Merge branch 'for-next/misc'

Conflicts:
	lib/Makefile

58 files changed, 1842 insertions, 790 deletions

diff --git a/Documentation/devicetree/bindings/leds/common.rst b/Documentation/devicetree/bindings/leds/common.rst
index c1fd1ab89e..1f5ae42caf 100644
--- a/Documentation/devicetree/bindings/leds/common.rst
+++ b/Documentation/devicetree/bindings/leds/common.rst
@@ -8,3 +8,5 @@ Common leds properties
     * ``panic`` - LED turns on when barebox panics
     * ``net`` - LED indicates network activity
 
+* ``label``: The label for this LED. If omitted, the label is taken
+  from the node name (excluding the unit address).
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index a3208d27e4..9f34e1089b 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -2,6 +2,8 @@ config ARM
 	bool
 	select HAS_KALLSYMS
 	select HAS_MODULES
+	select HAS_DMA
+	select HAS_CACHE
 	select HAVE_CONFIGURABLE_TEXT_BASE
 	select HAVE_PBL_IMAGE
 	select HAVE_IMAGE_COMPRESSION
diff --git a/arch/blackfin/Kconfig b/arch/blackfin/Kconfig
index bea9f51e1e..6233614e19 100644
--- a/arch/blackfin/Kconfig
+++ b/arch/blackfin/Kconfig
@@ -5,6 +5,7 @@ config BLACKFIN
 	select HAS_MODULES
 	select HAVE_CONFIGURABLE_MEMORY_LAYOUT
 	select HAVE_CONFIGURABLE_TEXT_BASE
+	select GENERIC_FIND_NEXT_BIT
 	default y
 
 config BF561
diff --git a/arch/blackfin/include/asm/bitops.h b/arch/blackfin/include/asm/bitops.h
index 4ab1471522..e77ab83202 100644
--- a/arch/blackfin/include/asm/bitops.h
+++ b/arch/blackfin/include/asm/bitops.h
@@ -1,11 +1,4 @@
 /*
- * barebox - bitops.h Routines for bit operations
- *
- * Copyright (c) 2005 blackfin.uclinux.org
- *
- * See file CREDITS for list of people who contributed to this
- * project.
- *
  * This program is free software; you can redistribute it and/or
  * modify it under the terms of the GNU General Public License as
  * published by the Free Software Foundation; either version 2 of
@@ -16,349 +9,27 @@
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  * GNU General Public License for more details.
  *
+ *
  */
 
-#ifndef _BLACKFIN_BITOPS_H
-#define _BLACKFIN_BITOPS_H
-
-/*
- * Copyright 1992, Linus Torvalds.
- */
-
-#include <asm/byteorder.h>
-#include <asm/system.h>
-
-#ifdef __KERNEL__
-/*
- * Function prototypes to keep gcc -Wall happy
- */
-
-/*
- * The __ functions are not atomic
- */
-
-/*
- * ffz = Find First Zero in word. Undefined if no zero exists,
- * so code should check against ~0UL first..
- */
-static __inline__ unsigned long ffz(unsigned long word)
-{
-	unsigned long result = 0;
-
-	while (word & 1) {
-		result++;
-		word >>= 1;
-	}
-	return result;
-}
-
-static __inline__ void set_bit(int nr, volatile void *addr)
-{
-	int *a = (int *) addr;
-	int mask;
-	unsigned long flags;
-
-	a += nr >> 5;
-	mask = 1 << (nr & 0x1f);
-	save_and_cli(flags);
-	*a |= mask;
-	restore_flags(flags);
-}
-
-static __inline__ void __set_bit(int nr, volatile void *addr)
-{
-	int *a = (int *) addr;
-	int mask;
-
-	a += nr >> 5;
-	mask = 1 << (nr & 0x1f);
-	*a |= mask;
-}
-
-/*
- * clear_bit() doesn't provide any barrier for the compiler.
- */
-#define smp_mb__before_clear_bit()	barrier()
-#define smp_mb__after_clear_bit()	barrier()
-
-static __inline__ void clear_bit(int nr, volatile void *addr)
-{
-	int *a = (int *) addr;
-	int mask;
-	unsigned long flags;
-
-	a += nr >> 5;
-	mask = 1 << (nr & 0x1f);
-	save_and_cli(flags);
-	*a &= ~mask;
-	restore_flags(flags);
-}
-
-static __inline__ void change_bit(int nr, volatile void *addr)
-{
-	int mask, flags;
-	unsigned long *ADDR = (unsigned long *) addr;
-
-	ADDR += nr >> 5;
-	mask = 1 << (nr & 31);
-	save_and_cli(flags);
-	*ADDR ^= mask;
-	restore_flags(flags);
-}
-
-static __inline__ void __change_bit(int nr, volatile void *addr)
-{
-	int mask;
-	unsigned long *ADDR = (unsigned long *) addr;
-
-	ADDR += nr >> 5;
-	mask = 1 << (nr & 31);
-	*ADDR ^= mask;
-}
-
-static __inline__ int test_and_set_bit(int nr, volatile void *addr)
-{
-	int mask, retval;
-	volatile unsigned int *a = (volatile unsigned int *) addr;
-	unsigned long flags;
-
-	a += nr >> 5;
-	mask = 1 << (nr & 0x1f);
-	save_and_cli(flags);
-	retval = (mask & *a) != 0;
-	*a |= mask;
-	restore_flags(flags);
-
-	return retval;
-}
-
-static __inline__ int __test_and_set_bit(int nr, volatile void *addr)
-{
-	int mask, retval;
-	volatile unsigned int *a = (volatile unsigned int *) addr;
-
-	a += nr >> 5;
-	mask = 1 << (nr & 0x1f);
-	retval = (mask & *a) != 0;
-	*a |= mask;
-	return retval;
-}
-
-static __inline__ int test_and_clear_bit(int nr, volatile void *addr)
-{
-	int mask, retval;
-	volatile unsigned int *a = (volatile unsigned int *) addr;
-	unsigned long flags;
-
-	a += nr >> 5;
-	mask = 1 << (nr & 0x1f);
-	save_and_cli(flags);
-	retval = (mask & *a) != 0;
-	*a &= ~mask;
-	restore_flags(flags);
-
-	return retval;
-}
-
-static __inline__ int __test_and_clear_bit(int nr, volatile void *addr)
-{
-	int mask, retval;
-	volatile unsigned int *a = (volatile unsigned int *) addr;
-
-	a += nr >> 5;
-	mask = 1 << (nr & 0x1f);
-	retval = (mask & *a) != 0;
-	*a &= ~mask;
-	return retval;
-}
-
-static __inline__ int test_and_change_bit(int nr, volatile void *addr)
-{
-	int mask, retval;
-	volatile unsigned int *a = (volatile unsigned int *) addr;
-	unsigned long flags;
-
-	a += nr >> 5;
-	mask = 1 << (nr & 0x1f);
-	save_and_cli(flags);
-	retval = (mask & *a) != 0;
-	*a ^= mask;
-	restore_flags(flags);
-
-	return retval;
-}
-
-static __inline__ int __test_and_change_bit(int nr, volatile void *addr)
-{
-	int mask, retval;
-	volatile unsigned int *a = (volatile unsigned int *) addr;
-
-	a += nr >> 5;
-	mask = 1 << (nr & 0x1f);
-	retval = (mask & *a) != 0;
-	*a ^= mask;
-	return retval;
-}
-
-/*
- * This routine doesn't need to be atomic.
- */
-static __inline__ int __constant_test_bit(int nr,
-					  const volatile void *addr)
-{
-	return ((1UL << (nr & 31)) &
-		(((const volatile unsigned int *) addr)[nr >> 5])) != 0;
-}
-
-static __inline__ int __test_bit(int nr, volatile void *addr)
-{
-	int *a = (int *) addr;
-	int mask;
-
-	a += nr >> 5;
-	mask = 1 << (nr & 0x1f);
-	return ((mask & *a) != 0);
-}
-
-#define	test_bit(nr,addr) \
-(__builtin_constant_p(nr) ? \
- __constant_test_bit((nr),(addr)) : \
- __test_bit((nr),(addr)))
-
-#define	find_first_zero_bit(addr, size) \
-	find_next_zero_bit((addr), (size), 0)
-
-static __inline__ int find_next_zero_bit(void *addr, int size, int offset)
-{
-	unsigned long *p = ((unsigned long *) addr) + (offset >> 5);
-	unsigned long result = offset & ~31UL;
-	unsigned long tmp;
-
-	if (offset >= size)
-		return size;
-	size -= result;
-	offset &= 31UL;
-	if (offset) {
-		tmp = *(p++);
-		tmp |= ~0UL >> (32 - offset);
-		if (size < 32)
-			goto found_first;
-		if (~tmp)
-			goto found_middle;
-		size -= 32;
-		result += 32;
-	}
-	while (size & ~31UL) {
-		if (~(tmp = *(p++)))
-			goto found_middle;
-		result += 32;
-		size -= 32;
-	}
-	if (!size)
-		return result;
-	tmp = *p;
-
-      found_first:
-	tmp |= ~0UL >> size;
-      found_middle:
-	return result + ffz(tmp);
-}
+#ifndef _ASM_BITOPS_H_
+#define _ASM_BITOPS_H_
 
 #include <asm-generic/bitops/__ffs.h>
 #include <asm-generic/bitops/__fls.h>
 #include <asm-generic/bitops/ffs.h>
 #include <asm-generic/bitops/fls.h>
+#include <asm-generic/bitops/ffz.h>
 #include <asm-generic/bitops/hweight.h>
-
-static __inline__ int ext2_set_bit(int nr, volatile void *addr)
-{
-	int mask, retval;
-	unsigned long flags;
-	volatile unsigned char *ADDR = (unsigned char *) addr;
-
-	ADDR += nr >> 3;
-	mask = 1 << (nr & 0x07);
-	save_and_cli(flags);
-	retval = (mask & *ADDR) != 0;
-	*ADDR |= mask;
-	restore_flags(flags);
-	return retval;
-}
-
-static __inline__ int ext2_clear_bit(int nr, volatile void *addr)
-{
-	int mask, retval;
-	unsigned long flags;
-	volatile unsigned char *ADDR = (unsigned char *) addr;
-
-	ADDR += nr >> 3;
-	mask = 1 << (nr & 0x07);
-	save_and_cli(flags);
-	retval = (mask & *ADDR) != 0;
-	*ADDR &= ~mask;
-	restore_flags(flags);
-	return retval;
-}
-
-static __inline__ int ext2_test_bit(int nr, const volatile void *addr)
-{
-	int mask;
-	const volatile unsigned char *ADDR = (const unsigned char *) addr;
-
-	ADDR += nr >> 3;
-	mask = 1 << (nr & 0x07);
-	return ((mask & *ADDR) != 0);
-}
-
-#define ext2_find_first_zero_bit(addr, size) \
-	ext2_find_next_zero_bit((addr), (size), 0)
-
-static __inline__ unsigned long ext2_find_next_zero_bit(void *addr,
-							unsigned long size,
-							unsigned long
-							offset)
-{
-	unsigned long *p = ((unsigned long *) addr) + (offset >> 5);
-	unsigned long result = offset & ~31UL;
-	unsigned long tmp;
-
-	if (offset >= size)
-		return size;
-	size -= result;
-	offset &= 31UL;
-	if (offset) {
-		tmp = *(p++);
-		tmp |= ~0UL >> (32 - offset);
-		if (size < 32)
-			goto found_first;
-		if (~tmp)
-			goto found_middle;
-		size -= 32;
-		result += 32;
-	}
-	while (size & ~31UL) {
-		if (~(tmp = *(p++)))
-			goto found_middle;
-		result += 32;
-		size -= 32;
-	}
-	if (!size)
-		return result;
-	tmp = *p;
-
-      found_first:
-	tmp |= ~0UL >> size;
-      found_middle:
-	return result + ffz(tmp);
-}
-
-/* Bitmap functions for the minix filesystem. */
-#define minix_test_and_set_bit(nr,addr)		test_and_set_bit(nr,addr)
-#define minix_set_bit(nr,addr)			set_bit(nr,addr)
-#define minix_test_and_clear_bit(nr,addr)	test_and_clear_bit(nr,addr)
-#define minix_test_bit(nr,addr)			test_bit(nr,addr)
-#define minix_find_first_zero_bit(addr,size)	find_first_zero_bit(addr,size)
-
-#endif
-
-#endif
+#include <asm-generic/bitops/fls64.h>
+#include <asm-generic/bitops/find.h>
+#include <asm-generic/bitops/ops.h>
+
+#define set_bit(x, y)			__set_bit(x, y)
+#define clear_bit(x, y)			__clear_bit(x, y)
+#define change_bit(x, y)		__change_bit(x, y)
+#define test_and_set_bit(x, y)		__test_and_set_bit(x, y)
+#define test_and_clear_bit(x, y)	__test_and_clear_bit(x, y)
+#define test_and_change_bit(x, y)	__test_and_change_bit(x, y)
+
+#endif /* _ASM_BITOPS_H_ */
diff --git a/arch/efi/Kconfig b/arch/efi/Kconfig
index 71ac1c74e8..26fecaa392 100644
--- a/arch/efi/Kconfig
+++ b/arch/efi/Kconfig
@@ -7,6 +7,7 @@ config ARCH_EFI
 	select EFI_GUID
 	select EFI_DEVICEPATH
 	select PRINTF_UUID
+	select GENERIC_FIND_NEXT_BIT
 
 config ARCH_TEXT_BASE
 	hex
diff --git a/arch/efi/include/asm/bitops.h b/arch/efi/include/asm/bitops.h
index 94646d4d0d..447023da63 100644
--- a/arch/efi/include/asm/bitops.h
+++ b/arch/efi/include/asm/bitops.h
@@ -12,4 +12,11 @@
 #include <asm-generic/bitops/hweight.h>
 #include <asm-generic/bitops/ops.h>
 
+#define set_bit(x, y)			__set_bit(x, y)
+#define clear_bit(x, y)			__clear_bit(x, y)
+#define change_bit(x, y)		__change_bit(x, y)
+#define test_and_set_bit(x, y)		__test_and_set_bit(x, y)
+#define test_and_clear_bit(x, y)	__test_and_clear_bit(x, y)
+#define test_and_change_bit(x, y)	__test_and_change_bit(x, y)
+
 #endif
diff --git a/arch/mips/dts/jz4755.dtsi b/arch/mips/dts/jz4755.dtsi
index 0e655b65a1..718463548b 100644
--- a/arch/mips/dts/jz4755.dtsi
+++ b/arch/mips/dts/jz4755.dtsi
@@ -8,6 +8,11 @@
 		#size-cells = <1>;
 		ranges;
 
+		wdt: wdt@b0002000 {
+			compatible = "ingenic,jz4740-wdt";
+			reg = <0xb0002000 0x10>;
+		};
+
 		serial0: serial@b0030000 {
 			compatible = "ingenic,jz4740-uart";
 			reg = <0xb0030000 0x20>;
diff --git a/arch/mips/include/asm/bitops.h b/arch/mips/include/asm/bitops.h
index ebf8cf04d3..e77ab83202 100644
--- a/arch/mips/include/asm/bitops.h
+++ b/arch/mips/include/asm/bitops.h
@@ -12,20 +12,24 @@
  *
  */
 
-/**
- * @file
- * @brief mips bit operations
- *
- * This file is required only to make all sources happy including
- * 'linux/bitops.h'
- */
-
-#ifndef _ASM_MIPS_BITOPS_H_
-#define _ASM_MIPS_BITOPS_H_
+#ifndef _ASM_BITOPS_H_
+#define _ASM_BITOPS_H_
 
 #include <asm-generic/bitops/__ffs.h>
 #include <asm-generic/bitops/__fls.h>
 #include <asm-generic/bitops/ffs.h>
 #include <asm-generic/bitops/fls.h>
+#include <asm-generic/bitops/ffz.h>
+#include <asm-generic/bitops/hweight.h>
+#include <asm-generic/bitops/fls64.h>
+#include <asm-generic/bitops/find.h>
+#include <asm-generic/bitops/ops.h>
+
+#define set_bit(x, y)			__set_bit(x, y)
+#define clear_bit(x, y)			__clear_bit(x, y)
+#define change_bit(x, y)		__change_bit(x, y)
+#define test_and_set_bit(x, y)		__test_and_set_bit(x, y)
+#define test_and_clear_bit(x, y)	__test_and_clear_bit(x, y)
+#define test_and_change_bit(x, y)	__test_and_change_bit(x, y)
 
-#endif /* _ASM_MIPS_BITOPS_H_ */
+#endif /* _ASM_BITOPS_H_ */
diff --git a/arch/mips/mach-xburst/Kconfig b/arch/mips/mach-xburst/Kconfig
index 706d59249b..f7b8470cb8 100644
--- a/arch/mips/mach-xburst/Kconfig
+++ b/arch/mips/mach-xburst/Kconfig
@@ -6,6 +6,8 @@ config ARCH_TEXT_BASE
 
 config CPU_JZ4755
 	bool
+	select WATCHDOG
+	select WATCHDOG_JZ4740
 
 choice
 	prompt "Board type"
diff --git a/arch/mips/mach-xburst/include/mach/jz4750d_regs.h b/arch/mips/mach-xburst/include/mach/jz4750d_regs.h
index 7a3daadb18..396c823a1f 100644
--- a/arch/mips/mach-xburst/include/mach/jz4750d_regs.h
+++ b/arch/mips/mach-xburst/include/mach/jz4750d_regs.h
@@ -59,28 +59,6 @@
 #define TCU_OSTCSR_PCK_EN		(1 << 0) /* select pclk as the timer clock input */
 
 /*************************************************************************
- * WDT (WatchDog Timer)
- *************************************************************************/
-#define WDT_TDR		(WDT_BASE + 0x00)
-#define WDT_TCER	(WDT_BASE + 0x04)
-#define WDT_TCNT	(WDT_BASE + 0x08)
-#define WDT_TCSR	(WDT_BASE + 0x0c)
-
-#define WDT_TCSR_PRESCALE_BIT	3
-#define WDT_TCSR_PRESCALE_MASK	(0x7 << WDT_TCSR_PRESCALE_BIT)
- #define WDT_TCSR_PRESCALE1	(0x0 << WDT_TCSR_PRESCALE_BIT)
- #define WDT_TCSR_PRESCALE4	(0x1 << WDT_TCSR_PRESCALE_BIT)
- #define WDT_TCSR_PRESCALE16	(0x2 << WDT_TCSR_PRESCALE_BIT)
- #define WDT_TCSR_PRESCALE64	(0x3 << WDT_TCSR_PRESCALE_BIT)
- #define WDT_TCSR_PRESCALE256	(0x4 << WDT_TCSR_PRESCALE_BIT)
- #define WDT_TCSR_PRESCALE1024	(0x5 << WDT_TCSR_PRESCALE_BIT)
-#define WDT_TCSR_EXT_EN		(1 << 2)
-#define WDT_TCSR_RTC_EN		(1 << 1)
-#define WDT_TCSR_PCK_EN		(1 << 0)
-
-#define WDT_TCER_TCEN		(1 << 0)
-
-/*************************************************************************
  * RTC
  *************************************************************************/
 #define RTC_RCR		(RTC_BASE + 0x00) /* RTC Control Register */
diff --git a/arch/mips/mach-xburst/reset-jz4750.c b/arch/mips/mach-xburst/reset-jz4750.c
index 8f33672280..25830f130e 100644
--- a/arch/mips/mach-xburst/reset-jz4750.c
+++ b/arch/mips/mach-xburst/reset-jz4750.c
@@ -24,8 +24,6 @@
 #include <io.h>
 #include <mach/jz4750d_regs.h>
 
-#define JZ_EXTAL 24000000
-
 static void __noreturn jz4750d_halt(void)
 {
 	while (1) {
@@ -39,22 +37,6 @@ static void __noreturn jz4750d_halt(void)
 	unreachable();
 }
 
-void __noreturn reset_cpu(ulong addr)
-{
-	__raw_writew(WDT_TCSR_PRESCALE4 | WDT_TCSR_EXT_EN, (u16 *)WDT_TCSR);
-	__raw_writew(0, (u16 *)WDT_TCNT);
-
-	/* reset after 4ms */
-	__raw_writew(JZ_EXTAL / 1000, (u16 *)WDT_TDR);
-	/* enable wdt clock */
-	__raw_writel(TCU_TSCR_WDTSC, (u32 *)TCU_TSCR);
-	/* start wdt */
-	__raw_writeb(WDT_TCER_TCEN, (u8 *)WDT_TCER);
-
-	unreachable();
-}
-EXPORT_SYMBOL(reset_cpu);
-
 void __noreturn poweroff()
 {
 	u32 ctrl;
diff --git a/arch/nios2/Kconfig b/arch/nios2/Kconfig
index 116daa9bb9..199540ba74 100644
--- a/arch/nios2/Kconfig
+++ b/arch/nios2/Kconfig
@@ -2,7 +2,9 @@ config NIOS2
 	bool
 	select HAS_KALLSYMS
 	select HAS_MODULES
+	select HAS_CACHE
 	select HAVE_CONFIGURABLE_MEMORY_LAYOUT
+	select GENERIC_FIND_NEXT_BIT
 	default y
 
 config ARCH_TEXT_BASE
diff --git a/arch/nios2/include/asm/bitops.h b/arch/nios2/include/asm/bitops.h
index 07128451c1..e77ab83202 100644
--- a/arch/nios2/include/asm/bitops.h
+++ b/arch/nios2/include/asm/bitops.h
@@ -1,9 +1,35 @@
-#ifndef _ASM_BITOPS_H
-#define _ASM_BITOPS_H
+/*
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation; either version 2 of
+ * the License, or (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ *
+ */
+
+#ifndef _ASM_BITOPS_H_
+#define _ASM_BITOPS_H_
 
 #include <asm-generic/bitops/__ffs.h>
 #include <asm-generic/bitops/__fls.h>
 #include <asm-generic/bitops/ffs.h>
 #include <asm-generic/bitops/fls.h>
+#include <asm-generic/bitops/ffz.h>
+#include <asm-generic/bitops/hweight.h>
+#include <asm-generic/bitops/fls64.h>
+#include <asm-generic/bitops/find.h>
+#include <asm-generic/bitops/ops.h>
+
+#define set_bit(x, y)			__set_bit(x, y)
+#define clear_bit(x, y)			__clear_bit(x, y)
+#define change_bit(x, y)		__change_bit(x, y)
+#define test_and_set_bit(x, y)		__test_and_set_bit(x, y)
+#define test_and_clear_bit(x, y)	__test_and_clear_bit(x, y)
+#define test_and_change_bit(x, y)	__test_and_change_bit(x, y)
 
-#endif /* _ASM_BITOPS_H */
+#endif /* _ASM_BITOPS_H_ */
diff --git a/arch/openrisc/Kconfig b/arch/openrisc/Kconfig
index d8d4ee9b6d..23c6a71f3a 100644
--- a/arch/openrisc/Kconfig
+++ b/arch/openrisc/Kconfig
@@ -1,7 +1,9 @@
 config OPENRISC
 	bool
+	select HAS_CACHE
 	select HAVE_CONFIGURABLE_MEMORY_LAYOUT
 	select HAVE_DEFAULT_ENVIRONMENT_NEW
+	select GENERIC_FIND_NEXT_BIT
 	default y
 
 # not used
diff --git a/arch/openrisc/include/asm/bitops.h b/arch/openrisc/include/asm/bitops.h
index fa57901476..e77ab83202 100644
--- a/arch/openrisc/include/asm/bitops.h
+++ b/arch/openrisc/include/asm/bitops.h
@@ -1,6 +1,4 @@
 /*
- * (C) Copyright 2011, Stefan Kristiansson <stefan.kristiansson@saunalahti.fi>
- *
  * This program is free software; you can redistribute it and/or
  * modify it under the terms of the GNU General Public License as
  * published by the Free Software Foundation; either version 2 of
@@ -11,14 +9,27 @@
  * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
  * GNU General Public License for more details.
  *
+ *
  */
 
-#ifndef __ASM_OPENRISC_BITOPS_H
-#define __ASM_OPENRISC_BITOPS_H
+#ifndef _ASM_BITOPS_H_
+#define _ASM_BITOPS_H_
+
+#include <asm-generic/bitops/__ffs.h>
+#include <asm-generic/bitops/__fls.h>
+#include <asm-generic/bitops/ffs.h>
+#include <asm-generic/bitops/fls.h>
+#include <asm-generic/bitops/ffz.h>
+#include <asm-generic/bitops/hweight.h>
+#include <asm-generic/bitops/fls64.h>
+#include <asm-generic/bitops/find.h>
+#include <asm-generic/bitops/ops.h>
 
-#define PLATFORM_FLS
-#include <asm/bitops/fls.h>
-#define PLATFORM_FFS
-#include <asm/bitops/ffs.h>
+#define set_bit(x, y)			__set_bit(x, y)
+#define clear_bit(x, y)			__clear_bit(x, y)
+#define change_bit(x, y)		__change_bit(x, y)
+#define test_and_set_bit(x, y)		__test_and_set_bit(x, y)
+#define test_and_clear_bit(x, y)	__test_and_clear_bit(x, y)
+#define test_and_change_bit(x, y)	__test_and_change_bit(x, y)
 
-#endif /* __ASM_GENERIC_BITOPS_H */
+#endif /* _ASM_BITOPS_H_ */
diff --git a/arch/ppc/Kconfig b/arch/ppc/Kconfig
index eaf60e0fe4..97e6c00689 100644
--- a/arch/ppc/Kconfig
+++ b/arch/ppc/Kconfig
@@ -3,6 +3,8 @@ config PPC
 	select HAVE_CONFIGURABLE_TEXT_BASE
 	select HAS_KALLSYMS
 	select HAS_MODULES
+	select HAS_CACHE
+	select GENERIC_FIND_NEXT_BIT
 	select OFTREE
 	default y
 
diff --git a/arch/ppc/include/asm/bitops.h b/arch/ppc/include/asm/bitops.h
index eea9e0c430..c4ed2de65f 100644
--- a/arch/ppc/include/asm/bitops.h
+++ b/arch/ppc/include/asm/bitops.h
@@ -153,6 +153,11 @@ extern __inline__ int ffz(unsigned int x)
 	return __ilog2(x & -x);
 }
 
+static __inline__ int __ffs(unsigned long x)
+{
+	return __ilog2(x & -x);
+}
+
 /*
  * fls: find last (most-significant) bit set.
  * Note fls(0) = 0, fls(1) = 1, fls(0x80000000) = 32.
@@ -182,49 +187,7 @@ extern __inline__ int ffs(int x)
 
 #endif /* __KERNEL__ */
 
-/*
- * This implementation of find_{first,next}_zero_bit was stolen from
- * Linus' asm-alpha/bitops.h.
- */
-#define find_first_zero_bit(addr, size) \
-	find_next_zero_bit((addr), (size), 0)
-
-extern __inline__ unsigned long find_next_zero_bit(void * addr,
-	unsigned long size, unsigned long offset)
-{
-	unsigned int * p = ((unsigned int *) addr) + (offset >> 5);
-	unsigned int result = offset & ~31UL;
-	unsigned int tmp;
-
-	if (offset >= size)
-		return size;
-	size -= result;
-	offset &= 31UL;
-	if (offset) {
-		tmp = *p++;
-		tmp |= ~0UL >> (32-offset);
-		if (size < 32)
-			goto found_first;
-		if (tmp != ~0U)
-			goto found_middle;
-		size -= 32;
-		result += 32;
-	}
-	while (size >= 32) {
-		if ((tmp = *p++) != ~0U)
-			goto found_middle;
-		result += 32;
-		size -= 32;
-	}
-	if (!size)
-		return result;
-	tmp = *p;
-found_first:
-	tmp |= ~0UL << size;
-found_middle:
-	return result + ffz(tmp);
-}
-
+#include <asm-generic/bitops/find.h>
 
 #define _EXT2_HAVE_ASM_BITOPS_
 
diff --git a/arch/sandbox/include/asm/bitops.h b/arch/sandbox/include/asm/bitops.h
index 447023da63..e77ab83202 100644
--- a/arch/sandbox/include/asm/bitops.h
+++ b/arch/sandbox/include/asm/bitops.h
@@ -1,15 +1,28 @@
-#ifndef _SANDBOX_BITOPS_H
-#define _SANDBOX_BITOPS_H
+/*
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation; either version 2 of
+ * the License, or (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ *
+ */
+
+#ifndef _ASM_BITOPS_H_
+#define _ASM_BITOPS_H_
 
-/* nothing but the defaults.. */
 #include <asm-generic/bitops/__ffs.h>
 #include <asm-generic/bitops/__fls.h>
 #include <asm-generic/bitops/ffs.h>
 #include <asm-generic/bitops/fls.h>
 #include <asm-generic/bitops/ffz.h>
-#include <asm-generic/bitops/find.h>
-#include <asm-generic/bitops/fls64.h>
 #include <asm-generic/bitops/hweight.h>
+#include <asm-generic/bitops/fls64.h>
+#include <asm-generic/bitops/find.h>
 #include <asm-generic/bitops/ops.h>
 
 #define set_bit(x, y)			__set_bit(x, y)
@@ -19,4 +32,4 @@
 #define test_and_clear_bit(x, y)	__test_and_clear_bit(x, y)
 #define test_and_change_bit(x, y)	__test_and_change_bit(x, y)
 
-#endif
+#endif /* _ASM_BITOPS_H_ */
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index d8d7f0e651..346640dcda 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -20,6 +20,7 @@ config X86
 	select HAS_MODULES
 	select HAVE_CONFIGURABLE_MEMORY_LAYOUT
 	select HAVE_CONFIGURABLE_TEXT_BASE
+	select GENERIC_FIND_NEXT_BIT
 	default y
 
 config X86_BOOTLOADER
diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h
index d741e44d4a..e77ab83202 100644
--- a/arch/x86/include/asm/bitops.h
+++ b/arch/x86/include/asm/bitops.h
@@ -12,22 +12,24 @@
  *
  */
 
-/**
- * @file
- * @brief x86 bit operations
- *
- * This file is required only to make all sources happy including
- * 'linux/bitops.h'
- */
-
-#ifndef _ASM_X86_BITOPS_H_
-#define _ASM_X86_BITOPS_H_
+#ifndef _ASM_BITOPS_H_
+#define _ASM_BITOPS_H_
 
-#define BITS_PER_LONG 32
-
-#include <asm-generic/bitops/__fls.h>
 #include <asm-generic/bitops/__ffs.h>
-#include <asm-generic/bitops/fls.h>
+#include <asm-generic/bitops/__fls.h>
 #include <asm-generic/bitops/ffs.h>
+#include <asm-generic/bitops/fls.h>
+#include <asm-generic/bitops/ffz.h>
+#include <asm-generic/bitops/hweight.h>
+#include <asm-generic/bitops/fls64.h>
+#include <asm-generic/bitops/find.h>
+#include <asm-generic/bitops/ops.h>
+
+#define set_bit(x, y)			__set_bit(x, y)
+#define clear_bit(x, y)			__clear_bit(x, y)
+#define change_bit(x, y)		__change_bit(x, y)
+#define test_and_set_bit(x, y)		__test_and_set_bit(x, y)
+#define test_and_clear_bit(x, y)	__test_and_clear_bit(x, y)
+#define test_and_change_bit(x, y)	__test_and_change_bit(x, y)
 
-#endif /* _ASM_X86_BITOPS_H_ */
+#endif /* _ASM_BITOPS_H_ */
diff --git a/arch/x86/include/asm/types.h b/arch/x86/include/asm/types.h
index d473405ff9..b3fd1f644b 100644
--- a/arch/x86/include/asm/types.h
+++ b/arch/x86/include/asm/types.h
@@ -41,6 +41,8 @@ typedef unsigned int u32;
 typedef signed long long s64;
 typedef unsigned long long u64;
 
+#define BITS_PER_LONG 32
+
 #endif /* __ASSEMBLY__ */
 
 #endif /* __ASM_X86_TYPES_H */
diff --git a/common/Kconfig b/common/Kconfig
index d3f9801647..d3d9b884cf 100644
--- a/common/Kconfig
+++ b/common/Kconfig
@@ -25,6 +25,22 @@ config ENV_HANDLING
 	select CRC32
 	bool
 
+config HAS_CACHE
+	bool
+	help
+	  This allows you do run "make ARCH=sandbox allyesconfig".
+
+	  Drivers that depend on a cache implementation can depend on this
+	  config, so that you don't get a compilation error.
+
+config HAS_DMA
+	bool
+	help
+	  This allows you do run "make ARCH=sandbox allyesconfig".
+
+	  Drivers that depend on a DMA implementation can depend on this
+	  config, so that you don't get a compilation error.
+
 config GENERIC_GPIO
 	bool
 
@@ -657,6 +673,7 @@ config BAREBOXENV_TARGET
 config BAREBOXCRC32_TARGET
 	bool
 	prompt "build bareboxcrc32 tool for target"
+	depends on !SANDBOX
 	help
 	  'bareboxcrc32' is a userspacetool to generate the crc32 checksums the same way
 	  barebox does. Say yes here to build it for the target.
@@ -691,6 +708,7 @@ config COMPILE_LOGLEVEL
 	  5    normal but significant condition (notice)
 	  6    informational (info)
 	  7    debug-level messages (debug)
+	  8    verbose debug messages (vdebug)
 
 config DEFAULT_LOGLEVEL
 	int "default loglevel"
@@ -707,6 +725,7 @@ config DEFAULT_LOGLEVEL
 	  5    normal but significant condition (notice)
 	  6    informational (info)
 	  7    debug-level messages (debug)
+	  8    verbose debug messages (vdebug)
 
 config DEBUG_INFO
 	bool
diff --git a/common/dlmalloc.c b/common/dlmalloc.c
index d831e90fe3..499ec93c28 100644
--- a/common/dlmalloc.c
+++ b/common/dlmalloc.c
@@ -1712,29 +1712,6 @@ void *memalign(size_t alignment, size_t bytes)
 	return chunk2mem(p);
 }
 
-#if 0
-/*
- * valloc just invokes memalign with alignment argument equal
- * to the page size of the system (or as near to this as can
- * be figured out from all the includes/defines above.)
- */
-void *valloc(size_t bytes)
-{
-	return memalign(malloc_getpagesize, bytes);
-}
-#endif
-
-/*
- * pvalloc just invokes valloc for the nearest pagesize
- * that will accommodate request
- */
-void *pvalloc (size_t bytes)
-{
-	size_t pagesize = malloc_getpagesize;
-
-	return memalign(pagesize, (bytes + pagesize - 1) & ~(pagesize - 1));
-}
-
 /*
  *
  * calloc calls malloc, then zeroes out the allocated chunk.
@@ -1774,115 +1751,6 @@ void *calloc(size_t n, size_t elem_size)
 	}
 }
 
-/*
- *
- * cfree just calls free. It is needed/defined on some systems
- * that pair it with calloc, presumably for odd historical reasons.
- */
-#if !defined(INTERNAL_LINUX_C_LIB) || !defined(__ELF__)
-void cfree(void *mem)
-{
-	free(mem);
-}
-#endif
-
-/*
-    Malloc_trim gives memory back to the system (via negative
-    arguments to sbrk) if there is unused memory at the `high' end of
-    the malloc pool. You can call this after freeing large blocks of
-    memory to potentially reduce the system-level memory requirements
-    of a program. However, it cannot guarantee to reduce memory. Under
-    some allocation patterns, some large free blocks of memory will be
-    locked between two used chunks, so they cannot be given back to
-    the system.
-
-    The `pad' argument to malloc_trim represents the amount of free
-    trailing space to leave untrimmed. If this argument is zero,
-    only the minimum amount of memory to maintain internal data
-    structures will be left (one page or less). Non-zero arguments
-    can be supplied to maintain enough trailing space to service
-    future expected allocations without having to re-obtain memory
-    from the system.
-
-    Malloc_trim returns 1 if it actually released any memory, else 0.
-*/
-#ifdef USE_MALLOC_TRIM
-int malloc_trim(size_t pad)
-{
-	long top_size;		/* Amount of top-most memory */
-	long extra;		/* Amount to release */
-	char *current_brk;	/* address returned by pre-check sbrk call */
-	char *new_brk;		/* address returned by negative sbrk call */
-
-	unsigned long pagesz = malloc_getpagesize;
-
-	top_size = chunksize(top);
-	extra = ((top_size - pad - MINSIZE + (pagesz - 1)) / pagesz -
-		 1) * pagesz;
-
-	if (extra < (long)pagesz)	/* Not enough memory to release */
-		return 0;
-
-	else {
-		/* Test to make sure no one else called sbrk */
-		current_brk = (char*)(sbrk(0));
-		if (current_brk != (char*)(top) + top_size)
-			return 0;	/* Apparently we don't own memory; must fail */
-
-		else {
-			new_brk = (char *) (sbrk(-extra));
-
-			if (new_brk == (char*)(NULL)) {	/* sbrk failed? */
-				/* Try to figure out what we have */
-				current_brk = (char*)(sbrk (0));
-				top_size = current_brk - (char*) top;
-				if (top_size >= (long)MINSIZE) { /* if not, we are very very dead! */
-					sbrked_mem = current_brk - sbrk_base;
-					set_head(top, top_size | PREV_INUSE);
-				}
-				return 0;
-			}
-
-			else {
-				/* Success. Adjust top accordingly. */
-				set_head(top, (top_size - extra) | PREV_INUSE);
-				sbrked_mem -= extra;
-				return 1;
-			}
-		}
-	}
-}
-#endif
-
-/*
- * malloc_usable_size:
- *
- * This routine tells you how many bytes you can actually use in an
- * allocated chunk, which may be more than you requested (although
- * often not). You can use this many bytes without worrying about
- * overwriting other allocated objects. Not a particularly great
- * programming practice, but still sometimes useful.
- */
-size_t malloc_usable_size(void *mem)
-{
-	mchunkptr p;
-
-	if (!mem)
-		return 0;
-	else {
-		p = mem2chunk(mem);
-		if (!chunk_is_mmapped(p)) {
-			if (!inuse(p))
-				return 0;
-			return chunksize(p) - SIZE_SZ;
-		}
-		return chunksize(p) - 2 * SIZE_SZ;
-	}
-}
-
-
-
-
 /* Utility to update current_mallinfo for malloc_stats and mallinfo() */
 
 #ifdef CONFIG_CMD_MEMINFO
@@ -1956,43 +1824,6 @@ void malloc_stats(void)
 #endif /* CONFIG_CMD_MEMINFO */
 
 /*
-  mallopt:
-
-    mallopt is the general SVID/XPG interface to tunable parameters.
-    The format is to provide a (parameter-number, parameter-value) pair.
-    mallopt then sets the corresponding parameter to the argument
-    value if it can (i.e., so long as the value is meaningful),
-    and returns 1 if successful else 0.
-
-    See descriptions of tunable parameters above.
-*/
-#ifndef __BAREBOX__
-int mallopt(int param_number, int value)
-{
-	switch (param_number) {
-	case M_TRIM_THRESHOLD:
-		trim_threshold = value;
-		return 1;
-	case M_TOP_PAD:
-		top_pad = value;
-		return 1;
-	case M_MMAP_THRESHOLD:
-		mmap_threshold = value;
-		return 1;
-	case M_MMAP_MAX:
-		if (value != 0)
-			return 0;
-		else
-			n_mmaps_max = value;
-		return 1;
-
-	default:
-		return 0;
-	}
-}
-#endif
-
-/*
 
 History:
 
diff --git a/common/hush.c b/common/hush.c
index 09d9326c85..b23b3f6633 100644
--- a/common/hush.c
+++ b/common/hush.c
@@ -1725,7 +1725,7 @@ static int parse_stream_outer(struct p_context *ctx, struct in_str *inp, int fla
 		b_free(&temp);
 	} while (rcode != -1 && !(flag & FLAG_EXIT_FROM_LOOP));   /* loop on syntax errors, return on EOF */
 
-	return (code != 0) ? 1 : 0;
+	return code;
 }
 
 static int parse_string_outer(struct p_context *ctx, const char *s, int flag)
diff --git a/common/resource.c b/common/resource.c
index 1ea2a7522a..fe4680e3bd 100644
--- a/common/resource.c
+++ b/common/resource.c
@@ -71,7 +71,7 @@ struct resource *__request_region(struct resource *parent,
 			goto ok;
 		if (start > r->end)
 			continue;
-		pr_warn("%s: 0x%08llx:0x%08llx conflicts with 0x%08llx:0x%08llx\n",
+		debug("%s: 0x%08llx:0x%08llx conflicts with 0x%08llx:0x%08llx\n",
 				__func__,
 				(unsigned long long)start,
 				(unsigned long long)end,
diff --git a/drivers/ata/Kconfig b/drivers/ata/Kconfig
index 9830cc07a8..7850e4a9c9 100644
--- a/drivers/ata/Kconfig
+++ b/drivers/ata/Kconfig
@@ -34,6 +34,7 @@ config DISK_ATA
 
 config DISK_AHCI
 	bool "AHCI support"
+	depends on HAS_DMA
 	select DISK_ATA
 
 config DISK_AHCI_IMX
diff --git a/drivers/clk/clk-divider.c b/drivers/clk/clk-divider.c
index 67783daabb..506a9668a9 100644
--- a/drivers/clk/clk-divider.c
+++ b/drivers/clk/clk-divider.c
@@ -186,7 +186,7 @@ static int clk_divider_set_rate(struct clk *clk, unsigned long rate,
 		div = clk_divider_bestdiv(clk, rate, &best_parent_rate);
 		clk_set_rate(clk_get_parent(clk), best_parent_rate);
 	} else {
-		div = parent_rate / rate;
+		div = DIV_ROUND_UP(parent_rate, rate);
 	}
 
 	value = _get_val(divider, div);
diff --git a/drivers/i2c/busses/i2c-omap.c b/drivers/i2c/busses/i2c-omap.c
index f7108c2605..adc952b043 100644
--- a/drivers/i2c/busses/i2c-omap.c
+++ b/drivers/i2c/busses/i2c-omap.c
@@ -1132,7 +1132,7 @@ static struct platform_device_id omap_i2c_ids[] = {
 	},
 };
 
-static __maybe_unused struct of_device_id omap_spi_dt_ids[] = {
+static __maybe_unused struct of_device_id omap_i2c_dt_ids[] = {
 	{
 		.compatible = "ti,omap3-i2c",
 		.data = (unsigned long)&omap3_data,
@@ -1148,7 +1148,7 @@ static struct driver_d omap_i2c_driver = {
 	.probe		= i2c_omap_probe,
 	.name		= DRIVER_NAME,
 	.id_table	= omap_i2c_ids,
-	.of_compatible = DRV_OF_COMPAT(omap_spi_dt_ids),
+	.of_compatible = DRV_OF_COMPAT(omap_i2c_dt_ids),
 };
 device_platform_driver(omap_i2c_driver);
 
diff --git a/drivers/input/Kconfig b/drivers/input/Kconfig
index 3d9016b3fa..07545ed310 100644
--- a/drivers/input/Kconfig
+++ b/drivers/input/Kconfig
@@ -32,7 +32,7 @@ config KEYBOARD_IMX_KEYPAD
 
 config KEYBOARD_QT1070
 	tristate "Atmel AT42QT1070 Touch Sensor Chip"
-	depends on I2C
+	depends on I2C && GENERIC_GPIO
 	select POLLER
 	help
 	  Say Y here if you want to use Atmel AT42QT1070 QTouch
diff --git a/drivers/led/led-gpio.c b/drivers/led/led-gpio.c
index 7bb3b49953..a1a661724d 100644
--- a/drivers/led/led-gpio.c
+++ b/drivers/led/led-gpio.c
@@ -206,13 +206,17 @@ static int led_gpio_of_probe(struct device_d *dev)
 		struct gpio_led *gled;
 		enum of_gpio_flags flags;
 		int gpio;
+		const char *label;
 
 		gpio = of_get_named_gpio_flags(child, "gpios", 0, &flags);
 		if (gpio < 0)
 			continue;
 
 		gled = xzalloc(sizeof(*gled));
-		gled->led.name = xstrdup(child->name);
+		if (of_property_read_string(child, "label", &label))
+			label = child->name;
+		gled->led.name = xstrdup(label);
+
 		gled->gpio = gpio;
 		gled->active_low = (flags & OF_GPIO_ACTIVE_LOW) ? 1 : 0;
 
diff --git a/drivers/mci/mci-core.c b/drivers/mci/mci-core.c
index ce6e590aaf..8221632ecb 100644
--- a/drivers/mci/mci-core.c
+++ b/drivers/mci/mci-core.c
@@ -616,6 +616,9 @@ retry_scr:
 		break;
 	}
 
+	if (mci->scr[0] & SD_DATA_4BIT)
+		mci->card_caps |= MMC_CAP_4_BIT_DATA;
+
 	/* Version 1.0 doesn't support switching */
 	if (mci->version == SD_VERSION_1_0)
 		return 0;
@@ -634,9 +637,6 @@ retry_scr:
 			break;
 	}
 
-	if (mci->scr[0] & SD_DATA_4BIT)
-		mci->card_caps |= MMC_CAP_4_BIT_DATA;
-
 	/* If high-speed isn't supported, we return */
 	if (!(__be32_to_cpu(switch_status[3]) & SD_HIGHSPEED_SUPPORTED))
 		return 0;
diff --git a/drivers/mfd/mc34704.c b/drivers/mfd/mc34704.c
index 9afab07a2d..3dc85f5474 100644
--- a/drivers/mfd/mc34704.c
+++ b/drivers/mfd/mc34704.c
@@ -123,9 +123,15 @@ static int mc34704_probe(struct device_d *dev)
 	return 0;
 }
 
+static __maybe_unused struct of_device_id mc34704_dt_ids[] = {
+	{ .compatible = "fsl,mc34704", },
+	{ }
+};
+
 static struct driver_d mc34704_driver = {
 	.name  = DRIVERNAME,
 	.probe = mc34704_probe,
+	.of_compatible = DRV_OF_COMPAT(mc34704_dt_ids),
 };
 
 static int mc34704_init(void)
diff --git a/drivers/mtd/nand/atmel_nand.c b/drivers/mtd/nand/atmel_nand.c
index 2e9f61f119..337e2256e3 100644
--- a/drivers/mtd/nand/atmel_nand.c
+++ b/drivers/mtd/nand/atmel_nand.c
@@ -796,7 +796,9 @@ static int __init atmel_pmecc_nand_init_params(struct device_d *dev,
 	switch (mtd->writesize) {
 	case 2048:
 	case 4096:
-		host->pmecc_degree = PMECC_GF_DIMENSION_13;
+	case 8192:
+		host->pmecc_degree = (sector_size == 512) ?
+					PMECC_GF_DIMENSION_13 : PMECC_GF_DIMENSION_14;
 		host->pmecc_cw_len = (1 << host->pmecc_degree) - 1;
 		host->pmecc_sector_number = mtd->writesize / sector_size;
 		host->pmecc_bytes_per_sector = pmecc_get_ecc_bytes(
@@ -1162,7 +1164,12 @@ static int __init atmel_nand_probe(struct device_d *dev)
 		nand_chip->ecc.mode = NAND_ECC_HW;
 	}
 
-	nand_chip->chip_delay = 20;		/* 20us command delay time */
+	nand_chip->chip_delay = 40;		/* 40us command delay time */
+
+	if (IS_ENABLED(CONFIG_NAND_ECC_BCH) &&
+			pdata->ecc_mode == NAND_ECC_SOFT_BCH) {
+		nand_chip->ecc.mode = NAND_ECC_SOFT_BCH;
+	}
 
 	if (host->board->bus_width_16) {	/* 16-bit bus width */
 		nand_chip->options |= NAND_BUSWIDTH_16;
diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig
index 43409a8f8c..c99fcc8316 100644
--- a/drivers/net/Kconfig
+++ b/drivers/net/Kconfig
@@ -34,6 +34,7 @@ config DRIVER_NET_AR231X
 
 config DRIVER_NET_ARC_EMAC
 	bool "ARC Ethernet MAC driver"
+	depends on HAS_DMA
 	select PHYLIB
 	help
 	  This option enables support for the ARC EMAC ethernet
@@ -46,6 +47,7 @@ config DRIVER_NET_AT91_ETHER
 
 config DRIVER_NET_CALXEDA_XGMAC
 	bool "Calxeda xgmac"
+	depends on HAS_DMA
 
 config DRIVER_NET_CS8900
 	bool "cs8900 ethernet driver"
@@ -63,6 +65,7 @@ config DRIVER_NET_DAVINCI_EMAC
 
 config DRIVER_NET_DESIGNWARE
 	bool "Designware Universal MAC ethernet driver"
+	depends on HAS_DMA
 	select PHYLIB
 	help
 	  This option enables support for the Synopsys
@@ -94,6 +97,7 @@ config DRIVER_NET_EP93XX
 
 config DRIVER_NET_ETHOC
 	bool "OpenCores ethernet MAC driver"
+	depends on HAS_CACHE
 	select PHYLIB
 	help
 	  This option enables support for the OpenCores 10/100 Mbps
diff --git a/drivers/net/gianfar.c b/drivers/net/gianfar.c
index 3370b5cdb3..a308035ff2 100644
--- a/drivers/net/gianfar.c
+++ b/drivers/net/gianfar.c
@@ -199,19 +199,19 @@ static int gfar_open(struct eth_device *edev)
 
 	/* Initialize the Rx Buffer descriptors */
 	for (ix = 0; ix < RX_BUF_CNT; ix++) {
-		priv->rxbd[ix].status = RXBD_EMPTY;
-		priv->rxbd[ix].length = 0;
-		priv->rxbd[ix].bufPtr = (uint) NetRxPackets[ix];
+		out_be16(&priv->rxbd[ix].status, RXBD_EMPTY);
+		out_be16(&priv->rxbd[ix].length, 0);
+		out_be32(&priv->rxbd[ix].bufPtr, (uint) NetRxPackets[ix]);
 	}
-	priv->rxbd[RX_BUF_CNT - 1].status |= RXBD_WRAP;
+	out_be16(&priv->rxbd[RX_BUF_CNT - 1].status, RXBD_EMPTY | RXBD_WRAP);
 
 	/* Initialize the TX Buffer Descriptors */
 	for (ix = 0; ix < TX_BUF_CNT; ix++) {
-		priv->txbd[ix].status = 0;
-		priv->txbd[ix].length = 0;
-		priv->txbd[ix].bufPtr = 0;
+		out_be16(&priv->txbd[ix].status, 0);
+		out_be16(&priv->txbd[ix].length, 0);
+		out_be32(&priv->txbd[ix].bufPtr, 0);
 	}
-	priv->txbd[TX_BUF_CNT - 1].status |= TXBD_WRAP;
+	out_be16(&priv->txbd[TX_BUF_CNT - 1].status, TXBD_WRAP);
 
 	/* Enable Transmit and Receive */
 	setbits_be32(regs + GFAR_MACCFG1_OFFSET, GFAR_MACCFG1_RX_EN |
@@ -366,30 +366,32 @@ static int gfar_send(struct eth_device *edev, void *packet, int length)
 	struct device_d *dev = edev->parent;
 	uint64_t start;
 	uint tidx;
+	uint16_t status;
 
 	tidx = priv->txidx;
-	priv->txbd[tidx].bufPtr = (uint) packet;
-	priv->txbd[tidx].length = length;
-	priv->txbd[tidx].status |= (TXBD_READY | TXBD_LAST |
-				TXBD_CRC | TXBD_INTERRUPT);
+	out_be32(&priv->txbd[tidx].bufPtr, (u32) packet);
+	out_be16(&priv->txbd[tidx].length, length);
+	out_be16(&priv->txbd[tidx].status,
+		in_be16(&priv->txbd[tidx].status) |
+		(TXBD_READY | TXBD_LAST | TXBD_CRC | TXBD_INTERRUPT));
 
 	/* Tell the DMA to go */
 	out_be32(regs + GFAR_TSTAT_OFFSET, GFAR_TSTAT_CLEAR_THALT);
 
 	/* Wait for buffer to be transmitted */
 	start = get_time_ns();
-	while (priv->txbd[tidx].status & TXBD_READY) {
+	while (in_be16(&priv->txbd[tidx].status) & TXBD_READY) {
 		if (is_timeout(start, 5 * MSECOND)) {
 			break;
 		}
 	}
 
-	if (priv->txbd[tidx].status & TXBD_READY) {
-		dev_err(dev, "tx timeout: 0x%x\n", priv->txbd[tidx].status);
+	status = in_be16(&priv->txbd[tidx].status);
+	if (status & TXBD_READY) {
+		dev_err(dev, "tx timeout: 0x%x\n", status);
 		return -EBUSY;
-	}
-	else if (priv->txbd[tidx].status & TXBD_STATS) {
-		dev_err(dev, "TX error: 0x%x\n", priv->txbd[tidx].status);
+	} else if (status & TXBD_STATS) {
+		dev_err(dev, "TX error: 0x%x\n", status);
 		return -EIO;
 	}
 
@@ -403,31 +405,28 @@ static int gfar_recv(struct eth_device *edev)
 	struct gfar_private *priv = edev->priv;
 	struct device_d *dev = edev->parent;
 	void __iomem *regs = priv->regs;
-	int length;
+	uint16_t status, length;
 
-	if (priv->rxbd[priv->rxidx].status & RXBD_EMPTY) {
-		return 0; /* no data */
-	}
+	if (in_be16(&priv->rxbd[priv->rxidx].status) & RXBD_EMPTY)
+		return 0;
 
-	length = priv->rxbd[priv->rxidx].length;
+	length = in_be16(&priv->rxbd[priv->rxidx].length);
 
 	/* Send the packet up if there were no errors */
-	if (!(priv->rxbd[priv->rxidx].status & RXBD_STATS)) {
+	status = in_be16(&priv->rxbd[priv->rxidx].status);
+	if (!(status & RXBD_STATS))
 		net_receive(edev, NetRxPackets[priv->rxidx], length - 4);
-	} else {
-		dev_err(dev, "Got error %x\n",
-		       (priv->rxbd[priv->rxidx].status & RXBD_STATS));
-	}
+	else
+		dev_err(dev, "Got error %x\n", status & RXBD_STATS);
 
-	priv->rxbd[priv->rxidx].length = 0;
+	out_be16(&priv->rxbd[priv->rxidx].length, 0);
 
+	status = RXBD_EMPTY;
 	/* Set the wrap bit if this is the last element in the list */
 	if ((priv->rxidx + 1) == RX_BUF_CNT)
-		priv->rxbd[priv->rxidx].status = RXBD_WRAP;
-	else
-		priv->rxbd[priv->rxidx].status = 0;
+		status |= RXBD_WRAP;
 
-	priv->rxbd[priv->rxidx].status |= RXBD_EMPTY;
+	out_be16(&priv->rxbd[priv->rxidx].status, status);
 	priv->rxidx = (priv->rxidx + 1) % RX_BUF_CNT;
 
 	if (in_be32(regs + GFAR_IEVENT_OFFSET) & GFAR_IEVENT_BSY) {
@@ -517,8 +516,9 @@ static int gfar_probe(struct device_d *dev)
 	size = ((TX_BUF_CNT * sizeof(struct txbd8)) +
 		(RX_BUF_CNT * sizeof(struct rxbd8))) + BUF_ALIGN;
 	p = (char *)xmemalign(BUF_ALIGN, size);
-	priv->txbd = (struct txbd8 *)p;
-	priv->rxbd = (struct rxbd8 *)(p + (TX_BUF_CNT * sizeof(struct txbd8)));
+	priv->txbd = (struct txbd8 __iomem *)p;
+	priv->rxbd = (struct rxbd8 __iomem *)(p +
+			(TX_BUF_CNT * sizeof(struct txbd8)));
 
 	edev->priv = priv;
 	edev->init = gfar_init;
diff --git a/drivers/net/gianfar.h b/drivers/net/gianfar.h
index 1aac47907a..c0b9763476 100644
--- a/drivers/net/gianfar.h
+++ b/drivers/net/gianfar.h
@@ -188,15 +188,15 @@
 #define RXBD_STATS		0x003f
 
 struct txbd8 {
-	ushort	     status;	     /* Status Fields */
-	ushort	     length;	     /* Buffer length */
-	uint	     bufPtr;	     /* Buffer Pointer */
+	uint16_t     status;	     /* Status Fields */
+	uint16_t     length;	     /* Buffer length */
+	uint32_t     bufPtr;	     /* Buffer Pointer */
 };
 
 struct rxbd8 {
-	ushort	     status;	     /* Status Fields */
-	ushort	     length;	     /* Buffer Length */
-	uint	     bufPtr;	     /* Buffer Pointer */
+	uint16_t     status;	     /* Status Fields */
+	uint16_t     length;	     /* Buffer Length */
+	uint32_t     bufPtr;	     /* Buffer Pointer */
 };
 
 /* eTSEC general control and status registers */
@@ -275,8 +275,8 @@ struct gfar_private {
 	struct gfar_phy *gfar_mdio;
 	struct gfar_phy *gfar_tbi;
 	struct phy_info *phyinfo;
-	volatile struct txbd8 *txbd;
-	volatile struct rxbd8 *rxbd;
+	struct txbd8 __iomem *txbd;
+	struct rxbd8 __iomem *rxbd;
 	uint txidx;
 	uint rxidx;
 	uint phyaddr;
diff --git a/drivers/of/of_mtd.c b/drivers/of/of_mtd.c
index 239f1f9892..97f3095740 100644
--- a/drivers/of/of_mtd.c
+++ b/drivers/of/of_mtd.c
@@ -20,6 +20,8 @@ static const char *nand_ecc_modes[] = {
 	[NAND_ECC_SOFT]		= "soft",
 	[NAND_ECC_HW]		= "hw",
 	[NAND_ECC_HW_SYNDROME]	= "hw_syndrome",
+	[NAND_ECC_HW_OOB_FIRST]	= "hw_oob_first",
+	[NAND_ECC_SOFT_BCH]	= "soft_bch",
 };
 
 /**
diff --git a/drivers/regulator/Kconfig b/drivers/regulator/Kconfig
index 55f87a45ba..493b18a898 100644
--- a/drivers/regulator/Kconfig
+++ b/drivers/regulator/Kconfig
@@ -6,6 +6,7 @@ if REGULATOR
 
 config REGULATOR_FIXED
 	bool "fixed/gpio regulator"
+	depends on GENERIC_GPIO
 	help
 	  This enables a simple fixed regulator. It is used for regulators
 	  which are not software controllable or controllable via gpio.
diff --git a/drivers/regulator/fixed.c b/drivers/regulator/fixed.c
index 7e649199bf..2515d3e70d 100644
--- a/drivers/regulator/fixed.c
+++ b/drivers/regulator/fixed.c
@@ -27,6 +27,7 @@
 struct regulator_fixed {
 	int gpio;
 	int active_low;
+	int always_on;
 	struct regulator_dev rdev;
 };
 
@@ -44,6 +45,9 @@ static int regulator_fixed_disable(struct regulator_dev *rdev)
 {
 	struct regulator_fixed *fix = container_of(rdev, struct regulator_fixed, rdev);
 
+	if (fix->always_on)
+		return 0;
+
 	if (!gpio_is_valid(fix->gpio))
 		return 0;
 
@@ -79,6 +83,11 @@ static int regulator_fixed_probe(struct device_d *dev)
 
 	fix->rdev.ops = &fixed_ops;
 
+	if (of_find_property(dev->device_node, "regulator-always-on", NULL)) {
+		fix->always_on = 1;
+		regulator_fixed_enable(&fix->rdev);
+	}
+
 	ret = of_regulator_register(&fix->rdev, dev->device_node);
 	if (ret)
 		return ret;
diff --git a/drivers/usb/gadget/u_serial.c b/drivers/usb/gadget/u_serial.c
index 375ec65141..2f9353edca 100644
--- a/drivers/usb/gadget/u_serial.c
+++ b/drivers/usb/gadget/u_serial.c
@@ -109,14 +109,6 @@ static unsigned	n_ports;
 
 #define GS_CLOSE_TIMEOUT		15		/* seconds */
 
-#ifdef VERBOSE_DEBUG
-#define pr_vdebug(fmt, arg...) \
-	pr_debug(fmt, ##arg)
-#else
-#define pr_vdebug(fmt, arg...) \
-	({ if (0) pr_debug(fmt, ##arg); })
-#endif
-
 static unsigned gs_start_rx(struct gs_port *port)
 {
 	struct list_head	*pool = &port->read_pool;
diff --git a/drivers/usb/host/Kconfig b/drivers/usb/host/Kconfig
index 5a3ce40705..a69e758910 100644
--- a/drivers/usb/host/Kconfig
+++ b/drivers/usb/host/Kconfig
@@ -1,5 +1,6 @@
 config USB_EHCI
 	bool "EHCI driver"
+	depends on HAS_DMA
 
 config USB_EHCI_OMAP
 	depends on ARCH_OMAP3
diff --git a/drivers/video/imx-ipu-v3/Kconfig b/drivers/video/imx-ipu-v3/Kconfig
index 3d656e5193..368167bfb6 100644
--- a/drivers/video/imx-ipu-v3/Kconfig
+++ b/drivers/video/imx-ipu-v3/Kconfig
@@ -1,5 +1,6 @@
 config DRIVER_VIDEO_IMX_IPUV3
 	bool "i.MX IPUv3 driver"
+	depends on ARCH_IMX
 	help
 	  Support the IPUv3 found on Freescale i.MX51/53/6 SoCs
 
diff --git a/drivers/watchdog/Kconfig b/drivers/watchdog/Kconfig
index 2e2900c10f..7f7b02e306 100644
--- a/drivers/watchdog/Kconfig
+++ b/drivers/watchdog/Kconfig
@@ -21,4 +21,11 @@ config WATCHDOG_IMX
 	depends on ARCH_IMX
 	help
 	  Add support for watchdog found on Freescale i.MX SoCs.
+
+config WATCHDOG_JZ4740
+	bool "Ingenic jz4740 SoC hardware watchdog"
+	depends on MACH_MIPS_XBURST
+	help
+	  Hardware driver for the built-in watchdog timer on Ingenic jz4740 SoCs.
+
 endif
diff --git a/drivers/watchdog/Makefile b/drivers/watchdog/Makefile
index f522b88708..865fc477b1 100644
--- a/drivers/watchdog/Makefile
+++ b/drivers/watchdog/Makefile
@@ -1,3 +1,4 @@
 obj-$(CONFIG_WATCHDOG) += wd_core.o
 obj-$(CONFIG_WATCHDOG_MXS28) += im28wd.o
+obj-$(CONFIG_WATCHDOG_JZ4740) += jz4740.o
 obj-$(CONFIG_WATCHDOG_IMX_RESET_SOURCE) += imxwd.o
diff --git a/drivers/watchdog/imxwd.c b/drivers/watchdog/imxwd.c
index 63c5605c99..31c3d0d853 100644
--- a/drivers/watchdog/imxwd.c
+++ b/drivers/watchdog/imxwd.c
@@ -159,6 +159,10 @@ static int imx_wd_probe(struct device_d *dev)
 
 	priv = xzalloc(sizeof(struct imx_wd));
 	priv->base = dev_request_mem_region(dev, 0);
+	if (!priv->base) {
+		dev_err(dev, "could not get memory region\n");
+		return -ENODEV;
+	}
 	priv->set_timeout = fn;
 	priv->wd.set_timeout = imx_watchdog_set_timeout;
 	priv->dev = dev;
diff --git a/drivers/watchdog/jz4740.c b/drivers/watchdog/jz4740.c
new file mode 100644
index 0000000000..8ac51e060a
--- /dev/null
+++ b/drivers/watchdog/jz4740.c
@@ -0,0 +1,102 @@
+/*
+ *  JZ4740 Watchdog driver
+ *
+ *  Copyright (C) 2014 Antony Pavlov <antonynpavlov@gmail.com>
+ *
+ *  Based on jz4740_wdt.c from linux-3.15.
+ *
+ *  Copyright (C) 2010, Paul Cercueil <paul@crapouillou.net>
+ *
+ *  This program is free software; you can redistribute it and/or modify it
+ *  under  the terms of the GNU General  Public License as published by the
+ *  Free Software Foundation;  either version 2 of the License, or (at your
+ *  option) any later version.
+ *
+ */
+
+#include <common.h>
+#include <init.h>
+#include <io.h>
+
+#define JZ_REG_WDT_TIMER_DATA     0x0
+#define JZ_REG_WDT_COUNTER_ENABLE 0x4
+#define JZ_REG_WDT_TIMER_COUNTER  0x8
+#define JZ_REG_WDT_TIMER_CONTROL  0xC
+
+#define JZ_WDT_CLOCK_PCLK 0x1
+#define JZ_WDT_CLOCK_RTC  0x2
+#define JZ_WDT_CLOCK_EXT  0x4
+
+#define JZ_WDT_CLOCK_DIV_SHIFT   3
+
+#define JZ_WDT_CLOCK_DIV_1    (0 << JZ_WDT_CLOCK_DIV_SHIFT)
+#define JZ_WDT_CLOCK_DIV_4    (1 << JZ_WDT_CLOCK_DIV_SHIFT)
+#define JZ_WDT_CLOCK_DIV_16   (2 << JZ_WDT_CLOCK_DIV_SHIFT)
+#define JZ_WDT_CLOCK_DIV_64   (3 << JZ_WDT_CLOCK_DIV_SHIFT)
+#define JZ_WDT_CLOCK_DIV_256  (4 << JZ_WDT_CLOCK_DIV_SHIFT)
+#define JZ_WDT_CLOCK_DIV_1024 (5 << JZ_WDT_CLOCK_DIV_SHIFT)
+
+#define JZ_EXTAL 24000000
+
+struct jz4740_wdt_drvdata {
+	void __iomem *base;
+};
+
+static struct jz4740_wdt_drvdata *reset_wd;
+
+void __noreturn reset_cpu(unsigned long addr)
+{
+	if (reset_wd) {
+		void __iomem *base = reset_wd->base;
+
+		writew(JZ_WDT_CLOCK_DIV_4 | JZ_WDT_CLOCK_EXT,
+				base + JZ_REG_WDT_TIMER_CONTROL);
+		writew(0, base + JZ_REG_WDT_TIMER_COUNTER);
+
+		/* reset after 4ms */
+		writew(JZ_EXTAL / 1000, base + JZ_REG_WDT_TIMER_DATA);
+
+		/* start wdt */
+		writeb(0x1, base + JZ_REG_WDT_COUNTER_ENABLE);
+
+		mdelay(1000);
+	} else
+		pr_err("%s: can't reset cpu\n", __func__);
+
+	hang();
+}
+EXPORT_SYMBOL(reset_cpu);
+
+static int jz4740_wdt_probe(struct device_d *dev)
+{
+	struct jz4740_wdt_drvdata *priv;
+
+	priv = xzalloc(sizeof(struct jz4740_wdt_drvdata));
+	priv->base = dev_request_mem_region(dev, 0);
+	if (!priv->base) {
+		dev_err(dev, "could not get memory region\n");
+		return -ENODEV;
+	}
+
+	if (!reset_wd)
+		reset_wd = priv;
+
+	dev->priv = priv;
+
+	return 0;
+}
+
+static __maybe_unused struct of_device_id jz4740_wdt_dt_ids[] = {
+	{
+		.compatible = "ingenic,jz4740-wdt",
+	}, {
+		/* sentinel */
+	}
+};
+
+static struct driver_d jz4740_wdt_driver = {
+	.name   = "jz4740-wdt",
+	.probe  = jz4740_wdt_probe,
+	.of_compatible = DRV_OF_COMPAT(jz4740_wdt_dt_ids),
+};
+device_platform_driver(jz4740_wdt_driver);
diff --git a/include/asm-generic/bitops/hweight.h b/include/asm-generic/bitops/hweight.h
index af9770de4e..7268c8b9ab 100644
--- a/include/asm-generic/bitops/hweight.h
+++ b/include/asm-generic/bitops/hweight.h
@@ -32,4 +32,19 @@ static inline unsigned int hweight8(unsigned int w)
 	return (res & 0x0F) + ((res >> 4) & 0x0F);
 }
 
+static inline unsigned long hweight64(__u64 w)
+{
+#if BITS_PER_LONG == 32
+	return hweight32((unsigned int)(w >> 32)) +
+		hweight32((unsigned int)w);
+#elif BITS_PER_LONG == 64
+	__u64 res = w - ((w >> 1) & 0x5555555555555555ul);
+	res = (res & 0x3333333333333333ul) + ((res >> 2) & 0x3333333333333333ul);
+	res = (res + (res >> 4)) & 0x0F0F0F0F0F0F0F0Ful;
+	res = res + (res >> 8);
+	res = res + (res >> 16);
+	return (res + (res >> 32)) & 0x00000000000000FFul;
+#endif
+}
+
 #endif				/* _ASM_GENERIC_BITOPS_HWEIGHT_H_ */
diff --git a/include/bbu.h b/include/bbu.h
index 095eebcf4a..adb52b0dec 100644
--- a/include/bbu.h
+++ b/include/bbu.h
@@ -1,6 +1,8 @@
 #ifndef __INCLUDE_BBU_H
 #define __INCLUDE_BBU_H
 
+#include <asm-generic/errno.h>
+
 struct bbu_data {
 #define BBU_FLAG_FORCE	(1 << 0)
 #define BBU_FLAG_YES	(1 << 1)
diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h
new file mode 100644
index 0000000000..4b98521a83
--- /dev/null
+++ b/include/linux/bitmap.h
@@ -0,0 +1,285 @@
+#ifndef __LINUX_BITMAP_H
+#define __LINUX_BITMAP_H
+
+#ifndef __ASSEMBLY__
+
+#include <linux/types.h>
+#include <linux/bitops.h>
+#include <linux/string.h>
+#include <linux/kernel.h>
+
+/*
+ * bitmaps provide bit arrays that consume one or more unsigned
+ * longs.  The bitmap interface and available operations are listed
+ * here, in bitmap.h
+ *
+ * Function implementations generic to all architectures are in
+ * lib/bitmap.c.  Functions implementations that are architecture
+ * specific are in various include/asm-<arch>/bitops.h headers
+ * and other arch/<arch> specific files.
+ *
+ * See lib/bitmap.c for more details.
+ */
+
+/*
+ * The available bitmap operations and their rough meaning in the
+ * case that the bitmap is a single unsigned long are thus:
+ *
+ * Note that nbits should be always a compile time evaluable constant.
+ * Otherwise many inlines will generate horrible code.
+ *
+ * bitmap_zero(dst, nbits)			*dst = 0UL
+ * bitmap_fill(dst, nbits)			*dst = ~0UL
+ * bitmap_copy(dst, src, nbits)			*dst = *src
+ * bitmap_and(dst, src1, src2, nbits)		*dst = *src1 & *src2
+ * bitmap_or(dst, src1, src2, nbits)		*dst = *src1 | *src2
+ * bitmap_xor(dst, src1, src2, nbits)		*dst = *src1 ^ *src2
+ * bitmap_andnot(dst, src1, src2, nbits)	*dst = *src1 & ~(*src2)
+ * bitmap_complement(dst, src, nbits)		*dst = ~(*src)
+ * bitmap_equal(src1, src2, nbits)		Are *src1 and *src2 equal?
+ * bitmap_intersects(src1, src2, nbits) 	Do *src1 and *src2 overlap?
+ * bitmap_subset(src1, src2, nbits)		Is *src1 a subset of *src2?
+ * bitmap_empty(src, nbits)			Are all bits zero in *src?
+ * bitmap_full(src, nbits)			Are all bits set in *src?
+ * bitmap_weight(src, nbits)			Hamming Weight: number set bits
+ * bitmap_set(dst, pos, nbits)			Set specified bit area
+ * bitmap_clear(dst, pos, nbits)		Clear specified bit area
+ * bitmap_find_next_zero_area(buf, len, pos, n, mask)	Find bit free area
+ * bitmap_shift_right(dst, src, n, nbits)	*dst = *src >> n
+ * bitmap_shift_left(dst, src, n, nbits)	*dst = *src << n
+ * bitmap_remap(dst, src, old, new, nbits)	*dst = map(old, new)(src)
+ * bitmap_bitremap(oldbit, old, new, nbits)	newbit = map(old, new)(oldbit)
+ * bitmap_onto(dst, orig, relmap, nbits)	*dst = orig relative to relmap
+ * bitmap_fold(dst, orig, sz, nbits)		dst bits = orig bits mod sz
+ * bitmap_find_free_region(bitmap, bits, order)	Find and allocate bit region
+ * bitmap_release_region(bitmap, pos, order)	Free specified bit region
+ * bitmap_allocate_region(bitmap, pos, order)	Allocate specified bit region
+ */
+
+/*
+ * Also the following operations in asm/bitops.h apply to bitmaps.
+ *
+ * set_bit(bit, addr)			*addr |= bit
+ * clear_bit(bit, addr)			*addr &= ~bit
+ * change_bit(bit, addr)		*addr ^= bit
+ * test_bit(bit, addr)			Is bit set in *addr?
+ * test_and_set_bit(bit, addr)		Set bit and return old value
+ * test_and_clear_bit(bit, addr)	Clear bit and return old value
+ * test_and_change_bit(bit, addr)	Change bit and return old value
+ * find_first_zero_bit(addr, nbits)	Position first zero bit in *addr
+ * find_first_bit(addr, nbits)		Position first set bit in *addr
+ * find_next_zero_bit(addr, nbits, bit)	Position next zero bit in *addr >= bit
+ * find_next_bit(addr, nbits, bit)	Position next set bit in *addr >= bit
+ */
+
+/*
+ * The DECLARE_BITMAP(name,bits) macro, in linux/types.h, can be used
+ * to declare an array named 'name' of just enough unsigned longs to
+ * contain all bit positions from 0 to 'bits' - 1.
+ */
+
+/*
+ * lib/bitmap.c provides these functions:
+ */
+
+extern int __bitmap_empty(const unsigned long *bitmap, int bits);
+extern int __bitmap_full(const unsigned long *bitmap, int bits);
+extern int __bitmap_equal(const unsigned long *bitmap1,
+			const unsigned long *bitmap2, int bits);
+extern void __bitmap_complement(unsigned long *dst, const unsigned long *src,
+			int bits);
+extern void __bitmap_shift_right(unsigned long *dst,
+                        const unsigned long *src, int shift, int bits);
+extern void __bitmap_shift_left(unsigned long *dst,
+                        const unsigned long *src, int shift, int bits);
+extern int __bitmap_and(unsigned long *dst, const unsigned long *bitmap1,
+			const unsigned long *bitmap2, int bits);
+extern void __bitmap_or(unsigned long *dst, const unsigned long *bitmap1,
+			const unsigned long *bitmap2, int bits);
+extern void __bitmap_xor(unsigned long *dst, const unsigned long *bitmap1,
+			const unsigned long *bitmap2, int bits);
+extern int __bitmap_andnot(unsigned long *dst, const unsigned long *bitmap1,
+			const unsigned long *bitmap2, int bits);
+extern int __bitmap_intersects(const unsigned long *bitmap1,
+			const unsigned long *bitmap2, int bits);
+extern int __bitmap_subset(const unsigned long *bitmap1,
+			const unsigned long *bitmap2, int bits);
+extern int __bitmap_weight(const unsigned long *bitmap, int bits);
+
+extern void bitmap_set(unsigned long *map, int i, int len);
+extern void bitmap_clear(unsigned long *map, int start, int nr);
+extern unsigned long bitmap_find_next_zero_area(unsigned long *map,
+					 unsigned long size,
+					 unsigned long start,
+					 unsigned int nr,
+					 unsigned long align_mask);
+
+extern void bitmap_remap(unsigned long *dst, const unsigned long *src,
+		const unsigned long *old, const unsigned long *new, int bits);
+extern int bitmap_bitremap(int oldbit,
+		const unsigned long *old, const unsigned long *new, int bits);
+extern void bitmap_onto(unsigned long *dst, const unsigned long *orig,
+		const unsigned long *relmap, int bits);
+extern void bitmap_fold(unsigned long *dst, const unsigned long *orig,
+		int sz, int bits);
+extern int bitmap_find_free_region(unsigned long *bitmap, int bits, int order);
+extern void bitmap_release_region(unsigned long *bitmap, int pos, int order);
+extern int bitmap_allocate_region(unsigned long *bitmap, int pos, int order);
+extern void bitmap_copy_le(void *dst, const unsigned long *src, int nbits);
+extern int bitmap_ord_to_pos(const unsigned long *bitmap, int n, int bits);
+
+#define BITMAP_FIRST_WORD_MASK(start) (~0UL << ((start) % BITS_PER_LONG))
+#define BITMAP_LAST_WORD_MASK(nbits)					\
+(									\
+	((nbits) % BITS_PER_LONG) ?					\
+		(1UL<<((nbits) % BITS_PER_LONG))-1 : ~0UL		\
+)
+
+#define small_const_nbits(nbits) \
+	(__builtin_constant_p(nbits) && (nbits) <= BITS_PER_LONG)
+
+static inline void bitmap_zero(unsigned long *dst, int nbits)
+{
+	if (small_const_nbits(nbits))
+		*dst = 0UL;
+	else {
+		int len = BITS_TO_LONGS(nbits) * sizeof(unsigned long);
+		memset(dst, 0, len);
+	}
+}
+
+static inline void bitmap_fill(unsigned long *dst, int nbits)
+{
+	size_t nlongs = BITS_TO_LONGS(nbits);
+	if (!small_const_nbits(nbits)) {
+		int len = (nlongs - 1) * sizeof(unsigned long);
+		memset(dst, 0xff,  len);
+	}
+	dst[nlongs - 1] = BITMAP_LAST_WORD_MASK(nbits);
+}
+
+static inline void bitmap_copy(unsigned long *dst, const unsigned long *src,
+			int nbits)
+{
+	if (small_const_nbits(nbits))
+		*dst = *src;
+	else {
+		int len = BITS_TO_LONGS(nbits) * sizeof(unsigned long);
+		memcpy(dst, src, len);
+	}
+}
+
+static inline int bitmap_and(unsigned long *dst, const unsigned long *src1,
+			const unsigned long *src2, int nbits)
+{
+	if (small_const_nbits(nbits))
+		return (*dst = *src1 & *src2) != 0;
+	return __bitmap_and(dst, src1, src2, nbits);
+}
+
+static inline void bitmap_or(unsigned long *dst, const unsigned long *src1,
+			const unsigned long *src2, int nbits)
+{
+	if (small_const_nbits(nbits))
+		*dst = *src1 | *src2;
+	else
+		__bitmap_or(dst, src1, src2, nbits);
+}
+
+static inline void bitmap_xor(unsigned long *dst, const unsigned long *src1,
+			const unsigned long *src2, int nbits)
+{
+	if (small_const_nbits(nbits))
+		*dst = *src1 ^ *src2;
+	else
+		__bitmap_xor(dst, src1, src2, nbits);
+}
+
+static inline int bitmap_andnot(unsigned long *dst, const unsigned long *src1,
+			const unsigned long *src2, int nbits)
+{
+	if (small_const_nbits(nbits))
+		return (*dst = *src1 & ~(*src2)) != 0;
+	return __bitmap_andnot(dst, src1, src2, nbits);
+}
+
+static inline void bitmap_complement(unsigned long *dst, const unsigned long *src,
+			int nbits)
+{
+	if (small_const_nbits(nbits))
+		*dst = ~(*src) & BITMAP_LAST_WORD_MASK(nbits);
+	else
+		__bitmap_complement(dst, src, nbits);
+}
+
+static inline int bitmap_equal(const unsigned long *src1,
+			const unsigned long *src2, int nbits)
+{
+	if (small_const_nbits(nbits))
+		return ! ((*src1 ^ *src2) & BITMAP_LAST_WORD_MASK(nbits));
+	else
+		return __bitmap_equal(src1, src2, nbits);
+}
+
+static inline int bitmap_intersects(const unsigned long *src1,
+			const unsigned long *src2, int nbits)
+{
+	if (small_const_nbits(nbits))
+		return ((*src1 & *src2) & BITMAP_LAST_WORD_MASK(nbits)) != 0;
+	else
+		return __bitmap_intersects(src1, src2, nbits);
+}
+
+static inline int bitmap_subset(const unsigned long *src1,
+			const unsigned long *src2, int nbits)
+{
+	if (small_const_nbits(nbits))
+		return ! ((*src1 & ~(*src2)) & BITMAP_LAST_WORD_MASK(nbits));
+	else
+		return __bitmap_subset(src1, src2, nbits);
+}
+
+static inline int bitmap_empty(const unsigned long *src, int nbits)
+{
+	if (small_const_nbits(nbits))
+		return ! (*src & BITMAP_LAST_WORD_MASK(nbits));
+	else
+		return __bitmap_empty(src, nbits);
+}
+
+static inline int bitmap_full(const unsigned long *src, int nbits)
+{
+	if (small_const_nbits(nbits))
+		return ! (~(*src) & BITMAP_LAST_WORD_MASK(nbits));
+	else
+		return __bitmap_full(src, nbits);
+}
+
+static inline int bitmap_weight(const unsigned long *src, int nbits)
+{
+	if (small_const_nbits(nbits))
+		return hweight_long(*src & BITMAP_LAST_WORD_MASK(nbits));
+	return __bitmap_weight(src, nbits);
+}
+
+static inline void bitmap_shift_right(unsigned long *dst,
+			const unsigned long *src, int n, int nbits)
+{
+	if (small_const_nbits(nbits))
+		*dst = *src >> n;
+	else
+		__bitmap_shift_right(dst, src, n, nbits);
+}
+
+static inline void bitmap_shift_left(unsigned long *dst,
+			const unsigned long *src, int n, int nbits)
+{
+	if (small_const_nbits(nbits))
+		*dst = (*src << n) & BITMAP_LAST_WORD_MASK(nbits);
+	else
+		__bitmap_shift_left(dst, src, n, nbits);
+}
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* __LINUX_BITMAP_H */
diff --git a/include/linux/bitops.h b/include/linux/bitops.h
index 127c1619fe..be5fd38bd5 100644
--- a/include/linux/bitops.h
+++ b/include/linux/bitops.h
@@ -1,15 +1,227 @@
 #ifndef _LINUX_BITOPS_H
 #define _LINUX_BITOPS_H
+#include <asm/types.h>
 
-#ifdef __BAREBOX__
+#ifdef	__KERNEL__
 #define BIT(nr)			(1UL << (nr))
+#define BIT_ULL(nr)		(1ULL << (nr))
 #define BIT_MASK(nr)		(1UL << ((nr) % BITS_PER_LONG))
 #define BIT_WORD(nr)		((nr) / BITS_PER_LONG)
+#define BIT_ULL_MASK(nr)	(1ULL << ((nr) % BITS_PER_LONG_LONG))
+#define BIT_ULL_WORD(nr)	((nr) / BITS_PER_LONG_LONG)
 #define BITS_PER_BYTE		8
 #define BITS_TO_LONGS(nr)	DIV_ROUND_UP(nr, BITS_PER_BYTE * sizeof(long))
 #endif
 
+/*
+ * Create a contiguous bitmask starting at bit position @l and ending at
+ * position @h. For example
+ * GENMASK_ULL(39, 21) gives us the 64bit vector 0x000000ffffe00000.
+ */
+#define GENMASK(h, l)		(((U32_C(1) << ((h) - (l) + 1)) - 1) << (l))
+#define GENMASK_ULL(h, l)	(((U64_C(1) << ((h) - (l) + 1)) - 1) << (l))
+
+extern unsigned int __sw_hweight8(unsigned int w);
+extern unsigned int __sw_hweight16(unsigned int w);
+extern unsigned int __sw_hweight32(unsigned int w);
+extern unsigned long __sw_hweight64(__u64 w);
+
+/*
+ * Include this here because some architectures need generic_ffs/fls in
+ * scope
+ */
 #include <asm/bitops.h>
 
+#define for_each_set_bit(bit, addr, size) \
+	for ((bit) = find_first_bit((addr), (size));		\
+	     (bit) < (size);					\
+	     (bit) = find_next_bit((addr), (size), (bit) + 1))
+
+/* same as for_each_set_bit() but use bit as value to start with */
+#define for_each_set_bit_from(bit, addr, size) \
+	for ((bit) = find_next_bit((addr), (size), (bit));	\
+	     (bit) < (size);					\
+	     (bit) = find_next_bit((addr), (size), (bit) + 1))
+
+#define for_each_clear_bit(bit, addr, size) \
+	for ((bit) = find_first_zero_bit((addr), (size));	\
+	     (bit) < (size);					\
+	     (bit) = find_next_zero_bit((addr), (size), (bit) + 1))
+
+/* same as for_each_clear_bit() but use bit as value to start with */
+#define for_each_clear_bit_from(bit, addr, size) \
+	for ((bit) = find_next_zero_bit((addr), (size), (bit));	\
+	     (bit) < (size);					\
+	     (bit) = find_next_zero_bit((addr), (size), (bit) + 1))
+
+static __inline__ int get_bitmask_order(unsigned int count)
+{
+	int order;
+
+	order = fls(count);
+	return order;	/* We could be slightly more clever with -1 here... */
+}
+
+static __inline__ int get_count_order(unsigned int count)
+{
+	int order;
+
+	order = fls(count) - 1;
+	if (count & (count - 1))
+		order++;
+	return order;
+}
+
+static inline unsigned long hweight_long(unsigned long w)
+{
+	return sizeof(w) == 4 ? hweight32(w) : hweight64(w);
+}
+
+/**
+ * rol64 - rotate a 64-bit value left
+ * @word: value to rotate
+ * @shift: bits to roll
+ */
+static inline __u64 rol64(__u64 word, unsigned int shift)
+{
+	return (word << shift) | (word >> (64 - shift));
+}
+
+/**
+ * ror64 - rotate a 64-bit value right
+ * @word: value to rotate
+ * @shift: bits to roll
+ */
+static inline __u64 ror64(__u64 word, unsigned int shift)
+{
+	return (word >> shift) | (word << (64 - shift));
+}
+
+/**
+ * rol32 - rotate a 32-bit value left
+ * @word: value to rotate
+ * @shift: bits to roll
+ */
+static inline __u32 rol32(__u32 word, unsigned int shift)
+{
+	return (word << shift) | (word >> (32 - shift));
+}
+
+/**
+ * ror32 - rotate a 32-bit value right
+ * @word: value to rotate
+ * @shift: bits to roll
+ */
+static inline __u32 ror32(__u32 word, unsigned int shift)
+{
+	return (word >> shift) | (word << (32 - shift));
+}
+
+/**
+ * rol16 - rotate a 16-bit value left
+ * @word: value to rotate
+ * @shift: bits to roll
+ */
+static inline __u16 rol16(__u16 word, unsigned int shift)
+{
+	return (word << shift) | (word >> (16 - shift));
+}
+
+/**
+ * ror16 - rotate a 16-bit value right
+ * @word: value to rotate
+ * @shift: bits to roll
+ */
+static inline __u16 ror16(__u16 word, unsigned int shift)
+{
+	return (word >> shift) | (word << (16 - shift));
+}
+
+/**
+ * rol8 - rotate an 8-bit value left
+ * @word: value to rotate
+ * @shift: bits to roll
+ */
+static inline __u8 rol8(__u8 word, unsigned int shift)
+{
+	return (word << shift) | (word >> (8 - shift));
+}
+
+/**
+ * ror8 - rotate an 8-bit value right
+ * @word: value to rotate
+ * @shift: bits to roll
+ */
+static inline __u8 ror8(__u8 word, unsigned int shift)
+{
+	return (word >> shift) | (word << (8 - shift));
+}
+
+/**
+ * sign_extend32 - sign extend a 32-bit value using specified bit as sign-bit
+ * @value: value to sign extend
+ * @index: 0 based bit index (0<=index<32) to sign bit
+ */
+static inline __s32 sign_extend32(__u32 value, int index)
+{
+	__u8 shift = 31 - index;
+	return (__s32)(value << shift) >> shift;
+}
+
+static inline unsigned fls_long(unsigned long l)
+{
+	if (sizeof(l) == 4)
+		return fls(l);
+	return fls64(l);
+}
+
+/**
+ * __ffs64 - find first set bit in a 64 bit word
+ * @word: The 64 bit word
+ *
+ * On 64 bit arches this is a synomyn for __ffs
+ * The result is not defined if no bits are set, so check that @word
+ * is non-zero before calling this.
+ */
+static inline unsigned long __ffs64(u64 word)
+{
+#if BITS_PER_LONG == 32
+	if (((u32)word) == 0UL)
+		return __ffs((u32)(word >> 32)) + 32;
+#elif BITS_PER_LONG != 64
+#error BITS_PER_LONG not 32 or 64
+#endif
+	return __ffs((unsigned long)word);
+}
+
+#ifdef __KERNEL__
+
+#ifndef set_mask_bits
+#define set_mask_bits(ptr, _mask, _bits)	\
+({								\
+	const typeof(*ptr) mask = (_mask), bits = (_bits);	\
+	typeof(*ptr) old, new;					\
+								\
+	do {							\
+		old = ACCESS_ONCE(*ptr);			\
+		new = (old & ~mask) | bits;			\
+	} while (cmpxchg(ptr, old, new) != old);		\
+								\
+	new;							\
+})
+#endif
+
+#ifndef find_last_bit
+/**
+ * find_last_bit - find the last set bit in a memory region
+ * @addr: The address to start the search at
+ * @size: The maximum size to search
+ *
+ * Returns the bit number of the first set bit, or size.
+ */
+extern unsigned long find_last_bit(const unsigned long *addr,
+				   unsigned long size);
+#endif
 
+#endif /* __KERNEL__ */
 #endif
diff --git a/include/linux/byteorder/generic.h b/include/linux/byteorder/generic.h
index 2d68d99fa4..e59ba455e3 100644
--- a/include/linux/byteorder/generic.h
+++ b/include/linux/byteorder/generic.h
@@ -175,5 +175,34 @@ extern unsigned short int	htons(unsigned short int);
 
 #endif /* OPTIMIZE */
 
+static inline void le16_add_cpu(__le16 *var, u16 val)
+{
+	*var = cpu_to_le16(le16_to_cpu(*var) + val);
+}
+
+static inline void le32_add_cpu(__le32 *var, u32 val)
+{
+	*var = cpu_to_le32(le32_to_cpu(*var) + val);
+}
+
+static inline void le64_add_cpu(__le64 *var, u64 val)
+{
+	*var = cpu_to_le64(le64_to_cpu(*var) + val);
+}
+
+static inline void be16_add_cpu(__be16 *var, u16 val)
+{
+	*var = cpu_to_be16(be16_to_cpu(*var) + val);
+}
+
+static inline void be32_add_cpu(__be32 *var, u32 val)
+{
+	*var = cpu_to_be32(be32_to_cpu(*var) + val);
+}
+
+static inline void be64_add_cpu(__be64 *var, u64 val)
+{
+	*var = cpu_to_be64(be64_to_cpu(*var) + val);
+}
 
 #endif /* _LINUX_BYTEORDER_GENERIC_H */
diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index c5ba99fe0a..d512adcea1 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -5,6 +5,19 @@
 #include <linux/barebox-wrapper.h>
 
 /*
+ * This looks more complex than it should be. But we need to
+ * get the type for the ~ right in round_down (it needs to be
+ * as wide as the result!), and we want to evaluate the macro
+ * arguments just once each.
+ *
+ * NOTE these functions only round to power-of-2 arguments. Use
+ * roundup/rounddown for non power-of-2-arguments.
+ */
+#define __round_mask(x, y) ((__typeof__(x))((y)-1))
+#define round_up(x, y) ((((x)-1) | __round_mask(x, y))+1)
+#define round_down(x, y) ((x) & ~__round_mask(x, y))
+
+/*
  * min()/max()/clamp() macros that also do
  * strict type-checking.. See the
  * "unnecessary" pointer comparison.
diff --git a/include/linux/types.h b/include/linux/types.h
index 14f8315410..c11e148c90 100644
--- a/include/linux/types.h
+++ b/include/linux/types.h
@@ -4,6 +4,9 @@
 #include <linux/posix_types.h>
 #include <asm/types.h>
 
+#define DECLARE_BITMAP(name,bits) \
+	unsigned long name[BITS_TO_LONGS(bits)]
+
 #ifndef __KERNEL_STRICT_NAMES
 
 typedef __u32 __kernel_dev_t;
diff --git a/include/malloc.h b/include/malloc.h
index 7b9b062ada..a36f3c0de4 100644
--- a/include/malloc.h
+++ b/include/malloc.h
@@ -3,22 +3,12 @@
 
 #include <types.h>
 
-/* Public routines */
-
-void* malloc(size_t);
-void free(void*);
-void* realloc(void*, size_t);
-void* memalign(size_t, size_t);
-void* vallocc(size_t);
-void* pvalloc(size_t);
-void* calloc(size_t, size_t);
-void cfree(void*);
-int malloc_trim(size_t);
-size_t malloc_usable_size(void*);
+void *malloc(size_t);
+void free(void *);
+void *realloc(void *, size_t);
+void *memalign(size_t, size_t);
+void *calloc(size_t, size_t);
 void malloc_stats(void);
-int mallopt(int, int);
-struct mallinfo mallinfo(void);
 void *sbrk(ptrdiff_t increment);
 
-#endif
-
+#endif /* __MALLOC_H */
diff --git a/include/printk.h b/include/printk.h
index f550f07bb8..454315632b 100644
--- a/include/printk.h
+++ b/include/printk.h
@@ -9,8 +9,11 @@
 #define MSG_NOTICE     5    /* normal but significant condition */
 #define MSG_INFO       6    /* informational */
 #define MSG_DEBUG      7    /* debug-level messages */
+#define MSG_VDEBUG     8    /* verbose debug messages */
 
-#ifdef DEBUG
+#ifdef VERBOSE_DEBUG
+#define LOGLEVEL	MSG_VDEBUG
+#elif defined DEBUG
 #define LOGLEVEL	MSG_DEBUG
 #else
 #define LOGLEVEL	CONFIG_COMPILE_LOGLEVEL
@@ -46,6 +49,8 @@ int dev_printf(int level, const struct device_d *dev, const char *format, ...)
 	__dev_printf(6, (dev) , format , ## arg)
 #define dev_dbg(dev, format, arg...)		\
 	__dev_printf(7, (dev) , format , ## arg)
+#define dev_vdbg(dev, format, arg...)		\
+	__dev_printf(8, (dev) , format , ## arg)
 
 #define __pr_printk(level, format, args...) \
 	({	\
@@ -65,5 +70,6 @@ int dev_printf(int level, const struct device_d *dev, const char *format, ...)
 #define pr_info(fmt, arg...)	__pr_printk(6, pr_fmt(fmt), ##arg)
 #define pr_debug(fmt, arg...)	__pr_printk(7, pr_fmt(fmt), ##arg)
 #define debug(fmt, arg...)	__pr_printk(7, pr_fmt(fmt), ##arg)
+#define pr_vdebug(fmt, arg...)	__pr_printk(8, pr_fmt(fmt), ##arg)
 
 #endif
diff --git a/lib/Makefile b/lib/Makefile
index a75653fb48..77207dc773 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -45,3 +45,4 @@ obj-y			+= unlink-recursive.o
 obj-$(CONFIG_STMP_DEVICE) += stmp-device.o
 obj-y			+= wchar.o
 obj-y			+= libfile.o
+obj-y			+= bitmap.o
diff --git a/lib/bitmap.c b/lib/bitmap.c
new file mode 100644
index 0000000000..5be6651941
--- /dev/null
+++ b/lib/bitmap.c
@@ -0,0 +1,839 @@
+/*
+ * lib/bitmap.c
+ * Helper functions for bitmap.h.
+ *
+ * This source code is licensed under the GNU General Public License,
+ * Version 2.  See the file COPYING for more details.
+ */
+#include <common.h>
+#include <linux/ctype.h>
+#include <linux/bitmap.h>
+#include <linux/bitops.h>
+
+/*
+ * bitmaps provide an array of bits, implemented using an an
+ * array of unsigned longs.  The number of valid bits in a
+ * given bitmap does _not_ need to be an exact multiple of
+ * BITS_PER_LONG.
+ *
+ * The possible unused bits in the last, partially used word
+ * of a bitmap are 'don't care'.  The implementation makes
+ * no particular effort to keep them zero.  It ensures that
+ * their value will not affect the results of any operation.
+ * The bitmap operations that return Boolean (bitmap_empty,
+ * for example) or scalar (bitmap_weight, for example) results
+ * carefully filter out these unused bits from impacting their
+ * results.
+ *
+ * These operations actually hold to a slightly stronger rule:
+ * if you don't input any bitmaps to these ops that have some
+ * unused bits set, then they won't output any set unused bits
+ * in output bitmaps.
+ *
+ * The byte ordering of bitmaps is more natural on little
+ * endian architectures.  See the big-endian headers
+ * include/asm-ppc64/bitops.h and include/asm-s390/bitops.h
+ * for the best explanations of this ordering.
+ */
+
+int __bitmap_empty(const unsigned long *bitmap, int bits)
+{
+	int k, lim = bits/BITS_PER_LONG;
+	for (k = 0; k < lim; ++k)
+		if (bitmap[k])
+			return 0;
+
+	if (bits % BITS_PER_LONG)
+		if (bitmap[k] & BITMAP_LAST_WORD_MASK(bits))
+			return 0;
+
+	return 1;
+}
+EXPORT_SYMBOL(__bitmap_empty);
+
+int __bitmap_full(const unsigned long *bitmap, int bits)
+{
+	int k, lim = bits/BITS_PER_LONG;
+	for (k = 0; k < lim; ++k)
+		if (~bitmap[k])
+			return 0;
+
+	if (bits % BITS_PER_LONG)
+		if (~bitmap[k] & BITMAP_LAST_WORD_MASK(bits))
+			return 0;
+
+	return 1;
+}
+EXPORT_SYMBOL(__bitmap_full);
+
+int __bitmap_equal(const unsigned long *bitmap1,
+		const unsigned long *bitmap2, int bits)
+{
+	int k, lim = bits/BITS_PER_LONG;
+	for (k = 0; k < lim; ++k)
+		if (bitmap1[k] != bitmap2[k])
+			return 0;
+
+	if (bits % BITS_PER_LONG)
+		if ((bitmap1[k] ^ bitmap2[k]) & BITMAP_LAST_WORD_MASK(bits))
+			return 0;
+
+	return 1;
+}
+EXPORT_SYMBOL(__bitmap_equal);
+
+void __bitmap_complement(unsigned long *dst, const unsigned long *src, int bits)
+{
+	int k, lim = bits/BITS_PER_LONG;
+	for (k = 0; k < lim; ++k)
+		dst[k] = ~src[k];
+
+	if (bits % BITS_PER_LONG)
+		dst[k] = ~src[k] & BITMAP_LAST_WORD_MASK(bits);
+}
+EXPORT_SYMBOL(__bitmap_complement);
+
+/**
+ * __bitmap_shift_right - logical right shift of the bits in a bitmap
+ *   @dst : destination bitmap
+ *   @src : source bitmap
+ *   @shift : shift by this many bits
+ *   @bits : bitmap size, in bits
+ *
+ * Shifting right (dividing) means moving bits in the MS -> LS bit
+ * direction.  Zeros are fed into the vacated MS positions and the
+ * LS bits shifted off the bottom are lost.
+ */
+void __bitmap_shift_right(unsigned long *dst,
+			const unsigned long *src, int shift, int bits)
+{
+	int k, lim = BITS_TO_LONGS(bits), left = bits % BITS_PER_LONG;
+	int off = shift/BITS_PER_LONG, rem = shift % BITS_PER_LONG;
+	unsigned long mask = (1UL << left) - 1;
+	for (k = 0; off + k < lim; ++k) {
+		unsigned long upper, lower;
+
+		/*
+		 * If shift is not word aligned, take lower rem bits of
+		 * word above and make them the top rem bits of result.
+		 */
+		if (!rem || off + k + 1 >= lim)
+			upper = 0;
+		else {
+			upper = src[off + k + 1];
+			if (off + k + 1 == lim - 1 && left)
+				upper &= mask;
+		}
+		lower = src[off + k];
+		if (left && off + k == lim - 1)
+			lower &= mask;
+		dst[k] = upper << (BITS_PER_LONG - rem) | lower >> rem;
+		if (left && k == lim - 1)
+			dst[k] &= mask;
+	}
+	if (off)
+		memset(&dst[lim - off], 0, off*sizeof(unsigned long));
+}
+EXPORT_SYMBOL(__bitmap_shift_right);
+
+
+/**
+ * __bitmap_shift_left - logical left shift of the bits in a bitmap
+ *   @dst : destination bitmap
+ *   @src : source bitmap
+ *   @shift : shift by this many bits
+ *   @bits : bitmap size, in bits
+ *
+ * Shifting left (multiplying) means moving bits in the LS -> MS
+ * direction.  Zeros are fed into the vacated LS bit positions
+ * and those MS bits shifted off the top are lost.
+ */
+
+void __bitmap_shift_left(unsigned long *dst,
+			const unsigned long *src, int shift, int bits)
+{
+	int k, lim = BITS_TO_LONGS(bits), left = bits % BITS_PER_LONG;
+	int off = shift/BITS_PER_LONG, rem = shift % BITS_PER_LONG;
+	for (k = lim - off - 1; k >= 0; --k) {
+		unsigned long upper, lower;
+
+		/*
+		 * If shift is not word aligned, take upper rem bits of
+		 * word below and make them the bottom rem bits of result.
+		 */
+		if (rem && k > 0)
+			lower = src[k - 1];
+		else
+			lower = 0;
+		upper = src[k];
+		if (left && k == lim - 1)
+			upper &= (1UL << left) - 1;
+		dst[k + off] = lower  >> (BITS_PER_LONG - rem) | upper << rem;
+		if (left && k + off == lim - 1)
+			dst[k + off] &= (1UL << left) - 1;
+	}
+	if (off)
+		memset(dst, 0, off*sizeof(unsigned long));
+}
+EXPORT_SYMBOL(__bitmap_shift_left);
+
+int __bitmap_and(unsigned long *dst, const unsigned long *bitmap1,
+				const unsigned long *bitmap2, int bits)
+{
+	int k;
+	int nr = BITS_TO_LONGS(bits);
+	unsigned long result = 0;
+
+	for (k = 0; k < nr; k++)
+		result |= (dst[k] = bitmap1[k] & bitmap2[k]);
+	return result != 0;
+}
+EXPORT_SYMBOL(__bitmap_and);
+
+void __bitmap_or(unsigned long *dst, const unsigned long *bitmap1,
+				const unsigned long *bitmap2, int bits)
+{
+	int k;
+	int nr = BITS_TO_LONGS(bits);
+
+	for (k = 0; k < nr; k++)
+		dst[k] = bitmap1[k] | bitmap2[k];
+}
+EXPORT_SYMBOL(__bitmap_or);
+
+void __bitmap_xor(unsigned long *dst, const unsigned long *bitmap1,
+				const unsigned long *bitmap2, int bits)
+{
+	int k;
+	int nr = BITS_TO_LONGS(bits);
+
+	for (k = 0; k < nr; k++)
+		dst[k] = bitmap1[k] ^ bitmap2[k];
+}
+EXPORT_SYMBOL(__bitmap_xor);
+
+int __bitmap_andnot(unsigned long *dst, const unsigned long *bitmap1,
+				const unsigned long *bitmap2, int bits)
+{
+	int k;
+	int nr = BITS_TO_LONGS(bits);
+	unsigned long result = 0;
+
+	for (k = 0; k < nr; k++)
+		result |= (dst[k] = bitmap1[k] & ~bitmap2[k]);
+	return result != 0;
+}
+EXPORT_SYMBOL(__bitmap_andnot);
+
+int __bitmap_intersects(const unsigned long *bitmap1,
+				const unsigned long *bitmap2, int bits)
+{
+	int k, lim = bits/BITS_PER_LONG;
+	for (k = 0; k < lim; ++k)
+		if (bitmap1[k] & bitmap2[k])
+			return 1;
+
+	if (bits % BITS_PER_LONG)
+		if ((bitmap1[k] & bitmap2[k]) & BITMAP_LAST_WORD_MASK(bits))
+			return 1;
+	return 0;
+}
+EXPORT_SYMBOL(__bitmap_intersects);
+
+int __bitmap_subset(const unsigned long *bitmap1,
+				const unsigned long *bitmap2, int bits)
+{
+	int k, lim = bits/BITS_PER_LONG;
+	for (k = 0; k < lim; ++k)
+		if (bitmap1[k] & ~bitmap2[k])
+			return 0;
+
+	if (bits % BITS_PER_LONG)
+		if ((bitmap1[k] & ~bitmap2[k]) & BITMAP_LAST_WORD_MASK(bits))
+			return 0;
+	return 1;
+}
+EXPORT_SYMBOL(__bitmap_subset);
+
+int __bitmap_weight(const unsigned long *bitmap, int bits)
+{
+	int k, w = 0, lim = bits/BITS_PER_LONG;
+
+	for (k = 0; k < lim; k++)
+		w += hweight_long(bitmap[k]);
+
+	if (bits % BITS_PER_LONG)
+		w += hweight_long(bitmap[k] & BITMAP_LAST_WORD_MASK(bits));
+
+	return w;
+}
+EXPORT_SYMBOL(__bitmap_weight);
+
+void bitmap_set(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) {
+		*p |= mask_to_set;
+		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);
+		*p |= mask_to_set;
+	}
+}
+EXPORT_SYMBOL(bitmap_set);
+
+void bitmap_clear(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) {
+		*p &= ~mask_to_clear;
+		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);
+		*p &= ~mask_to_clear;
+	}
+}
+EXPORT_SYMBOL(bitmap_clear);
+
+/*
+ * bitmap_find_next_zero_area - find a contiguous aligned zero area
+ * @map: The address to base the search on
+ * @size: The bitmap size in bits
+ * @start: The bitnumber to start searching at
+ * @nr: The number of zeroed bits we're looking for
+ * @align_mask: Alignment mask for zero area
+ *
+ * The @align_mask should be one less than a power of 2; the effect is that
+ * the bit offset of all zero areas this function finds is multiples of that
+ * power of 2. A @align_mask of 0 means no alignment is required.
+ */
+unsigned long bitmap_find_next_zero_area(unsigned long *map,
+					 unsigned long size,
+					 unsigned long start,
+					 unsigned int nr,
+					 unsigned long align_mask)
+{
+	unsigned long index, end, i;
+again:
+	index = find_next_zero_bit(map, size, start);
+
+	/* Align allocation */
+	index = __ALIGN_MASK(index, align_mask);
+
+	end = index + nr;
+	if (end > size)
+		return end;
+	i = find_next_bit(map, end, index);
+	if (i < end) {
+		start = i + 1;
+		goto again;
+	}
+	return index;
+}
+EXPORT_SYMBOL(bitmap_find_next_zero_area);
+
+/*
+ * Bitmap printing & parsing functions: first version by Nadia Yvette Chambers,
+ * second version by Paul Jackson, third by Joe Korty.
+ */
+
+#define CHUNKSZ				32
+#define nbits_to_hold_value(val)	fls(val)
+#define BASEDEC 10		/* fancier cpuset lists input in decimal */
+
+/**
+ * bitmap_pos_to_ord - find ordinal of set bit at given position in bitmap
+ *	@buf: pointer to a bitmap
+ *	@pos: a bit position in @buf (0 <= @pos < @bits)
+ *	@bits: number of valid bit positions in @buf
+ *
+ * Map the bit at position @pos in @buf (of length @bits) to the
+ * ordinal of which set bit it is.  If it is not set or if @pos
+ * is not a valid bit position, map to -1.
+ *
+ * If for example, just bits 4 through 7 are set in @buf, then @pos
+ * values 4 through 7 will get mapped to 0 through 3, respectively,
+ * and other @pos values will get mapped to 0.  When @pos value 7
+ * gets mapped to (returns) @ord value 3 in this example, that means
+ * that bit 7 is the 3rd (starting with 0th) set bit in @buf.
+ *
+ * The bit positions 0 through @bits are valid positions in @buf.
+ */
+static int bitmap_pos_to_ord(const unsigned long *buf, int pos, int bits)
+{
+	int i, ord;
+
+	if (pos < 0 || pos >= bits || !test_bit(pos, buf))
+		return -1;
+
+	i = find_first_bit(buf, bits);
+	ord = 0;
+	while (i < pos) {
+		i = find_next_bit(buf, bits, i + 1);
+		ord++;
+	}
+	BUG_ON(i != pos);
+
+	return ord;
+}
+
+/**
+ * bitmap_ord_to_pos - find position of n-th set bit in bitmap
+ *	@buf: pointer to bitmap
+ *	@ord: ordinal bit position (n-th set bit, n >= 0)
+ *	@bits: number of valid bit positions in @buf
+ *
+ * Map the ordinal offset of bit @ord in @buf to its position in @buf.
+ * Value of @ord should be in range 0 <= @ord < weight(buf), else
+ * results are undefined.
+ *
+ * If for example, just bits 4 through 7 are set in @buf, then @ord
+ * values 0 through 3 will get mapped to 4 through 7, respectively,
+ * and all other @ord values return undefined values.  When @ord value 3
+ * gets mapped to (returns) @pos value 7 in this example, that means
+ * that the 3rd set bit (starting with 0th) is at position 7 in @buf.
+ *
+ * The bit positions 0 through @bits are valid positions in @buf.
+ */
+int bitmap_ord_to_pos(const unsigned long *buf, int ord, int bits)
+{
+	int pos = 0;
+
+	if (ord >= 0 && ord < bits) {
+		int i;
+
+		for (i = find_first_bit(buf, bits);
+		     i < bits && ord > 0;
+		     i = find_next_bit(buf, bits, i + 1))
+			ord--;
+		if (i < bits && ord == 0)
+			pos = i;
+	}
+
+	return pos;
+}
+
+/**
+ * bitmap_remap - Apply map defined by a pair of bitmaps to another bitmap
+ *	@dst: remapped result
+ *	@src: subset to be remapped
+ *	@old: defines domain of map
+ *	@new: defines range of map
+ *	@bits: number of bits in each of these bitmaps
+ *
+ * Let @old and @new define a mapping of bit positions, such that
+ * whatever position is held by the n-th set bit in @old is mapped
+ * to the n-th set bit in @new.  In the more general case, allowing
+ * for the possibility that the weight 'w' of @new is less than the
+ * weight of @old, map the position of the n-th set bit in @old to
+ * the position of the m-th set bit in @new, where m == n % w.
+ *
+ * If either of the @old and @new bitmaps are empty, or if @src and
+ * @dst point to the same location, then this routine copies @src
+ * to @dst.
+ *
+ * The positions of unset bits in @old are mapped to themselves
+ * (the identify map).
+ *
+ * Apply the above specified mapping to @src, placing the result in
+ * @dst, clearing any bits previously set in @dst.
+ *
+ * For example, lets say that @old has bits 4 through 7 set, and
+ * @new has bits 12 through 15 set.  This defines the mapping of bit
+ * position 4 to 12, 5 to 13, 6 to 14 and 7 to 15, and of all other
+ * bit positions unchanged.  So if say @src comes into this routine
+ * with bits 1, 5 and 7 set, then @dst should leave with bits 1,
+ * 13 and 15 set.
+ */
+void bitmap_remap(unsigned long *dst, const unsigned long *src,
+		const unsigned long *old, const unsigned long *new,
+		int bits)
+{
+	int oldbit, w;
+
+	if (dst == src)		/* following doesn't handle inplace remaps */
+		return;
+	bitmap_zero(dst, bits);
+
+	w = bitmap_weight(new, bits);
+	for_each_set_bit(oldbit, src, bits) {
+		int n = bitmap_pos_to_ord(old, oldbit, bits);
+
+		if (n < 0 || w == 0)
+			set_bit(oldbit, dst);	/* identity map */
+		else
+			set_bit(bitmap_ord_to_pos(new, n % w, bits), dst);
+	}
+}
+EXPORT_SYMBOL(bitmap_remap);
+
+/**
+ * bitmap_bitremap - Apply map defined by a pair of bitmaps to a single bit
+ *	@oldbit: bit position to be mapped
+ *	@old: defines domain of map
+ *	@new: defines range of map
+ *	@bits: number of bits in each of these bitmaps
+ *
+ * Let @old and @new define a mapping of bit positions, such that
+ * whatever position is held by the n-th set bit in @old is mapped
+ * to the n-th set bit in @new.  In the more general case, allowing
+ * for the possibility that the weight 'w' of @new is less than the
+ * weight of @old, map the position of the n-th set bit in @old to
+ * the position of the m-th set bit in @new, where m == n % w.
+ *
+ * The positions of unset bits in @old are mapped to themselves
+ * (the identify map).
+ *
+ * Apply the above specified mapping to bit position @oldbit, returning
+ * the new bit position.
+ *
+ * For example, lets say that @old has bits 4 through 7 set, and
+ * @new has bits 12 through 15 set.  This defines the mapping of bit
+ * position 4 to 12, 5 to 13, 6 to 14 and 7 to 15, and of all other
+ * bit positions unchanged.  So if say @oldbit is 5, then this routine
+ * returns 13.
+ */
+int bitmap_bitremap(int oldbit, const unsigned long *old,
+				const unsigned long *new, int bits)
+{
+	int w = bitmap_weight(new, bits);
+	int n = bitmap_pos_to_ord(old, oldbit, bits);
+	if (n < 0 || w == 0)
+		return oldbit;
+	else
+		return bitmap_ord_to_pos(new, n % w, bits);
+}
+EXPORT_SYMBOL(bitmap_bitremap);
+
+/**
+ * bitmap_onto - translate one bitmap relative to another
+ *	@dst: resulting translated bitmap
+ * 	@orig: original untranslated bitmap
+ * 	@relmap: bitmap relative to which translated
+ *	@bits: number of bits in each of these bitmaps
+ *
+ * Set the n-th bit of @dst iff there exists some m such that the
+ * n-th bit of @relmap is set, the m-th bit of @orig is set, and
+ * the n-th bit of @relmap is also the m-th _set_ bit of @relmap.
+ * (If you understood the previous sentence the first time your
+ * read it, you're overqualified for your current job.)
+ *
+ * In other words, @orig is mapped onto (surjectively) @dst,
+ * using the the map { <n, m> | the n-th bit of @relmap is the
+ * m-th set bit of @relmap }.
+ *
+ * Any set bits in @orig above bit number W, where W is the
+ * weight of (number of set bits in) @relmap are mapped nowhere.
+ * In particular, if for all bits m set in @orig, m >= W, then
+ * @dst will end up empty.  In situations where the possibility
+ * of such an empty result is not desired, one way to avoid it is
+ * to use the bitmap_fold() operator, below, to first fold the
+ * @orig bitmap over itself so that all its set bits x are in the
+ * range 0 <= x < W.  The bitmap_fold() operator does this by
+ * setting the bit (m % W) in @dst, for each bit (m) set in @orig.
+ *
+ * Example [1] for bitmap_onto():
+ *  Let's say @relmap has bits 30-39 set, and @orig has bits
+ *  1, 3, 5, 7, 9 and 11 set.  Then on return from this routine,
+ *  @dst will have bits 31, 33, 35, 37 and 39 set.
+ *
+ *  When bit 0 is set in @orig, it means turn on the bit in
+ *  @dst corresponding to whatever is the first bit (if any)
+ *  that is turned on in @relmap.  Since bit 0 was off in the
+ *  above example, we leave off that bit (bit 30) in @dst.
+ *
+ *  When bit 1 is set in @orig (as in the above example), it
+ *  means turn on the bit in @dst corresponding to whatever
+ *  is the second bit that is turned on in @relmap.  The second
+ *  bit in @relmap that was turned on in the above example was
+ *  bit 31, so we turned on bit 31 in @dst.
+ *
+ *  Similarly, we turned on bits 33, 35, 37 and 39 in @dst,
+ *  because they were the 4th, 6th, 8th and 10th set bits
+ *  set in @relmap, and the 4th, 6th, 8th and 10th bits of
+ *  @orig (i.e. bits 3, 5, 7 and 9) were also set.
+ *
+ *  When bit 11 is set in @orig, it means turn on the bit in
+ *  @dst corresponding to whatever is the twelfth bit that is
+ *  turned on in @relmap.  In the above example, there were
+ *  only ten bits turned on in @relmap (30..39), so that bit
+ *  11 was set in @orig had no affect on @dst.
+ *
+ * Example [2] for bitmap_fold() + bitmap_onto():
+ *  Let's say @relmap has these ten bits set:
+ *		40 41 42 43 45 48 53 61 74 95
+ *  (for the curious, that's 40 plus the first ten terms of the
+ *  Fibonacci sequence.)
+ *
+ *  Further lets say we use the following code, invoking
+ *  bitmap_fold() then bitmap_onto, as suggested above to
+ *  avoid the possitility of an empty @dst result:
+ *
+ *	unsigned long *tmp;	// a temporary bitmap's bits
+ *
+ *	bitmap_fold(tmp, orig, bitmap_weight(relmap, bits), bits);
+ *	bitmap_onto(dst, tmp, relmap, bits);
+ *
+ *  Then this table shows what various values of @dst would be, for
+ *  various @orig's.  I list the zero-based positions of each set bit.
+ *  The tmp column shows the intermediate result, as computed by
+ *  using bitmap_fold() to fold the @orig bitmap modulo ten
+ *  (the weight of @relmap).
+ *
+ *      @orig           tmp            @dst
+ *      0                0             40
+ *      1                1             41
+ *      9                9             95
+ *      10               0             40 (*)
+ *      1 3 5 7          1 3 5 7       41 43 48 61
+ *      0 1 2 3 4        0 1 2 3 4     40 41 42 43 45
+ *      0 9 18 27        0 9 8 7       40 61 74 95
+ *      0 10 20 30       0             40
+ *      0 11 22 33       0 1 2 3       40 41 42 43
+ *      0 12 24 36       0 2 4 6       40 42 45 53
+ *      78 102 211       1 2 8         41 42 74 (*)
+ *
+ * (*) For these marked lines, if we hadn't first done bitmap_fold()
+ *     into tmp, then the @dst result would have been empty.
+ *
+ * If either of @orig or @relmap is empty (no set bits), then @dst
+ * will be returned empty.
+ *
+ * If (as explained above) the only set bits in @orig are in positions
+ * m where m >= W, (where W is the weight of @relmap) then @dst will
+ * once again be returned empty.
+ *
+ * All bits in @dst not set by the above rule are cleared.
+ */
+void bitmap_onto(unsigned long *dst, const unsigned long *orig,
+			const unsigned long *relmap, int bits)
+{
+	int n, m;       	/* same meaning as in above comment */
+
+	if (dst == orig)	/* following doesn't handle inplace mappings */
+		return;
+	bitmap_zero(dst, bits);
+
+	/*
+	 * The following code is a more efficient, but less
+	 * obvious, equivalent to the loop:
+	 *	for (m = 0; m < bitmap_weight(relmap, bits); m++) {
+	 *		n = bitmap_ord_to_pos(orig, m, bits);
+	 *		if (test_bit(m, orig))
+	 *			set_bit(n, dst);
+	 *	}
+	 */
+
+	m = 0;
+	for_each_set_bit(n, relmap, bits) {
+		/* m == bitmap_pos_to_ord(relmap, n, bits) */
+		if (test_bit(m, orig))
+			set_bit(n, dst);
+		m++;
+	}
+}
+EXPORT_SYMBOL(bitmap_onto);
+
+/**
+ * bitmap_fold - fold larger bitmap into smaller, modulo specified size
+ *	@dst: resulting smaller bitmap
+ *	@orig: original larger bitmap
+ *	@sz: specified size
+ *	@bits: number of bits in each of these bitmaps
+ *
+ * For each bit oldbit in @orig, set bit oldbit mod @sz in @dst.
+ * Clear all other bits in @dst.  See further the comment and
+ * Example [2] for bitmap_onto() for why and how to use this.
+ */
+void bitmap_fold(unsigned long *dst, const unsigned long *orig,
+			int sz, int bits)
+{
+	int oldbit;
+
+	if (dst == orig)	/* following doesn't handle inplace mappings */
+		return;
+	bitmap_zero(dst, bits);
+
+	for_each_set_bit(oldbit, orig, bits)
+		set_bit(oldbit % sz, dst);
+}
+EXPORT_SYMBOL(bitmap_fold);
+
+/*
+ * Common code for bitmap_*_region() routines.
+ *	bitmap: array of unsigned longs corresponding to the bitmap
+ *	pos: the beginning of the region
+ *	order: region size (log base 2 of number of bits)
+ *	reg_op: operation(s) to perform on that region of bitmap
+ *
+ * Can set, verify and/or release a region of bits in a bitmap,
+ * depending on which combination of REG_OP_* flag bits is set.
+ *
+ * A region of a bitmap is a sequence of bits in the bitmap, of
+ * some size '1 << order' (a power of two), aligned to that same
+ * '1 << order' power of two.
+ *
+ * Returns 1 if REG_OP_ISFREE succeeds (region is all zero bits).
+ * Returns 0 in all other cases and reg_ops.
+ */
+
+enum {
+	REG_OP_ISFREE,		/* true if region is all zero bits */
+	REG_OP_ALLOC,		/* set all bits in region */
+	REG_OP_RELEASE,		/* clear all bits in region */
+};
+
+static int __reg_op(unsigned long *bitmap, int pos, int order, int reg_op)
+{
+	int nbits_reg;		/* number of bits in region */
+	int index;		/* index first long of region in bitmap */
+	int offset;		/* bit offset region in bitmap[index] */
+	int nlongs_reg;		/* num longs spanned by region in bitmap */
+	int nbitsinlong;	/* num bits of region in each spanned long */
+	unsigned long mask;	/* bitmask for one long of region */
+	int i;			/* scans bitmap by longs */
+	int ret = 0;		/* return value */
+
+	/*
+	 * Either nlongs_reg == 1 (for small orders that fit in one long)
+	 * or (offset == 0 && mask == ~0UL) (for larger multiword orders.)
+	 */
+	nbits_reg = 1 << order;
+	index = pos / BITS_PER_LONG;
+	offset = pos - (index * BITS_PER_LONG);
+	nlongs_reg = BITS_TO_LONGS(nbits_reg);
+	nbitsinlong = min(nbits_reg,  BITS_PER_LONG);
+
+	/*
+	 * Can't do "mask = (1UL << nbitsinlong) - 1", as that
+	 * overflows if nbitsinlong == BITS_PER_LONG.
+	 */
+	mask = (1UL << (nbitsinlong - 1));
+	mask += mask - 1;
+	mask <<= offset;
+
+	switch (reg_op) {
+	case REG_OP_ISFREE:
+		for (i = 0; i < nlongs_reg; i++) {
+			if (bitmap[index + i] & mask)
+				goto done;
+		}
+		ret = 1;	/* all bits in region free (zero) */
+		break;
+
+	case REG_OP_ALLOC:
+		for (i = 0; i < nlongs_reg; i++)
+			bitmap[index + i] |= mask;
+		break;
+
+	case REG_OP_RELEASE:
+		for (i = 0; i < nlongs_reg; i++)
+			bitmap[index + i] &= ~mask;
+		break;
+	}
+done:
+	return ret;
+}
+
+/**
+ * bitmap_find_free_region - find a contiguous aligned mem region
+ *	@bitmap: array of unsigned longs corresponding to the bitmap
+ *	@bits: number of bits in the bitmap
+ *	@order: region size (log base 2 of number of bits) to find
+ *
+ * Find a region of free (zero) bits in a @bitmap of @bits bits and
+ * allocate them (set them to one).  Only consider regions of length
+ * a power (@order) of two, aligned to that power of two, which
+ * makes the search algorithm much faster.
+ *
+ * Return the bit offset in bitmap of the allocated region,
+ * or -errno on failure.
+ */
+int bitmap_find_free_region(unsigned long *bitmap, int bits, int order)
+{
+	int pos, end;		/* scans bitmap by regions of size order */
+
+	for (pos = 0 ; (end = pos + (1 << order)) <= bits; pos = end) {
+		if (!__reg_op(bitmap, pos, order, REG_OP_ISFREE))
+			continue;
+		__reg_op(bitmap, pos, order, REG_OP_ALLOC);
+		return pos;
+	}
+	return -ENOMEM;
+}
+EXPORT_SYMBOL(bitmap_find_free_region);
+
+/**
+ * bitmap_release_region - release allocated bitmap region
+ *	@bitmap: array of unsigned longs corresponding to the bitmap
+ *	@pos: beginning of bit region to release
+ *	@order: region size (log base 2 of number of bits) to release
+ *
+ * This is the complement to __bitmap_find_free_region() and releases
+ * the found region (by clearing it in the bitmap).
+ *
+ * No return value.
+ */
+void bitmap_release_region(unsigned long *bitmap, int pos, int order)
+{
+	__reg_op(bitmap, pos, order, REG_OP_RELEASE);
+}
+EXPORT_SYMBOL(bitmap_release_region);
+
+/**
+ * bitmap_allocate_region - allocate bitmap region
+ *	@bitmap: array of unsigned longs corresponding to the bitmap
+ *	@pos: beginning of bit region to allocate
+ *	@order: region size (log base 2 of number of bits) to allocate
+ *
+ * Allocate (set bits in) a specified region of a bitmap.
+ *
+ * Return 0 on success, or %-EBUSY if specified region wasn't
+ * free (not all bits were zero).
+ */
+int bitmap_allocate_region(unsigned long *bitmap, int pos, int order)
+{
+	if (!__reg_op(bitmap, pos, order, REG_OP_ISFREE))
+		return -EBUSY;
+	__reg_op(bitmap, pos, order, REG_OP_ALLOC);
+	return 0;
+}
+EXPORT_SYMBOL(bitmap_allocate_region);
+
+/**
+ * bitmap_copy_le - copy a bitmap, putting the bits into little-endian order.
+ * @dst:   destination buffer
+ * @src:   bitmap to copy
+ * @nbits: number of bits in the bitmap
+ *
+ * Require nbits % BITS_PER_LONG == 0.
+ */
+void bitmap_copy_le(void *dst, const unsigned long *src, int nbits)
+{
+	unsigned long *d = dst;
+	int i;
+
+	for (i = 0; i < nbits/BITS_PER_LONG; i++) {
+		if (BITS_PER_LONG == 64)
+			d[i] = cpu_to_le64(src[i]);
+		else
+			d[i] = cpu_to_le32(src[i]);
+	}
+}
+EXPORT_SYMBOL(bitmap_copy_le);
diff --git a/lib/readline.c b/lib/readline.c
index 240a131d96..b70bca8554 100644
--- a/lib/readline.c
+++ b/lib/readline.c
@@ -14,8 +14,6 @@
 		printf ("%.*s", n, str);	\
 	} while (0)
 
-#define MAX_CMDBUF_SIZE		256
-
 #define CTL_BACKSPACE		('\b')
 #define DEL			255
 #define DEL7			127
@@ -25,90 +23,82 @@
 #define getcmd_getch()		getc()
 #define getcmd_cbeep()		getcmd_putch('\a')
 
-#define HIST_MAX		20
-#define HIST_SIZE		MAX_CMDBUF_SIZE
-
-static int hist_max = 0;
-static int hist_add_idx = 0;
-static int hist_cur = -1;
-static unsigned hist_num = 0;
+struct history {
+	char *line;
+	struct list_head list;
+};
 
-static char* hist_list[HIST_MAX];
-static char hist_lines[HIST_MAX][HIST_SIZE];
+static LIST_HEAD(history_list);
 
-#define add_idx_minus_one() ((hist_add_idx == 0) ? hist_max : hist_add_idx-1)
+static struct list_head *history_current;
+static int history_num_entries;
 
-static int hist_init(void)
+static void cread_add_to_hist(char *line)
 {
-	int i;
+	struct history *history;
+	char *newline;
 
-	hist_max = 0;
-	hist_add_idx = 0;
-	hist_cur = -1;
-	hist_num = 0;
+	if (!list_empty(&history_list)) {
+		history = list_last_entry(&history_list, struct history, list);
 
-	for (i = 0; i < HIST_MAX; i++) {
-		hist_list[i] = hist_lines[i];
-		hist_list[i][0] = '\0';
+		if (!strcmp(line, history->line))
+			return;
 	}
-	return 0;
-}
-
-postcore_initcall(hist_init);
 
-static void cread_add_to_hist(char *line)
-{
-	strcpy(hist_list[hist_add_idx], line);
+	newline = strdup(line);
+	if (!newline)
+		return;
 
-	if (++hist_add_idx >= HIST_MAX)
-		hist_add_idx = 0;
+	if (history_num_entries < 32) {
+		history = xzalloc(sizeof(*history));
+		history_num_entries++;
+	} else {
+		history = list_first_entry(&history_list, struct history, list);
+		free(history->line);
+		list_del(&history->list);
+	}
 
-	if (hist_add_idx > hist_max)
-		hist_max = hist_add_idx;
+	history->line = newline;
 
-	hist_num++;
+	list_add_tail(&history->list, &history_list);
 }
 
-static char* hist_prev(void)
+static const char *hist_prev(void)
 {
-	char *ret;
-	int old_cur;
+	struct history *history;
 
-	if (hist_cur < 0)
-		return NULL;
+	if (history_current->prev == &history_list) {
+		history = list_entry(history_current, struct history, list);
+		getcmd_cbeep();
+		return history->line;
+	}
 
-	old_cur = hist_cur;
-	if (--hist_cur < 0)
-		hist_cur = hist_max;
+	history = list_entry(history_current->prev, struct history, list);
 
-	if (hist_cur == hist_add_idx) {
-		hist_cur = old_cur;
-		ret = NULL;
-	} else
-		ret = hist_list[hist_cur];
+	history_current = &history->list;
 
-	return (ret);
+	return history->line;
 }
 
-static char* hist_next(void)
+static const char *hist_next(void)
 {
-	char *ret;
+	struct history *history;
 
-	if (hist_cur < 0)
-		return NULL;
+	if (history_current->next == &history_list) {
+		history_current = &history_list;
+		return "";
+	}
 
-	if (hist_cur == hist_add_idx)
-		return NULL;
+	if (history_current == &history_list) {
+		getcmd_cbeep();
+		return "";
+	}
 
-	if (++hist_cur > hist_max)
-		hist_cur = 0;
+	history = list_entry(history_current->next, struct history, list);
 
-	if (hist_cur == hist_add_idx) {
-		ret = "";
-	} else
-		ret = hist_list[hist_cur];
+	history_current = &history->list;
 
-	return (ret);
+	return history->line;
 }
 
 #define BEGINNING_OF_LINE() {			\
@@ -198,6 +188,8 @@ int readline(const char *prompt, char *buf, int len)
 
 	complete_reset();
 #endif
+	history_current = &history_list;
+
 	puts (prompt);
 
 	while (1) {
@@ -302,18 +294,13 @@ int readline(const char *prompt, char *buf, int len)
 		case BB_KEY_UP:
 		case BB_KEY_DOWN:
 		{
-			char * hline;
+			const char *hline;
 
 			if (ichar == BB_KEY_UP)
 				hline = hist_prev();
 			else
 				hline = hist_next();
 
-			if (!hline) {
-				getcmd_cbeep();
-				continue;
-			}
-
 			/* nuke the current line */
 			/* first, go home */
 			BEGINNING_OF_LINE();
@@ -346,9 +333,8 @@ int readline(const char *prompt, char *buf, int len)
 	len = eol_num;
 	buf[eol_num] = '\0';	/* lose the newline */
 
-	if (buf[0] && buf[0] != CREAD_HIST_CHAR)
+	if (buf[0])
 		cread_add_to_hist(buf);
-	hist_cur = hist_add_idx;
 
 	return len;
 }