
+        zlib_syncsearch(&(state->have), buf, len);
+    }
+
+    /* search available input */
+    len = zlib_syncsearch(&(state->have), strm->next_in, strm->avail_in);
+    strm->avail_in -= len;
+    strm->next_in += len;
+    strm->total_in += len;
+
+    /* return no joy or set up to restart inflate() on a new block */
+    if (state->have != 4) return Z_DATA_ERROR;
+    in = strm->total_in;  out = strm->total_out;
+    zlib_inflateReset(strm);
+    strm->total_in = in;  strm->total_out = out;
+    state->mode = TYPE;
+    return Z_OK;
+}
+#endif
+
+/*
+ * This subroutine adds the data at next_in/avail_in to the output history
+ * without performing any output.  The output buffer must be "caught up";
+ * i.e. no pending output but this should always be the case. The state must
+ * be waiting on the start of a block (i.e. mode == TYPE or HEAD).  On exit,
+ * the output will also be caught up, and the checksum will have been updated
+ * if need be.
+ */
+int zlib_inflateIncomp(z_stream *z)
+{
+    struct inflate_state *state = (struct inflate_state *)z->state;
+    Byte *saved_no = z->next_out;
+    uInt saved_ao = z->avail_out;
+
+    if (state->mode != TYPE && state->mode != HEAD)
+	return Z_DATA_ERROR;
+
+    /* Setup some variables to allow misuse of updateWindow */
+    z->avail_out = 0;
+    z->next_out = z->next_in + z->avail_in;
+
+    zlib_updatewindow(z, z->avail_in);
+
+    /* Restore saved variables */
+    z->avail_out = saved_ao;
+    z->next_out = saved_no;
+
+    z->adler = state->check =
+        UPDATE(state->check, z->next_in, z->avail_in);
+
+    z->total_out += z->avail_in;
+    z->total_in += z->avail_in;
+    z->next_in += z->avail_in;
+    state->total += z->avail_in;
+    z->avail_in = 0;
+
+    return Z_OK;
+}

lib/zlib_inflate/inflate.h

@@ -0,0 +1,107 @@
+/* inflate.h -- internal inflate state definition
+ * Copyright (C) 1995-2004 Mark Adler
+ * For conditions of distribution and use, see copyright notice in zlib.h
+ */
+
+/* WARNING: this file should *not* be used by applications. It is
+   part of the implementation of the compression library and is
+   subject to change. Applications should only use zlib.h.
+ */
+
+/* Possible inflate modes between inflate() calls */
+typedef enum {
+    HEAD,       /* i: waiting for magic header */
+    FLAGS,      /* i: waiting for method and flags (gzip) */
+    TIME,       /* i: waiting for modification time (gzip) */
+    OS,         /* i: waiting for extra flags and operating system (gzip) */
+    EXLEN,      /* i: waiting for extra length (gzip) */
+    EXTRA,      /* i: waiting for extra bytes (gzip) */
+    NAME,       /* i: waiting for end of file name (gzip) */
+    COMMENT,    /* i: waiting for end of comment (gzip) */
+    HCRC,       /* i: waiting for header crc (gzip) */
+    DICTID,     /* i: waiting for dictionary check value */
+    DICT,       /* waiting for inflateSetDictionary() call */
+        TYPE,       /* i: waiting for type bits, including last-flag bit */
+        TYPEDO,     /* i: same, but skip check to exit inflate on new block */
+        STORED,     /* i: waiting for stored size (length and complement) */
+        COPY,       /* i/o: waiting for input or output to copy stored block */
+        TABLE,      /* i: waiting for dynamic block table lengths */
+        LENLENS,    /* i: waiting for code length code lengths */
+        CODELENS,   /* i: waiting for length/lit and distance code lengths */
+            LEN,        /* i: waiting for length/lit code */
+            LENEXT,     /* i: waiting for length extra bits */
+            DIST,       /* i: waiting for distance code */
+            DISTEXT,    /* i: waiting for distance extra bits */
+            MATCH,      /* o: waiting for output space to copy string */
+            LIT,        /* o: waiting for output space to write literal */
+    CHECK,      /* i: waiting for 32-bit check value */
+    LENGTH,     /* i: waiting for 32-bit length (gzip) */
+    DONE,       /* finished check, done -- remain here until reset */
+    BAD,        /* got a data error -- remain here until reset */
+    MEM,        /* got an inflate() memory error -- remain here until reset */
+    SYNC        /* looking for synchronization bytes to restart inflate() */
+} inflate_mode;
+
+/*
+    State transitions between above modes -
+
+    (most modes can go to the BAD or MEM mode -- not shown for clarity)
+
+    Process header:
+        HEAD -> (gzip) or (zlib)
+        (gzip) -> FLAGS -> TIME -> OS -> EXLEN -> EXTRA -> NAME
+        NAME -> COMMENT -> HCRC -> TYPE
+        (zlib) -> DICTID or TYPE
+        DICTID -> DICT -> TYPE
+    Read deflate blocks:
+            TYPE -> STORED or TABLE or LEN or CHECK
+            STORED -> COPY -> TYPE
+            TABLE -> LENLENS -> CODELENS -> LEN
+    Read deflate codes:
+                LEN -> LENEXT or LIT or TYPE
+                LENEXT -> DIST -> DISTEXT -> MATCH -> LEN
+                LIT -> LEN
+    Process trailer:
+        CHECK -> LENGTH -> DONE
+ */
+
+/* state maintained between inflate() calls.  Approximately 7K bytes. */
+struct inflate_state {
+    inflate_mode mode;          /* current inflate mode */
+    int last;                   /* true if processing last block */
+    int wrap;                   /* bit 0 true for zlib, bit 1 true for gzip */
+    int havedict;               /* true if dictionary provided */
+    int flags;                  /* gzip header method and flags (0 if zlib) */
+    unsigned dmax;              /* zlib header max distance (INFLATE_STRICT) */
+    unsigned long check;        /* protected copy of check value */
+    unsigned long total;        /* protected copy of output count */
+ /*   gz_headerp head; */           /* where to save gzip header information */
+        /* sliding window */
+    unsigned wbits;             /* log base 2 of requested window size */
+    unsigned wsize;             /* window size or zero if not using window */
+    unsigned whave;             /* valid bytes in the window */
+    unsigned write;             /* window write index */
+    unsigned char *window;  /* allocated sliding window, if needed */
+        /* bit accumulator */
+    unsigned long hold;         /* input bit accumulator */
+    unsigned bits;              /* number of bits in "in" */
+        /* for string and stored block copying */
+    unsigned length;            /* literal or length of data to copy */
+    unsigned offset;            /* distance back to copy string from */
+        /* for table and code decoding */
+    unsigned extra;             /* extra bits needed */
+        /* fixed and dynamic code tables */
+    code const *lencode;    /* starting table for length/literal codes */
+    code const *distcode;   /* starting table for distance codes */
+    unsigned lenbits;           /* index bits for lencode */
+    unsigned distbits;          /* index bits for distcode */
+        /* dynamic table building */
+    unsigned ncode;             /* number of code length code lengths */
+    unsigned nlen;              /* number of length code lengths */
+    unsigned ndist;             /* number of distance code lengths */
+    unsigned have;              /* number of code lengths in lens[] */
+    code *next;             /* next available space in codes[] */
+    unsigned short lens[320];   /* temporary storage for code lengths */
+    unsigned short work[288];   /* work area for code table building */
+    code codes[ENOUGH];         /* space for code tables */
+};

lib/zlib_inflate/inflate_syms.c

@@ -0,0 +1,19 @@
+/*
+ * linux/lib/zlib_inflate/inflate_syms.c
+ *
+ * Exported symbols for the inflate functionality.
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/init.h>
+
+#include <linux/zlib.h>
+
+EXPORT_SYMBOL(zlib_inflate_workspacesize);
+EXPORT_SYMBOL(zlib_inflate);
+EXPORT_SYMBOL(zlib_inflateInit2);
+EXPORT_SYMBOL(zlib_inflateEnd);
+EXPORT_SYMBOL(zlib_inflateReset);
+EXPORT_SYMBOL(zlib_inflateIncomp); 
+MODULE_LICENSE("GPL");

lib/zlib_inflate/inftrees.c

@@ -0,0 +1,315 @@
+/* inftrees.c -- generate Huffman trees for efficient decoding
+ * Copyright (C) 1995-2005 Mark Adler
+ * For conditions of distribution and use, see copyright notice in zlib.h
+ */
+
+#include <linux/zutil.h>
+#include "inftrees.h"
+
+#define MAXBITS 15
+
+/*
+   Build a set of tables to decode the provided canonical Huffman code.
+   The code lengths are lens[0..codes-1].  The result starts at *table,
+   whose indices are 0..2^bits-1.  work is a writable array of at least
+   lens shorts, which is used as a work area.  type is the type of code
+   to be generated, CODES, LENS, or DISTS.  On return, zero is success,
+   -1 is an invalid code, and +1 means that ENOUGH isn't enough.  table
+   on return points to the next available entry's address.  bits is the
+   requested root table index bits, and on return it is the actual root
+   table index bits.  It will differ if the request is greater than the
+   longest code or if it is less than the shortest code.
+ */
+int zlib_inflate_table(codetype type, unsigned short *lens, unsigned codes,
+			code **table, unsigned *bits, unsigned short *work)
+{
+    unsigned len;               /* a code's length in bits */
+    unsigned sym;               /* index of code symbols */
+    unsigned min, max;          /* minimum and maximum code lengths */
+    unsigned root;              /* number of index bits for root table */
+    unsigned curr;              /* number of index bits for current table */
+    unsigned drop;              /* code bits to drop for sub-table */
+    int left;                   /* number of prefix codes available */
+    unsigned used;              /* code entries in table used */
+    unsigned huff;              /* Huffman code */
+    unsigned incr;              /* for incrementing code, index */
+    unsigned fill;              /* index for replicating entries */
+    unsigned low;               /* low bits for current root entry */
+    unsigned mask;              /* mask for low root bits */
+    code this;                  /* table entry for duplication */
+    code *next;             /* next available space in table */
+    const unsigned short *base;     /* base value table to use */
+    const unsigned short *extra;    /* extra bits table to use */
+    int end;                    /* use base and extra for symbol > end */
+    unsigned short count[MAXBITS+1];    /* number of codes of each length */
+    unsigned short offs[MAXBITS+1];     /* offsets in table for each length */
+    static const unsigned short lbase[31] = { /* Length codes 257..285 base */
+        3, 4, 5, 6, 7, 8, 9, 10, 11, 13, 15, 17, 19, 23, 27, 31,
+        35, 43, 51, 59, 67, 83, 99, 115, 131, 163, 195, 227, 258, 0, 0};
+    static const unsigned short lext[31] = { /* Length codes 257..285 extra */
+        16, 16, 16, 16, 16, 16, 16, 16, 17, 17, 17, 17, 18, 18, 18, 18,
+        19, 19, 19, 19, 20, 20, 20, 20, 21, 21, 21, 21, 16, 201, 196};
+    static const unsigned short dbase[32] = { /* Distance codes 0..29 base */
+        1, 2, 3, 4, 5, 7, 9, 13, 17, 25, 33, 49, 65, 97, 129, 193,
+        257, 385, 513, 769, 1025, 1537, 2049, 3073, 4097, 6145,
+        8193, 12289, 16385, 24577, 0, 0};
+    static const unsigned short dext[32] = { /* Distance codes 0..29 extra */
+        16, 16, 16, 16, 17, 17, 18, 18, 19, 19, 20, 20, 21, 21, 22, 22,
+        23, 23, 24, 24, 25, 25, 26, 26, 27, 27,
+        28, 28, 29, 29, 64, 64};
+
+    /*
+       Process a set of code lengths to create a canonical Huffman code.  The
+       code lengths are lens[0..codes-1].  Each length corresponds to the
+       symbols 0..codes-1.  The Huffman code is generated by first sorting the
+       symbols by length from short to long, and retaining the symbol order
+       for codes with equal lengths.  Then the code starts with all zero bits
+       for the first code of the shortest length, and the codes are integer
+       increments for the same length, and zeros are appended as the length
+       increases.  For the deflate format, these bits are stored backwards
+       from their more natural integer increment ordering, and so when the
+       decoding tables are built in the large loop below, the integer codes
+       are incremented backwards.
+
+       This routine assumes, but does not check, that all of the entries in
+       lens[] are in the range 0..MAXBITS.  The caller must assure this.
+       1..MAXBITS is interpreted as that code length.  zero means that that
+       symbol does not occur in this code.
+
+       The codes are sorted by computing a count of codes for each length,
+       creating from that a table of starting indices for each length in the
+       sorted table, and then entering the symbols in order in the sorted
+       table.  The sorted table is work[], with that space being provided by
+       the caller.
+
+       The length counts are used for other purposes as well, i.e. finding
+       the minimum and maximum length codes, determining if there are any
+       codes at all, checking for a valid set of lengths, and looking ahead
+       at length counts to determine sub-table sizes when building the
+       decoding tables.
+     */
+
+    /* accumulate lengths for codes (assumes lens[] all in 0..MAXBITS) */
+    for (len = 0; len <= MAXBITS; len++)
+        count[len] = 0;
+    for (sym = 0; sym < codes; sym++)
+        count[lens[sym]]++;
+
+    /* bound code lengths, force root to be within code lengths */
+    root = *bits;
+    for (max = MAXBITS; max >= 1; max--)
+        if (count[max] != 0) break;
+    if (root > max) root = max;
+    if (max == 0) {                     /* no symbols to code at all */
+        this.op = (unsigned char)64;    /* invalid code marker */
+        this.bits = (unsigned char)1;
+        this.val = (unsigned short)0;
+        *(*table)++ = this;             /* make a table to force an error */
+        *(*table)++ = this;
+        *bits = 1;
+        return 0;     /* no symbols, but wait for decoding to report error */
+    }
+    for (min = 1; min <= MAXBITS; min++)
+        if (count[min] != 0) break;
+    if (root < min) root = min;
+
+    /* check for an over-subscribed or incomplete set of lengths */
+    left = 1;
+    for (len = 1; len <= MAXBITS; len++) {
+        left <<= 1;
+        left -= count[len];
+        if (left < 0) return -1;        /* over-subscribed */
+    }
+    if (left > 0 && (type == CODES || max != 1))
+        return -1;                      /* incomplete set */
+
+    /* generate offsets into symbol table for each length for sorting */
+    offs[1] = 0;
+    for (len = 1; len < MAXBITS; len++)
+        offs[len + 1] = offs[len] + count[len];
+
+    /* sort symbols by length, by symbol order within each length */
+    for (sym = 0; sym < codes; sym++)
+        if (lens[sym] != 0) work[offs[lens[sym]]++] = (unsigned short)sym;
+
+    /*
+       Create and fill in decoding tables.  In this loop, the table being
+       filled is at next and has curr index bits.  The code being used is huff
+       with length len.  That code is converted to an index by dropping drop
+       bits off of the bottom.  For codes where len is less than drop + curr,
+       those top drop + curr - len bits are incremented through all values to
+       fill the table with replicated entries.
+
+       root is the number of index bits for the root table.  When len exceeds
+       root, sub-tables are created pointed to by the root entry with an index
+       of the low root bits of huff.  This is saved in low to check for when a
+       new sub-table should be started.  drop is zero when the root table is
+       being filled, and drop is root when sub-tables are being filled.
+
+       When a new sub-table is needed, it is necessary to look ahead in the
+       code lengths to determine what size sub-table is needed.  The length
+       counts are used for this, and so count[] is decremented as codes are
+       entered in the tables.
+
+       used keeps track of how many table entries have been allocated from the
+       provided *table space.  It is checked when a LENS table is being made
+       against the space in *table, ENOUGH, minus the maximum space needed by
+       the worst case distance code, MAXD.  This should never happen, but the
+       sufficiency of ENOUGH has not been proven exhaustively, hence the check.
+       This assumes that when type == LENS, bits == 9.
+
+       sym increments through all symbols, and the loop terminates when
+       all codes of length max, i.e. all codes, have been processed.  This
+       routine permits incomplete codes, so another loop after this one fills
+       in the rest of the decoding tables with invalid code markers.
+     */
+
+    /* set up for code type */
+    switch (type) {
+    case CODES:
+        base = extra = work;    /* dummy value--not used */
+        end = 19;
+        break;
+    case LENS:
+        base = lbase;
+        base -= 257;
+        extra = lext;
+        extra -= 257;
+        end = 256;
+        break;
+    default:            /* DISTS */
+        base = dbase;
+        extra = dext;
+        end = -1;
+    }
+
+    /* initialize state for loop */
+    huff = 0;                   /* starting code */
+    sym = 0;                    /* starting code symbol */
+    len = min;                  /* starting code length */
+    next = *table;              /* current table to fill in */
+    curr = root;                /* current table index bits */
+    drop = 0;                   /* current bits to drop from code for index */
+    low = (unsigned)(-1);       /* trigger new sub-table when len > root */
+    used = 1U << root;          /* use root table entries */
+    mask = used - 1;            /* mask for comparing low */
+
+    /* check available table space */
+    if (type == LENS && used >= ENOUGH - MAXD)
+        return 1;
+
+    /* process all codes and make table entries */
+    for (;;) {
+        /* create table entry */
+        this.bits = (unsigned char)(len - drop);
+        if ((int)(work[sym]) < end) {
+            this.op = (unsigned char)0;
+            this.val = work[sym];
+        }
+        else if ((int)(work[sym]) > end) {
+            this.op = (unsigned char)(extra[work[sym]]);
+            this.val = base[work[sym]];
+        }
+        else {
+            this.op = (unsigned char)(32 + 64);         /* end of block */
+            this.val = 0;
+        }
+
+        /* replicate for those indices with low len bits equal to huff */
+        incr = 1U << (len - drop);
+        fill = 1U << curr;
+        min = fill;                 /* save offset to next table */
+        do {
+            fill -= incr;
+            next[(huff >> drop) + fill] = this;
+        } while (fill != 0);
+
+        /* backwards increment the len-bit code huff */
+        incr = 1U << (len - 1);
+        while (huff & incr)
+            incr >>= 1;
+        if (incr != 0) {
+            huff &= incr - 1;
+            huff += incr;
+        }
+        else
+            huff = 0;
+
+        /* go to next symbol, update count, len */
+        sym++;
+        if (--(count[len]) == 0) {
+            if (len == max) break;
+            len = lens[work[sym]];
+        }
+
+        /* create new sub-table if needed */
+        if (len > root && (huff & mask) != low) {
+            /* if first time, transition to sub-tables */
+            if (drop == 0)
+                drop = root;
+
+            /* increment past last table */
+            next += min;            /* here min is 1 << curr */
+
+            /* determine length of next table */
+            curr = len - drop;
+            left = (int)(1 << curr);
+            while (curr + drop < max) {
+                left -= count[curr + drop];
+                if (left <= 0) break;
+                curr++;
+                left <<= 1;
+            }
+
+            /* check for enough space */
+            used += 1U << curr;
+            if (type == LENS && used >= ENOUGH - MAXD)
+                return 1;
+
+            /* point entry in root table to sub-table */
+            low = huff & mask;
+            (*table)[low].op = (unsigned char)curr;
+            (*table)[low].bits = (unsigned char)root;
+            (*table)[low].val = (unsigned short)(next - *table);
+        }
+    }
+
+    /*
+       Fill in rest of table for incomplete codes.  This loop is similar to the
+       loop above in incrementing huff for table indices.  It is assumed that
+       len is equal to curr + drop, so there is no loop needed to increment
+       through high index bits.  When the current sub-table is filled, the loop
+       drops back to the root table to fill in any remaining entries there.
+     */
+    this.op = (unsigned char)64;                /* invalid code marker */
+    this.bits = (unsigned char)(len - drop);
+    this.val = (unsigned short)0;
+    while (huff != 0) {
+        /* when done with sub-table, drop back to root table */
+        if (drop != 0 && (huff & mask) != low) {
+            drop = 0;
+            len = root;
+            next = *table;
+            this.bits = (unsigned char)len;
+        }
+
+        /* put invalid code marker in table */
+        next[huff >> drop] = this;
+
+        /* backwards increment the len-bit code huff */
+        incr = 1U << (len - 1);
+        while (huff & incr)
+            incr >>= 1;
+        if (incr != 0) {
+            huff &= incr - 1;
+            huff += incr;
+        }
+        else
+            huff = 0;
+    }
+
+    /* set return parameters */
+    *table += used;
+    *bits = root;
+    return 0;
+}

lib/zlib_inflate/inftrees.h

@@ -0,0 +1,55 @@
+/* inftrees.h -- header to use inftrees.c
+ * Copyright (C) 1995-2005 Mark Adler
+ * For conditions of distribution and use, see copyright notice in zlib.h
+ */
+
+/* WARNING: this file should *not* be used by applications. It is
+   part of the implementation of the compression library and is
+   subject to change. Applications should only use zlib.h.
+ */
+
+/* Structure for decoding tables.  Each entry provides either the
+   information needed to do the operation requested by the code that
+   indexed that table entry, or it provides a pointer to another
+   table that indexes more bits of the code.  op indicates whether
+   the entry is a pointer to another table, a literal, a length or
+   distance, an end-of-block, or an invalid code.  For a table
+   pointer, the low four bits of op is the number of index bits of
+   that table.  For a length or distance, the low four bits of op
+   is the number of extra bits to get after the code.  bits is
+   the number of bits in this code or part of the code to drop off
+   of the bit buffer.  val is the actual byte to output in the case
+   of a literal, the base length or distance, or the offset from
+   the current table to the next table.  Each entry is four bytes. */
+typedef struct {
+    unsigned char op;           /* operation, extra bits, table bits */
+    unsigned char bits;         /* bits in this part of the code */
+    unsigned short val;         /* offset in table or code value */
+} code;
+
+/* op values as set by inflate_table():
+    00000000 - literal
+    0000tttt - table link, tttt != 0 is the number of table index bits
+    0001eeee - length or distance, eeee is the number of extra bits
+    01100000 - end of block
+    01000000 - invalid code
+ */
+
+/* Maximum size of dynamic tree.  The maximum found in a long but non-
+   exhaustive search was 1444 code structures (852 for length/literals
+   and 592 for distances, the latter actually the result of an
+   exhaustive search).  The true maximum is not known, but the value
+   below is more than safe. */
+#define ENOUGH 2048
+#define MAXD 592
+
+/* Type of code to build for inftable() */
+typedef enum {
+    CODES,
+    LENS,
+    DISTS
+} codetype;
+
+extern int zlib_inflate_table (codetype type, unsigned short *lens,
+                             unsigned codes, code **table,
+                             unsigned *bits, unsigned short *work);

lib/zlib_inflate/infutil.h

@@ -0,0 +1,25 @@
+/* infutil.h -- types and macros common to blocks and codes
+ * Copyright (C) 1995-1998 Mark Adler
+ * For conditions of distribution and use, see copyright notice in zlib.h 
+ */
+
+/* WARNING: this file should *not* be used by applications. It is
+   part of the implementation of the compression library and is
+   subject to change. Applications should only use zlib.h.
+ */
+
+#ifndef _INFUTIL_H
+#define _INFUTIL_H
+
+#include <linux/zlib.h>
+
+/* memory allocation for inflation */
+
+struct inflate_workspace {
+	struct inflate_state inflate_state;
+	unsigned char working_window[1 << MAX_WBITS];
+};
+
+#define WS(z) ((struct inflate_workspace *)(z->workspace))
+
+#endif