Merge branch '2.6.23' into 2.6.22.6-imx27

Conflicts:

	Documentation/kernel-parameters.txt
	Makefile
	arch/arm/Kconfig
	arch/arm/Makefile
	arch/arm/mach-mx3/Kconfig
	arch/arm/mach-mx3/Makefile
	arch/arm/mach-mx3/mm.c
	arch/arm/mach-mx3/mx31ads.c
	arch/arm/mm/Kconfig
	arch/arm/plat-mxc/Kconfig
	arch/arm/plat-mxc/Makefile
	arch/arm/plat-mxc/irq.c
	block/cfq-iosched.c
	drivers/ata/ahci.c
	drivers/ata/libata-core.c
	drivers/char/watchdog/Kconfig
	drivers/firewire/fw-sbp2.c
	drivers/md/dm-crypt.c
	drivers/media/video/pwc/pwc-if.c
	drivers/mmc/card/Kconfig
	drivers/mmc/card/queue.c
	drivers/mmc/core/Makefile
	drivers/mmc/core/bus.c
	drivers/mmc/core/core.c
	drivers/mmc/core/host.c
	drivers/mmc/core/mmc.c
	drivers/mmc/core/sd.c
	drivers/mmc/core/sd_ops.c
	drivers/mmc/host/at91_mci.c
	drivers/mmc/host/sdhci.c
	drivers/net/bonding/bond_main.c
	drivers/net/fec.c
	drivers/net/forcedeth.c
	drivers/net/r8169.c
	drivers/net/sky2.c
	drivers/rtc/Kconfig
	drivers/rtc/Makefile
	drivers/spi/Kconfig
	drivers/spi/Makefile
	drivers/usb/gadget/Makefile
	drivers/usb/gadget/gadget_chips.h
	drivers/usb/host/ehci.h
	drivers/video/logo/logo.c
	drivers/w1/slaves/Makefile
	fs/9p/conv.c
	fs/direct-io.c
	fs/exec.c
	fs/ocfs2/file.c
	fs/signalfd.c
	fs/sysfs/file.c
	include/asm-arm/arch-mxc/dma.h
	include/asm-arm/arch-mxc/entry-macro.S
	include/asm-arm/arch-mxc/hardware.h
	include/asm-arm/arch-mxc/io.h
	include/asm-arm/arch-mxc/irqs.h
	include/asm-arm/arch-mxc/memory.h
	include/asm-arm/arch-mxc/mx31.h
	include/asm-arm/arch-mxc/mxc.h
	include/asm-arm/arch-mxc/system.h
	include/asm-arm/arch-mxc/timex.h
	include/asm-arm/arch-mxc/uncompress.h
	include/asm-arm/arch-mxc/vmalloc.h
	include/linux/fsl_devices.h
	include/linux/ioprio.h
	kernel/lockdep_proc.c
	kernel/signal.c
	mm/hugetlb.c
	mm/readahead.c
	net/bluetooth/rfcomm/tty.c
	net/bridge/br_device.c
	net/core/dev.c
	net/ieee80211/softmac/ieee80211softmac_assoc.c
	net/ieee80211/softmac/ieee80211softmac_wx.c
	net/ipv4/netfilter/nf_conntrack_proto_icmp.c
	net/ipv4/tcp_input.c
	net/netfilter/nf_conntrack_proto_sctp.c

23 files changed, 1507 insertions, 132 deletions

diff --git a/lib/Kconfig b/lib/Kconfig
index 2e7ae6b9215b..ba3d104994d9 100644
--- a/lib/Kconfig
+++ b/lib/Kconfig
@@ -41,6 +41,14 @@ config CRC32
 	  kernel tree does. Such modules that use library CRC32 functions
 	  require M here.
 
+config CRC7
+	tristate "CRC7 functions"
+	help
+	  This option is provided for the case where no in-kernel-tree
+	  modules require CRC7 functions, but a module built outside
+	  the kernel tree does. Such modules that use library CRC7
+	  functions require M here.
+
 config LIBCRC32C
 	tristate "CRC32c (Castagnoli, et al) Cyclic Redundancy-Check"
 	help
@@ -64,6 +72,12 @@ config ZLIB_INFLATE
 config ZLIB_DEFLATE
 	tristate
 
+config LZO_COMPRESS
+	tristate
+
+config LZO_DECOMPRESS
+	tristate
+
 #
 # Generic allocator support is selected if needed
 #
@@ -124,4 +138,7 @@ config HAS_DMA
 	depends on !NO_DMA
 	default y
 
+config CHECK_SIGNATURE
+	bool
+
 endmenu
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index da95e10cfd70..cdc9b099e620 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -105,6 +105,15 @@ config DETECT_SOFTLOCKUP
 	   can be detected via the NMI-watchdog, on platforms that
 	   support it.)
 
+config SCHED_DEBUG
+	bool "Collect scheduler debugging info"
+	depends on DEBUG_KERNEL && PROC_FS
+	default y
+	help
+	  If you say Y here, the /proc/sched_debug file will be provided
+	  that can help debug the scheduler. The runtime overhead of this
+	  option is minimal.
+
 config SCHEDSTATS
 	bool "Collect scheduler statistics"
 	depends on DEBUG_KERNEL && PROC_FS
@@ -143,6 +152,19 @@ config DEBUG_SLAB_LEAK
 	bool "Memory leak debugging"
 	depends on DEBUG_SLAB
 
+config SLUB_DEBUG_ON
+	bool "SLUB debugging on by default"
+	depends on SLUB && SLUB_DEBUG
+	default n
+	help
+	  Boot with debugging on by default. SLUB boots by default with
+	  the runtime debug capabilities switched off. Enabling this is
+	  equivalent to specifying the "slub_debug" parameter on boot.
+	  There is no support for more fine grained debug control like
+	  possible with slub_debug=xxx. SLUB debugging may be switched
+	  off in a kernel built with CONFIG_SLUB_DEBUG_ON by specifying
+	  "slub_debug=-".
+
 config DEBUG_PREEMPT
 	bool "Debug preemptible kernel"
 	depends on DEBUG_KERNEL && PREEMPT && TRACE_IRQFLAGS_SUPPORT
@@ -261,6 +283,19 @@ config LOCKDEP
 	select KALLSYMS
 	select KALLSYMS_ALL
 
+config LOCK_STAT
+	bool "Lock usage statistics"
+	depends on DEBUG_KERNEL && TRACE_IRQFLAGS_SUPPORT && STACKTRACE_SUPPORT && LOCKDEP_SUPPORT
+	select LOCKDEP
+	select DEBUG_SPINLOCK
+	select DEBUG_MUTEXES
+	select DEBUG_LOCK_ALLOC
+	default n
+	help
+	 This feature enables tracking lock contention points
+
+	 For more details, see Documentation/lockstat.txt
+
 config DEBUG_LOCKDEP
 	bool "Lock dependency engine debugging"
 	depends on DEBUG_KERNEL && LOCKDEP
@@ -316,7 +351,7 @@ config DEBUG_HIGHMEM
 config DEBUG_BUGVERBOSE
 	bool "Verbose BUG() reporting (adds 70K)" if DEBUG_KERNEL && EMBEDDED
 	depends on BUG
-	depends on ARM || ARM26 || AVR32 || M32R || M68K || SPARC32 || SPARC64 || FRV || SUPERH || GENERIC_BUG || BFIN
+	depends on ARM || AVR32 || M32R || M68K || SPARC32 || SPARC64 || FRV || SUPERH || GENERIC_BUG || BFIN
 	default !EMBEDDED
 	help
 	  Say Y here to make BUG() panics output the file name and line number
diff --git a/lib/Makefile b/lib/Makefile
index c8c8e20784ce..4f3f3e256501 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -5,7 +5,7 @@
 lib-y := ctype.o string.o vsprintf.o cmdline.o \
 	 rbtree.o radix-tree.o dump_stack.o \
 	 idr.o int_sqrt.o bitmap.o extable.o prio_tree.o \
-	 sha1.o irq_regs.o reciprocal_div.o
+	 sha1.o irq_regs.o reciprocal_div.o argv_split.o
 
 lib-$(CONFIG_MMU) += ioremap.o
 lib-$(CONFIG_SMP) += cpumask.o
@@ -13,7 +13,7 @@ lib-$(CONFIG_SMP) += cpumask.o
 lib-y	+= kobject.o kref.o kobject_uevent.o klist.o
 
 obj-y += div64.o sort.o parser.o halfmd4.o debug_locks.o random32.o \
-	 bust_spinlocks.o hexdump.o
+	 bust_spinlocks.o hexdump.o kasprintf.o
 
 ifeq ($(CONFIG_DEBUG_KOBJECT),y)
 CFLAGS_kobject.o += -DDEBUG
@@ -22,6 +22,7 @@ endif
 
 obj-$(CONFIG_GENERIC_IOMAP) += iomap.o
 obj-$(CONFIG_HAS_IOMEM) += iomap_copy.o devres.o
+obj-$(CONFIG_CHECK_SIGNATURE) += check_signature.o
 obj-$(CONFIG_DEBUG_LOCKING_API_SELFTESTS) += locking-selftest.o
 obj-$(CONFIG_DEBUG_SPINLOCK) += spinlock_debug.o
 lib-$(CONFIG_RWSEM_GENERIC_SPINLOCK) += rwsem-spinlock.o
@@ -43,12 +44,15 @@ obj-$(CONFIG_CRC_CCITT)	+= crc-ccitt.o
 obj-$(CONFIG_CRC16)	+= crc16.o
 obj-$(CONFIG_CRC_ITU_T)	+= crc-itu-t.o
 obj-$(CONFIG_CRC32)	+= crc32.o
+obj-$(CONFIG_CRC7)	+= crc7.o
 obj-$(CONFIG_LIBCRC32C)	+= libcrc32c.o
 obj-$(CONFIG_GENERIC_ALLOCATOR) += genalloc.o
 
 obj-$(CONFIG_ZLIB_INFLATE) += zlib_inflate/
 obj-$(CONFIG_ZLIB_DEFLATE) += zlib_deflate/
 obj-$(CONFIG_REED_SOLOMON) += reed_solomon/
+obj-$(CONFIG_LZO_COMPRESS) += lzo/
+obj-$(CONFIG_LZO_DECOMPRESS) += lzo/
 
 obj-$(CONFIG_TEXTSEARCH) += textsearch.o
 obj-$(CONFIG_TEXTSEARCH_KMP) += ts_kmp.o
diff --git a/lib/argv_split.c b/lib/argv_split.c
new file mode 100644
index 000000000000..4096ed42f490
--- /dev/null
+++ b/lib/argv_split.c
@@ -0,0 +1,105 @@
+/*
+ * Helper function for splitting a string into an argv-like array.
+ */
+
+#include <linux/kernel.h>
+#include <linux/ctype.h>
+#include <linux/bug.h>
+
+static const char *skip_sep(const char *cp)
+{
+	while (*cp && isspace(*cp))
+		cp++;
+
+	return cp;
+}
+
+static const char *skip_arg(const char *cp)
+{
+	while (*cp && !isspace(*cp))
+		cp++;
+
+	return cp;
+}
+
+static int count_argc(const char *str)
+{
+	int count = 0;
+
+	while (*str) {
+		str = skip_sep(str);
+		if (*str) {
+			count++;
+			str = skip_arg(str);
+		}
+	}
+
+	return count;
+}
+
+/**
+ * argv_free - free an argv
+ * @argv - the argument vector to be freed
+ *
+ * Frees an argv and the strings it points to.
+ */
+void argv_free(char **argv)
+{
+	char **p;
+	for (p = argv; *p; p++)
+		kfree(*p);
+
+	kfree(argv);
+}
+EXPORT_SYMBOL(argv_free);
+
+/**
+ * argv_split - split a string at whitespace, returning an argv
+ * @gfp: the GFP mask used to allocate memory
+ * @str: the string to be split
+ * @argcp: returned argument count
+ *
+ * Returns an array of pointers to strings which are split out from
+ * @str.  This is performed by strictly splitting on white-space; no
+ * quote processing is performed.  Multiple whitespace characters are
+ * considered to be a single argument separator.  The returned array
+ * is always NULL-terminated.  Returns NULL on memory allocation
+ * failure.
+ */
+char **argv_split(gfp_t gfp, const char *str, int *argcp)
+{
+	int argc = count_argc(str);
+	char **argv = kzalloc(sizeof(*argv) * (argc+1), gfp);
+	char **argvp;
+
+	if (argv == NULL)
+		goto out;
+
+	*argcp = argc;
+	argvp = argv;
+
+	while (*str) {
+		str = skip_sep(str);
+
+		if (*str) {
+			const char *p = str;
+			char *t;
+
+			str = skip_arg(str);
+
+			t = kstrndup(p, str-p, gfp);
+			if (t == NULL)
+				goto fail;
+			*argvp++ = t;
+		}
+	}
+	*argvp = NULL;
+
+  out:
+	return argv;
+
+  fail:
+	argv_free(argv);
+	return NULL;
+}
+EXPORT_SYMBOL(argv_split);
diff --git a/lib/bug.c b/lib/bug.c
index 014b582c5c4b..530f38f55787 100644
--- a/lib/bug.c
+++ b/lib/bug.c
@@ -38,6 +38,7 @@
 #include <linux/list.h>
 #include <linux/module.h>
 #include <linux/bug.h>
+#include <linux/sched.h>
 
 extern const struct bug_entry __start___bug_table[], __stop___bug_table[];
 
@@ -112,7 +113,7 @@ const struct bug_entry *find_bug(unsigned long bugaddr)
 	return module_find_bug(bugaddr);
 }
 
-enum bug_trap_type report_bug(unsigned long bugaddr)
+enum bug_trap_type report_bug(unsigned long bugaddr, struct pt_regs *regs)
 {
 	const struct bug_entry *bug;
 	const char *file;
@@ -147,7 +148,7 @@ enum bug_trap_type report_bug(unsigned long bugaddr)
 			       "[verbose debug info unavailable]\n",
 			       (void *)bugaddr);
 
-		dump_stack();
+		show_regs(regs);
 		return BUG_TRAP_TYPE_WARN;
 	}
 
diff --git a/lib/check_signature.c b/lib/check_signature.c
new file mode 100644
index 000000000000..fd6af199247b
--- /dev/null
+++ b/lib/check_signature.c
@@ -0,0 +1,26 @@
+#include <linux/io.h>
+#include <linux/module.h>
+
+/**
+ *	check_signature		-	find BIOS signatures
+ *	@io_addr: mmio address to check
+ *	@signature:  signature block
+ *	@length: length of signature
+ *
+ *	Perform a signature comparison with the mmio address io_addr. This
+ *	address should have been obtained by ioremap.
+ *	Returns 1 on a match.
+ */
+
+int check_signature(const volatile void __iomem *io_addr,
+			const unsigned char *signature, int length)
+{
+	while (length--) {
+		if (readb(io_addr) != *signature)
+			return 0;
+		io_addr++;
+		signature++;
+	}
+	return 1;
+}
+EXPORT_SYMBOL(check_signature);
diff --git a/lib/crc7.c b/lib/crc7.c
new file mode 100644
index 000000000000..f1c3a144cec1
--- /dev/null
+++ b/lib/crc7.c
@@ -0,0 +1,68 @@
+/*
+ *      crc7.c
+ *
+ * This source code is licensed under the GNU General Public License,
+ * Version 2. See the file COPYING for more details.
+ */
+
+#include <linux/types.h>
+#include <linux/module.h>
+#include <linux/crc7.h>
+
+
+/* Table for CRC-7 (polynomial x^7 + x^3 + 1) */
+const u8 crc7_syndrome_table[256] = {
+	0x00, 0x09, 0x12, 0x1b, 0x24, 0x2d, 0x36, 0x3f,
+	0x48, 0x41, 0x5a, 0x53, 0x6c, 0x65, 0x7e, 0x77,
+	0x19, 0x10, 0x0b, 0x02, 0x3d, 0x34, 0x2f, 0x26,
+	0x51, 0x58, 0x43, 0x4a, 0x75, 0x7c, 0x67, 0x6e,
+	0x32, 0x3b, 0x20, 0x29, 0x16, 0x1f, 0x04, 0x0d,
+	0x7a, 0x73, 0x68, 0x61, 0x5e, 0x57, 0x4c, 0x45,
+	0x2b, 0x22, 0x39, 0x30, 0x0f, 0x06, 0x1d, 0x14,
+	0x63, 0x6a, 0x71, 0x78, 0x47, 0x4e, 0x55, 0x5c,
+	0x64, 0x6d, 0x76, 0x7f, 0x40, 0x49, 0x52, 0x5b,
+	0x2c, 0x25, 0x3e, 0x37, 0x08, 0x01, 0x1a, 0x13,
+	0x7d, 0x74, 0x6f, 0x66, 0x59, 0x50, 0x4b, 0x42,
+	0x35, 0x3c, 0x27, 0x2e, 0x11, 0x18, 0x03, 0x0a,
+	0x56, 0x5f, 0x44, 0x4d, 0x72, 0x7b, 0x60, 0x69,
+	0x1e, 0x17, 0x0c, 0x05, 0x3a, 0x33, 0x28, 0x21,
+	0x4f, 0x46, 0x5d, 0x54, 0x6b, 0x62, 0x79, 0x70,
+	0x07, 0x0e, 0x15, 0x1c, 0x23, 0x2a, 0x31, 0x38,
+	0x41, 0x48, 0x53, 0x5a, 0x65, 0x6c, 0x77, 0x7e,
+	0x09, 0x00, 0x1b, 0x12, 0x2d, 0x24, 0x3f, 0x36,
+	0x58, 0x51, 0x4a, 0x43, 0x7c, 0x75, 0x6e, 0x67,
+	0x10, 0x19, 0x02, 0x0b, 0x34, 0x3d, 0x26, 0x2f,
+	0x73, 0x7a, 0x61, 0x68, 0x57, 0x5e, 0x45, 0x4c,
+	0x3b, 0x32, 0x29, 0x20, 0x1f, 0x16, 0x0d, 0x04,
+	0x6a, 0x63, 0x78, 0x71, 0x4e, 0x47, 0x5c, 0x55,
+	0x22, 0x2b, 0x30, 0x39, 0x06, 0x0f, 0x14, 0x1d,
+	0x25, 0x2c, 0x37, 0x3e, 0x01, 0x08, 0x13, 0x1a,
+	0x6d, 0x64, 0x7f, 0x76, 0x49, 0x40, 0x5b, 0x52,
+	0x3c, 0x35, 0x2e, 0x27, 0x18, 0x11, 0x0a, 0x03,
+	0x74, 0x7d, 0x66, 0x6f, 0x50, 0x59, 0x42, 0x4b,
+	0x17, 0x1e, 0x05, 0x0c, 0x33, 0x3a, 0x21, 0x28,
+	0x5f, 0x56, 0x4d, 0x44, 0x7b, 0x72, 0x69, 0x60,
+	0x0e, 0x07, 0x1c, 0x15, 0x2a, 0x23, 0x38, 0x31,
+	0x46, 0x4f, 0x54, 0x5d, 0x62, 0x6b, 0x70, 0x79
+};
+EXPORT_SYMBOL(crc7_syndrome_table);
+
+/**
+ * crc7 - update the CRC7 for the data buffer
+ * @crc:     previous CRC7 value
+ * @buffer:  data pointer
+ * @len:     number of bytes in the buffer
+ * Context: any
+ *
+ * Returns the updated CRC7 value.
+ */
+u8 crc7(u8 crc, const u8 *buffer, size_t len)
+{
+	while (len--)
+		crc = crc7_byte(crc, *buffer++);
+	return crc;
+}
+EXPORT_SYMBOL(crc7);
+
+MODULE_DESCRIPTION("CRC7 calculations");
+MODULE_LICENSE("GPL");
diff --git a/lib/fault-inject.c b/lib/fault-inject.c
index b18fc2ff9ffe..23985a278bbb 100644
--- a/lib/fault-inject.c
+++ b/lib/fault-inject.c
@@ -139,12 +139,14 @@ static void debugfs_ul_set(void *data, u64 val)
 	*(unsigned long *)data = val;
 }
 
+#ifdef CONFIG_FAULT_INJECTION_STACKTRACE_FILTER
 static void debugfs_ul_set_MAX_STACK_TRACE_DEPTH(void *data, u64 val)
 {
 	*(unsigned long *)data =
 		val < MAX_STACK_TRACE_DEPTH ?
 		val : MAX_STACK_TRACE_DEPTH;
 }
+#endif /* CONFIG_FAULT_INJECTION_STACKTRACE_FILTER */
 
 static u64 debugfs_ul_get(void *data)
 {
@@ -159,6 +161,7 @@ static struct dentry *debugfs_create_ul(const char *name, mode_t mode,
 	return debugfs_create_file(name, mode, parent, value, &fops_ul);
 }
 
+#ifdef CONFIG_FAULT_INJECTION_STACKTRACE_FILTER
 DEFINE_SIMPLE_ATTRIBUTE(fops_ul_MAX_STACK_TRACE_DEPTH, debugfs_ul_get,
 			debugfs_ul_set_MAX_STACK_TRACE_DEPTH, "%llu\n");
 
@@ -169,6 +172,7 @@ static struct dentry *debugfs_create_ul_MAX_STACK_TRACE_DEPTH(
 	return debugfs_create_file(name, mode, parent, value,
 				   &fops_ul_MAX_STACK_TRACE_DEPTH);
 }
+#endif /* CONFIG_FAULT_INJECTION_STACKTRACE_FILTER */
 
 static void debugfs_atomic_t_set(void *data, u64 val)
 {
diff --git a/lib/genalloc.c b/lib/genalloc.c
index eb7c2bab9ebf..f6d276db2d58 100644
--- a/lib/genalloc.c
+++ b/lib/genalloc.c
@@ -54,11 +54,10 @@ int gen_pool_add(struct gen_pool *pool, unsigned long addr, size_t size,
 	int nbytes = sizeof(struct gen_pool_chunk) +
 				(nbits + BITS_PER_BYTE - 1) / BITS_PER_BYTE;
 
-	chunk = kmalloc_node(nbytes, GFP_KERNEL, nid);
+	chunk = kmalloc_node(nbytes, GFP_KERNEL | __GFP_ZERO, nid);
 	if (unlikely(chunk == NULL))
 		return -1;
 
-	memset(chunk, 0, nbytes);
 	spin_lock_init(&chunk->lock);
 	chunk->start_addr = addr;
 	chunk->end_addr = addr + size;
diff --git a/lib/hexdump.c b/lib/hexdump.c
index 473f5aed6cae..bd5edaeaa80b 100644
--- a/lib/hexdump.c
+++ b/lib/hexdump.c
@@ -145,9 +145,9 @@ EXPORT_SYMBOL(hex_dump_to_buffer);
  */
 void print_hex_dump(const char *level, const char *prefix_str, int prefix_type,
 			int rowsize, int groupsize,
-			void *buf, size_t len, bool ascii)
+			const void *buf, size_t len, bool ascii)
 {
-	u8 *ptr = buf;
+	const u8 *ptr = buf;
 	int i, linelen, remaining = len;
 	unsigned char linebuf[200];
 
@@ -189,7 +189,7 @@ EXPORT_SYMBOL(print_hex_dump);
  * rowsize of 16, groupsize of 1, and ASCII output included.
  */
 void print_hex_dump_bytes(const char *prefix_str, int prefix_type,
-			void *buf, size_t len)
+			const void *buf, size_t len)
 {
 	print_hex_dump(KERN_DEBUG, prefix_str, prefix_type, 16, 1,
 			buf, len, 1);
diff --git a/lib/idr.c b/lib/idr.c
index 305117ca2d41..d0f1acdbfa3a 100644
--- a/lib/idr.c
+++ b/lib/idr.c
@@ -70,6 +70,26 @@ static void free_layer(struct idr *idp, struct idr_layer *p)
 	spin_unlock_irqrestore(&idp->lock, flags);
 }
 
+static void idr_mark_full(struct idr_layer **pa, int id)
+{
+	struct idr_layer *p = pa[0];
+	int l = 0;
+
+	__set_bit(id & IDR_MASK, &p->bitmap);
+	/*
+	 * If this layer is full mark the bit in the layer above to
+	 * show that this part of the radix tree is full.  This may
+	 * complete the layer above and require walking up the radix
+	 * tree.
+	 */
+	while (p->bitmap == IDR_FULL) {
+		if (!(p = pa[++l]))
+			break;
+		id = id >> IDR_BITS;
+		__set_bit((id & IDR_MASK), &p->bitmap);
+	}
+}
+
 /**
  * idr_pre_get - reserver resources for idr allocation
  * @idp:	idr handle
@@ -95,15 +115,15 @@ int idr_pre_get(struct idr *idp, gfp_t gfp_mask)
 }
 EXPORT_SYMBOL(idr_pre_get);
 
-static int sub_alloc(struct idr *idp, void *ptr, int *starting_id)
+static int sub_alloc(struct idr *idp, int *starting_id, struct idr_layer **pa)
 {
 	int n, m, sh;
 	struct idr_layer *p, *new;
-	struct idr_layer *pa[MAX_LEVEL];
-	int l, id;
+	int l, id, oid;
 	long bm;
 
 	id = *starting_id;
+ restart:
 	p = idp->top;
 	l = idp->layers;
 	pa[l--] = NULL;
@@ -117,12 +137,23 @@ static int sub_alloc(struct idr *idp, void *ptr, int *starting_id)
 		if (m == IDR_SIZE) {
 			/* no space available go back to previous layer. */
 			l++;
+			oid = id;
 			id = (id | ((1 << (IDR_BITS * l)) - 1)) + 1;
+
+			/* if already at the top layer, we need to grow */
 			if (!(p = pa[l])) {
 				*starting_id = id;
 				return -2;
 			}
-			continue;
+
+			/* If we need to go up one layer, continue the
+			 * loop; otherwise, restart from the top.
+			 */
+			sh = IDR_BITS * (l + 1);
+			if (oid >> sh == id >> sh)
+				continue;
+			else
+				goto restart;
 		}
 		if (m != n) {
 			sh = IDR_BITS*l;
@@ -144,30 +175,13 @@ static int sub_alloc(struct idr *idp, void *ptr, int *starting_id)
 		pa[l--] = p;
 		p = p->ary[m];
 	}
-	/*
-	 * We have reached the leaf node, plant the
-	 * users pointer and return the raw id.
-	 */
-	p->ary[m] = (struct idr_layer *)ptr;
-	__set_bit(m, &p->bitmap);
-	p->count++;
-	/*
-	 * If this layer is full mark the bit in the layer above
-	 * to show that this part of the radix tree is full.
-	 * This may complete the layer above and require walking
-	 * up the radix tree.
-	 */
-	n = id;
-	while (p->bitmap == IDR_FULL) {
-		if (!(p = pa[++l]))
-			break;
-		n = n >> IDR_BITS;
-		__set_bit((n & IDR_MASK), &p->bitmap);
-	}
-	return(id);
+
+	pa[l] = p;
+	return id;
 }
 
-static int idr_get_new_above_int(struct idr *idp, void *ptr, int starting_id)
+static int idr_get_empty_slot(struct idr *idp, int starting_id,
+			      struct idr_layer **pa)
 {
 	struct idr_layer *p, *new;
 	int layers, v, id;
@@ -213,12 +227,31 @@ build_up:
 	}
 	idp->top = p;
 	idp->layers = layers;
-	v = sub_alloc(idp, ptr, &id);
+	v = sub_alloc(idp, &id, pa);
 	if (v == -2)
 		goto build_up;
 	return(v);
 }
 
+static int idr_get_new_above_int(struct idr *idp, void *ptr, int starting_id)
+{
+	struct idr_layer *pa[MAX_LEVEL];
+	int id;
+
+	id = idr_get_empty_slot(idp, starting_id, pa);
+	if (id >= 0) {
+		/*
+		 * Successfully found an empty slot.  Install the user
+		 * pointer and mark the slot full.
+		 */
+		pa[0]->ary[id & IDR_MASK] = (struct idr_layer *)ptr;
+		pa[0]->count++;
+		idr_mark_full(pa, id);
+	}
+
+	return id;
+}
+
 /**
  * idr_get_new_above - allocate new idr entry above or equal to a start id
  * @idp: idr handle
@@ -358,6 +391,53 @@ void idr_remove(struct idr *idp, int id)
 EXPORT_SYMBOL(idr_remove);
 
 /**
+ * idr_remove_all - remove all ids from the given idr tree
+ * @idp: idr handle
+ *
+ * idr_destroy() only frees up unused, cached idp_layers, but this
+ * function will remove all id mappings and leave all idp_layers
+ * unused.
+ *
+ * A typical clean-up sequence for objects stored in an idr tree, will
+ * use idr_for_each() to free all objects, if necessay, then
+ * idr_remove_all() to remove all ids, and idr_destroy() to free
+ * up the cached idr_layers.
+ */
+void idr_remove_all(struct idr *idp)
+{
+	int n, id, max;
+	struct idr_layer *p;
+	struct idr_layer *pa[MAX_LEVEL];
+	struct idr_layer **paa = &pa[0];
+
+	n = idp->layers * IDR_BITS;
+	p = idp->top;
+	max = 1 << n;
+
+	id = 0;
+	while (id < max) {
+		while (n > IDR_BITS && p) {
+			n -= IDR_BITS;
+			*paa++ = p;
+			p = p->ary[(id >> n) & IDR_MASK];
+		}
+
+		id += 1 << n;
+		while (n < fls(id)) {
+			if (p) {
+				memset(p, 0, sizeof *p);
+				free_layer(idp, p);
+			}
+			n += IDR_BITS;
+			p = *--paa;
+		}
+	}
+	idp->top = NULL;
+	idp->layers = 0;
+}
+EXPORT_SYMBOL(idr_remove_all);
+
+/**
  * idr_destroy - release all cached layers within an idr tree
  * idp: idr handle
  */
@@ -404,6 +484,61 @@ void *idr_find(struct idr *idp, int id)
 EXPORT_SYMBOL(idr_find);
 
 /**
+ * idr_for_each - iterate through all stored pointers
+ * @idp: idr handle
+ * @fn: function to be called for each pointer
+ * @data: data passed back to callback function
+ *
+ * Iterate over the pointers registered with the given idr.  The
+ * callback function will be called for each pointer currently
+ * registered, passing the id, the pointer and the data pointer passed
+ * to this function.  It is not safe to modify the idr tree while in
+ * the callback, so functions such as idr_get_new and idr_remove are
+ * not allowed.
+ *
+ * We check the return of @fn each time. If it returns anything other
+ * than 0, we break out and return that value.
+ *
+ * The caller must serialize idr_for_each() vs idr_get_new() and idr_remove().
+ */
+int idr_for_each(struct idr *idp,
+		 int (*fn)(int id, void *p, void *data), void *data)
+{
+	int n, id, max, error = 0;
+	struct idr_layer *p;
+	struct idr_layer *pa[MAX_LEVEL];
+	struct idr_layer **paa = &pa[0];
+
+	n = idp->layers * IDR_BITS;
+	p = idp->top;
+	max = 1 << n;
+
+	id = 0;
+	while (id < max) {
+		while (n > 0 && p) {
+			n -= IDR_BITS;
+			*paa++ = p;
+			p = p->ary[(id >> n) & IDR_MASK];
+		}
+
+		if (p) {
+			error = fn(id, (void *)p, data);
+			if (error)
+				break;
+		}
+
+		id += 1 << n;
+		while (n < fls(id)) {
+			n += IDR_BITS;
+			p = *--paa;
+		}
+	}
+
+	return error;
+}
+EXPORT_SYMBOL(idr_for_each);
+
+/**
  * idr_replace - replace pointer for given id
  * @idp: idr handle
  * @ptr: pointer you want associated with the id
@@ -455,7 +590,7 @@ static  int init_id_cache(void)
 {
 	if (!idr_layer_cache)
 		idr_layer_cache = kmem_cache_create("idr_layer_cache",
-			sizeof(struct idr_layer), 0, 0, idr_cache_ctor, NULL);
+			sizeof(struct idr_layer), 0, 0, idr_cache_ctor);
 	return 0;
 }
 
@@ -473,3 +608,248 @@ void idr_init(struct idr *idp)
 	spin_lock_init(&idp->lock);
 }
 EXPORT_SYMBOL(idr_init);
+
+
+/*
+ * IDA - IDR based ID allocator
+ *
+ * this is id allocator without id -> pointer translation.  Memory
+ * usage is much lower than full blown idr because each id only
+ * occupies a bit.  ida uses a custom leaf node which contains
+ * IDA_BITMAP_BITS slots.
+ *
+ * 2007-04-25  written by Tejun Heo <htejun@gmail.com>
+ */
+
+static void free_bitmap(struct ida *ida, struct ida_bitmap *bitmap)
+{
+	unsigned long flags;
+
+	if (!ida->free_bitmap) {
+		spin_lock_irqsave(&ida->idr.lock, flags);
+		if (!ida->free_bitmap) {
+			ida->free_bitmap = bitmap;
+			bitmap = NULL;
+		}
+		spin_unlock_irqrestore(&ida->idr.lock, flags);
+	}
+
+	kfree(bitmap);
+}
+
+/**
+ * ida_pre_get - reserve resources for ida allocation
+ * @ida:	ida handle
+ * @gfp_mask:	memory allocation flag
+ *
+ * This function should be called prior to locking and calling the
+ * following function.  It preallocates enough memory to satisfy the
+ * worst possible allocation.
+ *
+ * If the system is REALLY out of memory this function returns 0,
+ * otherwise 1.
+ */
+int ida_pre_get(struct ida *ida, gfp_t gfp_mask)
+{
+	/* allocate idr_layers */
+	if (!idr_pre_get(&ida->idr, gfp_mask))
+		return 0;
+
+	/* allocate free_bitmap */
+	if (!ida->free_bitmap) {
+		struct ida_bitmap *bitmap;
+
+		bitmap = kmalloc(sizeof(struct ida_bitmap), gfp_mask);
+		if (!bitmap)
+			return 0;
+
+		free_bitmap(ida, bitmap);
+	}
+
+	return 1;
+}
+EXPORT_SYMBOL(ida_pre_get);
+
+/**
+ * ida_get_new_above - allocate new ID above or equal to a start id
+ * @ida:	ida handle
+ * @staring_id:	id to start search at
+ * @p_id:	pointer to the allocated handle
+ *
+ * Allocate new ID above or equal to @ida.  It should be called with
+ * any required locks.
+ *
+ * If memory is required, it will return -EAGAIN, you should unlock
+ * and go back to the ida_pre_get() call.  If the ida is full, it will
+ * return -ENOSPC.
+ *
+ * @p_id returns a value in the range 0 ... 0x7fffffff.
+ */
+int ida_get_new_above(struct ida *ida, int starting_id, int *p_id)
+{
+	struct idr_layer *pa[MAX_LEVEL];
+	struct ida_bitmap *bitmap;
+	unsigned long flags;
+	int idr_id = starting_id / IDA_BITMAP_BITS;
+	int offset = starting_id % IDA_BITMAP_BITS;
+	int t, id;
+
+ restart:
+	/* get vacant slot */
+	t = idr_get_empty_slot(&ida->idr, idr_id, pa);
+	if (t < 0) {
+		if (t == -1)
+			return -EAGAIN;
+		else /* will be -3 */
+			return -ENOSPC;
+	}
+
+	if (t * IDA_BITMAP_BITS >= MAX_ID_BIT)
+		return -ENOSPC;
+
+	if (t != idr_id)
+		offset = 0;
+	idr_id = t;
+
+	/* if bitmap isn't there, create a new one */
+	bitmap = (void *)pa[0]->ary[idr_id & IDR_MASK];
+	if (!bitmap) {
+		spin_lock_irqsave(&ida->idr.lock, flags);
+		bitmap = ida->free_bitmap;
+		ida->free_bitmap = NULL;
+		spin_unlock_irqrestore(&ida->idr.lock, flags);
+
+		if (!bitmap)
+			return -EAGAIN;
+
+		memset(bitmap, 0, sizeof(struct ida_bitmap));
+		pa[0]->ary[idr_id & IDR_MASK] = (void *)bitmap;
+		pa[0]->count++;
+	}
+
+	/* lookup for empty slot */
+	t = find_next_zero_bit(bitmap->bitmap, IDA_BITMAP_BITS, offset);
+	if (t == IDA_BITMAP_BITS) {
+		/* no empty slot after offset, continue to the next chunk */
+		idr_id++;
+		offset = 0;
+		goto restart;
+	}
+
+	id = idr_id * IDA_BITMAP_BITS + t;
+	if (id >= MAX_ID_BIT)
+		return -ENOSPC;
+
+	__set_bit(t, bitmap->bitmap);
+	if (++bitmap->nr_busy == IDA_BITMAP_BITS)
+		idr_mark_full(pa, idr_id);
+
+	*p_id = id;
+
+	/* Each leaf node can handle nearly a thousand slots and the
+	 * whole idea of ida is to have small memory foot print.
+	 * Throw away extra resources one by one after each successful
+	 * allocation.
+	 */
+	if (ida->idr.id_free_cnt || ida->free_bitmap) {
+		struct idr_layer *p = alloc_layer(&ida->idr);
+		if (p)
+			kmem_cache_free(idr_layer_cache, p);
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL(ida_get_new_above);
+
+/**
+ * ida_get_new - allocate new ID
+ * @ida:	idr handle
+ * @p_id:	pointer to the allocated handle
+ *
+ * Allocate new ID.  It should be called with any required locks.
+ *
+ * If memory is required, it will return -EAGAIN, you should unlock
+ * and go back to the idr_pre_get() call.  If the idr is full, it will
+ * return -ENOSPC.
+ *
+ * @id returns a value in the range 0 ... 0x7fffffff.
+ */
+int ida_get_new(struct ida *ida, int *p_id)
+{
+	return ida_get_new_above(ida, 0, p_id);
+}
+EXPORT_SYMBOL(ida_get_new);
+
+/**
+ * ida_remove - remove the given ID
+ * @ida:	ida handle
+ * @id:		ID to free
+ */
+void ida_remove(struct ida *ida, int id)
+{
+	struct idr_layer *p = ida->idr.top;
+	int shift = (ida->idr.layers - 1) * IDR_BITS;
+	int idr_id = id / IDA_BITMAP_BITS;
+	int offset = id % IDA_BITMAP_BITS;
+	int n;
+	struct ida_bitmap *bitmap;
+
+	/* clear full bits while looking up the leaf idr_layer */
+	while ((shift > 0) && p) {
+		n = (idr_id >> shift) & IDR_MASK;
+		__clear_bit(n, &p->bitmap);
+		p = p->ary[n];
+		shift -= IDR_BITS;
+	}
+
+	if (p == NULL)
+		goto err;
+
+	n = idr_id & IDR_MASK;
+	__clear_bit(n, &p->bitmap);
+
+	bitmap = (void *)p->ary[n];
+	if (!test_bit(offset, bitmap->bitmap))
+		goto err;
+
+	/* update bitmap and remove it if empty */
+	__clear_bit(offset, bitmap->bitmap);
+	if (--bitmap->nr_busy == 0) {
+		__set_bit(n, &p->bitmap);	/* to please idr_remove() */
+		idr_remove(&ida->idr, idr_id);
+		free_bitmap(ida, bitmap);
+	}
+
+	return;
+
+ err:
+	printk(KERN_WARNING
+	       "ida_remove called for id=%d which is not allocated.\n", id);
+}
+EXPORT_SYMBOL(ida_remove);
+
+/**
+ * ida_destroy - release all cached layers within an ida tree
+ * ida:		ida handle
+ */
+void ida_destroy(struct ida *ida)
+{
+	idr_destroy(&ida->idr);
+	kfree(ida->free_bitmap);
+}
+EXPORT_SYMBOL(ida_destroy);
+
+/**
+ * ida_init - initialize ida handle
+ * @ida:	ida handle
+ *
+ * This function is use to set up the handle (@ida) that you will pass
+ * to the rest of the functions.
+ */
+void ida_init(struct ida *ida)
+{
+	memset(ida, 0, sizeof(struct ida));
+	idr_init(&ida->idr);
+
+}
+EXPORT_SYMBOL(ida_init);
diff --git a/lib/iomap.c b/lib/iomap.c
index a57d262a5ed9..864f2ec1966e 100644
--- a/lib/iomap.c
+++ b/lib/iomap.c
@@ -240,7 +240,20 @@ void ioport_unmap(void __iomem *addr)
 EXPORT_SYMBOL(ioport_map);
 EXPORT_SYMBOL(ioport_unmap);
 
-/* Create a virtual mapping cookie for a PCI BAR (memory or IO) */
+/**
+ * pci_iomap - create a virtual mapping cookie for a PCI BAR
+ * @dev: PCI device that owns the BAR
+ * @bar: BAR number
+ * @maxlen: length of the memory to map
+ *
+ * Using this function you will get a __iomem address to your device BAR.
+ * You can access it using ioread*() and iowrite*(). These functions hide
+ * the details if this is a MMIO or PIO address space and will just do what
+ * you expect from them in the correct way.
+ *
+ * @maxlen specifies the maximum length to map. If you want to get access to
+ * the complete BAR without checking for its length first, pass %0 here.
+ * */
 void __iomem *pci_iomap(struct pci_dev *dev, int bar, unsigned long maxlen)
 {
 	unsigned long start = pci_resource_start(dev, bar);
diff --git a/lib/kasprintf.c b/lib/kasprintf.c
new file mode 100644
index 000000000000..c5ff1fd10030
--- /dev/null
+++ b/lib/kasprintf.c
@@ -0,0 +1,44 @@
+/*
+ *  linux/lib/kasprintf.c
+ *
+ *  Copyright (C) 1991, 1992  Linus Torvalds
+ */
+
+#include <stdarg.h>
+#include <linux/module.h>
+#include <linux/types.h>
+#include <linux/string.h>
+
+/* Simplified asprintf. */
+char *kvasprintf(gfp_t gfp, const char *fmt, va_list ap)
+{
+	unsigned int len;
+	char *p;
+	va_list aq;
+
+	va_copy(aq, ap);
+	len = vsnprintf(NULL, 0, fmt, aq);
+	va_end(aq);
+
+	p = kmalloc(len+1, gfp);
+	if (!p)
+		return NULL;
+
+	vsnprintf(p, len+1, fmt, ap);
+
+	return p;
+}
+EXPORT_SYMBOL(kvasprintf);
+
+char *kasprintf(gfp_t gfp, const char *fmt, ...)
+{
+	va_list ap;
+	char *p;
+
+	va_start(ap, fmt);
+	p = kvasprintf(gfp, fmt, ap);
+	va_end(ap);
+
+	return p;
+}
+EXPORT_SYMBOL(kasprintf);
diff --git a/lib/kobject.c b/lib/kobject.c
index ac1520651b9b..4b08e0ff95c8 100644
--- a/lib/kobject.c
+++ b/lib/kobject.c
@@ -44,7 +44,7 @@ static int populate_dir(struct kobject * kobj)
 	return error;
 }
 
-static int create_dir(struct kobject * kobj, struct dentry *shadow_parent)
+static int create_dir(struct kobject *kobj, struct sysfs_dirent *shadow_parent)
 {
 	int error = 0;
 	if (kobject_name(kobj)) {
@@ -162,7 +162,7 @@ static void unlink(struct kobject * kobj)
  *	@shadow_parent: sysfs directory to add to.
  */
 
-int kobject_shadow_add(struct kobject * kobj, struct dentry *shadow_parent)
+int kobject_shadow_add(struct kobject *kobj, struct sysfs_dirent *shadow_parent)
 {
 	int error = 0;
 	struct kobject * parent;
@@ -338,7 +338,7 @@ int kobject_rename(struct kobject * kobj, const char *new_name)
 	/* Note : if we want to send the new name alone, not the full path,
 	 * we could probably use kobject_name(kobj); */
 
-	error = sysfs_rename_dir(kobj, kobj->parent->dentry, new_name);
+	error = sysfs_rename_dir(kobj, kobj->parent->sd, new_name);
 
 	/* This function is mostly/only used for network interface.
 	 * Some hotplug package track interfaces by their name and
@@ -361,8 +361,8 @@ out:
  *	@new_name: object's new name
  */
 
-int kobject_shadow_rename(struct kobject * kobj, struct dentry *new_parent,
-			  const char *new_name)
+int kobject_shadow_rename(struct kobject *kobj,
+			  struct sysfs_dirent *new_parent, const char *new_name)
 {
 	int error = 0;
 
@@ -597,10 +597,17 @@ int kset_add(struct kset * k)
 
 int kset_register(struct kset * k)
 {
+	int err;
+
 	if (!k)
 		return -EINVAL;
+
 	kset_init(k);
-	return kset_add(k);
+	err = kset_add(k);
+	if (err)
+		return err;
+	kobject_uevent(&k->kobj, KOBJ_ADD);
+	return 0;
 }
 
 
diff --git a/lib/kobject_uevent.c b/lib/kobject_uevent.c
index 12e311dc664c..df02814699d7 100644
--- a/lib/kobject_uevent.c
+++ b/lib/kobject_uevent.c
@@ -25,6 +25,16 @@
 #define BUFFER_SIZE	2048	/* buffer for the variables */
 #define NUM_ENVP	32	/* number of env pointers */
 
+/* the strings here must match the enum in include/linux/kobject.h */
+const char *kobject_actions[] = {
+	"add",
+	"remove",
+	"change",
+	"move",
+	"online",
+	"offline",
+};
+
 #if defined(CONFIG_HOTPLUG)
 u64 uevent_seqnum;
 char uevent_helper[UEVENT_HELPER_PATH_LEN] = "/sbin/hotplug";
@@ -33,26 +43,6 @@ static DEFINE_SPINLOCK(sequence_lock);
 static struct sock *uevent_sock;
 #endif
 
-static char *action_to_string(enum kobject_action action)
-{
-	switch (action) {
-	case KOBJ_ADD:
-		return "add";
-	case KOBJ_REMOVE:
-		return "remove";
-	case KOBJ_CHANGE:
-		return "change";
-	case KOBJ_OFFLINE:
-		return "offline";
-	case KOBJ_ONLINE:
-		return "online";
-	case KOBJ_MOVE:
-		return "move";
-	default:
-		return NULL;
-	}
-}
-
 /**
  * kobject_uevent_env - send an uevent with environmental data
  *
@@ -83,7 +73,7 @@ int kobject_uevent_env(struct kobject *kobj, enum kobject_action action,
 
 	pr_debug("%s\n", __FUNCTION__);
 
-	action_string = action_to_string(action);
+	action_string = kobject_actions[action];
 	if (!action_string) {
 		pr_debug("kobject attempted to send uevent without action_string!\n");
 		return -EINVAL;
@@ -208,7 +198,7 @@ int kobject_uevent_env(struct kobject *kobj, enum kobject_action action,
 		argv [0] = uevent_helper;
 		argv [1] = (char *)subsystem;
 		argv [2] = NULL;
-		call_usermodehelper (argv[0], argv, envp, 0);
+		call_usermodehelper (argv[0], argv, envp, UMH_WAIT_EXEC);
 	}
 
 exit:
diff --git a/lib/lzo/Makefile b/lib/lzo/Makefile
new file mode 100644
index 000000000000..e764116ea12d
--- /dev/null
+++ b/lib/lzo/Makefile
@@ -0,0 +1,5 @@
+lzo_compress-objs := lzo1x_compress.o
+lzo_decompress-objs := lzo1x_decompress.o
+
+obj-$(CONFIG_LZO_COMPRESS) += lzo_compress.o
+obj-$(CONFIG_LZO_DECOMPRESS) += lzo_decompress.o
diff --git a/lib/lzo/lzo1x_compress.c b/lib/lzo/lzo1x_compress.c
new file mode 100644
index 000000000000..a6040990a62e
--- /dev/null
+++ b/lib/lzo/lzo1x_compress.c
@@ -0,0 +1,226 @@
+/*
+ *  LZO1X Compressor from MiniLZO
+ *
+ *  Copyright (C) 1996-2005 Markus F.X.J. Oberhumer <markus@oberhumer.com>
+ *
+ *  The full LZO package can be found at:
+ *  http://www.oberhumer.com/opensource/lzo/
+ *
+ *  Changed for kernel use by:
+ *  Nitin Gupta <nitingupta910@gmail.com>
+ *  Richard Purdie <rpurdie@openedhand.com>
+ */
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/lzo.h>
+#include <asm/unaligned.h>
+#include "lzodefs.h"
+
+static noinline size_t
+_lzo1x_1_do_compress(const unsigned char *in, size_t in_len,
+		unsigned char *out, size_t *out_len, void *wrkmem)
+{
+	const unsigned char * const in_end = in + in_len;
+	const unsigned char * const ip_end = in + in_len - M2_MAX_LEN - 5;
+	const unsigned char ** const dict = wrkmem;
+	const unsigned char *ip = in, *ii = ip;
+	const unsigned char *end, *m, *m_pos;
+	size_t m_off, m_len, dindex;
+	unsigned char *op = out;
+
+	ip += 4;
+
+	for (;;) {
+		dindex = ((size_t)(0x21 * DX3(ip, 5, 5, 6)) >> 5) & D_MASK;
+		m_pos = dict[dindex];
+
+		if (m_pos < in)
+			goto literal;
+
+		if (ip == m_pos || ((size_t)(ip - m_pos) > M4_MAX_OFFSET))
+			goto literal;
+
+		m_off = ip - m_pos;
+		if (m_off <= M2_MAX_OFFSET || m_pos[3] == ip[3])
+			goto try_match;
+
+		dindex = (dindex & (D_MASK & 0x7ff)) ^ (D_HIGH | 0x1f);
+		m_pos = dict[dindex];
+
+		if (m_pos < in)
+			goto literal;
+
+		if (ip == m_pos || ((size_t)(ip - m_pos) > M4_MAX_OFFSET))
+			goto literal;
+
+		m_off = ip - m_pos;
+		if (m_off <= M2_MAX_OFFSET || m_pos[3] == ip[3])
+			goto try_match;
+
+		goto literal;
+
+try_match:
+		if (get_unaligned((const unsigned short *)m_pos)
+				== get_unaligned((const unsigned short *)ip)) {
+			if (likely(m_pos[2] == ip[2]))
+					goto match;
+		}
+
+literal:
+		dict[dindex] = ip;
+		++ip;
+		if (unlikely(ip >= ip_end))
+			break;
+		continue;
+
+match:
+		dict[dindex] = ip;
+		if (ip != ii) {
+			size_t t = ip - ii;
+
+			if (t <= 3) {
+				op[-2] |= t;
+			} else if (t <= 18) {
+				*op++ = (t - 3);
+			} else {
+				size_t tt = t - 18;
+
+				*op++ = 0;
+				while (tt > 255) {
+					tt -= 255;
+					*op++ = 0;
+				}
+				*op++ = tt;
+			}
+			do {
+				*op++ = *ii++;
+			} while (--t > 0);
+		}
+
+		ip += 3;
+		if (m_pos[3] != *ip++ || m_pos[4] != *ip++
+				|| m_pos[5] != *ip++ || m_pos[6] != *ip++
+				|| m_pos[7] != *ip++ || m_pos[8] != *ip++) {
+			--ip;
+			m_len = ip - ii;
+
+			if (m_off <= M2_MAX_OFFSET) {
+				m_off -= 1;
+				*op++ = (((m_len - 1) << 5)
+						| ((m_off & 7) << 2));
+				*op++ = (m_off >> 3);
+			} else if (m_off <= M3_MAX_OFFSET) {
+				m_off -= 1;
+				*op++ = (M3_MARKER | (m_len - 2));
+				goto m3_m4_offset;
+			} else {
+				m_off -= 0x4000;
+
+				*op++ = (M4_MARKER | ((m_off & 0x4000) >> 11)
+						| (m_len - 2));
+				goto m3_m4_offset;
+			}
+		} else {
+			end = in_end;
+			m = m_pos + M2_MAX_LEN + 1;
+
+			while (ip < end && *m == *ip) {
+				m++;
+				ip++;
+			}
+			m_len = ip - ii;
+
+			if (m_off <= M3_MAX_OFFSET) {
+				m_off -= 1;
+				if (m_len <= 33) {
+					*op++ = (M3_MARKER | (m_len - 2));
+				} else {
+					m_len -= 33;
+					*op++ = M3_MARKER | 0;
+					goto m3_m4_len;
+				}
+			} else {
+				m_off -= 0x4000;
+				if (m_len <= M4_MAX_LEN) {
+					*op++ = (M4_MARKER
+						| ((m_off & 0x4000) >> 11)
+						| (m_len - 2));
+				} else {
+					m_len -= M4_MAX_LEN;
+					*op++ = (M4_MARKER
+						| ((m_off & 0x4000) >> 11));
+m3_m4_len:
+					while (m_len > 255) {
+						m_len -= 255;
+						*op++ = 0;
+					}
+
+					*op++ = (m_len);
+				}
+			}
+m3_m4_offset:
+			*op++ = ((m_off & 63) << 2);
+			*op++ = (m_off >> 6);
+		}
+
+		ii = ip;
+		if (unlikely(ip >= ip_end))
+			break;
+	}
+
+	*out_len = op - out;
+	return in_end - ii;
+}
+
+int lzo1x_1_compress(const unsigned char *in, size_t in_len, unsigned char *out,
+			size_t *out_len, void *wrkmem)
+{
+	const unsigned char *ii;
+	unsigned char *op = out;
+	size_t t;
+
+	if (unlikely(in_len <= M2_MAX_LEN + 5)) {
+		t = in_len;
+	} else {
+		t = _lzo1x_1_do_compress(in, in_len, op, out_len, wrkmem);
+		op += *out_len;
+	}
+
+	if (t > 0) {
+		ii = in + in_len - t;
+
+		if (op == out && t <= 238) {
+			*op++ = (17 + t);
+		} else if (t <= 3) {
+			op[-2] |= t;
+		} else if (t <= 18) {
+			*op++ = (t - 3);
+		} else {
+			size_t tt = t - 18;
+
+			*op++ = 0;
+			while (tt > 255) {
+				tt -= 255;
+				*op++ = 0;
+			}
+
+			*op++ = tt;
+		}
+		do {
+			*op++ = *ii++;
+		} while (--t > 0);
+	}
+
+	*op++ = M4_MARKER | 1;
+	*op++ = 0;
+	*op++ = 0;
+
+	*out_len = op - out;
+	return LZO_E_OK;
+}
+EXPORT_SYMBOL_GPL(lzo1x_1_compress);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("LZO1X-1 Compressor");
+
diff --git a/lib/lzo/lzo1x_decompress.c b/lib/lzo/lzo1x_decompress.c
new file mode 100644
index 000000000000..9dc7056e5520
--- /dev/null
+++ b/lib/lzo/lzo1x_decompress.c
@@ -0,0 +1,254 @@
+/*
+ *  LZO1X Decompressor from MiniLZO
+ *
+ *  Copyright (C) 1996-2005 Markus F.X.J. Oberhumer <markus@oberhumer.com>
+ *
+ *  The full LZO package can be found at:
+ *  http://www.oberhumer.com/opensource/lzo/
+ *
+ *  Changed for kernel use by:
+ *  Nitin Gupta <nitingupta910@gmail.com>
+ *  Richard Purdie <rpurdie@openedhand.com>
+ */
+
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/lzo.h>
+#include <asm/byteorder.h>
+#include <asm/unaligned.h>
+#include "lzodefs.h"
+
+#define HAVE_IP(x, ip_end, ip) ((size_t)(ip_end - ip) < (x))
+#define HAVE_OP(x, op_end, op) ((size_t)(op_end - op) < (x))
+#define HAVE_LB(m_pos, out, op) (m_pos < out || m_pos >= op)
+
+#define COPY4(dst, src)	\
+		put_unaligned(get_unaligned((const u32 *)(src)), (u32 *)(dst))
+
+int lzo1x_decompress_safe(const unsigned char *in, size_t in_len,
+			unsigned char *out, size_t *out_len)
+{
+	const unsigned char * const ip_end = in + in_len;
+	unsigned char * const op_end = out + *out_len;
+	const unsigned char *ip = in, *m_pos;
+	unsigned char *op = out;
+	size_t t;
+
+	*out_len = 0;
+
+	if (*ip > 17) {
+		t = *ip++ - 17;
+		if (t < 4)
+			goto match_next;
+		if (HAVE_OP(t, op_end, op))
+			goto output_overrun;
+		if (HAVE_IP(t + 1, ip_end, ip))
+			goto input_overrun;
+		do {
+			*op++ = *ip++;
+		} while (--t > 0);
+		goto first_literal_run;
+	}
+
+	while ((ip < ip_end)) {
+		t = *ip++;
+		if (t >= 16)
+			goto match;
+		if (t == 0) {
+			if (HAVE_IP(1, ip_end, ip))
+				goto input_overrun;
+			while (*ip == 0) {
+				t += 255;
+				ip++;
+				if (HAVE_IP(1, ip_end, ip))
+					goto input_overrun;
+			}
+			t += 15 + *ip++;
+		}
+		if (HAVE_OP(t + 3, op_end, op))
+			goto output_overrun;
+		if (HAVE_IP(t + 4, ip_end, ip))
+			goto input_overrun;
+
+		COPY4(op, ip);
+		op += 4;
+		ip += 4;
+		if (--t > 0) {
+			if (t >= 4) {
+				do {
+					COPY4(op, ip);
+					op += 4;
+					ip += 4;
+					t -= 4;
+				} while (t >= 4);
+				if (t > 0) {
+					do {
+						*op++ = *ip++;
+					} while (--t > 0);
+				}
+			} else {
+				do {
+					*op++ = *ip++;
+				} while (--t > 0);
+			}
+		}
+
+first_literal_run:
+		t = *ip++;
+		if (t >= 16)
+			goto match;
+		m_pos = op - (1 + M2_MAX_OFFSET);
+		m_pos -= t >> 2;
+		m_pos -= *ip++ << 2;
+
+		if (HAVE_LB(m_pos, out, op))
+			goto lookbehind_overrun;
+
+		if (HAVE_OP(3, op_end, op))
+			goto output_overrun;
+		*op++ = *m_pos++;
+		*op++ = *m_pos++;
+		*op++ = *m_pos;
+
+		goto match_done;
+
+		do {
+match:
+			if (t >= 64) {
+				m_pos = op - 1;
+				m_pos -= (t >> 2) & 7;
+				m_pos -= *ip++ << 3;
+				t = (t >> 5) - 1;
+				if (HAVE_LB(m_pos, out, op))
+					goto lookbehind_overrun;
+				if (HAVE_OP(t + 3 - 1, op_end, op))
+					goto output_overrun;
+				goto copy_match;
+			} else if (t >= 32) {
+				t &= 31;
+				if (t == 0) {
+					if (HAVE_IP(1, ip_end, ip))
+						goto input_overrun;
+					while (*ip == 0) {
+						t += 255;
+						ip++;
+						if (HAVE_IP(1, ip_end, ip))
+							goto input_overrun;
+					}
+					t += 31 + *ip++;
+				}
+				m_pos = op - 1;
+				m_pos -= le16_to_cpu(get_unaligned(
+					(const unsigned short *)ip)) >> 2;
+				ip += 2;
+			} else if (t >= 16) {
+				m_pos = op;
+				m_pos -= (t & 8) << 11;
+
+				t &= 7;
+				if (t == 0) {
+					if (HAVE_IP(1, ip_end, ip))
+						goto input_overrun;
+					while (*ip == 0) {
+						t += 255;
+						ip++;
+						if (HAVE_IP(1, ip_end, ip))
+							goto input_overrun;
+					}
+					t += 7 + *ip++;
+				}
+				m_pos -= le16_to_cpu(get_unaligned(
+					(const unsigned short *)ip) >> 2);
+				ip += 2;
+				if (m_pos == op)
+					goto eof_found;
+				m_pos -= 0x4000;
+			} else {
+				m_pos = op - 1;
+				m_pos -= t >> 2;
+				m_pos -= *ip++ << 2;
+
+				if (HAVE_LB(m_pos, out, op))
+					goto lookbehind_overrun;
+				if (HAVE_OP(2, op_end, op))
+					goto output_overrun;
+
+				*op++ = *m_pos++;
+				*op++ = *m_pos;
+				goto match_done;
+			}
+
+			if (HAVE_LB(m_pos, out, op))
+				goto lookbehind_overrun;
+			if (HAVE_OP(t + 3 - 1, op_end, op))
+				goto output_overrun;
+
+			if (t >= 2 * 4 - (3 - 1) && (op - m_pos) >= 4) {
+				COPY4(op, m_pos);
+				op += 4;
+				m_pos += 4;
+				t -= 4 - (3 - 1);
+				do {
+					COPY4(op, m_pos);
+					op += 4;
+					m_pos += 4;
+					t -= 4;
+				} while (t >= 4);
+				if (t > 0)
+					do {
+						*op++ = *m_pos++;
+					} while (--t > 0);
+			} else {
+copy_match:
+				*op++ = *m_pos++;
+				*op++ = *m_pos++;
+				do {
+					*op++ = *m_pos++;
+				} while (--t > 0);
+			}
+match_done:
+			t = ip[-2] & 3;
+			if (t == 0)
+				break;
+match_next:
+			if (HAVE_OP(t, op_end, op))
+				goto output_overrun;
+			if (HAVE_IP(t + 1, ip_end, ip))
+				goto input_overrun;
+
+			*op++ = *ip++;
+			if (t > 1) {
+				*op++ = *ip++;
+				if (t > 2)
+					*op++ = *ip++;
+			}
+
+			t = *ip++;
+		} while (ip < ip_end);
+	}
+
+	*out_len = op - out;
+	return LZO_E_EOF_NOT_FOUND;
+
+eof_found:
+	*out_len = op - out;
+	return (ip == ip_end ? LZO_E_OK :
+		(ip < ip_end ? LZO_E_INPUT_NOT_CONSUMED : LZO_E_INPUT_OVERRUN));
+input_overrun:
+	*out_len = op - out;
+	return LZO_E_INPUT_OVERRUN;
+
+output_overrun:
+	*out_len = op - out;
+	return LZO_E_OUTPUT_OVERRUN;
+
+lookbehind_overrun:
+	*out_len = op - out;
+	return LZO_E_LOOKBEHIND_OVERRUN;
+}
+
+EXPORT_SYMBOL_GPL(lzo1x_decompress_safe);
+
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("LZO1X Decompressor");
+
diff --git a/lib/lzo/lzodefs.h b/lib/lzo/lzodefs.h
new file mode 100644
index 000000000000..b6d482c492ef
--- /dev/null
+++ b/lib/lzo/lzodefs.h
@@ -0,0 +1,43 @@
+/*
+ *  lzodefs.h -- architecture, OS and compiler specific defines
+ *
+ *  Copyright (C) 1996-2005 Markus F.X.J. Oberhumer <markus@oberhumer.com>
+ *
+ *  The full LZO package can be found at:
+ *  http://www.oberhumer.com/opensource/lzo/
+ *
+ *  Changed for kernel use by:
+ *  Nitin Gupta <nitingupta910@gmail.com>
+ *  Richard Purdie <rpurdie@openedhand.com>
+ */
+
+#define LZO_VERSION		0x2020
+#define LZO_VERSION_STRING	"2.02"
+#define LZO_VERSION_DATE	"Oct 17 2005"
+
+#define M1_MAX_OFFSET	0x0400
+#define M2_MAX_OFFSET	0x0800
+#define M3_MAX_OFFSET	0x4000
+#define M4_MAX_OFFSET	0xbfff
+
+#define M1_MIN_LEN	2
+#define M1_MAX_LEN	2
+#define M2_MIN_LEN	3
+#define M2_MAX_LEN	8
+#define M3_MIN_LEN	3
+#define M3_MAX_LEN	33
+#define M4_MIN_LEN	3
+#define M4_MAX_LEN	9
+
+#define M1_MARKER	0
+#define M2_MARKER	64
+#define M3_MARKER	32
+#define M4_MARKER	16
+
+#define D_BITS		14
+#define D_MASK		((1u << D_BITS) - 1)
+#define D_HIGH		((D_MASK >> 1) + 1)
+
+#define DX2(p, s1, s2)	(((((size_t)((p)[2]) << (s2)) ^ (p)[1]) \
+							<< (s1)) ^ (p)[0])
+#define DX3(p, s1, s2, s3)	((DX2((p)+1, s2, s3) << (s1)) ^ (p)[0])
diff --git a/lib/percpu_counter.c b/lib/percpu_counter.c
index 850449080e1c..cf22c617baa4 100644
--- a/lib/percpu_counter.c
+++ b/lib/percpu_counter.c
@@ -3,8 +3,17 @@
  */
 
 #include <linux/percpu_counter.h>
+#include <linux/notifier.h>
+#include <linux/mutex.h>
+#include <linux/init.h>
+#include <linux/cpu.h>
 #include <linux/module.h>
 
+#ifdef CONFIG_HOTPLUG_CPU
+static LIST_HEAD(percpu_counters);
+static DEFINE_MUTEX(percpu_counters_lock);
+#endif
+
 void percpu_counter_mod(struct percpu_counter *fbc, s32 amount)
 {
 	long count;
@@ -36,7 +45,7 @@ s64 percpu_counter_sum(struct percpu_counter *fbc)
 
 	spin_lock(&fbc->lock);
 	ret = fbc->count;
-	for_each_possible_cpu(cpu) {
+	for_each_online_cpu(cpu) {
 		s32 *pcount = per_cpu_ptr(fbc->counters, cpu);
 		ret += *pcount;
 	}
@@ -44,3 +53,60 @@ s64 percpu_counter_sum(struct percpu_counter *fbc)
 	return ret < 0 ? 0 : ret;
 }
 EXPORT_SYMBOL(percpu_counter_sum);
+
+void percpu_counter_init(struct percpu_counter *fbc, s64 amount)
+{
+	spin_lock_init(&fbc->lock);
+	fbc->count = amount;
+	fbc->counters = alloc_percpu(s32);
+#ifdef CONFIG_HOTPLUG_CPU
+	mutex_lock(&percpu_counters_lock);
+	list_add(&fbc->list, &percpu_counters);
+	mutex_unlock(&percpu_counters_lock);
+#endif
+}
+EXPORT_SYMBOL(percpu_counter_init);
+
+void percpu_counter_destroy(struct percpu_counter *fbc)
+{
+	free_percpu(fbc->counters);
+#ifdef CONFIG_HOTPLUG_CPU
+	mutex_lock(&percpu_counters_lock);
+	list_del(&fbc->list);
+	mutex_unlock(&percpu_counters_lock);
+#endif
+}
+EXPORT_SYMBOL(percpu_counter_destroy);
+
+#ifdef CONFIG_HOTPLUG_CPU
+static int __cpuinit percpu_counter_hotcpu_callback(struct notifier_block *nb,
+					unsigned long action, void *hcpu)
+{
+	unsigned int cpu;
+	struct percpu_counter *fbc;
+
+	if (action != CPU_DEAD)
+		return NOTIFY_OK;
+
+	cpu = (unsigned long)hcpu;
+	mutex_lock(&percpu_counters_lock);
+	list_for_each_entry(fbc, &percpu_counters, list) {
+		s32 *pcount;
+
+		spin_lock(&fbc->lock);
+		pcount = per_cpu_ptr(fbc->counters, cpu);
+		fbc->count += *pcount;
+		*pcount = 0;
+		spin_unlock(&fbc->lock);
+	}
+	mutex_unlock(&percpu_counters_lock);
+	return NOTIFY_OK;
+}
+
+static int __init percpu_counter_startup(void)
+{
+	hotcpu_notifier(percpu_counter_hotcpu_callback, 0);
+	return 0;
+}
+module_init(percpu_counter_startup);
+#endif
diff --git a/lib/radix-tree.c b/lib/radix-tree.c
index 402eb4eb6b23..514efb200be6 100644
--- a/lib/radix-tree.c
+++ b/lib/radix-tree.c
@@ -151,6 +151,7 @@ int radix_tree_preload(gfp_t gfp_mask)
 out:
 	return ret;
 }
+EXPORT_SYMBOL(radix_tree_preload);
 
 static inline void tag_set(struct radix_tree_node *node, unsigned int tag,
 		int offset)
@@ -1020,7 +1021,7 @@ void __init radix_tree_init(void)
 {
 	radix_tree_node_cachep = kmem_cache_create("radix_tree_node",
 			sizeof(struct radix_tree_node), 0,
-			SLAB_PANIC, radix_tree_node_ctor, NULL);
+			SLAB_PANIC, radix_tree_node_ctor);
 	radix_tree_init_maxindex();
 	hotcpu_notifier(radix_tree_callback, 0);
 }
diff --git a/lib/swiotlb.c b/lib/swiotlb.c
index 10c13ad0d82d..a7381d55663a 100644
--- a/lib/swiotlb.c
+++ b/lib/swiotlb.c
@@ -357,7 +357,8 @@ map_single(struct device *hwdev, char *buffer, size_t size, int dir)
 	 * This is needed when we sync the memory.  Then we sync the buffer if
 	 * needed.
 	 */
-	io_tlb_orig_addr[index] = buffer;
+	for (i = 0; i < nslots; i++)
+		io_tlb_orig_addr[index+i] = buffer + (i << IO_TLB_SHIFT);
 	if (dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL)
 		memcpy(dma_addr, buffer, size);
 
@@ -418,6 +419,8 @@ sync_single(struct device *hwdev, char *dma_addr, size_t size,
 	int index = (dma_addr - io_tlb_start) >> IO_TLB_SHIFT;
 	char *buffer = io_tlb_orig_addr[index];
 
+	buffer += ((unsigned long)dma_addr & ((1 << IO_TLB_SHIFT) - 1));
+
 	switch (target) {
 	case SYNC_FOR_CPU:
 		if (likely(dir == DMA_FROM_DEVICE || dir == DMA_BIDIRECTIONAL))
diff --git a/lib/vsprintf.c b/lib/vsprintf.c
index 017290241261..7b481cea54ae 100644
--- a/lib/vsprintf.c
+++ b/lib/vsprintf.c
@@ -135,6 +135,103 @@ static int skip_atoi(const char **s)
 	return i;
 }
 
+/* Decimal conversion is by far the most typical, and is used
+ * for /proc and /sys data. This directly impacts e.g. top performance
+ * with many processes running. We optimize it for speed
+ * using code from
+ * http://www.cs.uiowa.edu/~jones/bcd/decimal.html
+ * (with permission from the author, Douglas W. Jones). */
+
+/* Formats correctly any integer in [0,99999].
+ * Outputs from one to five digits depending on input.
+ * On i386 gcc 4.1.2 -O2: ~250 bytes of code. */
+static char* put_dec_trunc(char *buf, unsigned q)
+{
+	unsigned d3, d2, d1, d0;
+	d1 = (q>>4) & 0xf;
+	d2 = (q>>8) & 0xf;
+	d3 = (q>>12);
+
+	d0 = 6*(d3 + d2 + d1) + (q & 0xf);
+	q = (d0 * 0xcd) >> 11;
+	d0 = d0 - 10*q;
+	*buf++ = d0 + '0'; /* least significant digit */
+	d1 = q + 9*d3 + 5*d2 + d1;
+	if (d1 != 0) {
+		q = (d1 * 0xcd) >> 11;
+		d1 = d1 - 10*q;
+		*buf++ = d1 + '0'; /* next digit */
+
+		d2 = q + 2*d2;
+		if ((d2 != 0) || (d3 != 0)) {
+			q = (d2 * 0xd) >> 7;
+			d2 = d2 - 10*q;
+			*buf++ = d2 + '0'; /* next digit */
+
+			d3 = q + 4*d3;
+			if (d3 != 0) {
+				q = (d3 * 0xcd) >> 11;
+				d3 = d3 - 10*q;
+				*buf++ = d3 + '0';  /* next digit */
+				if (q != 0)
+					*buf++ = q + '0';  /* most sign. digit */
+			}
+		}
+	}
+	return buf;
+}
+/* Same with if's removed. Always emits five digits */
+static char* put_dec_full(char *buf, unsigned q)
+{
+	/* BTW, if q is in [0,9999], 8-bit ints will be enough, */
+	/* but anyway, gcc produces better code with full-sized ints */
+	unsigned d3, d2, d1, d0;
+	d1 = (q>>4) & 0xf;
+	d2 = (q>>8) & 0xf;
+	d3 = (q>>12);
+
+	/* Possible ways to approx. divide by 10 */
+	/* gcc -O2 replaces multiply with shifts and adds */
+	// (x * 0xcd) >> 11: 11001101 - shorter code than * 0x67 (on i386)
+	// (x * 0x67) >> 10:  1100111
+	// (x * 0x34) >> 9:    110100 - same
+	// (x * 0x1a) >> 8:     11010 - same
+	// (x * 0x0d) >> 7:      1101 - same, shortest code (on i386)
+
+	d0 = 6*(d3 + d2 + d1) + (q & 0xf);
+	q = (d0 * 0xcd) >> 11;
+	d0 = d0 - 10*q;
+	*buf++ = d0 + '0';
+	d1 = q + 9*d3 + 5*d2 + d1;
+		q = (d1 * 0xcd) >> 11;
+		d1 = d1 - 10*q;
+		*buf++ = d1 + '0';
+
+		d2 = q + 2*d2;
+			q = (d2 * 0xd) >> 7;
+			d2 = d2 - 10*q;
+			*buf++ = d2 + '0';
+
+			d3 = q + 4*d3;
+				q = (d3 * 0xcd) >> 11; /* - shorter code */
+				/* q = (d3 * 0x67) >> 10; - would also work */
+				d3 = d3 - 10*q;
+				*buf++ = d3 + '0';
+					*buf++ = q + '0';
+	return buf;
+}
+/* No inlining helps gcc to use registers better */
+static noinline char* put_dec(char *buf, unsigned long long num)
+{
+	while (1) {
+		unsigned rem;
+		if (num < 100000)
+			return put_dec_trunc(buf, num);
+		rem = do_div(num, 100000);
+		buf = put_dec_full(buf, rem);
+	}
+}
+
 #define ZEROPAD	1		/* pad with zero */
 #define SIGN	2		/* unsigned/signed long */
 #define PLUS	4		/* show plus */
@@ -143,12 +240,14 @@ static int skip_atoi(const char **s)
 #define SPECIAL	32		/* 0x */
 #define LARGE	64		/* use 'ABCDEF' instead of 'abcdef' */
 
-static char * number(char * buf, char * end, unsigned long long num, int base, int size, int precision, int type)
+static char *number(char *buf, char *end, unsigned long long num, int base, int size, int precision, int type)
 {
-	char c,sign,tmp[66];
+	char sign,tmp[66];
 	const char *digits;
-	static const char small_digits[] = "0123456789abcdefghijklmnopqrstuvwxyz";
-	static const char large_digits[] = "0123456789ABCDEFGHIJKLMNOPQRSTUVWXYZ";
+	/* we are called with base 8, 10 or 16, only, thus don't need "g..."  */
+	static const char small_digits[] = "0123456789abcdefx"; /* "ghijklmnopqrstuvwxyz"; */
+	static const char large_digits[] = "0123456789ABCDEFX"; /* "GHIJKLMNOPQRSTUVWXYZ"; */
+	int need_pfx = ((type & SPECIAL) && base != 10);
 	int i;
 
 	digits = (type & LARGE) ? large_digits : small_digits;
@@ -156,7 +255,6 @@ static char * number(char * buf, char * end, unsigned long long num, int base, i
 		type &= ~ZEROPAD;
 	if (base < 2 || base > 36)
 		return NULL;
-	c = (type & ZEROPAD) ? '0' : ' ';
 	sign = 0;
 	if (type & SIGN) {
 		if ((signed long long) num < 0) {
@@ -171,64 +269,85 @@ static char * number(char * buf, char * end, unsigned long long num, int base, i
 			size--;
 		}
 	}
-	if (type & SPECIAL) {
+	if (need_pfx) {
+		size--;
 		if (base == 16)
-			size -= 2;
-		else if (base == 8)
 			size--;
 	}
+
+	/* generate full string in tmp[], in reverse order */
 	i = 0;
 	if (num == 0)
-		tmp[i++]='0';
-	else while (num != 0)
+		tmp[i++] = '0';
+	/* Generic code, for any base:
+	else do {
 		tmp[i++] = digits[do_div(num,base)];
+	} while (num != 0);
+	*/
+	else if (base != 10) { /* 8 or 16 */
+		int mask = base - 1;
+		int shift = 3;
+		if (base == 16) shift = 4;
+		do {
+			tmp[i++] = digits[((unsigned char)num) & mask];
+			num >>= shift;
+		} while (num);
+	} else { /* base 10 */
+		i = put_dec(tmp, num) - tmp;
+	}
+
+	/* printing 100 using %2d gives "100", not "00" */
 	if (i > precision)
 		precision = i;
+	/* leading space padding */
 	size -= precision;
-	if (!(type&(ZEROPAD+LEFT))) {
-		while(size-->0) {
+	if (!(type & (ZEROPAD+LEFT))) {
+		while(--size >= 0) {
 			if (buf < end)
 				*buf = ' ';
 			++buf;
 		}
 	}
+	/* sign */
 	if (sign) {
 		if (buf < end)
 			*buf = sign;
 		++buf;
 	}
-	if (type & SPECIAL) {
-		if (base==8) {
-			if (buf < end)
-				*buf = '0';
-			++buf;
-		} else if (base==16) {
-			if (buf < end)
-				*buf = '0';
-			++buf;
+	/* "0x" / "0" prefix */
+	if (need_pfx) {
+		if (buf < end)
+			*buf = '0';
+		++buf;
+		if (base == 16) {
 			if (buf < end)
-				*buf = digits[33];
+				*buf = digits[16]; /* for arbitrary base: digits[33]; */
 			++buf;
 		}
 	}
+	/* zero or space padding */
 	if (!(type & LEFT)) {
-		while (size-- > 0) {
+		char c = (type & ZEROPAD) ? '0' : ' ';
+		while (--size >= 0) {
 			if (buf < end)
 				*buf = c;
 			++buf;
 		}
 	}
-	while (i < precision--) {
+	/* hmm even more zero padding? */
+	while (i <= --precision) {
 		if (buf < end)
 			*buf = '0';
 		++buf;
 	}
-	while (i-- > 0) {
+	/* actual digits of result */
+	while (--i >= 0) {
 		if (buf < end)
 			*buf = tmp[i];
 		++buf;
 	}
-	while (size-- > 0) {
+	/* trailing space padding */
+	while (--size >= 0) {
 		if (buf < end)
 			*buf = ' ';
 		++buf;
@@ -276,7 +395,7 @@ int vsnprintf(char *buf, size_t size, const char *fmt, va_list args)
 	   used for unknown buffer sizes. */
 	if (unlikely((int) size < 0)) {
 		/* There can be only one.. */
-		static int warn = 1;
+		static char warn = 1;
 		WARN_ON(warn);
 		warn = 0;
 		return 0;
@@ -859,38 +978,3 @@ int sscanf(const char * buf, const char * fmt, ...)
 }
 
 EXPORT_SYMBOL(sscanf);
-
-
-/* Simplified asprintf. */
-char *kvasprintf(gfp_t gfp, const char *fmt, va_list ap)
-{
-	unsigned int len;
-	char *p;
-	va_list aq;
-
-	va_copy(aq, ap);
-	len = vsnprintf(NULL, 0, fmt, aq);
-	va_end(aq);
-
-	p = kmalloc(len+1, gfp);
-	if (!p)
-		return NULL;
-
-	vsnprintf(p, len+1, fmt, ap);
-
-	return p;
-}
-EXPORT_SYMBOL(kvasprintf);
-
-char *kasprintf(gfp_t gfp, const char *fmt, ...)
-{
-	va_list ap;
-	char *p;
-
-	va_start(ap, fmt);
-	p = kvasprintf(gfp, fmt, ap);
-	va_end(ap);
-
-	return p;
-}
-EXPORT_SYMBOL(kasprintf);