Merge branch 'master' into x86/memblock

Conflicts & resolutions:

* arch/x86/xen/setup.c

	dc91c728fd "xen: allow extra memory to be in multiple regions"
	24aa07882b "memblock, x86: Replace memblock_x86_reserve/free..."

	conflicted on xen_add_extra_mem() updates.  The resolution is
	trivial as the latter just want to replace
	memblock_x86_reserve_range() with memblock_reserve().

* drivers/pci/intel-iommu.c

	166e9278a3f "x86/ia64: intel-iommu: move to drivers/iommu/"
	5dfe8660a3d "bootmem: Replace work_with_active_regions() with..."

	conflicted as the former moved the file under drivers/iommu/.
	Resolved by applying the chnages from the latter on the moved
	file.

* mm/Kconfig

	6661672053a "memblock: add NO_BOOTMEM config symbol"
	c378ddd53f9 "memblock, x86: Make ARCH_DISCARD_MEMBLOCK a config option"

	conflicted trivially.  Both added config options.  Just
	letting both add their own options resolves the conflict.

* mm/memblock.c

	d1f0ece6cdc "mm/memblock.c: small function definition fixes"
	ed7b56a799c "memblock: Remove memblock_memory_can_coalesce()"

	confliected.  The former updates function removed by the
	latter.  Resolution is trivial.

Signed-off-by: Tejun Heo <tj@kernel.org>

45 files changed, 1541 insertions, 540 deletions

diff --git a/lib/Kconfig b/lib/Kconfig
index 830181cc7a83..32f3e5ae2be5 100644
--- a/lib/Kconfig
+++ b/lib/Kconfig
@@ -79,6 +79,13 @@ config LIBCRC32C
 	  require M here.  See Castagnoli93.
 	  Module will be libcrc32c.
 
+config CRC8
+	tristate "CRC8 function"
+	help
+	  This option provides CRC8 function. Drivers may select this
+	  when they need to do cyclic redundancy check according CRC8
+	  algorithm. Module will be called crc8.
+
 config AUDIT_GENERIC
 	bool
 	depends on AUDIT && !AUDIT_ARCH
@@ -262,4 +269,11 @@ config AVERAGE
 
 	  If unsure, say N.
 
+config CORDIC
+	tristate "Cordic function"
+	help
+	  The option provides arithmetic function using cordic algorithm
+	  so its calculations are in fixed point. Modules can select this
+	  when they require this function. Module will be called cordic.
+
 endmenu
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index dd373c8ee943..82928f5ea049 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -117,31 +117,31 @@ config DEBUG_SECTION_MISMATCH
 	help
 	  The section mismatch analysis checks if there are illegal
 	  references from one section to another section.
-	  Linux will during link or during runtime drop some sections
-	  and any use of code/data previously in these sections will
+	  During linktime or runtime, some sections are dropped;
+	  any use of code/data previously in these sections would
 	  most likely result in an oops.
-	  In the code functions and variables are annotated with
-	  __init, __devinit etc. (see full list in include/linux/init.h)
+	  In the code, functions and variables are annotated with
+	  __init, __devinit, etc. (see the full list in include/linux/init.h),
 	  which results in the code/data being placed in specific sections.
-	  The section mismatch analysis is always done after a full
-	  kernel build but enabling this option will in addition
-	  do the following:
-	  - Add the option -fno-inline-functions-called-once to gcc
-	    When inlining a function annotated __init in a non-init
-	    function we would lose the section information and thus
+	  The section mismatch analysis is always performed after a full
+	  kernel build, and enabling this option causes the following
+	  additional steps to occur:
+	  - Add the option -fno-inline-functions-called-once to gcc commands.
+	    When inlining a function annotated with __init in a non-init
+	    function, we would lose the section information and thus
 	    the analysis would not catch the illegal reference.
-	    This option tells gcc to inline less but will also
-	    result in a larger kernel.
-	  - Run the section mismatch analysis for each module/built-in.o
-	    When we run the section mismatch analysis on vmlinux.o we
+	    This option tells gcc to inline less (but it does result in
+	    a larger kernel).
+	  - Run the section mismatch analysis for each module/built-in.o file.
+	    When we run the section mismatch analysis on vmlinux.o, we
 	    lose valueble information about where the mismatch was
 	    introduced.
 	    Running the analysis for each module/built-in.o file
-	    will tell where the mismatch happens much closer to the
-	    source. The drawback is that we will report the same
-	    mismatch at least twice.
-	  - Enable verbose reporting from modpost to help solving
-	    the section mismatches reported.
+	    tells where the mismatch happens much closer to the
+	    source. The drawback is that the same mismatch is
+	    reported at least twice.
+	  - Enable verbose reporting from modpost in order to help resolve
+	    the section mismatches that are reported.
 
 config DEBUG_KERNEL
 	bool "Kernel debugging"
@@ -227,7 +227,7 @@ config BOOTPARAM_SOFTLOCKUP_PANIC_VALUE
 config DETECT_HUNG_TASK
 	bool "Detect Hung Tasks"
 	depends on DEBUG_KERNEL
-	default DETECT_SOFTLOCKUP
+	default LOCKUP_DETECTOR
 	help
 	  Say Y here to enable the kernel to detect "hung tasks",
 	  which are bugs that cause the task to be stuck in
@@ -248,8 +248,9 @@ config DEFAULT_HUNG_TASK_TIMEOUT
 	  to determine when a task has become non-responsive and should
 	  be considered hung.
 
-	  It can be adjusted at runtime via the kernel.hung_task_timeout
-	  sysctl or by writing a value to /proc/sys/kernel/hung_task_timeout.
+	  It can be adjusted at runtime via the kernel.hung_task_timeout_secs
+	  sysctl or by writing a value to
+	  /proc/sys/kernel/hung_task_timeout_secs.
 
 	  A timeout of 0 disables the check.  The default is two minutes.
 	  Keeping the default should be fine in most cases.
@@ -648,12 +649,15 @@ config TRACE_IRQFLAGS
 	  Enables hooks to interrupt enabling and disabling for
 	  either tracing or lock debugging.
 
-config DEBUG_SPINLOCK_SLEEP
-	bool "Spinlock debugging: sleep-inside-spinlock checking"
+config DEBUG_ATOMIC_SLEEP
+	bool "Sleep inside atomic section checking"
+	select PREEMPT_COUNT
 	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.
+	  noisy if they are called inside atomic sections: when a spinlock is
+	  held, inside an rcu read side critical section, inside preempt disabled
+	  sections, inside an interrupt, etc...
 
 config DEBUG_LOCKING_API_SELFTESTS
 	bool "Locking API boot-time self-tests"
@@ -832,7 +836,7 @@ config DEBUG_CREDENTIALS
 
 #
 # Select this config option from the architecture Kconfig, if it
-# it is preferred to always offer frame pointers as a config
+# is preferred to always offer frame pointers as a config
 # option on the architecture (regardless of KERNEL_DEBUG):
 #
 config ARCH_WANT_FRAME_POINTERS
@@ -866,7 +870,7 @@ config BOOT_PRINTK_DELAY
 	  system, and then set "lpj=M" before setting "boot_delay=N".
 	  NOTE:  Using this option may adversely affect SMP systems.
 	  I.e., processors other than the first one may not boot up.
-	  BOOT_PRINTK_DELAY also may cause DETECT_SOFTLOCKUP to detect
+	  BOOT_PRINTK_DELAY also may cause LOCKUP_DETECTOR to detect
 	  what it believes to be lockup conditions.
 
 config RCU_TORTURE_TEST
@@ -1067,6 +1071,17 @@ config FAIL_IO_TIMEOUT
 	  Only works with drivers that use the generic timeout handling,
 	  for others it wont do anything.
 
+config FAIL_MMC_REQUEST
+	bool "Fault-injection capability for MMC IO"
+	select DEBUG_FS
+	depends on FAULT_INJECTION && MMC
+	help
+	  Provide fault-injection capability for MMC IO.
+	  This will make the mmc core return data errors. This is
+	  useful to test the error handling in the mmc block device
+	  and to test how the mmc host driver handles retries from
+	  the block device.
+
 config FAULT_INJECTION_DEBUG_FS
 	bool "Debugfs entries for fault-injection capabilities"
 	depends on FAULT_INJECTION && SYSFS && DEBUG_FS
@@ -1078,7 +1093,7 @@ config FAULT_INJECTION_STACKTRACE_FILTER
 	depends on FAULT_INJECTION_DEBUG_FS && STACKTRACE_SUPPORT
 	depends on !X86_64
 	select STACKTRACE
-	select FRAME_POINTER if !PPC && !S390 && !MICROBLAZE
+	select FRAME_POINTER if !PPC && !S390 && !MICROBLAZE && !ARM_UNWIND
 	help
 	  Provide stacktrace filter for fault-injection capabilities
 
@@ -1088,7 +1103,7 @@ config LATENCYTOP
 	depends on DEBUG_KERNEL
 	depends on STACKTRACE_SUPPORT
 	depends on PROC_FS
-	select FRAME_POINTER if !MIPS && !PPC && !S390 && !MICROBLAZE
+	select FRAME_POINTER if !MIPS && !PPC && !S390 && !MICROBLAZE && !ARM_UNWIND
 	select KALLSYMS
 	select KALLSYMS_ALL
 	select STACKTRACE
diff --git a/lib/Makefile b/lib/Makefile
index 6b597fdb1898..a4da283f5dc0 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -10,9 +10,9 @@ endif
 lib-y := ctype.o string.o vsprintf.o cmdline.o \
 	 rbtree.o radix-tree.o dump_stack.o timerqueue.o\
 	 idr.o int_sqrt.o extable.o prio_tree.o \
-	 sha1.o irq_regs.o reciprocal_div.o argv_split.o \
+	 sha1.o md5.o irq_regs.o reciprocal_div.o argv_split.o \
 	 proportions.o prio_heap.o ratelimit.o show_mem.o \
-	 is_single_threaded.o plist.o decompress.o find_next_bit.o
+	 is_single_threaded.o plist.o decompress.o
 
 lib-$(CONFIG_MMU) += ioremap.o
 lib-$(CONFIG_SMP) += cpumask.o
@@ -22,7 +22,7 @@ lib-y	+= kobject.o kref.o klist.o
 obj-y += bcd.o div64.o sort.o parser.o halfmd4.o debug_locks.o random32.o \
 	 bust_spinlocks.o hexdump.o kasprintf.o bitmap.o scatterlist.o \
 	 string_helpers.o gcd.o lcm.o list_sort.o uuid.o flex_array.o \
-	 bsearch.o find_last_bit.o
+	 bsearch.o find_last_bit.o find_next_bit.o llist.o
 obj-y += kstrtox.o
 obj-$(CONFIG_TEST_KSTRTOX) += test-kstrtox.o
 
@@ -61,6 +61,7 @@ obj-$(CONFIG_CRC_ITU_T)	+= crc-itu-t.o
 obj-$(CONFIG_CRC32)	+= crc32.o
 obj-$(CONFIG_CRC7)	+= crc7.o
 obj-$(CONFIG_LIBCRC32C)	+= libcrc32c.o
+obj-$(CONFIG_CRC8)	+= crc8.o
 obj-$(CONFIG_GENERIC_ALLOCATOR) += genalloc.o
 
 obj-$(CONFIG_ZLIB_INFLATE) += zlib_inflate/
@@ -112,6 +113,8 @@ obj-$(CONFIG_AVERAGE) += average.o
 
 obj-$(CONFIG_CPU_RMAP) += cpu_rmap.o
 
+obj-$(CONFIG_CORDIC) += cordic.o
+
 hostprogs-y	:= gen_crc32table
 clean-files	:= crc32table.h
 
diff --git a/lib/atomic64.c b/lib/atomic64.c
index a21c12bc727c..3975470caf4f 100644
--- a/lib/atomic64.c
+++ b/lib/atomic64.c
@@ -14,7 +14,7 @@
 #include <linux/spinlock.h>
 #include <linux/init.h>
 #include <linux/module.h>
-#include <asm/atomic.h>
+#include <linux/atomic.h>
 
 /*
  * We use a hashed array of spinlocks to provide exclusive access
@@ -29,11 +29,11 @@
  * Ensure each lock is in a separate cacheline.
  */
 static union {
-	spinlock_t lock;
+	raw_spinlock_t lock;
 	char pad[L1_CACHE_BYTES];
 } atomic64_lock[NR_LOCKS] __cacheline_aligned_in_smp;
 
-static inline spinlock_t *lock_addr(const atomic64_t *v)
+static inline raw_spinlock_t *lock_addr(const atomic64_t *v)
 {
 	unsigned long addr = (unsigned long) v;
 
@@ -45,12 +45,12 @@ static inline spinlock_t *lock_addr(const atomic64_t *v)
 long long atomic64_read(const atomic64_t *v)
 {
 	unsigned long flags;
-	spinlock_t *lock = lock_addr(v);
+	raw_spinlock_t *lock = lock_addr(v);
 	long long val;
 
-	spin_lock_irqsave(lock, flags);
+	raw_spin_lock_irqsave(lock, flags);
 	val = v->counter;
-	spin_unlock_irqrestore(lock, flags);
+	raw_spin_unlock_irqrestore(lock, flags);
 	return val;
 }
 EXPORT_SYMBOL(atomic64_read);
@@ -58,34 +58,34 @@ EXPORT_SYMBOL(atomic64_read);
 void atomic64_set(atomic64_t *v, long long i)
 {
 	unsigned long flags;
-	spinlock_t *lock = lock_addr(v);
+	raw_spinlock_t *lock = lock_addr(v);
 
-	spin_lock_irqsave(lock, flags);
+	raw_spin_lock_irqsave(lock, flags);
 	v->counter = i;
-	spin_unlock_irqrestore(lock, flags);
+	raw_spin_unlock_irqrestore(lock, flags);
 }
 EXPORT_SYMBOL(atomic64_set);
 
 void atomic64_add(long long a, atomic64_t *v)
 {
 	unsigned long flags;
-	spinlock_t *lock = lock_addr(v);
+	raw_spinlock_t *lock = lock_addr(v);
 
-	spin_lock_irqsave(lock, flags);
+	raw_spin_lock_irqsave(lock, flags);
 	v->counter += a;
-	spin_unlock_irqrestore(lock, flags);
+	raw_spin_unlock_irqrestore(lock, flags);
 }
 EXPORT_SYMBOL(atomic64_add);
 
 long long atomic64_add_return(long long a, atomic64_t *v)
 {
 	unsigned long flags;
-	spinlock_t *lock = lock_addr(v);
+	raw_spinlock_t *lock = lock_addr(v);
 	long long val;
 
-	spin_lock_irqsave(lock, flags);
+	raw_spin_lock_irqsave(lock, flags);
 	val = v->counter += a;
-	spin_unlock_irqrestore(lock, flags);
+	raw_spin_unlock_irqrestore(lock, flags);
 	return val;
 }
 EXPORT_SYMBOL(atomic64_add_return);
@@ -93,23 +93,23 @@ EXPORT_SYMBOL(atomic64_add_return);
 void atomic64_sub(long long a, atomic64_t *v)
 {
 	unsigned long flags;
-	spinlock_t *lock = lock_addr(v);
+	raw_spinlock_t *lock = lock_addr(v);
 
-	spin_lock_irqsave(lock, flags);
+	raw_spin_lock_irqsave(lock, flags);
 	v->counter -= a;
-	spin_unlock_irqrestore(lock, flags);
+	raw_spin_unlock_irqrestore(lock, flags);
 }
 EXPORT_SYMBOL(atomic64_sub);
 
 long long atomic64_sub_return(long long a, atomic64_t *v)
 {
 	unsigned long flags;
-	spinlock_t *lock = lock_addr(v);
+	raw_spinlock_t *lock = lock_addr(v);
 	long long val;
 
-	spin_lock_irqsave(lock, flags);
+	raw_spin_lock_irqsave(lock, flags);
 	val = v->counter -= a;
-	spin_unlock_irqrestore(lock, flags);
+	raw_spin_unlock_irqrestore(lock, flags);
 	return val;
 }
 EXPORT_SYMBOL(atomic64_sub_return);
@@ -117,14 +117,14 @@ EXPORT_SYMBOL(atomic64_sub_return);
 long long atomic64_dec_if_positive(atomic64_t *v)
 {
 	unsigned long flags;
-	spinlock_t *lock = lock_addr(v);
+	raw_spinlock_t *lock = lock_addr(v);
 	long long val;
 
-	spin_lock_irqsave(lock, flags);
+	raw_spin_lock_irqsave(lock, flags);
 	val = v->counter - 1;
 	if (val >= 0)
 		v->counter = val;
-	spin_unlock_irqrestore(lock, flags);
+	raw_spin_unlock_irqrestore(lock, flags);
 	return val;
 }
 EXPORT_SYMBOL(atomic64_dec_if_positive);
@@ -132,14 +132,14 @@ EXPORT_SYMBOL(atomic64_dec_if_positive);
 long long atomic64_cmpxchg(atomic64_t *v, long long o, long long n)
 {
 	unsigned long flags;
-	spinlock_t *lock = lock_addr(v);
+	raw_spinlock_t *lock = lock_addr(v);
 	long long val;
 
-	spin_lock_irqsave(lock, flags);
+	raw_spin_lock_irqsave(lock, flags);
 	val = v->counter;
 	if (val == o)
 		v->counter = n;
-	spin_unlock_irqrestore(lock, flags);
+	raw_spin_unlock_irqrestore(lock, flags);
 	return val;
 }
 EXPORT_SYMBOL(atomic64_cmpxchg);
@@ -147,13 +147,13 @@ EXPORT_SYMBOL(atomic64_cmpxchg);
 long long atomic64_xchg(atomic64_t *v, long long new)
 {
 	unsigned long flags;
-	spinlock_t *lock = lock_addr(v);
+	raw_spinlock_t *lock = lock_addr(v);
 	long long val;
 
-	spin_lock_irqsave(lock, flags);
+	raw_spin_lock_irqsave(lock, flags);
 	val = v->counter;
 	v->counter = new;
-	spin_unlock_irqrestore(lock, flags);
+	raw_spin_unlock_irqrestore(lock, flags);
 	return val;
 }
 EXPORT_SYMBOL(atomic64_xchg);
@@ -161,15 +161,15 @@ EXPORT_SYMBOL(atomic64_xchg);
 int atomic64_add_unless(atomic64_t *v, long long a, long long u)
 {
 	unsigned long flags;
-	spinlock_t *lock = lock_addr(v);
+	raw_spinlock_t *lock = lock_addr(v);
 	int ret = 0;
 
-	spin_lock_irqsave(lock, flags);
+	raw_spin_lock_irqsave(lock, flags);
 	if (v->counter != u) {
 		v->counter += a;
 		ret = 1;
 	}
-	spin_unlock_irqrestore(lock, flags);
+	raw_spin_unlock_irqrestore(lock, flags);
 	return ret;
 }
 EXPORT_SYMBOL(atomic64_add_unless);
@@ -179,7 +179,7 @@ static int init_atomic64_lock(void)
 	int i;
 
 	for (i = 0; i < NR_LOCKS; ++i)
-		spin_lock_init(&atomic64_lock[i].lock);
+		raw_spin_lock_init(&atomic64_lock[i].lock);
 	return 0;
 }
 
diff --git a/lib/atomic64_test.c b/lib/atomic64_test.c
index 44524cc8c32a..0c33cde2a1e6 100644
--- a/lib/atomic64_test.c
+++ b/lib/atomic64_test.c
@@ -10,7 +10,7 @@
  */
 #include <linux/init.h>
 #include <linux/kernel.h>
-#include <asm/atomic.h>
+#include <linux/atomic.h>
 
 #define INIT(c) do { atomic64_set(&v, c); r = c; } while (0)
 static __init int test_atomic64(void)
diff --git a/lib/bitmap.c b/lib/bitmap.c
index 3f3b68199d74..0d4a127dd9b3 100644
--- a/lib/bitmap.c
+++ b/lib/bitmap.c
@@ -271,8 +271,6 @@ int __bitmap_weight(const unsigned long *bitmap, int bits)
 }
 EXPORT_SYMBOL(__bitmap_weight);
 
-#define BITMAP_FIRST_WORD_MASK(start) (~0UL << ((start) % BITS_PER_LONG))
-
 void bitmap_set(unsigned long *map, int start, int nr)
 {
 	unsigned long *p = map + BIT_WORD(start);
@@ -421,7 +419,7 @@ int __bitmap_parse(const char *buf, unsigned int buflen,
 {
 	int c, old_c, totaldigits, ndigits, nchunks, nbits;
 	u32 chunk;
-	const char __user *ubuf = buf;
+	const char __user __force *ubuf = (const char __user __force *)buf;
 
 	bitmap_zero(maskp, nmaskbits);
 
@@ -506,7 +504,9 @@ int bitmap_parse_user(const char __user *ubuf,
 {
 	if (!access_ok(VERIFY_READ, ubuf, ulen))
 		return -EFAULT;
-	return __bitmap_parse((const char *)ubuf, ulen, 1, maskp, nmaskbits);
+	return __bitmap_parse((const char __force *)ubuf,
+				ulen, 1, maskp, nmaskbits);
+
 }
 EXPORT_SYMBOL(bitmap_parse_user);
 
@@ -596,7 +596,7 @@ static int __bitmap_parselist(const char *buf, unsigned int buflen,
 {
 	unsigned a, b;
 	int c, old_c, totaldigits;
-	const char __user *ubuf = buf;
+	const char __user __force *ubuf = (const char __user __force *)buf;
 	int exp_digit, in_range;
 
 	totaldigits = c = 0;
@@ -696,7 +696,7 @@ int bitmap_parselist_user(const char __user *ubuf,
 {
 	if (!access_ok(VERIFY_READ, ubuf, ulen))
 		return -EFAULT;
-	return __bitmap_parselist((const char *)ubuf,
+	return __bitmap_parselist((const char __force *)ubuf,
 					ulen, 1, maskp, nmaskbits);
 }
 EXPORT_SYMBOL(bitmap_parselist_user);
@@ -756,7 +756,7 @@ static int bitmap_pos_to_ord(const unsigned long *buf, int pos, int bits)
  *
  * 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 bitmap_ord_to_pos(const unsigned long *buf, int ord, int bits)
 {
 	int pos = 0;
 
diff --git a/lib/checksum.c b/lib/checksum.c
index 097508732f34..8df2f91e6d98 100644
--- a/lib/checksum.c
+++ b/lib/checksum.c
@@ -49,7 +49,7 @@ static inline unsigned short from32to16(unsigned int x)
 
 static unsigned int do_csum(const unsigned char *buff, int len)
 {
-	int odd, count;
+	int odd;
 	unsigned int result = 0;
 
 	if (len <= 0)
@@ -64,25 +64,22 @@ static unsigned int do_csum(const unsigned char *buff, int len)
 		len--;
 		buff++;
 	}
-	count = len >> 1;		/* nr of 16-bit words.. */
-	if (count) {
+	if (len >= 2) {
 		if (2 & (unsigned long) buff) {
 			result += *(unsigned short *) buff;
-			count--;
 			len -= 2;
 			buff += 2;
 		}
-		count >>= 1;		/* nr of 32-bit words.. */
-		if (count) {
+		if (len >= 4) {
+			const unsigned char *end = buff + ((unsigned)len & ~3);
 			unsigned int carry = 0;
 			do {
 				unsigned int w = *(unsigned int *) buff;
-				count--;
 				buff += 4;
 				result += carry;
 				result += w;
 				carry = (w > result);
-			} while (count);
+			} while (buff < end);
 			result += carry;
 			result = (result & 0xffff) + (result >> 16);
 		}
diff --git a/lib/cordic.c b/lib/cordic.c
new file mode 100644
index 000000000000..aa27a88d7e04
--- /dev/null
+++ b/lib/cordic.c
@@ -0,0 +1,101 @@
+/*
+ * Copyright (c) 2011 Broadcom Corporation
+ *
+ * Permission to use, copy, modify, and/or distribute this software for any
+ * purpose with or without fee is hereby granted, provided that the above
+ * copyright notice and this permission notice appear in all copies.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
+ * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
+ * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY
+ * SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
+ * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN ACTION
+ * OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF OR IN
+ * CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+ */
+#include <linux/module.h>
+#include <linux/cordic.h>
+
+#define CORDIC_ANGLE_GEN	39797
+#define CORDIC_PRECISION_SHIFT	16
+#define	CORDIC_NUM_ITER		(CORDIC_PRECISION_SHIFT + 2)
+
+#define	FIXED(X)	((s32)((X) << CORDIC_PRECISION_SHIFT))
+#define	FLOAT(X)	(((X) >= 0) \
+		? ((((X) >> (CORDIC_PRECISION_SHIFT - 1)) + 1) >> 1) \
+		: -((((-(X)) >> (CORDIC_PRECISION_SHIFT - 1)) + 1) >> 1))
+
+static const s32 arctan_table[] = {
+	2949120,
+	1740967,
+	919879,
+	466945,
+	234379,
+	117304,
+	58666,
+	29335,
+	14668,
+	7334,
+	3667,
+	1833,
+	917,
+	458,
+	229,
+	115,
+	57,
+	29
+};
+
+/*
+ * cordic_calc_iq() - calculates the i/q coordinate for given angle
+ *
+ * theta: angle in degrees for which i/q coordinate is to be calculated
+ * coord: function output parameter holding the i/q coordinate
+ */
+struct cordic_iq cordic_calc_iq(s32 theta)
+{
+	struct cordic_iq coord;
+	s32 angle, valtmp;
+	unsigned iter;
+	int signx = 1;
+	int signtheta;
+
+	coord.i = CORDIC_ANGLE_GEN;
+	coord.q = 0;
+	angle = 0;
+
+	theta = FIXED(theta);
+	signtheta = (theta < 0) ? -1 : 1;
+	theta = ((theta + FIXED(180) * signtheta) % FIXED(360)) -
+		FIXED(180) * signtheta;
+
+	if (FLOAT(theta) > 90) {
+		theta -= FIXED(180);
+		signx = -1;
+	} else if (FLOAT(theta) < -90) {
+		theta += FIXED(180);
+		signx = -1;
+	}
+
+	for (iter = 0; iter < CORDIC_NUM_ITER; iter++) {
+		if (theta > angle) {
+			valtmp = coord.i - (coord.q >> iter);
+			coord.q += (coord.i >> iter);
+			angle += arctan_table[iter];
+		} else {
+			valtmp = coord.i + (coord.q >> iter);
+			coord.q -= (coord.i >> iter);
+			angle -= arctan_table[iter];
+		}
+		coord.i = valtmp;
+	}
+
+	coord.i *= signx;
+	coord.q *= signx;
+	return coord;
+}
+EXPORT_SYMBOL(cordic_calc_iq);
+
+MODULE_DESCRIPTION("Cordic functions");
+MODULE_AUTHOR("Broadcom Corporation");
+MODULE_LICENSE("Dual BSD/GPL");
diff --git a/lib/cpumask.c b/lib/cpumask.c
index 05d6aca7fc19..af3e5817de98 100644
--- a/lib/cpumask.c
+++ b/lib/cpumask.c
@@ -30,7 +30,7 @@ int __any_online_cpu(const cpumask_t *mask)
 {
 	int cpu;
 
-	for_each_cpu_mask(cpu, *mask) {
+	for_each_cpu(cpu, mask) {
 		if (cpu_online(cpu))
 			break;
 	}
@@ -131,7 +131,7 @@ EXPORT_SYMBOL(zalloc_cpumask_var_node);
  */
 bool alloc_cpumask_var(cpumask_var_t *mask, gfp_t flags)
 {
-	return alloc_cpumask_var_node(mask, flags, numa_node_id());
+	return alloc_cpumask_var_node(mask, flags, NUMA_NO_NODE);
 }
 EXPORT_SYMBOL(alloc_cpumask_var);
 
diff --git a/lib/crc32.c b/lib/crc32.c
index 4855995fcde9..a6e633a48cea 100644
--- a/lib/crc32.c
+++ b/lib/crc32.c
@@ -26,7 +26,7 @@
 #include <linux/compiler.h>
 #include <linux/types.h>
 #include <linux/init.h>
-#include <asm/atomic.h>
+#include <linux/atomic.h>
 #include "crc32defs.h"
 #if CRC_LE_BITS == 8
 # define tole(x) __constant_cpu_to_le32(x)
diff --git a/lib/crc8.c b/lib/crc8.c
new file mode 100644
index 000000000000..87b59cafdb83
--- /dev/null
+++ b/lib/crc8.c
@@ -0,0 +1,86 @@
+/*
+ * Copyright (c) 2011 Broadcom Corporation
+ *
+ * Permission to use, copy, modify, and/or distribute this software for any
+ * purpose with or without fee is hereby granted, provided that the above
+ * copyright notice and this permission notice appear in all copies.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
+ * WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
+ * MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR ANY
+ * SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
+ * WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN ACTION
+ * OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF OR IN
+ * CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
+ */
+
+#define pr_fmt(fmt)		KBUILD_MODNAME ": " fmt
+
+#include <linux/module.h>
+#include <linux/crc8.h>
+#include <linux/printk.h>
+
+/*
+ * crc8_populate_msb - fill crc table for given polynomial in reverse bit order.
+ *
+ * table:	table to be filled.
+ * polynomial:	polynomial for which table is to be filled.
+ */
+void crc8_populate_msb(u8 table[CRC8_TABLE_SIZE], u8 polynomial)
+{
+	int i, j;
+	const u8 msbit = 0x80;
+	u8 t = msbit;
+
+	table[0] = 0;
+
+	for (i = 1; i < CRC8_TABLE_SIZE; i *= 2) {
+		t = (t << 1) ^ (t & msbit ? polynomial : 0);
+		for (j = 0; j < i; j++)
+			table[i+j] = table[j] ^ t;
+	}
+}
+EXPORT_SYMBOL(crc8_populate_msb);
+
+/*
+ * crc8_populate_lsb - fill crc table for given polynomial in regular bit order.
+ *
+ * table:	table to be filled.
+ * polynomial:	polynomial for which table is to be filled.
+ */
+void crc8_populate_lsb(u8 table[CRC8_TABLE_SIZE], u8 polynomial)
+{
+	int i, j;
+	u8 t = 1;
+
+	table[0] = 0;
+
+	for (i = (CRC8_TABLE_SIZE >> 1); i; i >>= 1) {
+		t = (t >> 1) ^ (t & 1 ? polynomial : 0);
+		for (j = 0; j < CRC8_TABLE_SIZE; j += 2*i)
+			table[i+j] = table[j] ^ t;
+	}
+}
+EXPORT_SYMBOL(crc8_populate_lsb);
+
+/*
+ * crc8 - calculate a crc8 over the given input data.
+ *
+ * table: crc table used for calculation.
+ * pdata: pointer to data buffer.
+ * nbytes: number of bytes in data buffer.
+ * crc:	previous returned crc8 value.
+ */
+u8 crc8(const u8 table[CRC8_TABLE_SIZE], u8 *pdata, size_t nbytes, u8 crc)
+{
+	/* loop over the buffer data */
+	while (nbytes-- > 0)
+		crc = table[(crc ^ *pdata++) & 0xff];
+
+	return crc;
+}
+EXPORT_SYMBOL(crc8);
+
+MODULE_DESCRIPTION("CRC8 (by Williams, Ross N.) function");
+MODULE_AUTHOR("Broadcom Corporation");
+MODULE_LICENSE("Dual BSD/GPL");
diff --git a/lib/dec_and_lock.c b/lib/dec_and_lock.c
index e73822aa6e9a..b5257725daad 100644
--- a/lib/dec_and_lock.c
+++ b/lib/dec_and_lock.c
@@ -1,6 +1,6 @@
 #include <linux/module.h>
 #include <linux/spinlock.h>
-#include <asm/atomic.h>
+#include <linux/atomic.h>
 
 /*
  * This is an implementation of the notion of "decrement a
diff --git a/lib/devres.c b/lib/devres.c
index 6efddf53b90c..7c0e953a7486 100644
--- a/lib/devres.c
+++ b/lib/devres.c
@@ -79,9 +79,9 @@ EXPORT_SYMBOL(devm_ioremap_nocache);
  */
 void devm_iounmap(struct device *dev, void __iomem *addr)
 {
-	iounmap(addr);
 	WARN_ON(devres_destroy(dev, devm_ioremap_release, devm_ioremap_match,
 			       (void *)addr));
+	iounmap(addr);
 }
 EXPORT_SYMBOL(devm_iounmap);
 
diff --git a/lib/dma-debug.c b/lib/dma-debug.c
index db07bfd9298e..74c6c7fce749 100644
--- a/lib/dma-debug.c
+++ b/lib/dma-debug.c
@@ -24,6 +24,7 @@
 #include <linux/spinlock.h>
 #include <linux/debugfs.h>
 #include <linux/uaccess.h>
+#include <linux/export.h>
 #include <linux/device.h>
 #include <linux/types.h>
 #include <linux/sched.h>
@@ -62,6 +63,8 @@ struct dma_debug_entry {
 #endif
 };
 
+typedef bool (*match_fn)(struct dma_debug_entry *, struct dma_debug_entry *);
+
 struct hash_bucket {
 	struct list_head list;
 	spinlock_t lock;
@@ -240,18 +243,37 @@ static void put_hash_bucket(struct hash_bucket *bucket,
 	spin_unlock_irqrestore(&bucket->lock, __flags);
 }
 
+static bool exact_match(struct dma_debug_entry *a, struct dma_debug_entry *b)
+{
+	return ((a->dev_addr == a->dev_addr) &&
+		(a->dev == b->dev)) ? true : false;
+}
+
+static bool containing_match(struct dma_debug_entry *a,
+			     struct dma_debug_entry *b)
+{
+	if (a->dev != b->dev)
+		return false;
+
+	if ((b->dev_addr <= a->dev_addr) &&
+	    ((b->dev_addr + b->size) >= (a->dev_addr + a->size)))
+		return true;
+
+	return false;
+}
+
 /*
  * Search a given entry in the hash bucket list
  */
-static struct dma_debug_entry *hash_bucket_find(struct hash_bucket *bucket,
-						struct dma_debug_entry *ref)
+static struct dma_debug_entry *__hash_bucket_find(struct hash_bucket *bucket,
+						  struct dma_debug_entry *ref,
+						  match_fn match)
 {
 	struct dma_debug_entry *entry, *ret = NULL;
 	int matches = 0, match_lvl, last_lvl = 0;
 
 	list_for_each_entry(entry, &bucket->list, list) {
-		if ((entry->dev_addr != ref->dev_addr) ||
-		    (entry->dev != ref->dev))
+		if (!match(ref, entry))
 			continue;
 
 		/*
@@ -293,6 +315,39 @@ static struct dma_debug_entry *hash_bucket_find(struct hash_bucket *bucket,
 	return ret;
 }
 
+static struct dma_debug_entry *bucket_find_exact(struct hash_bucket *bucket,
+						 struct dma_debug_entry *ref)
+{
+	return __hash_bucket_find(bucket, ref, exact_match);
+}
+
+static struct dma_debug_entry *bucket_find_contain(struct hash_bucket **bucket,
+						   struct dma_debug_entry *ref,
+						   unsigned long *flags)
+{
+
+	unsigned int max_range = dma_get_max_seg_size(ref->dev);
+	struct dma_debug_entry *entry, index = *ref;
+	unsigned int range = 0;
+
+	while (range <= max_range) {
+		entry = __hash_bucket_find(*bucket, &index, containing_match);
+
+		if (entry)
+			return entry;
+
+		/*
+		 * Nothing found, go back a hash bucket
+		 */
+		put_hash_bucket(*bucket, flags);
+		range          += (1 << HASH_FN_SHIFT);
+		index.dev_addr -= (1 << HASH_FN_SHIFT);
+		*bucket = get_hash_bucket(&index, flags);
+	}
+
+	return NULL;
+}
+
 /*
  * Add an entry to a hash bucket
  */
@@ -802,7 +857,7 @@ static void check_unmap(struct dma_debug_entry *ref)
 	}
 
 	bucket = get_hash_bucket(ref, &flags);
-	entry = hash_bucket_find(bucket, ref);
+	entry = bucket_find_exact(bucket, ref);
 
 	if (!entry) {
 		err_printk(ref->dev, NULL, "DMA-API: device driver tries "
@@ -902,7 +957,7 @@ static void check_sync(struct device *dev,
 
 	bucket = get_hash_bucket(ref, &flags);
 
-	entry = hash_bucket_find(bucket, ref);
+	entry = bucket_find_contain(&bucket, ref, &flags);
 
 	if (!entry) {
 		err_printk(dev, NULL, "DMA-API: device driver tries "
@@ -1060,7 +1115,7 @@ static int get_nr_mapped_entries(struct device *dev,
 	int mapped_ents;
 
 	bucket       = get_hash_bucket(ref, &flags);
-	entry        = hash_bucket_find(bucket, ref);
+	entry        = bucket_find_exact(bucket, ref);
 	mapped_ents  = 0;
 
 	if (entry)
diff --git a/lib/dynamic_debug.c b/lib/dynamic_debug.c
index 75ca78f3a8c9..dcdade39e47f 100644
--- a/lib/dynamic_debug.c
+++ b/lib/dynamic_debug.c
@@ -10,11 +10,12 @@
  * Copyright (C) 2011 Bart Van Assche.  All Rights Reserved.
  */
 
+#define pr_fmt(fmt) KBUILD_MODNAME ":%s: " fmt, __func__
+
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/moduleparam.h>
 #include <linux/kallsyms.h>
-#include <linux/version.h>
 #include <linux/types.h>
 #include <linux/mutex.h>
 #include <linux/proc_fs.h>
@@ -30,6 +31,8 @@
 #include <linux/jump_label.h>
 #include <linux/hardirq.h>
 #include <linux/sched.h>
+#include <linux/device.h>
+#include <linux/netdevice.h>
 
 extern struct _ddebug __start___verbose[];
 extern struct _ddebug __stop___verbose[];
@@ -38,7 +41,6 @@ struct ddebug_table {
 	struct list_head link;
 	char *mod_name;
 	unsigned int num_ddebugs;
-	unsigned int num_enabled;
 	struct _ddebug *ddebugs;
 };
 
@@ -148,19 +150,13 @@ static void ddebug_change(const struct ddebug_query *query,
 			newflags = (dp->flags & mask) | flags;
 			if (newflags == dp->flags)
 				continue;
-
-			if (!newflags)
-				dt->num_enabled--;
-			else if (!dp->flags)
-				dt->num_enabled++;
 			dp->flags = newflags;
 			if (newflags)
 				dp->enabled = 1;
 			else
 				dp->enabled = 0;
 			if (verbose)
-				printk(KERN_INFO
-					"ddebug: changed %s:%d [%s]%s %s\n",
+				pr_info("changed %s:%d [%s]%s %s\n",
 					dp->filename, dp->lineno,
 					dt->mod_name, dp->function,
 					ddebug_describe_flags(dp, flagbuf,
@@ -170,7 +166,7 @@ static void ddebug_change(const struct ddebug_query *query,
 	mutex_unlock(&ddebug_lock);
 
 	if (!nfound && verbose)
-		printk(KERN_INFO "ddebug: no matches for query\n");
+		pr_info("no matches for query\n");
 }
 
 /*
@@ -215,10 +211,10 @@ static int ddebug_tokenize(char *buf, char *words[], int maxwords)
 
 	if (verbose) {
 		int i;
-		printk(KERN_INFO "%s: split into words:", __func__);
+		pr_info("split into words:");
 		for (i = 0 ; i < nwords ; i++)
-			printk(" \"%s\"", words[i]);
-		printk("\n");
+			pr_cont(" \"%s\"", words[i]);
+		pr_cont("\n");
 	}
 
 	return nwords;
@@ -330,16 +326,15 @@ static int ddebug_parse_query(char *words[], int nwords,
 			}
 		} else {
 			if (verbose)
-				printk(KERN_ERR "%s: unknown keyword \"%s\"\n",
-					__func__, words[i]);
+				pr_err("unknown keyword \"%s\"\n", words[i]);
 			return -EINVAL;
 		}
 	}
 
 	if (verbose)
-		printk(KERN_INFO "%s: q->function=\"%s\" q->filename=\"%s\" "
-		       "q->module=\"%s\" q->format=\"%s\" q->lineno=%u-%u\n",
-			__func__, query->function, query->filename,
+		pr_info("q->function=\"%s\" q->filename=\"%s\" "
+			"q->module=\"%s\" q->format=\"%s\" q->lineno=%u-%u\n",
+			query->function, query->filename,
 			query->module, query->format, query->first_lineno,
 			query->last_lineno);
 
@@ -368,7 +363,7 @@ static int ddebug_parse_flags(const char *str, unsigned int *flagsp,
 		return -EINVAL;
 	}
 	if (verbose)
-		printk(KERN_INFO "%s: op='%c'\n", __func__, op);
+		pr_info("op='%c'\n", op);
 
 	for ( ; *str ; ++str) {
 		for (i = ARRAY_SIZE(opt_array) - 1; i >= 0; i--) {
@@ -383,7 +378,7 @@ static int ddebug_parse_flags(const char *str, unsigned int *flagsp,
 	if (flags == 0)
 		return -EINVAL;
 	if (verbose)
-		printk(KERN_INFO "%s: flags=0x%x\n", __func__, flags);
+		pr_info("flags=0x%x\n", flags);
 
 	/* calculate final *flagsp, *maskp according to mask and op */
 	switch (op) {
@@ -401,8 +396,7 @@ static int ddebug_parse_flags(const char *str, unsigned int *flagsp,
 		break;
 	}
 	if (verbose)
-		printk(KERN_INFO "%s: *flagsp=0x%x *maskp=0x%x\n",
-			__func__, *flagsp, *maskp);
+		pr_info("*flagsp=0x%x *maskp=0x%x\n", *flagsp, *maskp);
 	return 0;
 }
 
@@ -427,40 +421,117 @@ static int ddebug_exec_query(char *query_string)
 	return 0;
 }
 
+#define PREFIX_SIZE 64
+
+static int remaining(int wrote)
+{
+	if (PREFIX_SIZE - wrote > 0)
+		return PREFIX_SIZE - wrote;
+	return 0;
+}
+
+static char *dynamic_emit_prefix(const struct _ddebug *desc, char *buf)
+{
+	int pos_after_tid;
+	int pos = 0;
+
+	pos += snprintf(buf + pos, remaining(pos), "%s", KERN_DEBUG);
+	if (desc->flags & _DPRINTK_FLAGS_INCL_TID) {
+		if (in_interrupt())
+			pos += snprintf(buf + pos, remaining(pos), "%s ",
+						"<intr>");
+		else
+			pos += snprintf(buf + pos, remaining(pos), "[%d] ",
+						task_pid_vnr(current));
+	}
+	pos_after_tid = pos;
+	if (desc->flags & _DPRINTK_FLAGS_INCL_MODNAME)
+		pos += snprintf(buf + pos, remaining(pos), "%s:",
+					desc->modname);
+	if (desc->flags & _DPRINTK_FLAGS_INCL_FUNCNAME)
+		pos += snprintf(buf + pos, remaining(pos), "%s:",
+					desc->function);
+	if (desc->flags & _DPRINTK_FLAGS_INCL_LINENO)
+		pos += snprintf(buf + pos, remaining(pos), "%d:", desc->lineno);
+	if (pos - pos_after_tid)
+		pos += snprintf(buf + pos, remaining(pos), " ");
+	if (pos >= PREFIX_SIZE)
+		buf[PREFIX_SIZE - 1] = '\0';
+
+	return buf;
+}
+
 int __dynamic_pr_debug(struct _ddebug *descriptor, const char *fmt, ...)
 {
 	va_list args;
 	int res;
+	struct va_format vaf;
+	char buf[PREFIX_SIZE];
 
 	BUG_ON(!descriptor);
 	BUG_ON(!fmt);
 
 	va_start(args, fmt);
-	res = printk(KERN_DEBUG);
-	if (descriptor->flags & _DPRINTK_FLAGS_INCL_TID) {
-		if (in_interrupt())
-			res += printk(KERN_CONT "<intr> ");
-		else
-			res += printk(KERN_CONT "[%d] ", task_pid_vnr(current));
-	}
-	if (descriptor->flags & _DPRINTK_FLAGS_INCL_MODNAME)
-		res += printk(KERN_CONT "%s:", descriptor->modname);
-	if (descriptor->flags & _DPRINTK_FLAGS_INCL_FUNCNAME)
-		res += printk(KERN_CONT "%s:", descriptor->function);
-	if (descriptor->flags & _DPRINTK_FLAGS_INCL_LINENO)
-		res += printk(KERN_CONT "%d ", descriptor->lineno);
-	res += vprintk(fmt, args);
+	vaf.fmt = fmt;
+	vaf.va = &args;
+	res = printk("%s%pV", dynamic_emit_prefix(descriptor, buf), &vaf);
 	va_end(args);
 
 	return res;
 }
 EXPORT_SYMBOL(__dynamic_pr_debug);
 
+int __dynamic_dev_dbg(struct _ddebug *descriptor,
+		      const struct device *dev, const char *fmt, ...)
+{
+	struct va_format vaf;
+	va_list args;
+	int res;
+	char buf[PREFIX_SIZE];
+
+	BUG_ON(!descriptor);
+	BUG_ON(!fmt);
+
+	va_start(args, fmt);
+	vaf.fmt = fmt;
+	vaf.va = &args;
+	res = __dev_printk(dynamic_emit_prefix(descriptor, buf), dev, &vaf);
+	va_end(args);
+
+	return res;
+}
+EXPORT_SYMBOL(__dynamic_dev_dbg);
+
+#ifdef CONFIG_NET
+
+int __dynamic_netdev_dbg(struct _ddebug *descriptor,
+		      const struct net_device *dev, const char *fmt, ...)
+{
+	struct va_format vaf;
+	va_list args;
+	int res;
+	char buf[PREFIX_SIZE];
+
+	BUG_ON(!descriptor);
+	BUG_ON(!fmt);
+
+	va_start(args, fmt);
+	vaf.fmt = fmt;
+	vaf.va = &args;
+	res = __netdev_printk(dynamic_emit_prefix(descriptor, buf), dev, &vaf);
+	va_end(args);
+
+	return res;
+}
+EXPORT_SYMBOL(__dynamic_netdev_dbg);
+
+#endif
+
 static __initdata char ddebug_setup_string[1024];
 static __init int ddebug_setup_query(char *str)
 {
 	if (strlen(str) >= 1024) {
-		pr_warning("ddebug boot param string too large\n");
+		pr_warn("ddebug boot param string too large\n");
 		return 0;
 	}
 	strcpy(ddebug_setup_string, str);
@@ -488,8 +559,7 @@ static ssize_t ddebug_proc_write(struct file *file, const char __user *ubuf,
 		return -EFAULT;
 	tmpbuf[len] = '\0';
 	if (verbose)
-		printk(KERN_INFO "%s: read %d bytes from userspace\n",
-			__func__, (int)len);
+		pr_info("read %d bytes from userspace\n", (int)len);
 
 	ret = ddebug_exec_query(tmpbuf);
 	if (ret)
@@ -552,8 +622,7 @@ static void *ddebug_proc_start(struct seq_file *m, loff_t *pos)
 	int n = *pos;
 
 	if (verbose)
-		printk(KERN_INFO "%s: called m=%p *pos=%lld\n",
-			__func__, m, (unsigned long long)*pos);
+		pr_info("called m=%p *pos=%lld\n", m, (unsigned long long)*pos);
 
 	mutex_lock(&ddebug_lock);
 
@@ -578,8 +647,8 @@ static void *ddebug_proc_next(struct seq_file *m, void *p, loff_t *pos)
 	struct _ddebug *dp;
 
 	if (verbose)
-		printk(KERN_INFO "%s: called m=%p p=%p *pos=%lld\n",
-			__func__, m, p, (unsigned long long)*pos);
+		pr_info("called m=%p p=%p *pos=%lld\n",
+			m, p, (unsigned long long)*pos);
 
 	if (p == SEQ_START_TOKEN)
 		dp = ddebug_iter_first(iter);
@@ -602,8 +671,7 @@ static int ddebug_proc_show(struct seq_file *m, void *p)
 	char flagsbuf[8];
 
 	if (verbose)
-		printk(KERN_INFO "%s: called m=%p p=%p\n",
-			__func__, m, p);
+		pr_info("called m=%p p=%p\n", m, p);
 
 	if (p == SEQ_START_TOKEN) {
 		seq_puts(m,
@@ -628,8 +696,7 @@ static int ddebug_proc_show(struct seq_file *m, void *p)
 static void ddebug_proc_stop(struct seq_file *m, void *p)
 {
 	if (verbose)
-		printk(KERN_INFO "%s: called m=%p p=%p\n",
-			__func__, m, p);
+		pr_info("called m=%p p=%p\n", m, p);
 	mutex_unlock(&ddebug_lock);
 }
 
@@ -652,7 +719,7 @@ static int ddebug_proc_open(struct inode *inode, struct file *file)
 	int err;
 
 	if (verbose)
-		printk(KERN_INFO "%s: called\n", __func__);
+		pr_info("called\n");
 
 	iter = kzalloc(sizeof(*iter), GFP_KERNEL);
 	if (iter == NULL)
@@ -696,7 +763,6 @@ int ddebug_add_module(struct _ddebug *tab, unsigned int n,
 	}
 	dt->mod_name = new_name;
 	dt->num_ddebugs = n;
-	dt->num_enabled = 0;
 	dt->ddebugs = tab;
 
 	mutex_lock(&ddebug_lock);
@@ -704,8 +770,7 @@ int ddebug_add_module(struct _ddebug *tab, unsigned int n,
 	mutex_unlock(&ddebug_lock);
 
 	if (verbose)
-		printk(KERN_INFO "%u debug prints in module %s\n",
-				 n, dt->mod_name);
+		pr_info("%u debug prints in module %s\n", n, dt->mod_name);
 	return 0;
 }
 EXPORT_SYMBOL_GPL(ddebug_add_module);
@@ -727,8 +792,7 @@ int ddebug_remove_module(const char *mod_name)
 	int ret = -ENOENT;
 
 	if (verbose)
-		printk(KERN_INFO "%s: removing module \"%s\"\n",
-				__func__, mod_name);
+		pr_info("removing module \"%s\"\n", mod_name);
 
 	mutex_lock(&ddebug_lock);
 	list_for_each_entry_safe(dt, nextdt, &ddebug_tables, link) {
@@ -804,8 +868,8 @@ static int __init dynamic_debug_init(void)
 	if (ddebug_setup_string[0] != '\0') {
 		ret = ddebug_exec_query(ddebug_setup_string);
 		if (ret)
-			pr_warning("Invalid ddebug boot param %s",
-				   ddebug_setup_string);
+			pr_warn("Invalid ddebug boot param %s",
+				ddebug_setup_string);
 		else
 			pr_info("ddebug initialized with string %s",
 				ddebug_setup_string);
diff --git a/lib/fault-inject.c b/lib/fault-inject.c
index 7e65af70635e..4f7554025e30 100644
--- a/lib/fault-inject.c
+++ b/lib/fault-inject.c
@@ -8,14 +8,13 @@
 #include <linux/module.h>
 #include <linux/interrupt.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)
+int setup_fault_attr(struct fault_attr *attr, char *str)
 {
 	unsigned long probability;
 	unsigned long interval;
@@ -37,6 +36,7 @@ int __init setup_fault_attr(struct fault_attr *attr, char *str)
 
 	return 1;
 }
+EXPORT_SYMBOL_GPL(setup_fault_attr);
 
 static void fail_dump(struct fault_attr *attr)
 {
@@ -131,6 +131,7 @@ bool should_fail(struct fault_attr *attr, ssize_t size)
 
 	return true;
 }
+EXPORT_SYMBOL_GPL(should_fail);
 
 #ifdef CONFIG_FAULT_INJECTION_DEBUG_FS
 
@@ -140,16 +141,6 @@ static int debugfs_ul_set(void *data, u64 val)
 	return 0;
 }
 
-#ifdef CONFIG_FAULT_INJECTION_STACKTRACE_FILTER
-static int debugfs_ul_set_MAX_STACK_TRACE_DEPTH(void *data, u64 val)
-{
-	*(unsigned long *)data =
-		val < MAX_STACK_TRACE_DEPTH ?
-		val : MAX_STACK_TRACE_DEPTH;
-	return 0;
-}
-#endif /* CONFIG_FAULT_INJECTION_STACKTRACE_FILTER */
-
 static int debugfs_ul_get(void *data, u64 *val)
 {
 	*val = *(unsigned long *)data;
@@ -165,16 +156,26 @@ static struct dentry *debugfs_create_ul(const char *name, mode_t mode,
 }
 
 #ifdef CONFIG_FAULT_INJECTION_STACKTRACE_FILTER
-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(
+static int debugfs_stacktrace_depth_set(void *data, u64 val)
+{
+	*(unsigned long *)data =
+		min_t(unsigned long, val, MAX_STACK_TRACE_DEPTH);
+
+	return 0;
+}
+
+DEFINE_SIMPLE_ATTRIBUTE(fops_stacktrace_depth, debugfs_ul_get,
+			debugfs_stacktrace_depth_set, "%llu\n");
+
+static struct dentry *debugfs_create_stacktrace_depth(
 	const char *name, mode_t mode,
 	struct dentry *parent, unsigned long *value)
 {
 	return debugfs_create_file(name, mode, parent, value,
-				   &fops_ul_MAX_STACK_TRACE_DEPTH);
+				   &fops_stacktrace_depth);
 }
+
 #endif /* CONFIG_FAULT_INJECTION_STACKTRACE_FILTER */
 
 static int debugfs_atomic_t_set(void *data, u64 val)
@@ -198,118 +199,52 @@ static struct dentry *debugfs_create_atomic_t(const char *name, mode_t mode,
 	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)
+struct dentry *fault_create_debugfs_attr(const char *name,
+			struct dentry *parent, struct fault_attr *attr)
 {
 	mode_t mode = S_IFREG | S_IRUSR | S_IWUSR;
 	struct dentry *dir;
 
-	memset(&attr->dentries, 0, sizeof(attr->dentries));
-
-	dir = debugfs_create_dir(name, NULL);
+	dir = debugfs_create_dir(name, parent);
 	if (!dir)
-		goto fail;
-	attr->dentries.dir = dir;
-
-	attr->dentries.probability_file =
-		debugfs_create_ul("probability", mode, dir, &attr->probability);
+		return ERR_PTR(-ENOMEM);
 
-	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)
+	if (!debugfs_create_ul("probability", mode, dir, &attr->probability))
+		goto fail;
+	if (!debugfs_create_ul("interval", mode, dir, &attr->interval))
+		goto fail;
+	if (!debugfs_create_atomic_t("times", mode, dir, &attr->times))
+		goto fail;
+	if (!debugfs_create_atomic_t("space", mode, dir, &attr->space))
+		goto fail;
+	if (!debugfs_create_ul("verbose", mode, dir, &attr->verbose))
+		goto fail;
+	if (!debugfs_create_bool("task-filter", mode, dir, &attr->task_filter))
 		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)
+	if (!debugfs_create_stacktrace_depth("stacktrace-depth", mode, dir,
+				&attr->stacktrace_depth))
+		goto fail;
+	if (!debugfs_create_ul("require-start", mode, dir,
+				&attr->require_start))
+		goto fail;
+	if (!debugfs_create_ul("require-end", mode, dir, &attr->require_end))
+		goto fail;
+	if (!debugfs_create_ul("reject-start", mode, dir, &attr->reject_start))
+		goto fail;
+	if (!debugfs_create_ul("reject-end", mode, dir, &attr->reject_end))
 		goto fail;
 
 #endif /* CONFIG_FAULT_INJECTION_STACKTRACE_FILTER */
 
-	return 0;
+	return dir;
 fail:
-	cleanup_fault_attr_dentries(attr);
-	return -ENOMEM;
+	debugfs_remove_recursive(dir);
+
+	return ERR_PTR(-ENOMEM);
 }
+EXPORT_SYMBOL_GPL(fault_create_debugfs_attr);
 
 #endif /* CONFIG_FAULT_INJECTION_DEBUG_FS */
diff --git a/lib/genalloc.c b/lib/genalloc.c
index 577ddf805975..f352cc42f4f8 100644
--- a/lib/genalloc.c
+++ b/lib/genalloc.c
@@ -1,8 +1,26 @@
 /*
- * 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.
+ * Basic general purpose allocator for managing special purpose
+ * memory, for example, memory that is not managed by the regular
+ * kmalloc/kfree interface.  Uses for this includes on-device special
+ * memory, uncached memory etc.
+ *
+ * It is safe to use the allocator in NMI handlers and other special
+ * unblockable contexts that could otherwise deadlock on locks.  This
+ * is implemented by using atomic operations and retries on any
+ * conflicts.  The disadvantage is that there may be livelocks in
+ * extreme cases.  For better scalability, one allocator can be used
+ * for each CPU.
+ *
+ * The lockless operation only works if there is enough memory
+ * available.  If new memory is added to the pool a lock has to be
+ * still taken.  So any user relying on locklessness has to ensure
+ * that sufficient memory is preallocated.
+ *
+ * The basic atomic operation of this allocator is cmpxchg on long.
+ * On architectures that don't have NMI-safe cmpxchg implementation,
+ * the allocator can NOT be used in NMI handler.  So code uses the
+ * allocator in NMI handler should depend on
+ * CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG.
  *
  * Copyright 2005 (C) Jes Sorensen <jes@trained-monkey.org>
  *
@@ -13,8 +31,109 @@
 #include <linux/slab.h>
 #include <linux/module.h>
 #include <linux/bitmap.h>
+#include <linux/rculist.h>
+#include <linux/interrupt.h>
 #include <linux/genalloc.h>
 
+static int set_bits_ll(unsigned long *addr, unsigned long mask_to_set)
+{
+	unsigned long val, nval;
+
+	nval = *addr;
+	do {
+		val = nval;
+		if (val & mask_to_set)
+			return -EBUSY;
+		cpu_relax();
+	} while ((nval = cmpxchg(addr, val, val | mask_to_set)) != val);
+
+	return 0;
+}
+
+static int clear_bits_ll(unsigned long *addr, unsigned long mask_to_clear)
+{
+	unsigned long val, nval;
+
+	nval = *addr;
+	do {
+		val = nval;
+		if ((val & mask_to_clear) != mask_to_clear)
+			return -EBUSY;
+		cpu_relax();
+	} while ((nval = cmpxchg(addr, val, val & ~mask_to_clear)) != val);
+
+	return 0;
+}
+
+/*
+ * bitmap_set_ll - set the specified number of bits at the specified position
+ * @map: pointer to a bitmap
+ * @start: a bit position in @map
+ * @nr: number of bits to set
+ *
+ * Set @nr bits start from @start in @map lock-lessly. Several users
+ * can set/clear the same bitmap simultaneously without lock. If two
+ * users set the same bit, one user will return remain bits, otherwise
+ * return 0.
+ */
+static int bitmap_set_ll(unsigned long *map, int start, int nr)
+{
+	unsigned long *p = map + BIT_WORD(start);
+	const int size = start + nr;
+	int bits_to_set = BITS_PER_LONG - (start % BITS_PER_LONG);
+	unsigned long mask_to_set = BITMAP_FIRST_WORD_MASK(start);
+
+	while (nr - bits_to_set >= 0) {
+		if (set_bits_ll(p, mask_to_set))
+			return nr;
+		nr -= bits_to_set;
+		bits_to_set = BITS_PER_LONG;
+		mask_to_set = ~0UL;
+		p++;
+	}
+	if (nr) {
+		mask_to_set &= BITMAP_LAST_WORD_MASK(size);
+		if (set_bits_ll(p, mask_to_set))
+			return nr;
+	}
+
+	return 0;
+}
+
+/*
+ * bitmap_clear_ll - clear the specified number of bits at the specified position
+ * @map: pointer to a bitmap
+ * @start: a bit position in @map
+ * @nr: number of bits to set
+ *
+ * Clear @nr bits start from @start in @map lock-lessly. Several users
+ * can set/clear the same bitmap simultaneously without lock. If two
+ * users clear the same bit, one user will return remain bits,
+ * otherwise return 0.
+ */
+static int bitmap_clear_ll(unsigned long *map, int start, int nr)
+{
+	unsigned long *p = map + BIT_WORD(start);
+	const int size = start + nr;
+	int bits_to_clear = BITS_PER_LONG - (start % BITS_PER_LONG);
+	unsigned long mask_to_clear = BITMAP_FIRST_WORD_MASK(start);
+
+	while (nr - bits_to_clear >= 0) {
+		if (clear_bits_ll(p, mask_to_clear))
+			return nr;
+		nr -= bits_to_clear;
+		bits_to_clear = BITS_PER_LONG;
+		mask_to_clear = ~0UL;
+		p++;
+	}
+	if (nr) {
+		mask_to_clear &= BITMAP_LAST_WORD_MASK(size);
+		if (clear_bits_ll(p, mask_to_clear))
+			return nr;
+	}
+
+	return 0;
+}
 
 /**
  * gen_pool_create - create a new special memory pool
@@ -30,7 +149,7 @@ struct gen_pool *gen_pool_create(int min_alloc_order, int nid)
 
 	pool = kmalloc_node(sizeof(struct gen_pool), GFP_KERNEL, nid);
 	if (pool != NULL) {
-		rwlock_init(&pool->lock);
+		spin_lock_init(&pool->lock);
 		INIT_LIST_HEAD(&pool->chunks);
 		pool->min_alloc_order = min_alloc_order;
 	}
@@ -63,14 +182,14 @@ int gen_pool_add_virt(struct gen_pool *pool, unsigned long virt, phys_addr_t phy
 	if (unlikely(chunk == NULL))
 		return -ENOMEM;
 
-	spin_lock_init(&chunk->lock);
 	chunk->phys_addr = phys;
 	chunk->start_addr = virt;
 	chunk->end_addr = virt + size;
+	atomic_set(&chunk->avail, size);
 
-	write_lock(&pool->lock);
-	list_add(&chunk->next_chunk, &pool->chunks);
-	write_unlock(&pool->lock);
+	spin_lock(&pool->lock);
+	list_add_rcu(&chunk->next_chunk, &pool->chunks);
+	spin_unlock(&pool->lock);
 
 	return 0;
 }
@@ -85,19 +204,19 @@ EXPORT_SYMBOL(gen_pool_add_virt);
  */
 phys_addr_t gen_pool_virt_to_phys(struct gen_pool *pool, unsigned long addr)
 {
-	struct list_head *_chunk;
 	struct gen_pool_chunk *chunk;
+	phys_addr_t paddr = -1;
 
-	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)
-			return chunk->phys_addr + addr - chunk->start_addr;
+	rcu_read_lock();
+	list_for_each_entry_rcu(chunk, &pool->chunks, next_chunk) {
+		if (addr >= chunk->start_addr && addr < chunk->end_addr) {
+			paddr = chunk->phys_addr + (addr - chunk->start_addr);
+			break;
+		}
 	}
-	read_unlock(&pool->lock);
+	rcu_read_unlock();
 
-	return -1;
+	return paddr;
 }
 EXPORT_SYMBOL(gen_pool_virt_to_phys);
 
@@ -115,7 +234,6 @@ void gen_pool_destroy(struct gen_pool *pool)
 	int order = pool->min_alloc_order;
 	int bit, end_bit;
 
-
 	list_for_each_safe(_chunk, _next_chunk, &pool->chunks) {
 		chunk = list_entry(_chunk, struct gen_pool_chunk, next_chunk);
 		list_del(&chunk->next_chunk);
@@ -137,44 +255,50 @@ EXPORT_SYMBOL(gen_pool_destroy);
  * @size: number of bytes to allocate from the pool
  *
  * Allocate the requested number of bytes from the specified pool.
- * Uses a first-fit algorithm.
+ * Uses a first-fit algorithm. Can not be used in NMI handler on
+ * architectures without NMI-safe cmpxchg implementation.
  */
 unsigned long gen_pool_alloc(struct gen_pool *pool, size_t size)
 {
-	struct list_head *_chunk;
 	struct gen_pool_chunk *chunk;
-	unsigned long addr, flags;
+	unsigned long addr = 0;
 	int order = pool->min_alloc_order;
-	int nbits, start_bit, end_bit;
+	int nbits, start_bit = 0, end_bit, remain;
+
+#ifndef CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG
+	BUG_ON(in_nmi());
+#endif
 
 	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);
+	rcu_read_lock();
+	list_for_each_entry_rcu(chunk, &pool->chunks, next_chunk) {
+		if (size > atomic_read(&chunk->avail))
+			continue;
 
 		end_bit = (chunk->end_addr - chunk->start_addr) >> order;
-
-		spin_lock_irqsave(&chunk->lock, flags);
-		start_bit = bitmap_find_next_zero_area(chunk->bits, end_bit, 0,
-						nbits, 0);
-		if (start_bit >= end_bit) {
-			spin_unlock_irqrestore(&chunk->lock, flags);
+retry:
+		start_bit = bitmap_find_next_zero_area(chunk->bits, end_bit,
+						       start_bit, nbits, 0);
+		if (start_bit >= end_bit)
 			continue;
+		remain = bitmap_set_ll(chunk->bits, start_bit, nbits);
+		if (remain) {
+			remain = bitmap_clear_ll(chunk->bits, start_bit,
+						 nbits - remain);
+			BUG_ON(remain);
+			goto retry;
 		}
 
 		addr = chunk->start_addr + ((unsigned long)start_bit << order);
-
-		bitmap_set(chunk->bits, start_bit, nbits);
-		spin_unlock_irqrestore(&chunk->lock, flags);
-		read_unlock(&pool->lock);
-		return addr;
+		size = nbits << order;
+		atomic_sub(size, &chunk->avail);
+		break;
 	}
-	read_unlock(&pool->lock);
-	return 0;
+	rcu_read_unlock();
+	return addr;
 }
 EXPORT_SYMBOL(gen_pool_alloc);
 
@@ -184,33 +308,95 @@ EXPORT_SYMBOL(gen_pool_alloc);
  * @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.
+ * Free previously allocated special memory back to the specified
+ * pool.  Can not be used in NMI handler on architectures without
+ * NMI-safe cmpxchg implementation.
  */
 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;
+	int start_bit, nbits, remain;
 
-	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);
+#ifndef CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG
+	BUG_ON(in_nmi());
+#endif
 
+	nbits = (size + (1UL << order) - 1) >> order;
+	rcu_read_lock();
+	list_for_each_entry_rcu(chunk, &pool->chunks, 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;
+			start_bit = (addr - chunk->start_addr) >> order;
+			remain = bitmap_clear_ll(chunk->bits, start_bit, nbits);
+			BUG_ON(remain);
+			size = nbits << order;
+			atomic_add(size, &chunk->avail);
+			rcu_read_unlock();
+			return;
 		}
 	}
-	BUG_ON(nbits > 0);
-	read_unlock(&pool->lock);
+	rcu_read_unlock();
+	BUG();
 }
 EXPORT_SYMBOL(gen_pool_free);
+
+/**
+ * gen_pool_for_each_chunk - call func for every chunk of generic memory pool
+ * @pool:	the generic memory pool
+ * @func:	func to call
+ * @data:	additional data used by @func
+ *
+ * Call @func for every chunk of generic memory pool.  The @func is
+ * called with rcu_read_lock held.
+ */
+void gen_pool_for_each_chunk(struct gen_pool *pool,
+	void (*func)(struct gen_pool *pool, struct gen_pool_chunk *chunk, void *data),
+	void *data)
+{
+	struct gen_pool_chunk *chunk;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(chunk, &(pool)->chunks, next_chunk)
+		func(pool, chunk, data);
+	rcu_read_unlock();
+}
+EXPORT_SYMBOL(gen_pool_for_each_chunk);
+
+/**
+ * gen_pool_avail - get available free space of the pool
+ * @pool: pool to get available free space
+ *
+ * Return available free space of the specified pool.
+ */
+size_t gen_pool_avail(struct gen_pool *pool)
+{
+	struct gen_pool_chunk *chunk;
+	size_t avail = 0;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(chunk, &pool->chunks, next_chunk)
+		avail += atomic_read(&chunk->avail);
+	rcu_read_unlock();
+	return avail;
+}
+EXPORT_SYMBOL_GPL(gen_pool_avail);
+
+/**
+ * gen_pool_size - get size in bytes of memory managed by the pool
+ * @pool: pool to get size
+ *
+ * Return size in bytes of memory managed by the pool.
+ */
+size_t gen_pool_size(struct gen_pool *pool)
+{
+	struct gen_pool_chunk *chunk;
+	size_t size = 0;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(chunk, &pool->chunks, next_chunk)
+		size += chunk->end_addr - chunk->start_addr;
+	rcu_read_unlock();
+	return size;
+}
+EXPORT_SYMBOL_GPL(gen_pool_size);
diff --git a/lib/hexdump.c b/lib/hexdump.c
index f5fe6ba7a3ab..51d5ae210244 100644
--- a/lib/hexdump.c
+++ b/lib/hexdump.c
@@ -38,14 +38,21 @@ EXPORT_SYMBOL(hex_to_bin);
  * @dst: binary result
  * @src: ascii hexadecimal string
  * @count: result length
+ *
+ * Return 0 on success, -1 in case of bad input.
  */
-void hex2bin(u8 *dst, const char *src, size_t count)
+int hex2bin(u8 *dst, const char *src, size_t count)
 {
 	while (count--) {
-		*dst = hex_to_bin(*src++) << 4;
-		*dst += hex_to_bin(*src++);
-		dst++;
+		int hi = hex_to_bin(*src++);
+		int lo = hex_to_bin(*src++);
+
+		if ((hi < 0) || (lo < 0))
+			return -1;
+
+		*dst++ = (hi << 4) | lo;
 	}
+	return 0;
 }
 EXPORT_SYMBOL(hex2bin);
 
diff --git a/lib/idr.c b/lib/idr.c
index e15502e8b21e..ed055b297c81 100644
--- a/lib/idr.c
+++ b/lib/idr.c
@@ -34,8 +34,10 @@
 #include <linux/err.h>
 #include <linux/string.h>
 #include <linux/idr.h>
+#include <linux/spinlock.h>
 
 static struct kmem_cache *idr_layer_cache;
+static DEFINE_SPINLOCK(simple_ida_lock);
 
 static struct idr_layer *get_from_free_list(struct idr *idp)
 {
@@ -765,8 +767,8 @@ EXPORT_SYMBOL(ida_pre_get);
  * @starting_id: id to start search at
  * @p_id:	pointer to the allocated handle
  *
- * Allocate new ID above or equal to @ida.  It should be called with
- * any required locks.
+ * Allocate new ID above or equal to @starting_id.  It should be called
+ * with any required locks.
  *
  * If memory is required, it will return %-EAGAIN, you should unlock
  * and go back to the ida_pre_get() call.  If the ida is full, it will
@@ -858,7 +860,7 @@ EXPORT_SYMBOL(ida_get_new_above);
  * and go back to the idr_pre_get() call.  If the idr is full, it will
  * return %-ENOSPC.
  *
- * @id returns a value in the range %0 ... %0x7fffffff.
+ * @p_id returns a value in the range %0 ... %0x7fffffff.
  */
 int ida_get_new(struct ida *ida, int *p_id)
 {
@@ -926,6 +928,74 @@ void ida_destroy(struct ida *ida)
 EXPORT_SYMBOL(ida_destroy);
 
 /**
+ * ida_simple_get - get a new id.
+ * @ida: the (initialized) ida.
+ * @start: the minimum id (inclusive, < 0x8000000)
+ * @end: the maximum id (exclusive, < 0x8000000 or 0)
+ * @gfp_mask: memory allocation flags
+ *
+ * Allocates an id in the range start <= id < end, or returns -ENOSPC.
+ * On memory allocation failure, returns -ENOMEM.
+ *
+ * Use ida_simple_remove() to get rid of an id.
+ */
+int ida_simple_get(struct ida *ida, unsigned int start, unsigned int end,
+		   gfp_t gfp_mask)
+{
+	int ret, id;
+	unsigned int max;
+	unsigned long flags;
+
+	BUG_ON((int)start < 0);
+	BUG_ON((int)end < 0);
+
+	if (end == 0)
+		max = 0x80000000;
+	else {
+		BUG_ON(end < start);
+		max = end - 1;
+	}
+
+again:
+	if (!ida_pre_get(ida, gfp_mask))
+		return -ENOMEM;
+
+	spin_lock_irqsave(&simple_ida_lock, flags);
+	ret = ida_get_new_above(ida, start, &id);
+	if (!ret) {
+		if (id > max) {
+			ida_remove(ida, id);
+			ret = -ENOSPC;
+		} else {
+			ret = id;
+		}
+	}
+	spin_unlock_irqrestore(&simple_ida_lock, flags);
+
+	if (unlikely(ret == -EAGAIN))
+		goto again;
+
+	return ret;
+}
+EXPORT_SYMBOL(ida_simple_get);
+
+/**
+ * ida_simple_remove - remove an allocated id.
+ * @ida: the (initialized) ida.
+ * @id: the id returned by ida_simple_get.
+ */
+void ida_simple_remove(struct ida *ida, unsigned int id)
+{
+	unsigned long flags;
+
+	BUG_ON((int)id < 0);
+	spin_lock_irqsave(&simple_ida_lock, flags);
+	ida_remove(ida, id);
+	spin_unlock_irqrestore(&simple_ida_lock, flags);
+}
+EXPORT_SYMBOL(ida_simple_remove);
+
+/**
  * ida_init - initialize ida handle
  * @ida:	ida handle
  *
diff --git a/lib/iomap.c b/lib/iomap.c
index d32229385151..5dbcb4b2d864 100644
--- a/lib/iomap.c
+++ b/lib/iomap.c
@@ -224,6 +224,7 @@ EXPORT_SYMBOL(iowrite8_rep);
 EXPORT_SYMBOL(iowrite16_rep);
 EXPORT_SYMBOL(iowrite32_rep);
 
+#ifdef CONFIG_HAS_IOPORT
 /* Create a virtual mapping cookie for an IO port range */
 void __iomem *ioport_map(unsigned long port, unsigned int nr)
 {
@@ -238,7 +239,9 @@ void ioport_unmap(void __iomem *addr)
 }
 EXPORT_SYMBOL(ioport_map);
 EXPORT_SYMBOL(ioport_unmap);
+#endif /* CONFIG_HAS_IOPORT */
 
+#ifdef CONFIG_PCI
 /**
  * pci_iomap - create a virtual mapping cookie for a PCI BAR
  * @dev: PCI device that owns the BAR
@@ -280,3 +283,4 @@ void pci_iounmap(struct pci_dev *dev, void __iomem * addr)
 }
 EXPORT_SYMBOL(pci_iomap);
 EXPORT_SYMBOL(pci_iounmap);
+#endif /* CONFIG_PCI */
diff --git a/lib/kobject_uevent.c b/lib/kobject_uevent.c
index 70af0a7f97c0..ad72a03ce5e9 100644
--- a/lib/kobject_uevent.c
+++ b/lib/kobject_uevent.c
@@ -282,7 +282,7 @@ int kobject_uevent_env(struct kobject *kobj, enum kobject_action action,
 							    kobj_bcast_filter,
 							    kobj);
 			/* ENOBUFS should be handled in userspace */
-			if (retval == -ENOBUFS)
+			if (retval == -ENOBUFS || retval == -ESRCH)
 				retval = 0;
 		} else
 			retval = -ENOMEM;
diff --git a/lib/kstrtox.c b/lib/kstrtox.c
index 2dbae88090ac..7a94c8f14e29 100644
--- a/lib/kstrtox.c
+++ b/lib/kstrtox.c
@@ -18,31 +18,40 @@
 #include <linux/module.h>
 #include <linux/types.h>
 #include <asm/uaccess.h>
+#include "kstrtox.h"
 
-static inline char _tolower(const char c)
+const char *_parse_integer_fixup_radix(const char *s, unsigned int *base)
 {
-	return c | 0x20;
-}
-
-static int _kstrtoull(const char *s, unsigned int base, unsigned long long *res)
-{
-	unsigned long long acc;
-	int ok;
-
-	if (base == 0) {
+	if (*base == 0) {
 		if (s[0] == '0') {
 			if (_tolower(s[1]) == 'x' && isxdigit(s[2]))
-				base = 16;
+				*base = 16;
 			else
-				base = 8;
+				*base = 8;
 		} else
-			base = 10;
+			*base = 10;
 	}
-	if (base == 16 && s[0] == '0' && _tolower(s[1]) == 'x')
+	if (*base == 16 && s[0] == '0' && _tolower(s[1]) == 'x')
 		s += 2;
+	return s;
+}
 
-	acc = 0;
-	ok = 0;
+/*
+ * Convert non-negative integer string representation in explicitly given radix
+ * to an integer.
+ * Return number of characters consumed maybe or-ed with overflow bit.
+ * If overflow occurs, result integer (incorrect) is still returned.
+ *
+ * Don't you dare use this function.
+ */
+unsigned int _parse_integer(const char *s, unsigned int base, unsigned long long *res)
+{
+	unsigned int rv;
+	int overflow;
+
+	*res = 0;
+	rv = 0;
+	overflow = 0;
 	while (*s) {
 		unsigned int val;
 
@@ -50,23 +59,40 @@ static int _kstrtoull(const char *s, unsigned int base, unsigned long long *res)
 			val = *s - '0';
 		else if ('a' <= _tolower(*s) && _tolower(*s) <= 'f')
 			val = _tolower(*s) - 'a' + 10;
-		else if (*s == '\n' && *(s + 1) == '\0')
-			break;
 		else
-			return -EINVAL;
+			break;
 
 		if (val >= base)
-			return -EINVAL;
-		if (acc > div_u64(ULLONG_MAX - val, base))
-			return -ERANGE;
-		acc = acc * base + val;
-		ok = 1;
-
+			break;
+		if (*res > div_u64(ULLONG_MAX - val, base))
+			overflow = 1;
+		*res = *res * base + val;
+		rv++;
 		s++;
 	}
-	if (!ok)
+	if (overflow)
+		rv |= KSTRTOX_OVERFLOW;
+	return rv;
+}
+
+static int _kstrtoull(const char *s, unsigned int base, unsigned long long *res)
+{
+	unsigned long long _res;
+	unsigned int rv;
+
+	s = _parse_integer_fixup_radix(s, &base);
+	rv = _parse_integer(s, base, &_res);
+	if (rv & KSTRTOX_OVERFLOW)
+		return -ERANGE;
+	rv &= ~KSTRTOX_OVERFLOW;
+	if (rv == 0)
+		return -EINVAL;
+	s += rv;
+	if (*s == '\n')
+		s++;
+	if (*s)
 		return -EINVAL;
-	*res = acc;
+	*res = _res;
 	return 0;
 }
 
diff --git a/lib/kstrtox.h b/lib/kstrtox.h
new file mode 100644
index 000000000000..f13eeeaf441d
--- /dev/null
+++ b/lib/kstrtox.h
@@ -0,0 +1,8 @@
+#ifndef _LIB_KSTRTOX_H
+#define _LIB_KSTRTOX_H
+
+#define KSTRTOX_OVERFLOW	(1U << 31)
+const char *_parse_integer_fixup_radix(const char *s, unsigned int *base);
+unsigned int _parse_integer(const char *s, unsigned int base, unsigned long long *res);
+
+#endif
diff --git a/lib/lcm.c b/lib/lcm.c
index 157cd88a6ffc..10b5cfcacf6b 100644
--- a/lib/lcm.c
+++ b/lib/lcm.c
@@ -1,6 +1,7 @@
 #include <linux/kernel.h>
 #include <linux/gcd.h>
 #include <linux/module.h>
+#include <linux/lcm.h>
 
 /* Lowest common multiple */
 unsigned long lcm(unsigned long a, unsigned long b)
diff --git a/lib/llist.c b/lib/llist.c
new file mode 100644
index 000000000000..700cff77a387
--- /dev/null
+++ b/lib/llist.c
@@ -0,0 +1,89 @@
+/*
+ * Lock-less NULL terminated single linked list
+ *
+ * The basic atomic operation of this list is cmpxchg on long.  On
+ * architectures that don't have NMI-safe cmpxchg implementation, the
+ * list can NOT be used in NMI handlers.  So code that uses the list in
+ * an NMI handler should depend on CONFIG_ARCH_HAVE_NMI_SAFE_CMPXCHG.
+ *
+ * Copyright 2010,2011 Intel Corp.
+ *   Author: Huang Ying <ying.huang@intel.com>
+ *
+ * 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;
+ *
+ * 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
+ */
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/interrupt.h>
+#include <linux/llist.h>
+
+#include <asm/system.h>
+
+/**
+ * llist_add_batch - add several linked entries in batch
+ * @new_first:	first entry in batch to be added
+ * @new_last:	last entry in batch to be added
+ * @head:	the head for your lock-less list
+ *
+ * Return whether list is empty before adding.
+ */
+bool llist_add_batch(struct llist_node *new_first, struct llist_node *new_last,
+		     struct llist_head *head)
+{
+	struct llist_node *entry, *old_entry;
+
+	entry = head->first;
+	for (;;) {
+		old_entry = entry;
+		new_last->next = entry;
+		entry = cmpxchg(&head->first, old_entry, new_first);
+		if (entry == old_entry)
+			break;
+	}
+
+	return old_entry == NULL;
+}
+EXPORT_SYMBOL_GPL(llist_add_batch);
+
+/**
+ * llist_del_first - delete the first entry of lock-less list
+ * @head:	the head for your lock-less list
+ *
+ * If list is empty, return NULL, otherwise, return the first entry
+ * deleted, this is the newest added one.
+ *
+ * Only one llist_del_first user can be used simultaneously with
+ * multiple llist_add users without lock.  Because otherwise
+ * llist_del_first, llist_add, llist_add (or llist_del_all, llist_add,
+ * llist_add) sequence in another user may change @head->first->next,
+ * but keep @head->first.  If multiple consumers are needed, please
+ * use llist_del_all or use lock between consumers.
+ */
+struct llist_node *llist_del_first(struct llist_head *head)
+{
+	struct llist_node *entry, *old_entry, *next;
+
+	entry = head->first;
+	for (;;) {
+		if (entry == NULL)
+			return NULL;
+		old_entry = entry;
+		next = entry->next;
+		entry = cmpxchg(&head->first, old_entry, next);
+		if (entry == old_entry)
+			break;
+	}
+
+	return entry;
+}
+EXPORT_SYMBOL_GPL(llist_del_first);
diff --git a/lib/md5.c b/lib/md5.c
new file mode 100644
index 000000000000..c777180e1f2f
--- /dev/null
+++ b/lib/md5.c
@@ -0,0 +1,95 @@
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/cryptohash.h>
+
+#define F1(x, y, z)	(z ^ (x & (y ^ z)))
+#define F2(x, y, z)	F1(z, x, y)
+#define F3(x, y, z)	(x ^ y ^ z)
+#define F4(x, y, z)	(y ^ (x | ~z))
+
+#define MD5STEP(f, w, x, y, z, in, s) \
+	(w += f(x, y, z) + in, w = (w<<s | w>>(32-s)) + x)
+
+void md5_transform(__u32 *hash, __u32 const *in)
+{
+	u32 a, b, c, d;
+
+	a = hash[0];
+	b = hash[1];
+	c = hash[2];
+	d = hash[3];
+
+	MD5STEP(F1, a, b, c, d, in[0] + 0xd76aa478, 7);
+	MD5STEP(F1, d, a, b, c, in[1] + 0xe8c7b756, 12);
+	MD5STEP(F1, c, d, a, b, in[2] + 0x242070db, 17);
+	MD5STEP(F1, b, c, d, a, in[3] + 0xc1bdceee, 22);
+	MD5STEP(F1, a, b, c, d, in[4] + 0xf57c0faf, 7);
+	MD5STEP(F1, d, a, b, c, in[5] + 0x4787c62a, 12);
+	MD5STEP(F1, c, d, a, b, in[6] + 0xa8304613, 17);
+	MD5STEP(F1, b, c, d, a, in[7] + 0xfd469501, 22);
+	MD5STEP(F1, a, b, c, d, in[8] + 0x698098d8, 7);
+	MD5STEP(F1, d, a, b, c, in[9] + 0x8b44f7af, 12);
+	MD5STEP(F1, c, d, a, b, in[10] + 0xffff5bb1, 17);
+	MD5STEP(F1, b, c, d, a, in[11] + 0x895cd7be, 22);
+	MD5STEP(F1, a, b, c, d, in[12] + 0x6b901122, 7);
+	MD5STEP(F1, d, a, b, c, in[13] + 0xfd987193, 12);
+	MD5STEP(F1, c, d, a, b, in[14] + 0xa679438e, 17);
+	MD5STEP(F1, b, c, d, a, in[15] + 0x49b40821, 22);
+
+	MD5STEP(F2, a, b, c, d, in[1] + 0xf61e2562, 5);
+	MD5STEP(F2, d, a, b, c, in[6] + 0xc040b340, 9);
+	MD5STEP(F2, c, d, a, b, in[11] + 0x265e5a51, 14);
+	MD5STEP(F2, b, c, d, a, in[0] + 0xe9b6c7aa, 20);
+	MD5STEP(F2, a, b, c, d, in[5] + 0xd62f105d, 5);
+	MD5STEP(F2, d, a, b, c, in[10] + 0x02441453, 9);
+	MD5STEP(F2, c, d, a, b, in[15] + 0xd8a1e681, 14);
+	MD5STEP(F2, b, c, d, a, in[4] + 0xe7d3fbc8, 20);
+	MD5STEP(F2, a, b, c, d, in[9] + 0x21e1cde6, 5);
+	MD5STEP(F2, d, a, b, c, in[14] + 0xc33707d6, 9);
+	MD5STEP(F2, c, d, a, b, in[3] + 0xf4d50d87, 14);
+	MD5STEP(F2, b, c, d, a, in[8] + 0x455a14ed, 20);
+	MD5STEP(F2, a, b, c, d, in[13] + 0xa9e3e905, 5);
+	MD5STEP(F2, d, a, b, c, in[2] + 0xfcefa3f8, 9);
+	MD5STEP(F2, c, d, a, b, in[7] + 0x676f02d9, 14);
+	MD5STEP(F2, b, c, d, a, in[12] + 0x8d2a4c8a, 20);
+
+	MD5STEP(F3, a, b, c, d, in[5] + 0xfffa3942, 4);
+	MD5STEP(F3, d, a, b, c, in[8] + 0x8771f681, 11);
+	MD5STEP(F3, c, d, a, b, in[11] + 0x6d9d6122, 16);
+	MD5STEP(F3, b, c, d, a, in[14] + 0xfde5380c, 23);
+	MD5STEP(F3, a, b, c, d, in[1] + 0xa4beea44, 4);
+	MD5STEP(F3, d, a, b, c, in[4] + 0x4bdecfa9, 11);
+	MD5STEP(F3, c, d, a, b, in[7] + 0xf6bb4b60, 16);
+	MD5STEP(F3, b, c, d, a, in[10] + 0xbebfbc70, 23);
+	MD5STEP(F3, a, b, c, d, in[13] + 0x289b7ec6, 4);
+	MD5STEP(F3, d, a, b, c, in[0] + 0xeaa127fa, 11);
+	MD5STEP(F3, c, d, a, b, in[3] + 0xd4ef3085, 16);
+	MD5STEP(F3, b, c, d, a, in[6] + 0x04881d05, 23);
+	MD5STEP(F3, a, b, c, d, in[9] + 0xd9d4d039, 4);
+	MD5STEP(F3, d, a, b, c, in[12] + 0xe6db99e5, 11);
+	MD5STEP(F3, c, d, a, b, in[15] + 0x1fa27cf8, 16);
+	MD5STEP(F3, b, c, d, a, in[2] + 0xc4ac5665, 23);
+
+	MD5STEP(F4, a, b, c, d, in[0] + 0xf4292244, 6);
+	MD5STEP(F4, d, a, b, c, in[7] + 0x432aff97, 10);
+	MD5STEP(F4, c, d, a, b, in[14] + 0xab9423a7, 15);
+	MD5STEP(F4, b, c, d, a, in[5] + 0xfc93a039, 21);
+	MD5STEP(F4, a, b, c, d, in[12] + 0x655b59c3, 6);
+	MD5STEP(F4, d, a, b, c, in[3] + 0x8f0ccc92, 10);
+	MD5STEP(F4, c, d, a, b, in[10] + 0xffeff47d, 15);
+	MD5STEP(F4, b, c, d, a, in[1] + 0x85845dd1, 21);
+	MD5STEP(F4, a, b, c, d, in[8] + 0x6fa87e4f, 6);
+	MD5STEP(F4, d, a, b, c, in[15] + 0xfe2ce6e0, 10);
+	MD5STEP(F4, c, d, a, b, in[6] + 0xa3014314, 15);
+	MD5STEP(F4, b, c, d, a, in[13] + 0x4e0811a1, 21);
+	MD5STEP(F4, a, b, c, d, in[4] + 0xf7537e82, 6);
+	MD5STEP(F4, d, a, b, c, in[11] + 0xbd3af235, 10);
+	MD5STEP(F4, c, d, a, b, in[2] + 0x2ad7d2bb, 15);
+	MD5STEP(F4, b, c, d, a, in[9] + 0xeb86d391, 21);
+
+	hash[0] += a;
+	hash[1] += b;
+	hash[2] += c;
+	hash[3] += d;
+}
+EXPORT_SYMBOL(md5_transform);
diff --git a/lib/nlattr.c b/lib/nlattr.c
index ac09f2226dc7..a8408b6cacdf 100644
--- a/lib/nlattr.c
+++ b/lib/nlattr.c
@@ -20,6 +20,7 @@ static const u16 nla_attr_minlen[NLA_TYPE_MAX+1] = {
 	[NLA_U16]	= sizeof(u16),
 	[NLA_U32]	= sizeof(u32),
 	[NLA_U64]	= sizeof(u64),
+	[NLA_MSECS]	= sizeof(u64),
 	[NLA_NESTED]	= NLA_HDRLEN,
 };
 
diff --git a/lib/percpu_counter.c b/lib/percpu_counter.c
index 28f2c33c6b53..f8a3f1a829b8 100644
--- a/lib/percpu_counter.c
+++ b/lib/percpu_counter.c
@@ -10,8 +10,10 @@
 #include <linux/module.h>
 #include <linux/debugobjects.h>
 
+#ifdef CONFIG_HOTPLUG_CPU
 static LIST_HEAD(percpu_counters);
 static DEFINE_MUTEX(percpu_counters_lock);
+#endif
 
 #ifdef CONFIG_DEBUG_OBJECTS_PERCPU_COUNTER
 
@@ -59,13 +61,13 @@ void percpu_counter_set(struct percpu_counter *fbc, s64 amount)
 {
 	int cpu;
 
-	spin_lock(&fbc->lock);
+	raw_spin_lock(&fbc->lock);
 	for_each_possible_cpu(cpu) {
 		s32 *pcount = per_cpu_ptr(fbc->counters, cpu);
 		*pcount = 0;
 	}
 	fbc->count = amount;
-	spin_unlock(&fbc->lock);
+	raw_spin_unlock(&fbc->lock);
 }
 EXPORT_SYMBOL(percpu_counter_set);
 
@@ -76,10 +78,10 @@ void __percpu_counter_add(struct percpu_counter *fbc, s64 amount, s32 batch)
 	preempt_disable();
 	count = __this_cpu_read(*fbc->counters) + amount;
 	if (count >= batch || count <= -batch) {
-		spin_lock(&fbc->lock);
+		raw_spin_lock(&fbc->lock);
 		fbc->count += count;
 		__this_cpu_write(*fbc->counters, 0);
-		spin_unlock(&fbc->lock);
+		raw_spin_unlock(&fbc->lock);
 	} else {
 		__this_cpu_write(*fbc->counters, count);
 	}
@@ -96,13 +98,13 @@ s64 __percpu_counter_sum(struct percpu_counter *fbc)
 	s64 ret;
 	int cpu;
 
-	spin_lock(&fbc->lock);
+	raw_spin_lock(&fbc->lock);
 	ret = fbc->count;
 	for_each_online_cpu(cpu) {
 		s32 *pcount = per_cpu_ptr(fbc->counters, cpu);
 		ret += *pcount;
 	}
-	spin_unlock(&fbc->lock);
+	raw_spin_unlock(&fbc->lock);
 	return ret;
 }
 EXPORT_SYMBOL(__percpu_counter_sum);
@@ -110,7 +112,7 @@ EXPORT_SYMBOL(__percpu_counter_sum);
 int __percpu_counter_init(struct percpu_counter *fbc, s64 amount,
 			  struct lock_class_key *key)
 {
-	spin_lock_init(&fbc->lock);
+	raw_spin_lock_init(&fbc->lock);
 	lockdep_set_class(&fbc->lock, key);
 	fbc->count = amount;
 	fbc->counters = alloc_percpu(s32);
@@ -173,11 +175,11 @@ static int __cpuinit percpu_counter_hotcpu_callback(struct notifier_block *nb,
 		s32 *pcount;
 		unsigned long flags;
 
-		spin_lock_irqsave(&fbc->lock, flags);
+		raw_spin_lock_irqsave(&fbc->lock, flags);
 		pcount = per_cpu_ptr(fbc->counters, cpu);
 		fbc->count += *pcount;
 		*pcount = 0;
-		spin_unlock_irqrestore(&fbc->lock, flags);
+		raw_spin_unlock_irqrestore(&fbc->lock, flags);
 	}
 	mutex_unlock(&percpu_counters_lock);
 #endif
diff --git a/lib/plist.c b/lib/plist.c
index 0ae7e6431726..a0a4da489c22 100644
--- a/lib/plist.c
+++ b/lib/plist.c
@@ -56,11 +56,6 @@ static void plist_check_list(struct list_head *top)
 
 static void plist_check_head(struct plist_head *head)
 {
-	WARN_ON(head != &test_head && !head->rawlock && !head->spinlock);
-	if (head->rawlock)
-		WARN_ON_SMP(!raw_spin_is_locked(head->rawlock));
-	if (head->spinlock)
-		WARN_ON_SMP(!spin_is_locked(head->spinlock));
 	if (!plist_head_empty(head))
 		plist_check_list(&plist_first(head)->prio_list);
 	plist_check_list(&head->node_list);
@@ -180,7 +175,7 @@ static int  __init plist_test(void)
 	unsigned int r = local_clock();
 
 	printk(KERN_INFO "start plist test\n");
-	plist_head_init(&test_head, NULL);
+	plist_head_init(&test_head);
 	for (i = 0; i < ARRAY_SIZE(test_node); i++)
 		plist_node_init(test_node + i, 0);
 
diff --git a/lib/proportions.c b/lib/proportions.c
index d50746a79de2..05df84801b56 100644
--- a/lib/proportions.c
+++ b/lib/proportions.c
@@ -190,7 +190,7 @@ prop_adjust_shift(int *pl_shift, unsigned long *pl_period, int new_shift)
 
 int prop_local_init_percpu(struct prop_local_percpu *pl)
 {
-	spin_lock_init(&pl->lock);
+	raw_spin_lock_init(&pl->lock);
 	pl->shift = 0;
 	pl->period = 0;
 	return percpu_counter_init(&pl->events, 0);
@@ -226,7 +226,7 @@ void prop_norm_percpu(struct prop_global *pg, struct prop_local_percpu *pl)
 	if (pl->period == global_period)
 		return;
 
-	spin_lock_irqsave(&pl->lock, flags);
+	raw_spin_lock_irqsave(&pl->lock, flags);
 	prop_adjust_shift(&pl->shift, &pl->period, pg->shift);
 
 	/*
@@ -247,7 +247,7 @@ void prop_norm_percpu(struct prop_global *pg, struct prop_local_percpu *pl)
 		percpu_counter_set(&pl->events, 0);
 
 	pl->period = global_period;
-	spin_unlock_irqrestore(&pl->lock, flags);
+	raw_spin_unlock_irqrestore(&pl->lock, flags);
 }
 
 /*
@@ -324,7 +324,7 @@ void prop_fraction_percpu(struct prop_descriptor *pd,
 
 int prop_local_init_single(struct prop_local_single *pl)
 {
-	spin_lock_init(&pl->lock);
+	raw_spin_lock_init(&pl->lock);
 	pl->shift = 0;
 	pl->period = 0;
 	pl->events = 0;
@@ -356,7 +356,7 @@ void prop_norm_single(struct prop_global *pg, struct prop_local_single *pl)
 	if (pl->period == global_period)
 		return;
 
-	spin_lock_irqsave(&pl->lock, flags);
+	raw_spin_lock_irqsave(&pl->lock, flags);
 	prop_adjust_shift(&pl->shift, &pl->period, pg->shift);
 	/*
 	 * For each missed period, we half the local counter.
@@ -367,7 +367,7 @@ void prop_norm_single(struct prop_global *pg, struct prop_local_single *pl)
 	else
 		pl->events = 0;
 	pl->period = global_period;
-	spin_unlock_irqrestore(&pl->lock, flags);
+	raw_spin_unlock_irqrestore(&pl->lock, flags);
 }
 
 /*
diff --git a/lib/radix-tree.c b/lib/radix-tree.c
index 7ea2e033d715..d9df7454519c 100644
--- a/lib/radix-tree.c
+++ b/lib/radix-tree.c
@@ -576,7 +576,6 @@ int radix_tree_tag_get(struct radix_tree_root *root,
 {
 	unsigned int height, shift;
 	struct radix_tree_node *node;
-	int saw_unset_tag = 0;
 
 	/* check the root's tag bit */
 	if (!root_tag_get(root, tag))
@@ -603,15 +602,10 @@ int radix_tree_tag_get(struct radix_tree_root *root,
 			return 0;
 
 		offset = (index >> shift) & RADIX_TREE_MAP_MASK;
-
-		/*
-		 * This is just a debug check.  Later, we can bale as soon as
-		 * we see an unset tag.
-		 */
 		if (!tag_get(node, tag, offset))
-			saw_unset_tag = 1;
+			return 0;
 		if (height == 1)
-			return !!tag_get(node, tag, offset);
+			return 1;
 		node = rcu_dereference_raw(node->slots[offset]);
 		shift -= RADIX_TREE_MAP_SHIFT;
 		height--;
@@ -823,8 +817,8 @@ unsigned long radix_tree_prev_hole(struct radix_tree_root *root,
 EXPORT_SYMBOL(radix_tree_prev_hole);
 
 static unsigned int
-__lookup(struct radix_tree_node *slot, void ***results, unsigned long index,
-	unsigned int max_items, unsigned long *next_index)
+__lookup(struct radix_tree_node *slot, void ***results, unsigned long *indices,
+	unsigned long index, unsigned int max_items, unsigned long *next_index)
 {
 	unsigned int nr_found = 0;
 	unsigned int shift, height;
@@ -857,12 +851,16 @@ __lookup(struct radix_tree_node *slot, void ***results, unsigned long index,
 
 	/* Bottom level: grab some items */
 	for (i = index & RADIX_TREE_MAP_MASK; i < RADIX_TREE_MAP_SIZE; i++) {
-		index++;
 		if (slot->slots[i]) {
-			results[nr_found++] = &(slot->slots[i]);
-			if (nr_found == max_items)
+			results[nr_found] = &(slot->slots[i]);
+			if (indices)
+				indices[nr_found] = index;
+			if (++nr_found == max_items) {
+				index++;
 				goto out;
+			}
 		}
+		index++;
 	}
 out:
 	*next_index = index;
@@ -918,8 +916,8 @@ radix_tree_gang_lookup(struct radix_tree_root *root, void **results,
 
 		if (cur_index > max_index)
 			break;
-		slots_found = __lookup(node, (void ***)results + ret, cur_index,
-					max_items - ret, &next_index);
+		slots_found = __lookup(node, (void ***)results + ret, NULL,
+				cur_index, max_items - ret, &next_index);
 		nr_found = 0;
 		for (i = 0; i < slots_found; i++) {
 			struct radix_tree_node *slot;
@@ -944,6 +942,7 @@ EXPORT_SYMBOL(radix_tree_gang_lookup);
  *	radix_tree_gang_lookup_slot - perform multiple slot lookup on radix tree
  *	@root:		radix tree root
  *	@results:	where the results of the lookup are placed
+ *	@indices:	where their indices should be placed (but usually NULL)
  *	@first_index:	start the lookup from this key
  *	@max_items:	place up to this many items at *results
  *
@@ -958,7 +957,8 @@ EXPORT_SYMBOL(radix_tree_gang_lookup);
  *	protection, radix_tree_deref_slot may fail requiring a retry.
  */
 unsigned int
-radix_tree_gang_lookup_slot(struct radix_tree_root *root, void ***results,
+radix_tree_gang_lookup_slot(struct radix_tree_root *root,
+			void ***results, unsigned long *indices,
 			unsigned long first_index, unsigned int max_items)
 {
 	unsigned long max_index;
@@ -974,6 +974,8 @@ radix_tree_gang_lookup_slot(struct radix_tree_root *root, void ***results,
 		if (first_index > 0)
 			return 0;
 		results[0] = (void **)&root->rnode;
+		if (indices)
+			indices[0] = 0;
 		return 1;
 	}
 	node = indirect_to_ptr(node);
@@ -987,8 +989,9 @@ radix_tree_gang_lookup_slot(struct radix_tree_root *root, void ***results,
 
 		if (cur_index > max_index)
 			break;
-		slots_found = __lookup(node, results + ret, cur_index,
-					max_items - ret, &next_index);
+		slots_found = __lookup(node, results + ret,
+				indices ? indices + ret : NULL,
+				cur_index, max_items - ret, &next_index);
 		ret += slots_found;
 		if (next_index == 0)
 			break;
@@ -1194,6 +1197,98 @@ radix_tree_gang_lookup_tag_slot(struct radix_tree_root *root, void ***results,
 }
 EXPORT_SYMBOL(radix_tree_gang_lookup_tag_slot);
 
+#if defined(CONFIG_SHMEM) && defined(CONFIG_SWAP)
+#include <linux/sched.h> /* for cond_resched() */
+
+/*
+ * This linear search is at present only useful to shmem_unuse_inode().
+ */
+static unsigned long __locate(struct radix_tree_node *slot, void *item,
+			      unsigned long index, unsigned long *found_index)
+{
+	unsigned int shift, height;
+	unsigned long i;
+
+	height = slot->height;
+	shift = (height-1) * RADIX_TREE_MAP_SHIFT;
+
+	for ( ; height > 1; height--) {
+		i = (index >> shift) & RADIX_TREE_MAP_MASK;
+		for (;;) {
+			if (slot->slots[i] != NULL)
+				break;
+			index &= ~((1UL << shift) - 1);
+			index += 1UL << shift;
+			if (index == 0)
+				goto out;	/* 32-bit wraparound */
+			i++;
+			if (i == RADIX_TREE_MAP_SIZE)
+				goto out;
+		}
+
+		shift -= RADIX_TREE_MAP_SHIFT;
+		slot = rcu_dereference_raw(slot->slots[i]);
+		if (slot == NULL)
+			goto out;
+	}
+
+	/* Bottom level: check items */
+	for (i = 0; i < RADIX_TREE_MAP_SIZE; i++) {
+		if (slot->slots[i] == item) {
+			*found_index = index + i;
+			index = 0;
+			goto out;
+		}
+	}
+	index += RADIX_TREE_MAP_SIZE;
+out:
+	return index;
+}
+
+/**
+ *	radix_tree_locate_item - search through radix tree for item
+ *	@root:		radix tree root
+ *	@item:		item to be found
+ *
+ *	Returns index where item was found, or -1 if not found.
+ *	Caller must hold no lock (since this time-consuming function needs
+ *	to be preemptible), and must check afterwards if item is still there.
+ */
+unsigned long radix_tree_locate_item(struct radix_tree_root *root, void *item)
+{
+	struct radix_tree_node *node;
+	unsigned long max_index;
+	unsigned long cur_index = 0;
+	unsigned long found_index = -1;
+
+	do {
+		rcu_read_lock();
+		node = rcu_dereference_raw(root->rnode);
+		if (!radix_tree_is_indirect_ptr(node)) {
+			rcu_read_unlock();
+			if (node == item)
+				found_index = 0;
+			break;
+		}
+
+		node = indirect_to_ptr(node);
+		max_index = radix_tree_maxindex(node->height);
+		if (cur_index > max_index)
+			break;
+
+		cur_index = __locate(node, item, cur_index, &found_index);
+		rcu_read_unlock();
+		cond_resched();
+	} while (cur_index != 0 && cur_index <= max_index);
+
+	return found_index;
+}
+#else
+unsigned long radix_tree_locate_item(struct radix_tree_root *root, void *item)
+{
+	return -1;
+}
+#endif /* CONFIG_SHMEM && CONFIG_SWAP */
 
 /**
  *	radix_tree_shrink    -    shrink height of a radix tree to minimal
diff --git a/lib/raid6/algos.c b/lib/raid6/algos.c
index b595f560bee7..8b02f60ffc86 100644
--- a/lib/raid6/algos.c
+++ b/lib/raid6/algos.c
@@ -17,6 +17,7 @@
  */
 
 #include <linux/raid/pq.h>
+#include <linux/module.h>
 #ifndef __KERNEL__
 #include <sys/mman.h>
 #include <stdio.h>
diff --git a/lib/raid6/int.uc b/lib/raid6/int.uc
index d1e276a14fab..5b50f8dfc5d2 100644
--- a/lib/raid6/int.uc
+++ b/lib/raid6/int.uc
@@ -11,7 +11,7 @@
  * ----------------------------------------------------------------------- */
 
 /*
- * raid6int$#.c
+ * int$#.c
  *
  * $#-way unrolled portable integer math RAID-6 instruction set
  *
diff --git a/lib/raid6/mktables.c b/lib/raid6/mktables.c
index 3b1500843bba..8a3780902cec 100644
--- a/lib/raid6/mktables.c
+++ b/lib/raid6/mktables.c
@@ -60,6 +60,7 @@ int main(int argc, char *argv[])
 	uint8_t exptbl[256], invtbl[256];
 
 	printf("#include <linux/raid/pq.h>\n");
+	printf("#include <linux/export.h>\n");
 
 	/* Compute multiplication table */
 	printf("\nconst u8  __attribute__((aligned(256)))\n"
diff --git a/lib/raid6/recov.c b/lib/raid6/recov.c
index 8590d19cf522..fe275d7b6b36 100644
--- a/lib/raid6/recov.c
+++ b/lib/raid6/recov.c
@@ -18,6 +18,7 @@
  * the syndrome.)
  */
 
+#include <linux/export.h>
 #include <linux/raid/pq.h>
 
 /* Recover two failed data blocks. */
diff --git a/lib/ratelimit.c b/lib/ratelimit.c
index 027a03f4c56d..c96d500577de 100644
--- a/lib/ratelimit.c
+++ b/lib/ratelimit.c
@@ -39,7 +39,7 @@ int ___ratelimit(struct ratelimit_state *rs, const char *func)
 	 * in addition to the one that will be printed by
 	 * the entity that is holding the lock already:
 	 */
-	if (!spin_trylock_irqsave(&rs->lock, flags))
+	if (!raw_spin_trylock_irqsave(&rs->lock, flags))
 		return 0;
 
 	if (!rs->begin)
@@ -60,7 +60,7 @@ int ___ratelimit(struct ratelimit_state *rs, const char *func)
 		rs->missed++;
 		ret = 0;
 	}
-	spin_unlock_irqrestore(&rs->lock, flags);
+	raw_spin_unlock_irqrestore(&rs->lock, flags);
 
 	return ret;
 }
diff --git a/lib/rwsem-spinlock.c b/lib/rwsem-spinlock.c
index ffc9fc7f3b05..f2393c21fe85 100644
--- a/lib/rwsem-spinlock.c
+++ b/lib/rwsem-spinlock.c
@@ -22,9 +22,9 @@ int rwsem_is_locked(struct rw_semaphore *sem)
 	int ret = 1;
 	unsigned long flags;
 
-	if (spin_trylock_irqsave(&sem->wait_lock, flags)) {
+	if (raw_spin_trylock_irqsave(&sem->wait_lock, flags)) {
 		ret = (sem->activity != 0);
-		spin_unlock_irqrestore(&sem->wait_lock, flags);
+		raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
 	}
 	return ret;
 }
@@ -44,7 +44,7 @@ void __init_rwsem(struct rw_semaphore *sem, const char *name,
 	lockdep_init_map(&sem->dep_map, name, key, 0);
 #endif
 	sem->activity = 0;
-	spin_lock_init(&sem->wait_lock);
+	raw_spin_lock_init(&sem->wait_lock);
 	INIT_LIST_HEAD(&sem->wait_list);
 }
 EXPORT_SYMBOL(__init_rwsem);
@@ -145,12 +145,12 @@ void __sched __down_read(struct rw_semaphore *sem)
 	struct task_struct *tsk;
 	unsigned long flags;
 
-	spin_lock_irqsave(&sem->wait_lock, flags);
+	raw_spin_lock_irqsave(&sem->wait_lock, flags);
 
 	if (sem->activity >= 0 && list_empty(&sem->wait_list)) {
 		/* granted */
 		sem->activity++;
-		spin_unlock_irqrestore(&sem->wait_lock, flags);
+		raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
 		goto out;
 	}
 
@@ -165,7 +165,7 @@ void __sched __down_read(struct rw_semaphore *sem)
 	list_add_tail(&waiter.list, &sem->wait_list);
 
 	/* we don't need to touch the semaphore struct anymore */
-	spin_unlock_irqrestore(&sem->wait_lock, flags);
+	raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
 
 	/* wait to be given the lock */
 	for (;;) {
@@ -189,7 +189,7 @@ int __down_read_trylock(struct rw_semaphore *sem)
 	int ret = 0;
 
 
-	spin_lock_irqsave(&sem->wait_lock, flags);
+	raw_spin_lock_irqsave(&sem->wait_lock, flags);
 
 	if (sem->activity >= 0 && list_empty(&sem->wait_list)) {
 		/* granted */
@@ -197,7 +197,7 @@ int __down_read_trylock(struct rw_semaphore *sem)
 		ret = 1;
 	}
 
-	spin_unlock_irqrestore(&sem->wait_lock, flags);
+	raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
 
 	return ret;
 }
@@ -212,12 +212,12 @@ void __sched __down_write_nested(struct rw_semaphore *sem, int subclass)
 	struct task_struct *tsk;
 	unsigned long flags;
 
-	spin_lock_irqsave(&sem->wait_lock, flags);
+	raw_spin_lock_irqsave(&sem->wait_lock, flags);
 
 	if (sem->activity == 0 && list_empty(&sem->wait_list)) {
 		/* granted */
 		sem->activity = -1;
-		spin_unlock_irqrestore(&sem->wait_lock, flags);
+		raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
 		goto out;
 	}
 
@@ -232,7 +232,7 @@ void __sched __down_write_nested(struct rw_semaphore *sem, int subclass)
 	list_add_tail(&waiter.list, &sem->wait_list);
 
 	/* we don't need to touch the semaphore struct anymore */
-	spin_unlock_irqrestore(&sem->wait_lock, flags);
+	raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
 
 	/* wait to be given the lock */
 	for (;;) {
@@ -260,7 +260,7 @@ int __down_write_trylock(struct rw_semaphore *sem)
 	unsigned long flags;
 	int ret = 0;
 
-	spin_lock_irqsave(&sem->wait_lock, flags);
+	raw_spin_lock_irqsave(&sem->wait_lock, flags);
 
 	if (sem->activity == 0 && list_empty(&sem->wait_list)) {
 		/* granted */
@@ -268,7 +268,7 @@ int __down_write_trylock(struct rw_semaphore *sem)
 		ret = 1;
 	}
 
-	spin_unlock_irqrestore(&sem->wait_lock, flags);
+	raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
 
 	return ret;
 }
@@ -280,12 +280,12 @@ void __up_read(struct rw_semaphore *sem)
 {
 	unsigned long flags;
 
-	spin_lock_irqsave(&sem->wait_lock, flags);
+	raw_spin_lock_irqsave(&sem->wait_lock, flags);
 
 	if (--sem->activity == 0 && !list_empty(&sem->wait_list))
 		sem = __rwsem_wake_one_writer(sem);
 
-	spin_unlock_irqrestore(&sem->wait_lock, flags);
+	raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
 }
 
 /*
@@ -295,13 +295,13 @@ void __up_write(struct rw_semaphore *sem)
 {
 	unsigned long flags;
 
-	spin_lock_irqsave(&sem->wait_lock, flags);
+	raw_spin_lock_irqsave(&sem->wait_lock, flags);
 
 	sem->activity = 0;
 	if (!list_empty(&sem->wait_list))
 		sem = __rwsem_do_wake(sem, 1);
 
-	spin_unlock_irqrestore(&sem->wait_lock, flags);
+	raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
 }
 
 /*
@@ -312,12 +312,12 @@ void __downgrade_write(struct rw_semaphore *sem)
 {
 	unsigned long flags;
 
-	spin_lock_irqsave(&sem->wait_lock, flags);
+	raw_spin_lock_irqsave(&sem->wait_lock, flags);
 
 	sem->activity = 1;
 	if (!list_empty(&sem->wait_list))
 		sem = __rwsem_do_wake(sem, 0);
 
-	spin_unlock_irqrestore(&sem->wait_lock, flags);
+	raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
 }
 
diff --git a/lib/rwsem.c b/lib/rwsem.c
index aa7c3052261f..410aa1189b13 100644
--- a/lib/rwsem.c
+++ b/lib/rwsem.c
@@ -22,7 +22,7 @@ void __init_rwsem(struct rw_semaphore *sem, const char *name,
 	lockdep_init_map(&sem->dep_map, name, key, 0);
 #endif
 	sem->count = RWSEM_UNLOCKED_VALUE;
-	spin_lock_init(&sem->wait_lock);
+	raw_spin_lock_init(&sem->wait_lock);
 	INIT_LIST_HEAD(&sem->wait_list);
 }
 
@@ -180,7 +180,7 @@ rwsem_down_failed_common(struct rw_semaphore *sem,
 	set_task_state(tsk, TASK_UNINTERRUPTIBLE);
 
 	/* set up my own style of waitqueue */
-	spin_lock_irq(&sem->wait_lock);
+	raw_spin_lock_irq(&sem->wait_lock);
 	waiter.task = tsk;
 	waiter.flags = flags;
 	get_task_struct(tsk);
@@ -204,7 +204,7 @@ rwsem_down_failed_common(struct rw_semaphore *sem,
 		 adjustment == -RWSEM_ACTIVE_WRITE_BIAS)
 		sem = __rwsem_do_wake(sem, RWSEM_WAKE_READ_OWNED);
 
-	spin_unlock_irq(&sem->wait_lock);
+	raw_spin_unlock_irq(&sem->wait_lock);
 
 	/* wait to be given the lock */
 	for (;;) {
@@ -245,13 +245,13 @@ struct rw_semaphore *rwsem_wake(struct rw_semaphore *sem)
 {
 	unsigned long flags;
 
-	spin_lock_irqsave(&sem->wait_lock, flags);
+	raw_spin_lock_irqsave(&sem->wait_lock, flags);
 
 	/* do nothing if list empty */
 	if (!list_empty(&sem->wait_list))
 		sem = __rwsem_do_wake(sem, RWSEM_WAKE_ANY);
 
-	spin_unlock_irqrestore(&sem->wait_lock, flags);
+	raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
 
 	return sem;
 }
@@ -265,13 +265,13 @@ struct rw_semaphore *rwsem_downgrade_wake(struct rw_semaphore *sem)
 {
 	unsigned long flags;
 
-	spin_lock_irqsave(&sem->wait_lock, flags);
+	raw_spin_lock_irqsave(&sem->wait_lock, flags);
 
 	/* do nothing if list empty */
 	if (!list_empty(&sem->wait_list))
 		sem = __rwsem_do_wake(sem, RWSEM_WAKE_READ_OWNED);
 
-	spin_unlock_irqrestore(&sem->wait_lock, flags);
+	raw_spin_unlock_irqrestore(&sem->wait_lock, flags);
 
 	return sem;
 }
diff --git a/lib/sha1.c b/lib/sha1.c
index 4c45fd50e913..1de509a159c8 100644
--- a/lib/sha1.c
+++ b/lib/sha1.c
@@ -1,31 +1,73 @@
 /*
- * SHA transform algorithm, originally taken from code written by
- * Peter Gutmann, and placed in the public domain.
+ * SHA1 routine optimized to do word accesses rather than byte accesses,
+ * and to avoid unnecessary copies into the context array.
+ *
+ * This was based on the git SHA1 implementation.
  */
 
 #include <linux/kernel.h>
 #include <linux/module.h>
+#include <linux/bitops.h>
 #include <linux/cryptohash.h>
+#include <asm/unaligned.h>
 
-/* The SHA f()-functions.  */
+/*
+ * If you have 32 registers or more, the compiler can (and should)
+ * try to change the array[] accesses into registers. However, on
+ * machines with less than ~25 registers, that won't really work,
+ * and at least gcc will make an unholy mess of it.
+ *
+ * So to avoid that mess which just slows things down, we force
+ * the stores to memory to actually happen (we might be better off
+ * with a 'W(t)=(val);asm("":"+m" (W(t))' there instead, as
+ * suggested by Artur Skawina - that will also make gcc unable to
+ * try to do the silly "optimize away loads" part because it won't
+ * see what the value will be).
+ *
+ * Ben Herrenschmidt reports that on PPC, the C version comes close
+ * to the optimized asm with this (ie on PPC you don't want that
+ * 'volatile', since there are lots of registers).
+ *
+ * On ARM we get the best code generation by forcing a full memory barrier
+ * between each SHA_ROUND, otherwise gcc happily get wild with spilling and
+ * the stack frame size simply explode and performance goes down the drain.
+ */
 
-#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 */
+#ifdef CONFIG_X86
+  #define setW(x, val) (*(volatile __u32 *)&W(x) = (val))
+#elif defined(CONFIG_ARM)
+  #define setW(x, val) do { W(x) = (val); __asm__("":::"memory"); } while (0)
+#else
+  #define setW(x, val) (W(x) = (val))
+#endif
 
-/* The SHA Mysterious Constants */
+/* This "rolls" over the 512-bit array */
+#define W(x) (array[(x)&15])
 
-#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 */
+/*
+ * Where do we get the source from? The first 16 iterations get it from
+ * the input data, the next mix it from the 512-bit array.
+ */
+#define SHA_SRC(t) get_unaligned_be32((__u32 *)data + t)
+#define SHA_MIX(t) rol32(W(t+13) ^ W(t+8) ^ W(t+2) ^ W(t), 1)
+
+#define SHA_ROUND(t, input, fn, constant, A, B, C, D, E) do { \
+	__u32 TEMP = input(t); setW(t, TEMP); \
+	E += TEMP + rol32(A,5) + (fn) + (constant); \
+	B = ror32(B, 2); } while (0)
+
+#define T_0_15(t, A, B, C, D, E)  SHA_ROUND(t, SHA_SRC, (((C^D)&B)^D) , 0x5a827999, A, B, C, D, E )
+#define T_16_19(t, A, B, C, D, E) SHA_ROUND(t, SHA_MIX, (((C^D)&B)^D) , 0x5a827999, A, B, C, D, E )
+#define T_20_39(t, A, B, C, D, E) SHA_ROUND(t, SHA_MIX, (B^C^D) , 0x6ed9eba1, A, B, C, D, E )
+#define T_40_59(t, A, B, C, D, E) SHA_ROUND(t, SHA_MIX, ((B&C)+(D&(B^C))) , 0x8f1bbcdc, A, B, C, D, E )
+#define T_60_79(t, A, B, C, D, E) SHA_ROUND(t, SHA_MIX, (B^C^D) ,  0xca62c1d6, A, B, C, D, E )
 
 /**
  * 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)
+ * @array:  16 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
@@ -36,47 +78,111 @@
  * 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)
+void sha_transform(__u32 *digest, const char *data, __u32 *array)
 {
-	__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;
+	__u32 A, B, C, D, E;
+
+	A = digest[0];
+	B = digest[1];
+	C = digest[2];
+	D = digest[3];
+	E = digest[4];
+
+	/* Round 1 - iterations 0-16 take their input from 'data' */
+	T_0_15( 0, A, B, C, D, E);
+	T_0_15( 1, E, A, B, C, D);
+	T_0_15( 2, D, E, A, B, C);
+	T_0_15( 3, C, D, E, A, B);
+	T_0_15( 4, B, C, D, E, A);
+	T_0_15( 5, A, B, C, D, E);
+	T_0_15( 6, E, A, B, C, D);
+	T_0_15( 7, D, E, A, B, C);
+	T_0_15( 8, C, D, E, A, B);
+	T_0_15( 9, B, C, D, E, A);
+	T_0_15(10, A, B, C, D, E);
+	T_0_15(11, E, A, B, C, D);
+	T_0_15(12, D, E, A, B, C);
+	T_0_15(13, C, D, E, A, B);
+	T_0_15(14, B, C, D, E, A);
+	T_0_15(15, A, B, C, D, E);
+
+	/* Round 1 - tail. Input from 512-bit mixing array */
+	T_16_19(16, E, A, B, C, D);
+	T_16_19(17, D, E, A, B, C);
+	T_16_19(18, C, D, E, A, B);
+	T_16_19(19, B, C, D, E, A);
+
+	/* Round 2 */
+	T_20_39(20, A, B, C, D, E);
+	T_20_39(21, E, A, B, C, D);
+	T_20_39(22, D, E, A, B, C);
+	T_20_39(23, C, D, E, A, B);
+	T_20_39(24, B, C, D, E, A);
+	T_20_39(25, A, B, C, D, E);
+	T_20_39(26, E, A, B, C, D);
+	T_20_39(27, D, E, A, B, C);
+	T_20_39(28, C, D, E, A, B);
+	T_20_39(29, B, C, D, E, A);
+	T_20_39(30, A, B, C, D, E);
+	T_20_39(31, E, A, B, C, D);
+	T_20_39(32, D, E, A, B, C);
+	T_20_39(33, C, D, E, A, B);
+	T_20_39(34, B, C, D, E, A);
+	T_20_39(35, A, B, C, D, E);
+	T_20_39(36, E, A, B, C, D);
+	T_20_39(37, D, E, A, B, C);
+	T_20_39(38, C, D, E, A, B);
+	T_20_39(39, B, C, D, E, A);
+
+	/* Round 3 */
+	T_40_59(40, A, B, C, D, E);
+	T_40_59(41, E, A, B, C, D);
+	T_40_59(42, D, E, A, B, C);
+	T_40_59(43, C, D, E, A, B);
+	T_40_59(44, B, C, D, E, A);
+	T_40_59(45, A, B, C, D, E);
+	T_40_59(46, E, A, B, C, D);
+	T_40_59(47, D, E, A, B, C);
+	T_40_59(48, C, D, E, A, B);
+	T_40_59(49, B, C, D, E, A);
+	T_40_59(50, A, B, C, D, E);
+	T_40_59(51, E, A, B, C, D);
+	T_40_59(52, D, E, A, B, C);
+	T_40_59(53, C, D, E, A, B);
+	T_40_59(54, B, C, D, E, A);
+	T_40_59(55, A, B, C, D, E);
+	T_40_59(56, E, A, B, C, D);
+	T_40_59(57, D, E, A, B, C);
+	T_40_59(58, C, D, E, A, B);
+	T_40_59(59, B, C, D, E, A);
+
+	/* Round 4 */
+	T_60_79(60, A, B, C, D, E);
+	T_60_79(61, E, A, B, C, D);
+	T_60_79(62, D, E, A, B, C);
+	T_60_79(63, C, D, E, A, B);
+	T_60_79(64, B, C, D, E, A);
+	T_60_79(65, A, B, C, D, E);
+	T_60_79(66, E, A, B, C, D);
+	T_60_79(67, D, E, A, B, C);
+	T_60_79(68, C, D, E, A, B);
+	T_60_79(69, B, C, D, E, A);
+	T_60_79(70, A, B, C, D, E);
+	T_60_79(71, E, A, B, C, D);
+	T_60_79(72, D, E, A, B, C);
+	T_60_79(73, C, D, E, A, B);
+	T_60_79(74, B, C, D, E, A);
+	T_60_79(75, A, B, C, D, E);
+	T_60_79(76, E, A, B, C, D);
+	T_60_79(77, D, E, A, B, C);
+	T_60_79(78, C, D, E, A, B);
+	T_60_79(79, B, C, D, E, A);
+
+	digest[0] += A;
+	digest[1] += B;
+	digest[2] += C;
+	digest[3] += D;
+	digest[4] += E;
 }
 EXPORT_SYMBOL(sha_transform);
 
@@ -92,4 +198,3 @@ void sha_init(__u32 *buf)
 	buf[3] = 0x10325476;
 	buf[4] = 0xc3d2e1f0;
 }
-
diff --git a/lib/smp_processor_id.c b/lib/smp_processor_id.c
index 4689cb073da4..503f087382a4 100644
--- a/lib/smp_processor_id.c
+++ b/lib/smp_processor_id.c
@@ -22,7 +22,7 @@ notrace unsigned int debug_smp_processor_id(void)
 	 * Kernel threads bound to a single CPU can safely use
 	 * smp_processor_id():
 	 */
-	if (cpumask_equal(&current->cpus_allowed, cpumask_of(this_cpu)))
+	if (cpumask_equal(tsk_cpus_allowed(current), cpumask_of(this_cpu)))
 		goto out;
 
 	/*
diff --git a/lib/spinlock_debug.c b/lib/spinlock_debug.c
index 4755b98b6dfb..5f3eacdd6178 100644
--- a/lib/spinlock_debug.c
+++ b/lib/spinlock_debug.c
@@ -49,13 +49,10 @@ void __rwlock_init(rwlock_t *lock, const char *name,
 
 EXPORT_SYMBOL(__rwlock_init);
 
-static void spin_bug(raw_spinlock_t *lock, const char *msg)
+static void spin_dump(raw_spinlock_t *lock, const char *msg)
 {
 	struct task_struct *owner = NULL;
 
-	if (!debug_locks_off())
-		return;
-
 	if (lock->owner && lock->owner != SPINLOCK_OWNER_INIT)
 		owner = lock->owner;
 	printk(KERN_EMERG "BUG: spinlock %s on CPU#%d, %s/%d\n",
@@ -70,6 +67,14 @@ static void spin_bug(raw_spinlock_t *lock, const char *msg)
 	dump_stack();
 }
 
+static void spin_bug(raw_spinlock_t *lock, const char *msg)
+{
+	if (!debug_locks_off())
+		return;
+
+	spin_dump(lock, msg);
+}
+
 #define SPIN_BUG_ON(cond, lock, msg) if (unlikely(cond)) spin_bug(lock, msg)
 
 static inline void
@@ -113,11 +118,7 @@ static void __spin_lock_debug(raw_spinlock_t *lock)
 		/* lockup suspected: */
 		if (print_once) {
 			print_once = 0;
-			printk(KERN_EMERG "BUG: spinlock lockup on CPU#%d, "
-					"%s/%d, %p\n",
-				raw_smp_processor_id(), current->comm,
-				task_pid_nr(current), lock);
-			dump_stack();
+			spin_dump(lock, "lockup");
 #ifdef CONFIG_SMP
 			trigger_all_cpu_backtrace();
 #endif
diff --git a/lib/string.c b/lib/string.c
index 01fad9b203e1..dc4a86341f91 100644
--- a/lib/string.c
+++ b/lib/string.c
@@ -360,7 +360,6 @@ char *strim(char *s)
 	size_t size;
 	char *end;
 
-	s = skip_spaces(s);
 	size = strlen(s);
 	if (!size)
 		return s;
@@ -370,7 +369,7 @@ char *strim(char *s)
 		end--;
 	*(end + 1) = '\0';
 
-	return s;
+	return skip_spaces(s);
 }
 EXPORT_SYMBOL(strim);
 
@@ -756,3 +755,57 @@ void *memchr(const void *s, int c, size_t n)
 }
 EXPORT_SYMBOL(memchr);
 #endif
+
+static void *check_bytes8(const u8 *start, u8 value, unsigned int bytes)
+{
+	while (bytes) {
+		if (*start != value)
+			return (void *)start;
+		start++;
+		bytes--;
+	}
+	return NULL;
+}
+
+/**
+ * memchr_inv - Find an unmatching character in an area of memory.
+ * @start: The memory area
+ * @c: Find a character other than c
+ * @bytes: The size of the area.
+ *
+ * returns the address of the first character other than @c, or %NULL
+ * if the whole buffer contains just @c.
+ */
+void *memchr_inv(const void *start, int c, size_t bytes)
+{
+	u8 value = c;
+	u64 value64;
+	unsigned int words, prefix;
+
+	if (bytes <= 16)
+		return check_bytes8(start, value, bytes);
+
+	value64 = value | value << 8 | value << 16 | value << 24;
+	value64 = (value64 & 0xffffffff) | value64 << 32;
+	prefix = 8 - ((unsigned long)start) % 8;
+
+	if (prefix) {
+		u8 *r = check_bytes8(start, value, prefix);
+		if (r)
+			return r;
+		start += prefix;
+		bytes -= prefix;
+	}
+
+	words = bytes / 8;
+
+	while (words) {
+		if (*(u64 *)start != value64)
+			return check_bytes8(start, value, 8);
+		start += 8;
+		words--;
+	}
+
+	return check_bytes8(start, value, bytes % 8);
+}
+EXPORT_SYMBOL(memchr_inv);
diff --git a/lib/vsprintf.c b/lib/vsprintf.c
index 4365df31a1d5..993599e66e5a 100644
--- a/lib/vsprintf.c
+++ b/lib/vsprintf.c
@@ -31,20 +31,7 @@
 #include <asm/div64.h>
 #include <asm/sections.h>	/* for dereference_function_descriptor() */
 
-/* Works only for digits and letters, but small and fast */
-#define TOLOWER(x) ((x) | 0x20)
-
-static unsigned int simple_guess_base(const char *cp)
-{
-	if (cp[0] == '0') {
-		if (TOLOWER(cp[1]) == 'x' && isxdigit(cp[2]))
-			return 16;
-		else
-			return 8;
-	} else {
-		return 10;
-	}
-}
+#include "kstrtox.h"
 
 /**
  * simple_strtoull - convert a string to an unsigned long long
@@ -54,23 +41,14 @@ static unsigned int simple_guess_base(const char *cp)
  */
 unsigned long long simple_strtoull(const char *cp, char **endp, unsigned int base)
 {
-	unsigned long long result = 0;
-
-	if (!base)
-		base = simple_guess_base(cp);
-
-	if (base == 16 && cp[0] == '0' && TOLOWER(cp[1]) == 'x')
-		cp += 2;
+	unsigned long long result;
+	unsigned int rv;
 
-	while (isxdigit(*cp)) {
-		unsigned int value;
+	cp = _parse_integer_fixup_radix(cp, &base);
+	rv = _parse_integer(cp, base, &result);
+	/* FIXME */
+	cp += (rv & ~KSTRTOX_OVERFLOW);
 
-		value = isdigit(*cp) ? *cp - '0' : TOLOWER(*cp) - 'a' + 10;
-		if (value >= base)
-			break;
-		result = result * base + value;
-		cp++;
-	}
 	if (endp)
 		*endp = (char *)cp;
 
@@ -569,7 +547,7 @@ char *mac_address_string(char *buf, char *end, u8 *addr,
 	}
 
 	for (i = 0; i < 6; i++) {
-		p = pack_hex_byte(p, addr[i]);
+		p = hex_byte_pack(p, addr[i]);
 		if (fmt[0] == 'M' && i != 5)
 			*p++ = separator;
 	}
@@ -689,13 +667,13 @@ char *ip6_compressed_string(char *p, const char *addr)
 		lo = word & 0xff;
 		if (hi) {
 			if (hi > 0x0f)
-				p = pack_hex_byte(p, hi);
+				p = hex_byte_pack(p, hi);
 			else
 				*p++ = hex_asc_lo(hi);
-			p = pack_hex_byte(p, lo);
+			p = hex_byte_pack(p, lo);
 		}
 		else if (lo > 0x0f)
-			p = pack_hex_byte(p, lo);
+			p = hex_byte_pack(p, lo);
 		else
 			*p++ = hex_asc_lo(lo);
 		needcolon = true;
@@ -717,8 +695,8 @@ char *ip6_string(char *p, const char *addr, const char *fmt)
 	int i;
 
 	for (i = 0; i < 8; i++) {
-		p = pack_hex_byte(p, *addr++);
-		p = pack_hex_byte(p, *addr++);
+		p = hex_byte_pack(p, *addr++);
+		p = hex_byte_pack(p, *addr++);
 		if (fmt[0] == 'I' && i != 7)
 			*p++ = ':';
 	}
@@ -776,7 +754,7 @@ char *uuid_string(char *buf, char *end, const u8 *addr,
 	}
 
 	for (i = 0; i < 16; i++) {
-		p = pack_hex_byte(p, addr[index[i]]);
+		p = hex_byte_pack(p, addr[index[i]]);
 		switch (i) {
 		case 3:
 		case 5:
@@ -1036,8 +1014,8 @@ precision:
 qualifier:
 	/* get the conversion qualifier */
 	spec->qualifier = -1;
-	if (*fmt == 'h' || TOLOWER(*fmt) == 'l' ||
-	    TOLOWER(*fmt) == 'z' || *fmt == 't') {
+	if (*fmt == 'h' || _tolower(*fmt) == 'l' ||
+	    _tolower(*fmt) == 'z' || *fmt == 't') {
 		spec->qualifier = *fmt++;
 		if (unlikely(spec->qualifier == *fmt)) {
 			if (spec->qualifier == 'l') {
@@ -1104,7 +1082,7 @@ qualifier:
 			spec->type = FORMAT_TYPE_LONG;
 		else
 			spec->type = FORMAT_TYPE_ULONG;
-	} else if (TOLOWER(spec->qualifier) == 'z') {
+	} else if (_tolower(spec->qualifier) == 'z') {
 		spec->type = FORMAT_TYPE_SIZE_T;
 	} else if (spec->qualifier == 't') {
 		spec->type = FORMAT_TYPE_PTRDIFF;
@@ -1149,8 +1127,7 @@ qualifier:
  * %pi4 print an IPv4 address with leading zeros
  * %pI6 print an IPv6 address with colons
  * %pi6 print an IPv6 address without colons
- * %pI6c print an IPv6 address as specified by
- *   http://tools.ietf.org/html/draft-ietf-6man-text-addr-representation-00
+ * %pI6c print an IPv6 address as specified by RFC 5952
  * %pU[bBlL] print a UUID/GUID in big or little endian using lower or upper
  *   case.
  * %n is ignored
@@ -1263,7 +1240,7 @@ int vsnprintf(char *buf, size_t size, const char *fmt, va_list args)
 			if (qualifier == 'l') {
 				long *ip = va_arg(args, long *);
 				*ip = (str - buf);
-			} else if (TOLOWER(qualifier) == 'z') {
+			} else if (_tolower(qualifier) == 'z') {
 				size_t *ip = va_arg(args, size_t *);
 				*ip = (str - buf);
 			} else {
@@ -1550,7 +1527,7 @@ do {									\
 			void *skip_arg;
 			if (qualifier == 'l')
 				skip_arg = va_arg(args, long *);
-			else if (TOLOWER(qualifier) == 'z')
+			else if (_tolower(qualifier) == 'z')
 				skip_arg = va_arg(args, size_t *);
 			else
 				skip_arg = va_arg(args, int *);
@@ -1856,8 +1833,8 @@ int vsscanf(const char *buf, const char *fmt, va_list args)
 
 		/* get conversion qualifier */
 		qualifier = -1;
-		if (*fmt == 'h' || TOLOWER(*fmt) == 'l' ||
-		    TOLOWER(*fmt) == 'z') {
+		if (*fmt == 'h' || _tolower(*fmt) == 'l' ||
+		    _tolower(*fmt) == 'z') {
 			qualifier = *fmt++;
 			if (unlikely(qualifier == *fmt)) {
 				if (qualifier == 'h') {
diff --git a/lib/xz/xz_dec_bcj.c b/lib/xz/xz_dec_bcj.c
index e51e2558ca9d..a768e6d28bbb 100644
--- a/lib/xz/xz_dec_bcj.c
+++ b/lib/xz/xz_dec_bcj.c
@@ -441,8 +441,12 @@ XZ_EXTERN enum xz_ret xz_dec_bcj_run(struct xz_dec_bcj *s,
 	 * next filter in the chain. Apply the BCJ filter on the new data
 	 * in the output buffer. If everything cannot be filtered, copy it
 	 * to temp and rewind the output buffer position accordingly.
+	 *
+	 * This needs to be always run when temp.size == 0 to handle a special
+	 * case where the output buffer is full and the next filter has no
+	 * more output coming but hasn't returned XZ_STREAM_END yet.
 	 */
-	if (s->temp.size < b->out_size - b->out_pos) {
+	if (s->temp.size < b->out_size - b->out_pos || s->temp.size == 0) {
 		out_start = b->out_pos;
 		memcpy(b->out + b->out_pos, s->temp.buf, s->temp.size);
 		b->out_pos += s->temp.size;
@@ -465,16 +469,25 @@ XZ_EXTERN enum xz_ret xz_dec_bcj_run(struct xz_dec_bcj *s,
 		s->temp.size = b->out_pos - out_start;
 		b->out_pos -= s->temp.size;
 		memcpy(s->temp.buf, b->out + b->out_pos, s->temp.size);
+
+		/*
+		 * If there wasn't enough input to the next filter to fill
+		 * the output buffer with unfiltered data, there's no point
+		 * to try decoding more data to temp.
+		 */
+		if (b->out_pos + s->temp.size < b->out_size)
+			return XZ_OK;
 	}
 
 	/*
-	 * If we have unfiltered data in temp, try to fill by decoding more
-	 * data from the next filter. Apply the BCJ filter on temp. Then we
-	 * hopefully can fill the actual output buffer by copying filtered
-	 * data from temp. A mix of filtered and unfiltered data may be left
-	 * in temp; it will be taken care on the next call to this function.
+	 * We have unfiltered data in temp. If the output buffer isn't full
+	 * yet, try to fill the temp buffer by decoding more data from the
+	 * next filter. Apply the BCJ filter on temp. Then we hopefully can
+	 * fill the actual output buffer by copying filtered data from temp.
+	 * A mix of filtered and unfiltered data may be left in temp; it will
+	 * be taken care on the next call to this function.
 	 */
-	if (s->temp.size > 0) {
+	if (b->out_pos < b->out_size) {
 		/* Make b->out{,_pos,_size} temporarily point to s->temp. */
 		s->out = b->out;
 		s->out_pos = b->out_pos;
diff --git a/lib/xz/xz_private.h b/lib/xz/xz_private.h
index a65633e06962..482b90f363fe 100644
--- a/lib/xz/xz_private.h
+++ b/lib/xz/xz_private.h
@@ -12,7 +12,7 @@
 
 #ifdef __KERNEL__
 #	include <linux/xz.h>
-#	include <asm/byteorder.h>
+#	include <linux/kernel.h>
 #	include <asm/unaligned.h>
 	/* XZ_PREBOOT may be defined only via decompress_unxz.c. */
 #	ifndef XZ_PREBOOT