MERGE-via-pending-tracking-hist-MERGE-via-stable-tracking-MERGE-via-mokopatches-tracking-fix-stray-endmenu-patch-1232632040-1232632141

pending-tracking-hist top was MERGE-via-stable-tracking-MERGE-via-mokopatches-tracking-fix-stray-endmenu-patch-1232632040-1232632141 / fdf777a63bcb59e0dfd78bfe2c6242e01f6d4eb9 ... parent commitmessage:
From: merge <null@invalid>
MERGE-via-stable-tracking-hist-MERGE-via-mokopatches-tracking-fix-stray-endmenu-patch-1232632040

stable-tracking-hist top was MERGE-via-mokopatches-tracking-fix-stray-endmenu-patch-1232632040 / 90463bfd2d5a3c8b52f6e6d71024a00e052b0ced ... parent commitmessage:
From: merge <null@invalid>
MERGE-via-mokopatches-tracking-hist-fix-stray-endmenu-patch

mokopatches-tracking-hist top was fix-stray-endmenu-patch / 3630e0be570de8057e7f8d2fe501ed353cdf34e6 ... parent commitmessage:
From: Andy Green <andy@openmoko.com>
fix-stray-endmenu.patch

Signed-off-by: Andy Green <andy@openmoko.com>

24 files changed, 681 insertions, 360 deletions

diff --git a/lib/Kconfig b/lib/Kconfig
index 85cf7ea978a..03c2c24b908 100644
--- a/lib/Kconfig
+++ b/lib/Kconfig
@@ -13,6 +13,10 @@ config GENERIC_FIND_FIRST_BIT
 config GENERIC_FIND_NEXT_BIT
 	bool
 
+config GENERIC_FIND_LAST_BIT
+	bool
+	default y
+
 config CRC_CCITT
 	tristate "CRC-CCITT functions"
 	help
@@ -64,6 +68,8 @@ config CRC7
 
 config LIBCRC32C
 	tristate "CRC32c (Castagnoli, et al) Cyclic Redundancy-Check"
+	select CRYPTO
+	select CRYPTO_CRC32C
 	help
 	  This option is provided for the case where no in-kernel-tree
 	  modules require CRC32c functions, but a module built outside the
@@ -157,4 +163,15 @@ config CHECK_SIGNATURE
 config HAVE_LMB
 	boolean
 
+config CPUMASK_OFFSTACK
+	bool "Force CPU masks off stack" if DEBUG_PER_CPU_MAPS
+	help
+	  Use dynamic allocation for cpumask_var_t, instead of putting
+	  them on the stack.  This is a bit more expensive, but avoids
+	  stack overflow.
+
+config DISABLE_OBSOLETE_CPUMASK_FUNCTIONS
+       bool "Disable obsolete cpumask functions" if DEBUG_PER_CPU_MAPS
+       depends on EXPERIMENTAL && BROKEN
+
 endmenu
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index b0f239e443b..4c9ae6085c7 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -252,6 +252,14 @@ config DEBUG_OBJECTS_TIMERS
 	  timer routines to track the life time of timer objects and
 	  validate the timer operations.
 
+config DEBUG_OBJECTS_ENABLE_DEFAULT
+	int "debug_objects bootup default value (0-1)"
+        range 0 1
+        default "1"
+        depends on DEBUG_OBJECTS
+        help
+          Debug objects boot parameter default value
+
 config DEBUG_SLAB
 	bool "Debug slab memory allocations"
 	depends on DEBUG_KERNEL && SLAB
@@ -504,6 +512,13 @@ config DEBUG_VIRTUAL
 
 	  If unsure, say N.
 
+config DEBUG_NOMMU_REGIONS
+	bool "Debug the global anon/private NOMMU mapping region tree"
+	depends on DEBUG_KERNEL && !MMU
+	help
+	  This option causes the global tree of anonymous and private mapping
+	  regions to be regularly checked for invalid topology.
+
 config DEBUG_WRITECOUNT
 	bool "Debug filesystem writers count"
 	depends on DEBUG_KERNEL
@@ -545,17 +560,27 @@ config DEBUG_SG
 
 	  If unsure, say N.
 
+config DEBUG_NOTIFIERS
+	bool "Debug notifier call chains"
+	depends on DEBUG_KERNEL
+	help
+	  Enable this to turn on sanity checking for notifier call chains.
+	  This is most useful for kernel developers to make sure that
+	  modules properly unregister themselves from notifier chains.
+	  This is a relatively cheap check but if you care about maximum
+	  performance, say N.
+
 config FRAME_POINTER
 	bool "Compile the kernel with frame pointers"
 	depends on DEBUG_KERNEL && \
-		(X86 || CRIS || M68K || M68KNOMMU || FRV || UML || S390 || \
-		 AVR32 || SUPERH || BLACKFIN || MN10300)
-	default y if DEBUG_INFO && UML
+		(CRIS || M68K || M68KNOMMU || FRV || UML || S390 || \
+		 AVR32 || SUPERH || BLACKFIN || MN10300) || \
+		ARCH_WANT_FRAME_POINTERS
+	default y if (DEBUG_INFO && UML) || ARCH_WANT_FRAME_POINTERS
 	help
-	  If you say Y here the resulting kernel image will be slightly larger
-	  and slower, but it might give very useful debugging information on
-	  some architectures or if you use external debuggers.
-	  If you don't debug the kernel, you can say N.
+	  If you say Y here the resulting kernel image will be slightly
+	  larger and slower, but it gives very useful debugging information
+	  in case of kernel bugs. (precise oopses/stacktraces/warnings)
 
 config BOOT_PRINTK_DELAY
 	bool "Delay each boot printk message by N milliseconds"
@@ -619,6 +644,19 @@ config RCU_CPU_STALL_DETECTOR
 
 	  Say N if you are unsure.
 
+config RCU_CPU_STALL_DETECTOR
+	bool "Check for stalled CPUs delaying RCU grace periods"
+	depends on CLASSIC_RCU || TREE_RCU
+	default n
+	help
+	  This option causes RCU to printk information on which
+	  CPUs are delaying the current grace period, but only when
+	  the grace period extends for excessive time periods.
+
+	  Say Y if you want RCU to perform such checks.
+
+	  Say N if you are unsure.
+
 config KPROBES_SANITY_TEST
 	bool "Kprobes sanity tests"
 	depends on DEBUG_KERNEL
@@ -699,6 +737,7 @@ config FAULT_INJECTION
 config FAILSLAB
 	bool "Fault-injection capability for kmalloc"
 	depends on FAULT_INJECTION
+	depends on SLAB || SLUB
 	help
 	  Provide fault-injection capability for kmalloc.
 
diff --git a/lib/Makefile b/lib/Makefile
index 7cb65d85aeb..32b0e64ded2 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -11,7 +11,7 @@ lib-y := ctype.o string.o vsprintf.o cmdline.o \
 	 rbtree.o radix-tree.o dump_stack.o \
 	 idr.o int_sqrt.o extable.o prio_tree.o \
 	 sha1.o irq_regs.o reciprocal_div.o argv_split.o \
-	 proportions.o prio_heap.o ratelimit.o show_mem.o
+	 proportions.o prio_heap.o ratelimit.o show_mem.o is_single_threaded.o
 
 lib-$(CONFIG_MMU) += ioremap.o
 lib-$(CONFIG_SMP) += cpumask.o
@@ -37,6 +37,7 @@ lib-$(CONFIG_RWSEM_GENERIC_SPINLOCK) += rwsem-spinlock.o
 lib-$(CONFIG_RWSEM_XCHGADD_ALGORITHM) += rwsem.o
 lib-$(CONFIG_GENERIC_FIND_FIRST_BIT) += find_next_bit.o
 lib-$(CONFIG_GENERIC_FIND_NEXT_BIT) += find_next_bit.o
+lib-$(CONFIG_GENERIC_FIND_LAST_BIT) += find_last_bit.o
 obj-$(CONFIG_GENERIC_HWEIGHT) += hweight.o
 obj-$(CONFIG_LOCK_KERNEL) += kernel_lock.o
 obj-$(CONFIG_PLIST) += plist.o
diff --git a/lib/bug.c b/lib/bug.c
index bfeafd60ee9..300e41afbf9 100644
--- a/lib/bug.c
+++ b/lib/bug.c
@@ -5,6 +5,8 @@
 
   CONFIG_BUG - emit BUG traps.  Nothing happens without this.
   CONFIG_GENERIC_BUG - enable this code.
+  CONFIG_GENERIC_BUG_RELATIVE_POINTERS - use 32-bit pointers relative to
+	the containing struct bug_entry for bug_addr and file.
   CONFIG_DEBUG_BUGVERBOSE - emit full file+line information for each BUG
 
   CONFIG_BUG and CONFIG_DEBUG_BUGVERBOSE are potentially user-settable
@@ -43,6 +45,15 @@
 
 extern const struct bug_entry __start___bug_table[], __stop___bug_table[];
 
+static inline unsigned long bug_addr(const struct bug_entry *bug)
+{
+#ifndef CONFIG_GENERIC_BUG_RELATIVE_POINTERS
+	return bug->bug_addr;
+#else
+	return (unsigned long)bug + bug->bug_addr_disp;
+#endif
+}
+
 #ifdef CONFIG_MODULES
 static LIST_HEAD(module_bug_list);
 
@@ -55,7 +66,7 @@ static const struct bug_entry *module_find_bug(unsigned long bugaddr)
 		unsigned i;
 
 		for (i = 0; i < mod->num_bugs; ++i, ++bug)
-			if (bugaddr == bug->bug_addr)
+			if (bugaddr == bug_addr(bug))
 				return bug;
 	}
 	return NULL;
@@ -108,7 +119,7 @@ const struct bug_entry *find_bug(unsigned long bugaddr)
 	const struct bug_entry *bug;
 
 	for (bug = __start___bug_table; bug < __stop___bug_table; ++bug)
-		if (bugaddr == bug->bug_addr)
+		if (bugaddr == bug_addr(bug))
 			return bug;
 
 	return module_find_bug(bugaddr);
@@ -133,7 +144,11 @@ enum bug_trap_type report_bug(unsigned long bugaddr, struct pt_regs *regs)
 
 	if (bug) {
 #ifdef CONFIG_DEBUG_BUGVERBOSE
+#ifndef CONFIG_GENERIC_BUG_RELATIVE_POINTERS
 		file = bug->file;
+#else
+		file = (const char *)bug + bug->file_disp;
+#endif
 		line = bug->line;
 #endif
 		warning = (bug->flags & BUGFLAG_WARNING) != 0;
diff --git a/lib/bust_spinlocks.c b/lib/bust_spinlocks.c
index 486da62b2b0..9681d54b95d 100644
--- a/lib/bust_spinlocks.c
+++ b/lib/bust_spinlocks.c
@@ -12,6 +12,7 @@
 #include <linux/tty.h>
 #include <linux/wait.h>
 #include <linux/vt_kern.h>
+#include <linux/console.h>
 
 
 void __attribute__((weak)) bust_spinlocks(int yes)
@@ -22,6 +23,7 @@ void __attribute__((weak)) bust_spinlocks(int yes)
 #ifdef CONFIG_VT
 		unblank_screen();
 #endif
+		console_unblank();
 		if (--oops_in_progress == 0)
 			wake_up_klogd();
 	}
diff --git a/lib/cpumask.c b/lib/cpumask.c
index 8d03f22c6ce..3389e2440da 100644
--- a/lib/cpumask.c
+++ b/lib/cpumask.c
@@ -76,15 +76,28 @@ int cpumask_any_but(const struct cpumask *mask, unsigned int cpu)
 
 /* These are not inline because of header tangles. */
 #ifdef CONFIG_CPUMASK_OFFSTACK
-bool alloc_cpumask_var(cpumask_var_t *mask, gfp_t flags)
+/**
+ * alloc_cpumask_var_node - allocate a struct cpumask on a given node
+ * @mask: pointer to cpumask_var_t where the cpumask is returned
+ * @flags: GFP_ flags
+ *
+ * Only defined when CONFIG_CPUMASK_OFFSTACK=y, otherwise is
+ * a nop returning a constant 1 (in <linux/cpumask.h>)
+ * Returns TRUE if memory allocation succeeded, FALSE otherwise.
+ *
+ * In addition, mask will be NULL if this fails.  Note that gcc is
+ * usually smart enough to know that mask can never be NULL if
+ * CONFIG_CPUMASK_OFFSTACK=n, so does code elimination in that case
+ * too.
+ */
+bool alloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node)
 {
 	if (likely(slab_is_available()))
-		*mask = kmalloc(cpumask_size(), flags);
+		*mask = kmalloc_node(cpumask_size(), flags, node);
 	else {
 #ifdef CONFIG_DEBUG_PER_CPU_MAPS
 		printk(KERN_ERR
 			"=> alloc_cpumask_var: kmalloc not available!\n");
-		dump_stack();
 #endif
 		*mask = NULL;
 	}
@@ -94,21 +107,64 @@ bool alloc_cpumask_var(cpumask_var_t *mask, gfp_t flags)
 		dump_stack();
 	}
 #endif
+	/* FIXME: Bandaid to save us from old primitives which go to NR_CPUS. */
+	if (*mask) {
+		unsigned int tail;
+		tail = BITS_TO_LONGS(NR_CPUS - nr_cpumask_bits) * sizeof(long);
+		memset(cpumask_bits(*mask) + cpumask_size() - tail,
+		       0, tail);
+	}
+
 	return *mask != NULL;
 }
+EXPORT_SYMBOL(alloc_cpumask_var_node);
+
+/**
+ * alloc_cpumask_var - allocate a struct cpumask
+ * @mask: pointer to cpumask_var_t where the cpumask is returned
+ * @flags: GFP_ flags
+ *
+ * Only defined when CONFIG_CPUMASK_OFFSTACK=y, otherwise is
+ * a nop returning a constant 1 (in <linux/cpumask.h>).
+ *
+ * See alloc_cpumask_var_node.
+ */
+bool alloc_cpumask_var(cpumask_var_t *mask, gfp_t flags)
+{
+	return alloc_cpumask_var_node(mask, flags, numa_node_id());
+}
 EXPORT_SYMBOL(alloc_cpumask_var);
 
+/**
+ * alloc_bootmem_cpumask_var - allocate a struct cpumask from the bootmem arena.
+ * @mask: pointer to cpumask_var_t where the cpumask is returned
+ *
+ * Only defined when CONFIG_CPUMASK_OFFSTACK=y, otherwise is
+ * a nop (in <linux/cpumask.h>).
+ * Either returns an allocated (zero-filled) cpumask, or causes the
+ * system to panic.
+ */
 void __init alloc_bootmem_cpumask_var(cpumask_var_t *mask)
 {
 	*mask = alloc_bootmem(cpumask_size());
 }
 
+/**
+ * free_cpumask_var - frees memory allocated for a struct cpumask.
+ * @mask: cpumask to free
+ *
+ * This is safe on a NULL mask.
+ */
 void free_cpumask_var(cpumask_var_t mask)
 {
 	kfree(mask);
 }
 EXPORT_SYMBOL(free_cpumask_var);
 
+/**
+ * free_bootmem_cpumask_var - frees result of alloc_bootmem_cpumask_var
+ * @mask: cpumask to free
+ */
 void __init free_bootmem_cpumask_var(cpumask_var_t mask)
 {
 	free_bootmem((unsigned long)mask, cpumask_size());
diff --git a/lib/debugobjects.c b/lib/debugobjects.c
index e3ab374e133..5d99be1fd98 100644
--- a/lib/debugobjects.c
+++ b/lib/debugobjects.c
@@ -45,7 +45,9 @@ static struct kmem_cache	*obj_cache;
 static int			debug_objects_maxchain __read_mostly;
 static int			debug_objects_fixups __read_mostly;
 static int			debug_objects_warnings __read_mostly;
-static int			debug_objects_enabled __read_mostly;
+static int			debug_objects_enabled __read_mostly
+				= CONFIG_DEBUG_OBJECTS_ENABLE_DEFAULT;
+
 static struct debug_obj_descr	*descr_test  __read_mostly;
 
 static int __init enable_object_debug(char *str)
diff --git a/lib/dynamic_printk.c b/lib/dynamic_printk.c
index d83660fd6fd..165a19763dc 100644
--- a/lib/dynamic_printk.c
+++ b/lib/dynamic_printk.c
@@ -135,7 +135,7 @@ int unregister_dynamic_debug_module(char *mod_name)
 	nr_entries--;
 out:
 	up(&debug_list_mutex);
-	return 0;
+	return ret;
 }
 EXPORT_SYMBOL_GPL(unregister_dynamic_debug_module);
 
@@ -277,40 +277,34 @@ static ssize_t pr_debug_write(struct file *file, const char __user *buf,
 				dynamic_enabled = DYNAMIC_ENABLED_NONE;
 			}
 			err = 0;
-		} else {
-			if (elem) {
-				if (value && (elem->enable == 0)) {
-					dynamic_printk_enabled |=
-							(1LL << elem->hash1);
-					dynamic_printk_enabled2 |=
-							(1LL << elem->hash2);
-					elem->enable = 1;
-					num_enabled++;
-					dynamic_enabled = DYNAMIC_ENABLED_SOME;
-					err = 0;
-					printk(KERN_DEBUG
-					       "debugging enabled for module %s",
-					       elem->name);
-				} else if (!value && (elem->enable == 1)) {
-					elem->enable = 0;
-					num_enabled--;
-					if (disabled_hash(elem->hash1, true))
-						dynamic_printk_enabled &=
+		} else if (elem) {
+			if (value && (elem->enable == 0)) {
+				dynamic_printk_enabled |= (1LL << elem->hash1);
+				dynamic_printk_enabled2 |= (1LL << elem->hash2);
+				elem->enable = 1;
+				num_enabled++;
+				dynamic_enabled = DYNAMIC_ENABLED_SOME;
+				err = 0;
+				printk(KERN_DEBUG
+					"debugging enabled for module %s\n",
+					elem->name);
+			} else if (!value && (elem->enable == 1)) {
+				elem->enable = 0;
+				num_enabled--;
+				if (disabled_hash(elem->hash1, true))
+					dynamic_printk_enabled &=
 							~(1LL << elem->hash1);
-					if (disabled_hash(elem->hash2, false))
-						dynamic_printk_enabled2 &=
+				if (disabled_hash(elem->hash2, false))
+					dynamic_printk_enabled2 &=
 							~(1LL << elem->hash2);
-					if (num_enabled)
-						dynamic_enabled =
-							DYNAMIC_ENABLED_SOME;
-					else
-						dynamic_enabled =
-							DYNAMIC_ENABLED_NONE;
-					err = 0;
-					printk(KERN_DEBUG
-					       "debugging disabled for module "
-					       "%s", elem->name);
-				}
+				if (num_enabled)
+					dynamic_enabled = DYNAMIC_ENABLED_SOME;
+				else
+					dynamic_enabled = DYNAMIC_ENABLED_NONE;
+				err = 0;
+				printk(KERN_DEBUG
+					"debugging disabled for module %s\n",
+					elem->name);
 			}
 		}
 	}
diff --git a/lib/fault-inject.c b/lib/fault-inject.c
index a50a311554c..f97af55bdd9 100644
--- a/lib/fault-inject.c
+++ b/lib/fault-inject.c
@@ -6,7 +6,6 @@
 #include <linux/fs.h>
 #include <linux/module.h>
 #include <linux/interrupt.h>
-#include <linux/unwind.h>
 #include <linux/stacktrace.h>
 #include <linux/kallsyms.h>
 #include <linux/fault-inject.h>
diff --git a/lib/find_last_bit.c b/lib/find_last_bit.c
new file mode 100644
index 00000000000..5d202e36bdd
--- /dev/null
+++ b/lib/find_last_bit.c
@@ -0,0 +1,45 @@
+/* find_last_bit.c: fallback find next bit implementation
+ *
+ * Copyright (C) 2008 IBM Corporation
+ * Written by Rusty Russell <rusty@rustcorp.com.au>
+ * (Inspired by David Howell's find_next_bit implementation)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/bitops.h>
+#include <linux/module.h>
+#include <asm/types.h>
+#include <asm/byteorder.h>
+
+unsigned long find_last_bit(const unsigned long *addr, unsigned long size)
+{
+	unsigned long words;
+	unsigned long tmp;
+
+	/* Start at final word. */
+	words = size / BITS_PER_LONG;
+
+	/* Partial final word? */
+	if (size & (BITS_PER_LONG-1)) {
+		tmp = (addr[words] & (~0UL >> (BITS_PER_LONG
+					 - (size & (BITS_PER_LONG-1)))));
+		if (tmp)
+			goto found;
+	}
+
+	while (words) {
+		tmp = addr[--words];
+		if (tmp) {
+found:
+			return words * BITS_PER_LONG + __fls(tmp);
+		}
+	}
+
+	/* Not found */
+	return size;
+}
+EXPORT_SYMBOL(find_last_bit);
diff --git a/lib/idr.c b/lib/idr.c
index e728c7fccc4..c11c5765cde 100644
--- a/lib/idr.c
+++ b/lib/idr.c
@@ -121,7 +121,7 @@ int idr_pre_get(struct idr *idp, gfp_t gfp_mask)
 {
 	while (idp->id_free_cnt < IDR_FREE_MAX) {
 		struct idr_layer *new;
-		new = kmem_cache_alloc(idr_layer_cache, gfp_mask);
+		new = kmem_cache_zalloc(idr_layer_cache, gfp_mask);
 		if (new == NULL)
 			return (0);
 		move_to_free_list(idp, new);
@@ -185,6 +185,7 @@ static int sub_alloc(struct idr *idp, int *starting_id, struct idr_layer **pa)
 			new = get_from_free_list(idp);
 			if (!new)
 				return -1;
+			new->layer = l-1;
 			rcu_assign_pointer(p->ary[m], new);
 			p->count++;
 		}
@@ -210,6 +211,7 @@ build_up:
 	if (unlikely(!p)) {
 		if (!(p = get_from_free_list(idp)))
 			return -1;
+		p->layer = 0;
 		layers = 1;
 	}
 	/*
@@ -218,8 +220,14 @@ build_up:
 	 */
 	while ((layers < (MAX_LEVEL - 1)) && (id >= (1 << (layers*IDR_BITS)))) {
 		layers++;
-		if (!p->count)
+		if (!p->count) {
+			/* special case: if the tree is currently empty,
+			 * then we grow the tree by moving the top node
+			 * upwards.
+			 */
+			p->layer++;
 			continue;
+		}
 		if (!(new = get_from_free_list(idp))) {
 			/*
 			 * The allocation failed.  If we built part of
@@ -237,6 +245,7 @@ build_up:
 		}
 		new->ary[0] = p;
 		new->count = 1;
+		new->layer = layers-1;
 		if (p->bitmap == IDR_FULL)
 			__set_bit(0, &new->bitmap);
 		p = new;
@@ -283,7 +292,7 @@ static int idr_get_new_above_int(struct idr *idp, void *ptr, int starting_id)
  * 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
+ * @id returns a value in the range @starting_id ... 0x7fffffff
  */
 int idr_get_new_above(struct idr *idp, void *ptr, int starting_id, int *id)
 {
@@ -493,17 +502,21 @@ void *idr_find(struct idr *idp, int id)
 	int n;
 	struct idr_layer *p;
 
-	n = idp->layers * IDR_BITS;
 	p = rcu_dereference(idp->top);
+	if (!p)
+		return NULL;
+	n = (p->layer+1) * IDR_BITS;
 
 	/* Mask off upper bits we don't use for the search. */
 	id &= MAX_ID_MASK;
 
 	if (id >= (1 << n))
 		return NULL;
+	BUG_ON(n == 0);
 
 	while (n > 0 && p) {
 		n -= IDR_BITS;
+		BUG_ON(n != p->layer*IDR_BITS);
 		p = rcu_dereference(p->ary[(id >> n) & IDR_MASK]);
 	}
 	return((void *)p);
@@ -582,8 +595,11 @@ void *idr_replace(struct idr *idp, void *ptr, int id)
 	int n;
 	struct idr_layer *p, *old_p;
 
-	n = idp->layers * IDR_BITS;
 	p = idp->top;
+	if (!p)
+		return ERR_PTR(-EINVAL);
+
+	n = (p->layer+1) * IDR_BITS;
 
 	id &= MAX_ID_MASK;
 
@@ -607,16 +623,10 @@ void *idr_replace(struct idr *idp, void *ptr, int id)
 }
 EXPORT_SYMBOL(idr_replace);
 
-static void idr_cache_ctor(void *idr_layer)
-{
-	memset(idr_layer, 0, sizeof(struct idr_layer));
-}
-
 void __init idr_init_cache(void)
 {
 	idr_layer_cache = kmem_cache_create("idr_layer_cache",
-				sizeof(struct idr_layer), 0, SLAB_PANIC,
-				idr_cache_ctor);
+				sizeof(struct idr_layer), 0, SLAB_PANIC, NULL);
 }
 
 /**
@@ -707,7 +717,7 @@ EXPORT_SYMBOL(ida_pre_get);
  * 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.
+ * @p_id returns a value in the range @starting_id ... 0x7fffffff.
  */
 int ida_get_new_above(struct ida *ida, int starting_id, int *p_id)
 {
diff --git a/lib/is_single_threaded.c b/lib/is_single_threaded.c
new file mode 100644
index 00000000000..f1ed2fe76c6
--- /dev/null
+++ b/lib/is_single_threaded.c
@@ -0,0 +1,45 @@
+/* Function to determine if a thread group is single threaded or not
+ *
+ * Copyright (C) 2008 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ * - Derived from security/selinux/hooks.c
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+
+#include <linux/sched.h>
+
+/**
+ * is_single_threaded - Determine if a thread group is single-threaded or not
+ * @p: A task in the thread group in question
+ *
+ * This returns true if the thread group to which a task belongs is single
+ * threaded, false if it is not.
+ */
+bool is_single_threaded(struct task_struct *p)
+{
+	struct task_struct *g, *t;
+	struct mm_struct *mm = p->mm;
+
+	if (atomic_read(&p->signal->count) != 1)
+		goto no;
+
+	if (atomic_read(&p->mm->mm_users) != 1) {
+		read_lock(&tasklist_lock);
+		do_each_thread(g, t) {
+			if (t->mm == mm && t != p)
+				goto no_unlock;
+		} while_each_thread(g, t);
+		read_unlock(&tasklist_lock);
+	}
+
+	return true;
+
+no_unlock:
+	read_unlock(&tasklist_lock);
+no:
+	return false;
+}
diff --git a/lib/klist.c b/lib/klist.c
index bbdd3015c2c..573d6068a42 100644
--- a/lib/klist.c
+++ b/lib/klist.c
@@ -36,6 +36,7 @@
 
 #include <linux/klist.h>
 #include <linux/module.h>
+#include <linux/sched.h>
 
 /*
  * Use the lowest bit of n_klist to mark deleted nodes and exclude
@@ -108,7 +109,6 @@ static void add_tail(struct klist *k, struct klist_node *n)
 static void klist_node_init(struct klist *k, struct klist_node *n)
 {
 	INIT_LIST_HEAD(&n->n_node);
-	init_completion(&n->n_removed);
 	kref_init(&n->n_ref);
 	knode_set_klist(n, k);
 	if (k->get)
@@ -171,13 +171,34 @@ void klist_add_before(struct klist_node *n, struct klist_node *pos)
 }
 EXPORT_SYMBOL_GPL(klist_add_before);
 
+struct klist_waiter {
+	struct list_head list;
+	struct klist_node *node;
+	struct task_struct *process;
+	int woken;
+};
+
+static DEFINE_SPINLOCK(klist_remove_lock);
+static LIST_HEAD(klist_remove_waiters);
+
 static void klist_release(struct kref *kref)
 {
+	struct klist_waiter *waiter, *tmp;
 	struct klist_node *n = container_of(kref, struct klist_node, n_ref);
 
 	WARN_ON(!knode_dead(n));
 	list_del(&n->n_node);
-	complete(&n->n_removed);
+	spin_lock(&klist_remove_lock);
+	list_for_each_entry_safe(waiter, tmp, &klist_remove_waiters, list) {
+		if (waiter->node != n)
+			continue;
+
+		waiter->woken = 1;
+		mb();
+		wake_up_process(waiter->process);
+		list_del(&waiter->list);
+	}
+	spin_unlock(&klist_remove_lock);
 	knode_set_klist(n, NULL);
 }
 
@@ -217,8 +238,24 @@ EXPORT_SYMBOL_GPL(klist_del);
  */
 void klist_remove(struct klist_node *n)
 {
+	struct klist_waiter waiter;
+
+	waiter.node = n;
+	waiter.process = current;
+	waiter.woken = 0;
+	spin_lock(&klist_remove_lock);
+	list_add(&waiter.list, &klist_remove_waiters);
+	spin_unlock(&klist_remove_lock);
+
 	klist_del(n);
-	wait_for_completion(&n->n_removed);
+
+	for (;;) {
+		set_current_state(TASK_UNINTERRUPTIBLE);
+		if (waiter.woken)
+			break;
+		schedule();
+	}
+	__set_current_state(TASK_RUNNING);
 }
 EXPORT_SYMBOL_GPL(klist_remove);
 
diff --git a/lib/kobject_uevent.c b/lib/kobject_uevent.c
index 3f914725bda..318328ddbd1 100644
--- a/lib/kobject_uevent.c
+++ b/lib/kobject_uevent.c
@@ -165,7 +165,7 @@ int kobject_uevent_env(struct kobject *kobj, enum kobject_action action,
 	/* keys passed in from the caller */
 	if (envp_ext) {
 		for (i = 0; envp_ext[i]; i++) {
-			retval = add_uevent_var(env, envp_ext[i]);
+			retval = add_uevent_var(env, "%s", envp_ext[i]);
 			if (retval)
 				goto exit;
 		}
@@ -225,8 +225,10 @@ int kobject_uevent_env(struct kobject *kobj, enum kobject_action action,
 			}
 
 			NETLINK_CB(skb).dst_group = 1;
-			netlink_broadcast(uevent_sock, skb, 0, 1, GFP_KERNEL);
-		}
+			retval = netlink_broadcast(uevent_sock, skb, 0, 1,
+						   GFP_KERNEL);
+		} else
+			retval = -ENOMEM;
 	}
 #endif
 
diff --git a/lib/libcrc32c.c b/lib/libcrc32c.c
index b5c3287d8ea..244f5480c89 100644
--- a/lib/libcrc32c.c
+++ b/lib/libcrc32c.c
@@ -30,168 +30,52 @@
  * any later version.
  *
  */
-#include <linux/crc32c.h>
-#include <linux/compiler.h>
-#include <linux/module.h>
-
-MODULE_AUTHOR("Clay Haapala <chaapala@cisco.com>");
-MODULE_DESCRIPTION("CRC32c (Castagnoli) calculations");
-MODULE_LICENSE("GPL");
 
-#define CRC32C_POLY_BE 0x1EDC6F41
-#define CRC32C_POLY_LE 0x82F63B78
+#include <crypto/hash.h>
+#include <linux/err.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
 
-#ifndef CRC_LE_BITS 
-# define CRC_LE_BITS 8
-#endif
+static struct crypto_shash *tfm;
 
+u32 crc32c(u32 crc, const void *address, unsigned int length)
+{
+	struct {
+		struct shash_desc shash;
+		char ctx[crypto_shash_descsize(tfm)];
+	} desc;
+	int err;
 
-/*
- * Haven't generated a big-endian table yet, but the bit-wise version
- * should at least work.
- */
-#if defined CRC_BE_BITS && CRC_BE_BITS != 1
-#undef CRC_BE_BITS
-#endif
-#ifndef CRC_BE_BITS
-# define CRC_BE_BITS 1
-#endif
+	desc.shash.tfm = tfm;
+	desc.shash.flags = 0;
+	*(u32 *)desc.ctx = crc;
 
-EXPORT_SYMBOL(crc32c_le);
+	err = crypto_shash_update(&desc.shash, address, length);
+	BUG_ON(err);
 
-#if CRC_LE_BITS == 1
-/*
- * Compute things bit-wise, as done in crc32.c.  We could share the tight 
- * loop below with crc32 and vary the POLY if we don't find value in terms
- * of space and maintainability in keeping the two modules separate.
- */
-u32 __pure
-crc32c_le(u32 crc, unsigned char const *p, size_t len)
-{
-	int i;
-	while (len--) {
-		crc ^= *p++;
-		for (i = 0; i < 8; i++)
-			crc = (crc >> 1) ^ ((crc & 1) ? CRC32C_POLY_LE : 0);
-	}
-	return crc;
+	return *(u32 *)desc.ctx;
 }
-#else
-
-/*
- * This is the CRC-32C table
- * Generated with:
- * width = 32 bits
- * poly = 0x1EDC6F41
- * reflect input bytes = true
- * reflect output bytes = true
- */
-
-static const u32 crc32c_table[256] = {
-	0x00000000L, 0xF26B8303L, 0xE13B70F7L, 0x1350F3F4L,
-	0xC79A971FL, 0x35F1141CL, 0x26A1E7E8L, 0xD4CA64EBL,
-	0x8AD958CFL, 0x78B2DBCCL, 0x6BE22838L, 0x9989AB3BL,
-	0x4D43CFD0L, 0xBF284CD3L, 0xAC78BF27L, 0x5E133C24L,
-	0x105EC76FL, 0xE235446CL, 0xF165B798L, 0x030E349BL,
-	0xD7C45070L, 0x25AFD373L, 0x36FF2087L, 0xC494A384L,
-	0x9A879FA0L, 0x68EC1CA3L, 0x7BBCEF57L, 0x89D76C54L,
-	0x5D1D08BFL, 0xAF768BBCL, 0xBC267848L, 0x4E4DFB4BL,
-	0x20BD8EDEL, 0xD2D60DDDL, 0xC186FE29L, 0x33ED7D2AL,
-	0xE72719C1L, 0x154C9AC2L, 0x061C6936L, 0xF477EA35L,
-	0xAA64D611L, 0x580F5512L, 0x4B5FA6E6L, 0xB93425E5L,
-	0x6DFE410EL, 0x9F95C20DL, 0x8CC531F9L, 0x7EAEB2FAL,
-	0x30E349B1L, 0xC288CAB2L, 0xD1D83946L, 0x23B3BA45L,
-	0xF779DEAEL, 0x05125DADL, 0x1642AE59L, 0xE4292D5AL,
-	0xBA3A117EL, 0x4851927DL, 0x5B016189L, 0xA96AE28AL,
-	0x7DA08661L, 0x8FCB0562L, 0x9C9BF696L, 0x6EF07595L,
-	0x417B1DBCL, 0xB3109EBFL, 0xA0406D4BL, 0x522BEE48L,
-	0x86E18AA3L, 0x748A09A0L, 0x67DAFA54L, 0x95B17957L,
-	0xCBA24573L, 0x39C9C670L, 0x2A993584L, 0xD8F2B687L,
-	0x0C38D26CL, 0xFE53516FL, 0xED03A29BL, 0x1F682198L,
-	0x5125DAD3L, 0xA34E59D0L, 0xB01EAA24L, 0x42752927L,
-	0x96BF4DCCL, 0x64D4CECFL, 0x77843D3BL, 0x85EFBE38L,
-	0xDBFC821CL, 0x2997011FL, 0x3AC7F2EBL, 0xC8AC71E8L,
-	0x1C661503L, 0xEE0D9600L, 0xFD5D65F4L, 0x0F36E6F7L,
-	0x61C69362L, 0x93AD1061L, 0x80FDE395L, 0x72966096L,
-	0xA65C047DL, 0x5437877EL, 0x4767748AL, 0xB50CF789L,
-	0xEB1FCBADL, 0x197448AEL, 0x0A24BB5AL, 0xF84F3859L,
-	0x2C855CB2L, 0xDEEEDFB1L, 0xCDBE2C45L, 0x3FD5AF46L,
-	0x7198540DL, 0x83F3D70EL, 0x90A324FAL, 0x62C8A7F9L,
-	0xB602C312L, 0x44694011L, 0x5739B3E5L, 0xA55230E6L,
-	0xFB410CC2L, 0x092A8FC1L, 0x1A7A7C35L, 0xE811FF36L,
-	0x3CDB9BDDL, 0xCEB018DEL, 0xDDE0EB2AL, 0x2F8B6829L,
-	0x82F63B78L, 0x709DB87BL, 0x63CD4B8FL, 0x91A6C88CL,
-	0x456CAC67L, 0xB7072F64L, 0xA457DC90L, 0x563C5F93L,
-	0x082F63B7L, 0xFA44E0B4L, 0xE9141340L, 0x1B7F9043L,
-	0xCFB5F4A8L, 0x3DDE77ABL, 0x2E8E845FL, 0xDCE5075CL,
-	0x92A8FC17L, 0x60C37F14L, 0x73938CE0L, 0x81F80FE3L,
-	0x55326B08L, 0xA759E80BL, 0xB4091BFFL, 0x466298FCL,
-	0x1871A4D8L, 0xEA1A27DBL, 0xF94AD42FL, 0x0B21572CL,
-	0xDFEB33C7L, 0x2D80B0C4L, 0x3ED04330L, 0xCCBBC033L,
-	0xA24BB5A6L, 0x502036A5L, 0x4370C551L, 0xB11B4652L,
-	0x65D122B9L, 0x97BAA1BAL, 0x84EA524EL, 0x7681D14DL,
-	0x2892ED69L, 0xDAF96E6AL, 0xC9A99D9EL, 0x3BC21E9DL,
-	0xEF087A76L, 0x1D63F975L, 0x0E330A81L, 0xFC588982L,
-	0xB21572C9L, 0x407EF1CAL, 0x532E023EL, 0xA145813DL,
-	0x758FE5D6L, 0x87E466D5L, 0x94B49521L, 0x66DF1622L,
-	0x38CC2A06L, 0xCAA7A905L, 0xD9F75AF1L, 0x2B9CD9F2L,
-	0xFF56BD19L, 0x0D3D3E1AL, 0x1E6DCDEEL, 0xEC064EEDL,
-	0xC38D26C4L, 0x31E6A5C7L, 0x22B65633L, 0xD0DDD530L,
-	0x0417B1DBL, 0xF67C32D8L, 0xE52CC12CL, 0x1747422FL,
-	0x49547E0BL, 0xBB3FFD08L, 0xA86F0EFCL, 0x5A048DFFL,
-	0x8ECEE914L, 0x7CA56A17L, 0x6FF599E3L, 0x9D9E1AE0L,
-	0xD3D3E1ABL, 0x21B862A8L, 0x32E8915CL, 0xC083125FL,
-	0x144976B4L, 0xE622F5B7L, 0xF5720643L, 0x07198540L,
-	0x590AB964L, 0xAB613A67L, 0xB831C993L, 0x4A5A4A90L,
-	0x9E902E7BL, 0x6CFBAD78L, 0x7FAB5E8CL, 0x8DC0DD8FL,
-	0xE330A81AL, 0x115B2B19L, 0x020BD8EDL, 0xF0605BEEL,
-	0x24AA3F05L, 0xD6C1BC06L, 0xC5914FF2L, 0x37FACCF1L,
-	0x69E9F0D5L, 0x9B8273D6L, 0x88D28022L, 0x7AB90321L,
-	0xAE7367CAL, 0x5C18E4C9L, 0x4F48173DL, 0xBD23943EL,
-	0xF36E6F75L, 0x0105EC76L, 0x12551F82L, 0xE03E9C81L,
-	0x34F4F86AL, 0xC69F7B69L, 0xD5CF889DL, 0x27A40B9EL,
-	0x79B737BAL, 0x8BDCB4B9L, 0x988C474DL, 0x6AE7C44EL,
-	0xBE2DA0A5L, 0x4C4623A6L, 0x5F16D052L, 0xAD7D5351L
-};
 
-/*
- * Steps through buffer one byte at at time, calculates reflected 
- * crc using table.
- */
+EXPORT_SYMBOL(crc32c);
 
-u32 __pure
-crc32c_le(u32 crc, unsigned char const *data, size_t length)
+static int __init libcrc32c_mod_init(void)
 {
-	while (length--)
-		crc =
-		    crc32c_table[(crc ^ *data++) & 0xFFL] ^ (crc >> 8);
+	tfm = crypto_alloc_shash("crc32c", 0, 0);
+	if (IS_ERR(tfm))
+		return PTR_ERR(tfm);
 
-	return crc;
+	return 0;
 }
 
-#endif	/* CRC_LE_BITS == 8 */
-
-EXPORT_SYMBOL(crc32c_be);
-
-#if CRC_BE_BITS == 1
-u32 __pure
-crc32c_be(u32 crc, unsigned char const *p, size_t len)
+static void __exit libcrc32c_mod_fini(void)
 {
-	int i;
-	while (len--) {
-		crc ^= *p++ << 24;
-		for (i = 0; i < 8; i++)
-			crc =
-			    (crc << 1) ^ ((crc & 0x80000000) ? CRC32C_POLY_BE :
-					  0);
-	}
-	return crc;
+	crypto_free_shash(tfm);
 }
-#endif
 
-/*
- * Unit test
- *
- * A small unit test suite is implemented as part of the crypto suite.
- * Select CRYPTO_CRC32C and use the tcrypt module to run the tests.
- */
+module_init(libcrc32c_mod_init);
+module_exit(libcrc32c_mod_fini);
+
+MODULE_AUTHOR("Clay Haapala <chaapala@cisco.com>");
+MODULE_DESCRIPTION("CRC32c (Castagnoli) calculations");
+MODULE_LICENSE("GPL");
diff --git a/lib/percpu_counter.c b/lib/percpu_counter.c
index a8663890a88..aeaa6d73444 100644
--- a/lib/percpu_counter.c
+++ b/lib/percpu_counter.c
@@ -9,10 +9,8 @@
 #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_set(struct percpu_counter *fbc, s64 amount)
 {
@@ -62,20 +60,17 @@ s64 __percpu_counter_sum(struct percpu_counter *fbc)
 	for_each_online_cpu(cpu) {
 		s32 *pcount = per_cpu_ptr(fbc->counters, cpu);
 		ret += *pcount;
-		*pcount = 0;
 	}
-	fbc->count = ret;
-
 	spin_unlock(&fbc->lock);
 	return ret;
 }
 EXPORT_SYMBOL(__percpu_counter_sum);
 
-static struct lock_class_key percpu_counter_irqsafe;
-
-int percpu_counter_init(struct percpu_counter *fbc, s64 amount)
+int __percpu_counter_init(struct percpu_counter *fbc, s64 amount,
+			  struct lock_class_key *key)
 {
 	spin_lock_init(&fbc->lock);
+	lockdep_set_class(&fbc->lock, key);
 	fbc->count = amount;
 	fbc->counters = alloc_percpu(s32);
 	if (!fbc->counters)
@@ -87,40 +82,41 @@ int percpu_counter_init(struct percpu_counter *fbc, s64 amount)
 #endif
 	return 0;
 }
-EXPORT_SYMBOL(percpu_counter_init);
-
-int percpu_counter_init_irq(struct percpu_counter *fbc, s64 amount)
-{
-	int err;
-
-	err = percpu_counter_init(fbc, amount);
-	if (!err)
-		lockdep_set_class(&fbc->lock, &percpu_counter_irqsafe);
-	return err;
-}
+EXPORT_SYMBOL(__percpu_counter_init);
 
 void percpu_counter_destroy(struct percpu_counter *fbc)
 {
 	if (!fbc->counters)
 		return;
 
-	free_percpu(fbc->counters);
-	fbc->counters = NULL;
 #ifdef CONFIG_HOTPLUG_CPU
 	mutex_lock(&percpu_counters_lock);
 	list_del(&fbc->list);
 	mutex_unlock(&percpu_counters_lock);
 #endif
+	free_percpu(fbc->counters);
+	fbc->counters = NULL;
 }
 EXPORT_SYMBOL(percpu_counter_destroy);
 
-#ifdef CONFIG_HOTPLUG_CPU
+int percpu_counter_batch __read_mostly = 32;
+EXPORT_SYMBOL(percpu_counter_batch);
+
+static void compute_batch_value(void)
+{
+	int nr = num_online_cpus();
+
+	percpu_counter_batch = max(32, nr*2);
+}
+
 static int __cpuinit percpu_counter_hotcpu_callback(struct notifier_block *nb,
 					unsigned long action, void *hcpu)
 {
+#ifdef CONFIG_HOTPLUG_CPU
 	unsigned int cpu;
 	struct percpu_counter *fbc;
 
+	compute_batch_value();
 	if (action != CPU_DEAD)
 		return NOTIFY_OK;
 
@@ -137,13 +133,14 @@ static int __cpuinit percpu_counter_hotcpu_callback(struct notifier_block *nb,
 		spin_unlock_irqrestore(&fbc->lock, flags);
 	}
 	mutex_unlock(&percpu_counters_lock);
+#endif
 	return NOTIFY_OK;
 }
 
 static int __init percpu_counter_startup(void)
 {
+	compute_batch_value();
 	hotcpu_notifier(percpu_counter_hotcpu_callback, 0);
 	return 0;
 }
 module_init(percpu_counter_startup);
-#endif
diff --git a/lib/prio_heap.c b/lib/prio_heap.c
index 471944a54e2..a7af6f85eca 100644
--- a/lib/prio_heap.c
+++ b/lib/prio_heap.c
@@ -31,7 +31,7 @@ void *heap_insert(struct ptr_heap *heap, void *p)
 
 	if (heap->size < heap->max) {
 		/* Heap insertion */
-		int pos = heap->size++;
+		pos = heap->size++;
 		while (pos > 0 && heap->gt(p, ptrs[(pos-1)/2])) {
 			ptrs[pos] = ptrs[(pos-1)/2];
 			pos = (pos-1)/2;
diff --git a/lib/proportions.c b/lib/proportions.c
index 4f387a643d7..d50746a79de 100644
--- a/lib/proportions.c
+++ b/lib/proportions.c
@@ -83,11 +83,11 @@ int prop_descriptor_init(struct prop_descriptor *pd, int shift)
 	pd->index = 0;
 	pd->pg[0].shift = shift;
 	mutex_init(&pd->mutex);
-	err = percpu_counter_init_irq(&pd->pg[0].events, 0);
+	err = percpu_counter_init(&pd->pg[0].events, 0);
 	if (err)
 		goto out;
 
-	err = percpu_counter_init_irq(&pd->pg[1].events, 0);
+	err = percpu_counter_init(&pd->pg[1].events, 0);
 	if (err)
 		percpu_counter_destroy(&pd->pg[0].events);
 
@@ -147,6 +147,7 @@ out:
  * this is used to track the active references.
  */
 static struct prop_global *prop_get_global(struct prop_descriptor *pd)
+__acquires(RCU)
 {
 	int index;
 
@@ -160,6 +161,7 @@ static struct prop_global *prop_get_global(struct prop_descriptor *pd)
 }
 
 static void prop_put_global(struct prop_descriptor *pd, struct prop_global *pg)
+__releases(RCU)
 {
 	rcu_read_unlock();
 }
@@ -191,7 +193,7 @@ int prop_local_init_percpu(struct prop_local_percpu *pl)
 	spin_lock_init(&pl->lock);
 	pl->shift = 0;
 	pl->period = 0;
-	return percpu_counter_init_irq(&pl->events, 0);
+	return percpu_counter_init(&pl->events, 0);
 }
 
 void prop_local_destroy_percpu(struct prop_local_percpu *pl)
diff --git a/lib/radix-tree.c b/lib/radix-tree.c
index be86b32bc87..4bb42a0344e 100644
--- a/lib/radix-tree.c
+++ b/lib/radix-tree.c
@@ -81,7 +81,7 @@ struct radix_tree_preload {
 	int nr;
 	struct radix_tree_node *nodes[RADIX_TREE_MAX_PATH];
 };
-DEFINE_PER_CPU(struct radix_tree_preload, radix_tree_preloads) = { 0, };
+static DEFINE_PER_CPU(struct radix_tree_preload, radix_tree_preloads) = { 0, };
 
 static inline gfp_t root_gfp_mask(struct radix_tree_root *root)
 {
@@ -640,13 +640,14 @@ EXPORT_SYMBOL(radix_tree_tag_get);
  *
  *	Returns: the index of the hole if found, otherwise returns an index
  *	outside of the set specified (in which case 'return - index >= max_scan'
- *	will be true).
+ *	will be true). In rare cases of index wrap-around, 0 will be returned.
  *
  *	radix_tree_next_hole may be called under rcu_read_lock. However, like
- *	radix_tree_gang_lookup, this will not atomically search a snapshot of the
- *	tree at a single point in time. For example, if a hole is created at index
- *	5, then subsequently a hole is created at index 10, radix_tree_next_hole
- *	covering both indexes may return 10 if called under rcu_read_lock.
+ *	radix_tree_gang_lookup, this will not atomically search a snapshot of
+ *	the tree at a single point in time. For example, if a hole is created
+ *	at index 5, then subsequently a hole is created at index 10,
+ *	radix_tree_next_hole covering both indexes may return 10 if called
+ *	under rcu_read_lock.
  */
 unsigned long radix_tree_next_hole(struct radix_tree_root *root,
 				unsigned long index, unsigned long max_scan)
diff --git a/lib/rbtree.c b/lib/rbtree.c
index 48499c2d88c..9956b99649f 100644
--- a/lib/rbtree.c
+++ b/lib/rbtree.c
@@ -292,7 +292,7 @@ EXPORT_SYMBOL(rb_erase);
 /*
  * This function returns the first node (in sort order) of the tree.
  */
-struct rb_node *rb_first(struct rb_root *root)
+struct rb_node *rb_first(const struct rb_root *root)
 {
 	struct rb_node	*n;
 
@@ -305,7 +305,7 @@ struct rb_node *rb_first(struct rb_root *root)
 }
 EXPORT_SYMBOL(rb_first);
 
-struct rb_node *rb_last(struct rb_root *root)
+struct rb_node *rb_last(const struct rb_root *root)
 {
 	struct rb_node	*n;
 
@@ -318,7 +318,7 @@ struct rb_node *rb_last(struct rb_root *root)
 }
 EXPORT_SYMBOL(rb_last);
 
-struct rb_node *rb_next(struct rb_node *node)
+struct rb_node *rb_next(const struct rb_node *node)
 {
 	struct rb_node *parent;
 
@@ -331,7 +331,7 @@ struct rb_node *rb_next(struct rb_node *node)
 		node = node->rb_right; 
 		while (node->rb_left)
 			node=node->rb_left;
-		return node;
+		return (struct rb_node *)node;
 	}
 
 	/* No right-hand children.  Everything down and left is
@@ -347,7 +347,7 @@ struct rb_node *rb_next(struct rb_node *node)
 }
 EXPORT_SYMBOL(rb_next);
 
-struct rb_node *rb_prev(struct rb_node *node)
+struct rb_node *rb_prev(const struct rb_node *node)
 {
 	struct rb_node *parent;
 
@@ -360,7 +360,7 @@ struct rb_node *rb_prev(struct rb_node *node)
 		node = node->rb_left; 
 		while (node->rb_right)
 			node=node->rb_right;
-		return node;
+		return (struct rb_node *)node;
 	}
 
 	/* No left-hand children. Go up till we find an ancestor which
diff --git a/lib/scatterlist.c b/lib/scatterlist.c
index 8d2688ff135..b7b449dafbe 100644
--- a/lib/scatterlist.c
+++ b/lib/scatterlist.c
@@ -395,7 +395,7 @@ void sg_miter_stop(struct sg_mapping_iter *miter)
 			WARN_ON(!irqs_disabled());
 			kunmap_atomic(miter->addr, KM_BIO_SRC_IRQ);
 		} else
-			kunmap(miter->addr);
+			kunmap(miter->page);
 
 		miter->page = NULL;
 		miter->addr = NULL;
diff --git a/lib/sort.c b/lib/sort.c
index 6abbaf3d585..926d00429ed 100644
--- a/lib/sort.c
+++ b/lib/sort.c
@@ -32,11 +32,11 @@ static void generic_swap(void *a, void *b, int size)
  * @base: pointer to data to sort
  * @num: number of elements
  * @size: size of each element
- * @cmp: pointer to comparison function
- * @swap: pointer to swap function or NULL
+ * @cmp_func: pointer to comparison function
+ * @swap_func: pointer to swap function or NULL
  *
  * This function does a heapsort on the given array. You may provide a
- * swap function optimized to your element type.
+ * swap_func function optimized to your element type.
  *
  * Sorting time is O(n log n) both on average and worst-case. While
  * qsort is about 20% faster on average, it suffers from exploitable
@@ -45,37 +45,39 @@ static void generic_swap(void *a, void *b, int size)
  */
 
 void sort(void *base, size_t num, size_t size,
-	  int (*cmp)(const void *, const void *),
-	  void (*swap)(void *, void *, int size))
+	  int (*cmp_func)(const void *, const void *),
+	  void (*swap_func)(void *, void *, int size))
 {
 	/* pre-scale counters for performance */
 	int i = (num/2 - 1) * size, n = num * size, c, r;
 
-	if (!swap)
-		swap = (size == 4 ? u32_swap : generic_swap);
+	if (!swap_func)
+		swap_func = (size == 4 ? u32_swap : generic_swap);
 
 	/* heapify */
 	for ( ; i >= 0; i -= size) {
 		for (r = i; r * 2 + size < n; r  = c) {
 			c = r * 2 + size;
-			if (c < n - size && cmp(base + c, base + c + size) < 0)
+			if (c < n - size &&
+					cmp_func(base + c, base + c + size) < 0)
 				c += size;
-			if (cmp(base + r, base + c) >= 0)
+			if (cmp_func(base + r, base + c) >= 0)
 				break;
-			swap(base + r, base + c, size);
+			swap_func(base + r, base + c, size);
 		}
 	}
 
 	/* sort */
 	for (i = n - size; i > 0; i -= size) {
-		swap(base, base + i, size);
+		swap_func(base, base + i, size);
 		for (r = 0; r * 2 + size < i; r = c) {
 			c = r * 2 + size;
-			if (c < i - size && cmp(base + c, base + c + size) < 0)
+			if (c < i - size &&
+					cmp_func(base + c, base + c + size) < 0)
 				c += size;
-			if (cmp(base + r, base + c) >= 0)
+			if (cmp_func(base + r, base + c) >= 0)
 				break;
-			swap(base + r, base + c, size);
+			swap_func(base + r, base + c, size);
 		}
 	}
 }
diff --git a/lib/swiotlb.c b/lib/swiotlb.c
index 78330c37a61..1f991acc2a0 100644
--- a/lib/swiotlb.c
+++ b/lib/swiotlb.c
@@ -14,6 +14,7 @@
  * 04/07/.. ak		Better overflow handling. Assorted fixes.
  * 05/09/10 linville	Add support for syncing ranges, support syncing for
  *			DMA_BIDIRECTIONAL mappings, miscellaneous cleanup.
+ * 08/12/11 beckyb	Add highmem support
  */
 
 #include <linux/cache.h>
@@ -22,8 +23,11 @@
 #include <linux/module.h>
 #include <linux/spinlock.h>
 #include <linux/string.h>
+#include <linux/swiotlb.h>
+#include <linux/pfn.h>
 #include <linux/types.h>
 #include <linux/ctype.h>
+#include <linux/highmem.h>
 
 #include <asm/io.h>
 #include <asm/dma.h>
@@ -36,22 +40,6 @@
 #define OFFSET(val,align) ((unsigned long)	\
 	                   ( (val) & ( (align) - 1)))
 
-#define SG_ENT_VIRT_ADDRESS(sg)	(sg_virt((sg)))
-#define SG_ENT_PHYS_ADDRESS(sg)	virt_to_bus(SG_ENT_VIRT_ADDRESS(sg))
-
-/*
- * Maximum allowable number of contiguous slabs to map,
- * must be a power of 2.  What is the appropriate value ?
- * The complexity of {map,unmap}_single is linearly dependent on this value.
- */
-#define IO_TLB_SEGSIZE	128
-
-/*
- * log of the size of each IO TLB slab.  The number of slabs is command line
- * controllable.
- */
-#define IO_TLB_SHIFT 11
-
 #define SLABS_PER_PAGE (1 << (PAGE_SHIFT - IO_TLB_SHIFT))
 
 /*
@@ -102,7 +90,7 @@ static unsigned int io_tlb_index;
  * We need to save away the original address corresponding to a mapped entry
  * for the sync operations.
  */
-static unsigned char **io_tlb_orig_addr;
+static phys_addr_t *io_tlb_orig_addr;
 
 /*
  * Protect the above data structures in the map and unmap calls
@@ -126,6 +114,56 @@ setup_io_tlb_npages(char *str)
 __setup("swiotlb=", setup_io_tlb_npages);
 /* make io_tlb_overflow tunable too? */
 
+void * __weak __init swiotlb_alloc_boot(size_t size, unsigned long nslabs)
+{
+	return alloc_bootmem_low_pages(size);
+}
+
+void * __weak swiotlb_alloc(unsigned order, unsigned long nslabs)
+{
+	return (void *)__get_free_pages(GFP_DMA | __GFP_NOWARN, order);
+}
+
+dma_addr_t __weak swiotlb_phys_to_bus(struct device *hwdev, phys_addr_t paddr)
+{
+	return paddr;
+}
+
+phys_addr_t __weak swiotlb_bus_to_phys(dma_addr_t baddr)
+{
+	return baddr;
+}
+
+static dma_addr_t swiotlb_virt_to_bus(struct device *hwdev,
+				      volatile void *address)
+{
+	return swiotlb_phys_to_bus(hwdev, virt_to_phys(address));
+}
+
+static void *swiotlb_bus_to_virt(dma_addr_t address)
+{
+	return phys_to_virt(swiotlb_bus_to_phys(address));
+}
+
+int __weak swiotlb_arch_range_needs_mapping(void *ptr, size_t size)
+{
+	return 0;
+}
+
+static void swiotlb_print_info(unsigned long bytes)
+{
+	phys_addr_t pstart, pend;
+
+	pstart = virt_to_phys(io_tlb_start);
+	pend = virt_to_phys(io_tlb_end);
+
+	printk(KERN_INFO "Placing %luMB software IO TLB between %p - %p\n",
+	       bytes >> 20, io_tlb_start, io_tlb_end);
+	printk(KERN_INFO "software IO TLB at phys %#llx - %#llx\n",
+	       (unsigned long long)pstart,
+	       (unsigned long long)pend);
+}
+
 /*
  * Statically reserve bounce buffer space and initialize bounce buffer data
  * structures for the software IO TLB used to implement the DMA API.
@@ -145,7 +183,7 @@ swiotlb_init_with_default_size(size_t default_size)
 	/*
 	 * Get IO TLB memory from the low pages
 	 */
-	io_tlb_start = alloc_bootmem_low_pages(bytes);
+	io_tlb_start = swiotlb_alloc_boot(bytes, io_tlb_nslabs);
 	if (!io_tlb_start)
 		panic("Cannot allocate SWIOTLB buffer");
 	io_tlb_end = io_tlb_start + bytes;
@@ -159,7 +197,7 @@ swiotlb_init_with_default_size(size_t default_size)
 	for (i = 0; i < io_tlb_nslabs; i++)
  		io_tlb_list[i] = IO_TLB_SEGSIZE - OFFSET(i, IO_TLB_SEGSIZE);
 	io_tlb_index = 0;
-	io_tlb_orig_addr = alloc_bootmem(io_tlb_nslabs * sizeof(char *));
+	io_tlb_orig_addr = alloc_bootmem(io_tlb_nslabs * sizeof(phys_addr_t));
 
 	/*
 	 * Get the overflow emergency buffer
@@ -168,8 +206,7 @@ swiotlb_init_with_default_size(size_t default_size)
 	if (!io_tlb_overflow_buffer)
 		panic("Cannot allocate SWIOTLB overflow buffer!\n");
 
-	printk(KERN_INFO "Placing software IO TLB between 0x%lx - 0x%lx\n",
-	       virt_to_bus(io_tlb_start), virt_to_bus(io_tlb_end));
+	swiotlb_print_info(bytes);
 }
 
 void __init
@@ -202,8 +239,7 @@ swiotlb_late_init_with_default_size(size_t default_size)
 	bytes = io_tlb_nslabs << IO_TLB_SHIFT;
 
 	while ((SLABS_PER_PAGE << order) > IO_TLB_MIN_SLABS) {
-		io_tlb_start = (char *)__get_free_pages(GFP_DMA | __GFP_NOWARN,
-		                                        order);
+		io_tlb_start = swiotlb_alloc(order, io_tlb_nslabs);
 		if (io_tlb_start)
 			break;
 		order--;
@@ -235,12 +271,14 @@ swiotlb_late_init_with_default_size(size_t default_size)
  		io_tlb_list[i] = IO_TLB_SEGSIZE - OFFSET(i, IO_TLB_SEGSIZE);
 	io_tlb_index = 0;
 
-	io_tlb_orig_addr = (unsigned char **)__get_free_pages(GFP_KERNEL,
-	                           get_order(io_tlb_nslabs * sizeof(char *)));
+	io_tlb_orig_addr = (phys_addr_t *)
+		__get_free_pages(GFP_KERNEL,
+				 get_order(io_tlb_nslabs *
+					   sizeof(phys_addr_t)));
 	if (!io_tlb_orig_addr)
 		goto cleanup3;
 
-	memset(io_tlb_orig_addr, 0, io_tlb_nslabs * sizeof(char *));
+	memset(io_tlb_orig_addr, 0, io_tlb_nslabs * sizeof(phys_addr_t));
 
 	/*
 	 * Get the overflow emergency buffer
@@ -250,15 +288,13 @@ swiotlb_late_init_with_default_size(size_t default_size)
 	if (!io_tlb_overflow_buffer)
 		goto cleanup4;
 
-	printk(KERN_INFO "Placing %luMB software IO TLB between 0x%lx - "
-	       "0x%lx\n", bytes >> 20,
-	       virt_to_bus(io_tlb_start), virt_to_bus(io_tlb_end));
+	swiotlb_print_info(bytes);
 
 	return 0;
 
 cleanup4:
-	free_pages((unsigned long)io_tlb_orig_addr, get_order(io_tlb_nslabs *
-	                                                      sizeof(char *)));
+	free_pages((unsigned long)io_tlb_orig_addr,
+		   get_order(io_tlb_nslabs * sizeof(phys_addr_t)));
 	io_tlb_orig_addr = NULL;
 cleanup3:
 	free_pages((unsigned long)io_tlb_list, get_order(io_tlb_nslabs *
@@ -279,16 +315,62 @@ address_needs_mapping(struct device *hwdev, dma_addr_t addr, size_t size)
 	return !is_buffer_dma_capable(dma_get_mask(hwdev), addr, size);
 }
 
+static inline int range_needs_mapping(void *ptr, size_t size)
+{
+	return swiotlb_force || swiotlb_arch_range_needs_mapping(ptr, size);
+}
+
 static int is_swiotlb_buffer(char *addr)
 {
 	return addr >= io_tlb_start && addr < io_tlb_end;
 }
 
 /*
+ * Bounce: copy the swiotlb buffer back to the original dma location
+ */
+static void swiotlb_bounce(phys_addr_t phys, char *dma_addr, size_t size,
+			   enum dma_data_direction dir)
+{
+	unsigned long pfn = PFN_DOWN(phys);
+
+	if (PageHighMem(pfn_to_page(pfn))) {
+		/* The buffer does not have a mapping.  Map it in and copy */
+		unsigned int offset = phys & ~PAGE_MASK;
+		char *buffer;
+		unsigned int sz = 0;
+		unsigned long flags;
+
+		while (size) {
+			sz = min(PAGE_SIZE - offset, size);
+
+			local_irq_save(flags);
+			buffer = kmap_atomic(pfn_to_page(pfn),
+					     KM_BOUNCE_READ);
+			if (dir == DMA_TO_DEVICE)
+				memcpy(dma_addr, buffer + offset, sz);
+			else
+				memcpy(buffer + offset, dma_addr, sz);
+			kunmap_atomic(buffer, KM_BOUNCE_READ);
+			local_irq_restore(flags);
+
+			size -= sz;
+			pfn++;
+			dma_addr += sz;
+			offset = 0;
+		}
+	} else {
+		if (dir == DMA_TO_DEVICE)
+			memcpy(dma_addr, phys_to_virt(phys), size);
+		else
+			memcpy(phys_to_virt(phys), dma_addr, size);
+	}
+}
+
+/*
  * Allocates bounce buffer and returns its kernel virtual address.
  */
 static void *
-map_single(struct device *hwdev, char *buffer, size_t size, int dir)
+map_single(struct device *hwdev, phys_addr_t phys, size_t size, int dir)
 {
 	unsigned long flags;
 	char *dma_addr;
@@ -300,9 +382,13 @@ map_single(struct device *hwdev, char *buffer, size_t size, int dir)
 	unsigned long max_slots;
 
 	mask = dma_get_seg_boundary(hwdev);
-	start_dma_addr = virt_to_bus(io_tlb_start) & mask;
+	start_dma_addr = swiotlb_virt_to_bus(hwdev, io_tlb_start) & mask;
 
 	offset_slots = ALIGN(start_dma_addr, 1 << IO_TLB_SHIFT) >> IO_TLB_SHIFT;
+
+	/*
+ 	 * Carefully handle integer overflow which can occur when mask == ~0UL.
+ 	 */
 	max_slots = mask + 1
 		    ? ALIGN(mask + 1, 1 << IO_TLB_SHIFT) >> IO_TLB_SHIFT
 		    : 1UL << (BITS_PER_LONG - IO_TLB_SHIFT);
@@ -379,9 +465,9 @@ found:
 	 * needed.
 	 */
 	for (i = 0; i < nslots; i++)
-		io_tlb_orig_addr[index+i] = buffer + (i << IO_TLB_SHIFT);
+		io_tlb_orig_addr[index+i] = phys + (i << IO_TLB_SHIFT);
 	if (dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL)
-		memcpy(dma_addr, buffer, size);
+		swiotlb_bounce(phys, dma_addr, size, DMA_TO_DEVICE);
 
 	return dma_addr;
 }
@@ -395,17 +481,13 @@ unmap_single(struct device *hwdev, char *dma_addr, size_t size, int dir)
 	unsigned long flags;
 	int i, count, nslots = ALIGN(size, 1 << IO_TLB_SHIFT) >> IO_TLB_SHIFT;
 	int index = (dma_addr - io_tlb_start) >> IO_TLB_SHIFT;
-	char *buffer = io_tlb_orig_addr[index];
+	phys_addr_t phys = io_tlb_orig_addr[index];
 
 	/*
 	 * First, sync the memory before unmapping the entry
 	 */
-	if (buffer && ((dir == DMA_FROM_DEVICE) || (dir == DMA_BIDIRECTIONAL)))
-		/*
-		 * bounce... copy the data back into the original buffer * and
-		 * delete the bounce buffer.
-		 */
-		memcpy(buffer, dma_addr, size);
+	if (phys && ((dir == DMA_FROM_DEVICE) || (dir == DMA_BIDIRECTIONAL)))
+		swiotlb_bounce(phys, dma_addr, size, DMA_FROM_DEVICE);
 
 	/*
 	 * Return the buffer to the free list by setting the corresponding
@@ -438,20 +520,20 @@ sync_single(struct device *hwdev, char *dma_addr, size_t size,
 	    int dir, int target)
 {
 	int index = (dma_addr - io_tlb_start) >> IO_TLB_SHIFT;
-	char *buffer = io_tlb_orig_addr[index];
+	phys_addr_t phys = io_tlb_orig_addr[index];
 
-	buffer += ((unsigned long)dma_addr & ((1 << IO_TLB_SHIFT) - 1));
+	phys += ((unsigned long)dma_addr & ((1 << IO_TLB_SHIFT) - 1));
 
 	switch (target) {
 	case SYNC_FOR_CPU:
 		if (likely(dir == DMA_FROM_DEVICE || dir == DMA_BIDIRECTIONAL))
-			memcpy(buffer, dma_addr, size);
+			swiotlb_bounce(phys, dma_addr, size, DMA_FROM_DEVICE);
 		else
 			BUG_ON(dir != DMA_TO_DEVICE);
 		break;
 	case SYNC_FOR_DEVICE:
 		if (likely(dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL))
-			memcpy(dma_addr, buffer, size);
+			swiotlb_bounce(phys, dma_addr, size, DMA_TO_DEVICE);
 		else
 			BUG_ON(dir != DMA_FROM_DEVICE);
 		break;
@@ -467,9 +549,15 @@ swiotlb_alloc_coherent(struct device *hwdev, size_t size,
 	dma_addr_t dev_addr;
 	void *ret;
 	int order = get_order(size);
+	u64 dma_mask = DMA_32BIT_MASK;
+
+	if (hwdev && hwdev->coherent_dma_mask)
+		dma_mask = hwdev->coherent_dma_mask;
 
 	ret = (void *)__get_free_pages(flags, order);
-	if (ret && address_needs_mapping(hwdev, virt_to_bus(ret), size)) {
+	if (ret &&
+	    !is_buffer_dma_capable(dma_mask, swiotlb_virt_to_bus(hwdev, ret),
+				   size)) {
 		/*
 		 * The allocated memory isn't reachable by the device.
 		 * Fall back on swiotlb_map_single().
@@ -484,18 +572,18 @@ swiotlb_alloc_coherent(struct device *hwdev, size_t size,
 		 * swiotlb_map_single(), which will grab memory from
 		 * the lowest available address range.
 		 */
-		ret = map_single(hwdev, NULL, size, DMA_FROM_DEVICE);
+		ret = map_single(hwdev, 0, size, DMA_FROM_DEVICE);
 		if (!ret)
 			return NULL;
 	}
 
 	memset(ret, 0, size);
-	dev_addr = virt_to_bus(ret);
+	dev_addr = swiotlb_virt_to_bus(hwdev, ret);
 
 	/* Confirm address can be DMA'd by device */
-	if (address_needs_mapping(hwdev, dev_addr, size)) {
+	if (!is_buffer_dma_capable(dma_mask, dev_addr, size)) {
 		printk("hwdev DMA mask = 0x%016Lx, dev_addr = 0x%016Lx\n",
-		       (unsigned long long)*hwdev->dma_mask,
+		       (unsigned long long)dma_mask,
 		       (unsigned long long)dev_addr);
 
 		/* DMA_TO_DEVICE to avoid memcpy in unmap_single */
@@ -505,6 +593,7 @@ swiotlb_alloc_coherent(struct device *hwdev, size_t size,
 	*dma_handle = dev_addr;
 	return ret;
 }
+EXPORT_SYMBOL(swiotlb_alloc_coherent);
 
 void
 swiotlb_free_coherent(struct device *hwdev, size_t size, void *vaddr,
@@ -517,6 +606,7 @@ swiotlb_free_coherent(struct device *hwdev, size_t size, void *vaddr,
 		/* DMA_TO_DEVICE to avoid memcpy in unmap_single */
 		unmap_single(hwdev, vaddr, size, DMA_TO_DEVICE);
 }
+EXPORT_SYMBOL(swiotlb_free_coherent);
 
 static void
 swiotlb_full(struct device *dev, size_t size, int dir, int do_panic)
@@ -529,7 +619,7 @@ swiotlb_full(struct device *dev, size_t size, int dir, int do_panic)
 	 * the damage, or panic when the transfer is too big.
 	 */
 	printk(KERN_ERR "DMA: Out of SW-IOMMU space for %zu bytes at "
-	       "device %s\n", size, dev ? dev->bus_id : "?");
+	       "device %s\n", size, dev ? dev_name(dev) : "?");
 
 	if (size > io_tlb_overflow && do_panic) {
 		if (dir == DMA_FROM_DEVICE || dir == DMA_BIDIRECTIONAL)
@@ -550,7 +640,7 @@ dma_addr_t
 swiotlb_map_single_attrs(struct device *hwdev, void *ptr, size_t size,
 			 int dir, struct dma_attrs *attrs)
 {
-	dma_addr_t dev_addr = virt_to_bus(ptr);
+	dma_addr_t dev_addr = swiotlb_virt_to_bus(hwdev, ptr);
 	void *map;
 
 	BUG_ON(dir == DMA_NONE);
@@ -559,19 +649,20 @@ swiotlb_map_single_attrs(struct device *hwdev, void *ptr, size_t size,
 	 * we can safely return the device addr and not worry about bounce
 	 * buffering it.
 	 */
-	if (!address_needs_mapping(hwdev, dev_addr, size) && !swiotlb_force)
+	if (!address_needs_mapping(hwdev, dev_addr, size) &&
+	    !range_needs_mapping(ptr, size))
 		return dev_addr;
 
 	/*
 	 * Oh well, have to allocate and map a bounce buffer.
 	 */
-	map = map_single(hwdev, ptr, size, dir);
+	map = map_single(hwdev, virt_to_phys(ptr), size, dir);
 	if (!map) {
 		swiotlb_full(hwdev, size, dir, 1);
 		map = io_tlb_overflow_buffer;
 	}
 
-	dev_addr = virt_to_bus(map);
+	dev_addr = swiotlb_virt_to_bus(hwdev, map);
 
 	/*
 	 * Ensure that the address returned is DMA'ble
@@ -588,6 +679,7 @@ swiotlb_map_single(struct device *hwdev, void *ptr, size_t size, int dir)
 {
 	return swiotlb_map_single_attrs(hwdev, ptr, size, dir, NULL);
 }
+EXPORT_SYMBOL(swiotlb_map_single);
 
 /*
  * Unmap a single streaming mode DMA translation.  The dma_addr and size must
@@ -601,7 +693,7 @@ void
 swiotlb_unmap_single_attrs(struct device *hwdev, dma_addr_t dev_addr,
 			   size_t size, int dir, struct dma_attrs *attrs)
 {
-	char *dma_addr = bus_to_virt(dev_addr);
+	char *dma_addr = swiotlb_bus_to_virt(dev_addr);
 
 	BUG_ON(dir == DMA_NONE);
 	if (is_swiotlb_buffer(dma_addr))
@@ -617,6 +709,8 @@ swiotlb_unmap_single(struct device *hwdev, dma_addr_t dev_addr, size_t size,
 {
 	return swiotlb_unmap_single_attrs(hwdev, dev_addr, size, dir, NULL);
 }
+EXPORT_SYMBOL(swiotlb_unmap_single);
+
 /*
  * Make physical memory consistent for a single streaming mode DMA translation
  * after a transfer.
@@ -631,7 +725,7 @@ static void
 swiotlb_sync_single(struct device *hwdev, dma_addr_t dev_addr,
 		    size_t size, int dir, int target)
 {
-	char *dma_addr = bus_to_virt(dev_addr);
+	char *dma_addr = swiotlb_bus_to_virt(dev_addr);
 
 	BUG_ON(dir == DMA_NONE);
 	if (is_swiotlb_buffer(dma_addr))
@@ -646,6 +740,7 @@ swiotlb_sync_single_for_cpu(struct device *hwdev, dma_addr_t dev_addr,
 {
 	swiotlb_sync_single(hwdev, dev_addr, size, dir, SYNC_FOR_CPU);
 }
+EXPORT_SYMBOL(swiotlb_sync_single_for_cpu);
 
 void
 swiotlb_sync_single_for_device(struct device *hwdev, dma_addr_t dev_addr,
@@ -653,6 +748,7 @@ swiotlb_sync_single_for_device(struct device *hwdev, dma_addr_t dev_addr,
 {
 	swiotlb_sync_single(hwdev, dev_addr, size, dir, SYNC_FOR_DEVICE);
 }
+EXPORT_SYMBOL(swiotlb_sync_single_for_device);
 
 /*
  * Same as above, but for a sub-range of the mapping.
@@ -662,7 +758,7 @@ swiotlb_sync_single_range(struct device *hwdev, dma_addr_t dev_addr,
 			  unsigned long offset, size_t size,
 			  int dir, int target)
 {
-	char *dma_addr = bus_to_virt(dev_addr) + offset;
+	char *dma_addr = swiotlb_bus_to_virt(dev_addr) + offset;
 
 	BUG_ON(dir == DMA_NONE);
 	if (is_swiotlb_buffer(dma_addr))
@@ -678,6 +774,7 @@ swiotlb_sync_single_range_for_cpu(struct device *hwdev, dma_addr_t dev_addr,
 	swiotlb_sync_single_range(hwdev, dev_addr, offset, size, dir,
 				  SYNC_FOR_CPU);
 }
+EXPORT_SYMBOL_GPL(swiotlb_sync_single_range_for_cpu);
 
 void
 swiotlb_sync_single_range_for_device(struct device *hwdev, dma_addr_t dev_addr,
@@ -686,9 +783,8 @@ swiotlb_sync_single_range_for_device(struct device *hwdev, dma_addr_t dev_addr,
 	swiotlb_sync_single_range(hwdev, dev_addr, offset, size, dir,
 				  SYNC_FOR_DEVICE);
 }
+EXPORT_SYMBOL_GPL(swiotlb_sync_single_range_for_device);
 
-void swiotlb_unmap_sg_attrs(struct device *, struct scatterlist *, int, int,
-			    struct dma_attrs *);
 /*
  * Map a set of buffers described by scatterlist in streaming mode for DMA.
  * This is the scatter-gather version of the above swiotlb_map_single
@@ -710,18 +806,18 @@ swiotlb_map_sg_attrs(struct device *hwdev, struct scatterlist *sgl, int nelems,
 		     int dir, struct dma_attrs *attrs)
 {
 	struct scatterlist *sg;
-	void *addr;
-	dma_addr_t dev_addr;
 	int i;
 
 	BUG_ON(dir == DMA_NONE);
 
 	for_each_sg(sgl, sg, nelems, i) {
-		addr = SG_ENT_VIRT_ADDRESS(sg);
-		dev_addr = virt_to_bus(addr);
-		if (swiotlb_force ||
+		void *addr = sg_virt(sg);
+		dma_addr_t dev_addr = swiotlb_virt_to_bus(hwdev, addr);
+
+		if (range_needs_mapping(addr, sg->length) ||
 		    address_needs_mapping(hwdev, dev_addr, sg->length)) {
-			void *map = map_single(hwdev, addr, sg->length, dir);
+			void *map = map_single(hwdev, sg_phys(sg),
+					       sg->length, dir);
 			if (!map) {
 				/* Don't panic here, we expect map_sg users
 				   to do proper error handling. */
@@ -731,7 +827,7 @@ swiotlb_map_sg_attrs(struct device *hwdev, struct scatterlist *sgl, int nelems,
 				sgl[0].dma_length = 0;
 				return 0;
 			}
-			sg->dma_address = virt_to_bus(map);
+			sg->dma_address = swiotlb_virt_to_bus(hwdev, map);
 		} else
 			sg->dma_address = dev_addr;
 		sg->dma_length = sg->length;
@@ -746,6 +842,7 @@ swiotlb_map_sg(struct device *hwdev, struct scatterlist *sgl, int nelems,
 {
 	return swiotlb_map_sg_attrs(hwdev, sgl, nelems, dir, NULL);
 }
+EXPORT_SYMBOL(swiotlb_map_sg);
 
 /*
  * Unmap a set of streaming mode DMA translations.  Again, cpu read rules
@@ -761,11 +858,11 @@ swiotlb_unmap_sg_attrs(struct device *hwdev, struct scatterlist *sgl,
 	BUG_ON(dir == DMA_NONE);
 
 	for_each_sg(sgl, sg, nelems, i) {
-		if (sg->dma_address != SG_ENT_PHYS_ADDRESS(sg))
-			unmap_single(hwdev, bus_to_virt(sg->dma_address),
+		if (sg->dma_address != swiotlb_virt_to_bus(hwdev, sg_virt(sg)))
+			unmap_single(hwdev, swiotlb_bus_to_virt(sg->dma_address),
 				     sg->dma_length, dir);
 		else if (dir == DMA_FROM_DEVICE)
-			dma_mark_clean(SG_ENT_VIRT_ADDRESS(sg), sg->dma_length);
+			dma_mark_clean(sg_virt(sg), sg->dma_length);
 	}
 }
 EXPORT_SYMBOL(swiotlb_unmap_sg_attrs);
@@ -776,6 +873,7 @@ swiotlb_unmap_sg(struct device *hwdev, struct scatterlist *sgl, int nelems,
 {
 	return swiotlb_unmap_sg_attrs(hwdev, sgl, nelems, dir, NULL);
 }
+EXPORT_SYMBOL(swiotlb_unmap_sg);
 
 /*
  * Make physical memory consistent for a set of streaming mode DMA translations
@@ -794,11 +892,11 @@ swiotlb_sync_sg(struct device *hwdev, struct scatterlist *sgl,
 	BUG_ON(dir == DMA_NONE);
 
 	for_each_sg(sgl, sg, nelems, i) {
-		if (sg->dma_address != SG_ENT_PHYS_ADDRESS(sg))
-			sync_single(hwdev, bus_to_virt(sg->dma_address),
+		if (sg->dma_address != swiotlb_virt_to_bus(hwdev, sg_virt(sg)))
+			sync_single(hwdev, swiotlb_bus_to_virt(sg->dma_address),
 				    sg->dma_length, dir, target);
 		else if (dir == DMA_FROM_DEVICE)
-			dma_mark_clean(SG_ENT_VIRT_ADDRESS(sg), sg->dma_length);
+			dma_mark_clean(sg_virt(sg), sg->dma_length);
 	}
 }
 
@@ -808,6 +906,7 @@ swiotlb_sync_sg_for_cpu(struct device *hwdev, struct scatterlist *sg,
 {
 	swiotlb_sync_sg(hwdev, sg, nelems, dir, SYNC_FOR_CPU);
 }
+EXPORT_SYMBOL(swiotlb_sync_sg_for_cpu);
 
 void
 swiotlb_sync_sg_for_device(struct device *hwdev, struct scatterlist *sg,
@@ -815,12 +914,14 @@ swiotlb_sync_sg_for_device(struct device *hwdev, struct scatterlist *sg,
 {
 	swiotlb_sync_sg(hwdev, sg, nelems, dir, SYNC_FOR_DEVICE);
 }
+EXPORT_SYMBOL(swiotlb_sync_sg_for_device);
 
 int
 swiotlb_dma_mapping_error(struct device *hwdev, dma_addr_t dma_addr)
 {
-	return (dma_addr == virt_to_bus(io_tlb_overflow_buffer));
+	return (dma_addr == swiotlb_virt_to_bus(hwdev, io_tlb_overflow_buffer));
 }
+EXPORT_SYMBOL(swiotlb_dma_mapping_error);
 
 /*
  * Return whether the given device DMA address mask can be supported
@@ -831,20 +932,6 @@ swiotlb_dma_mapping_error(struct device *hwdev, dma_addr_t dma_addr)
 int
 swiotlb_dma_supported(struct device *hwdev, u64 mask)
 {
-	return virt_to_bus(io_tlb_end - 1) <= mask;
+	return swiotlb_virt_to_bus(hwdev, io_tlb_end - 1) <= mask;
 }
-
-EXPORT_SYMBOL(swiotlb_map_single);
-EXPORT_SYMBOL(swiotlb_unmap_single);
-EXPORT_SYMBOL(swiotlb_map_sg);
-EXPORT_SYMBOL(swiotlb_unmap_sg);
-EXPORT_SYMBOL(swiotlb_sync_single_for_cpu);
-EXPORT_SYMBOL(swiotlb_sync_single_for_device);
-EXPORT_SYMBOL_GPL(swiotlb_sync_single_range_for_cpu);
-EXPORT_SYMBOL_GPL(swiotlb_sync_single_range_for_device);
-EXPORT_SYMBOL(swiotlb_sync_sg_for_cpu);
-EXPORT_SYMBOL(swiotlb_sync_sg_for_device);
-EXPORT_SYMBOL(swiotlb_dma_mapping_error);
-EXPORT_SYMBOL(swiotlb_alloc_coherent);
-EXPORT_SYMBOL(swiotlb_free_coherent);
 EXPORT_SYMBOL(swiotlb_dma_supported);
diff --git a/lib/vsprintf.c b/lib/vsprintf.c
index a013bbc2371..0fbd0121d91 100644
--- a/lib/vsprintf.c
+++ b/lib/vsprintf.c
@@ -170,6 +170,8 @@ int strict_strtoul(const char *cp, unsigned int base, unsigned long *res)
 		return -EINVAL;
 
 	val = simple_strtoul(cp, &tail, base);
+	if (tail == cp)
+		return -EINVAL;
 	if ((*tail == '\0') ||
 		((len == (size_t)(tail - cp) + 1) && (*tail == '\n'))) {
 		*res = val;
@@ -241,6 +243,8 @@ int strict_strtoull(const char *cp, unsigned int base, unsigned long long *res)
 		return -EINVAL;
 
 	val = simple_strtoull(cp, &tail, base);
+	if (tail == cp)
+		return -EINVAL;
 	if ((*tail == '\0') ||
 		((len == (size_t)(tail - cp) + 1) && (*tail == '\n'))) {
 		*res = val;
@@ -581,6 +585,62 @@ static char *resource_string(char *buf, char *end, struct resource *res, int fie
 	return string(buf, end, sym, field_width, precision, flags);
 }
 
+static char *mac_address_string(char *buf, char *end, u8 *addr, int field_width,
+				int precision, int flags)
+{
+	char mac_addr[6 * 3]; /* (6 * 2 hex digits), 5 colons and trailing zero */
+	char *p = mac_addr;
+	int i;
+
+	for (i = 0; i < 6; i++) {
+		p = pack_hex_byte(p, addr[i]);
+		if (!(flags & SPECIAL) && i != 5)
+			*p++ = ':';
+	}
+	*p = '\0';
+
+	return string(buf, end, mac_addr, field_width, precision, flags & ~SPECIAL);
+}
+
+static char *ip6_addr_string(char *buf, char *end, u8 *addr, int field_width,
+			 int precision, int flags)
+{
+	char ip6_addr[8 * 5]; /* (8 * 4 hex digits), 7 colons and trailing zero */
+	char *p = ip6_addr;
+	int i;
+
+	for (i = 0; i < 8; i++) {
+		p = pack_hex_byte(p, addr[2 * i]);
+		p = pack_hex_byte(p, addr[2 * i + 1]);
+		if (!(flags & SPECIAL) && i != 7)
+			*p++ = ':';
+	}
+	*p = '\0';
+
+	return string(buf, end, ip6_addr, field_width, precision, flags & ~SPECIAL);
+}
+
+static char *ip4_addr_string(char *buf, char *end, u8 *addr, int field_width,
+			 int precision, int flags)
+{
+	char ip4_addr[4 * 4]; /* (4 * 3 decimal digits), 3 dots and trailing zero */
+	char temp[3];	/* hold each IP quad in reverse order */
+	char *p = ip4_addr;
+	int i, digits;
+
+	for (i = 0; i < 4; i++) {
+		digits = put_dec_trunc(temp, addr[i]) - temp;
+		/* reverse the digits in the quad */
+		while (digits--)
+			*p++ = temp[digits];
+		if (i != 3)
+			*p++ = '.';
+	}
+	*p = '\0';
+
+	return string(buf, end, ip4_addr, field_width, precision, flags & ~SPECIAL);
+}
+
 /*
  * Show a '%p' thing.  A kernel extension is that the '%p' is followed
  * by an extra set of alphanumeric characters that are extended format
@@ -592,6 +652,12 @@ static char *resource_string(char *buf, char *end, struct resource *res, int fie
  * - 'S' For symbolic direct pointers
  * - 'R' For a struct resource pointer, it prints the range of
  *       addresses (not the name nor the flags)
+ * - 'M' For a 6-byte MAC address, it prints the address in the
+ *       usual colon-separated hex notation
+ * - 'I' [46] for IPv4/IPv6 addresses printed in the usual way (dot-separated
+ *       decimal for v4 and colon separated network-order 16 bit hex for v6)
+ * - 'i' [46] for 'raw' IPv4/IPv6 addresses, IPv6 omits the colons, IPv4 is
+ *       currently the same
  *
  * Note: The difference between 'S' and 'F' is that on ia64 and ppc64
  * function pointers are really function descriptors, which contain a
@@ -599,6 +665,9 @@ static char *resource_string(char *buf, char *end, struct resource *res, int fie
  */
 static char *pointer(const char *fmt, char *buf, char *end, void *ptr, int field_width, int precision, int flags)
 {
+	if (!ptr)
+		return string(buf, end, "(null)", field_width, precision, flags);
+
 	switch (*fmt) {
 	case 'F':
 		ptr = dereference_function_descriptor(ptr);
@@ -607,6 +676,21 @@ static char *pointer(const char *fmt, char *buf, char *end, void *ptr, int field
 		return symbol_string(buf, end, ptr, field_width, precision, flags);
 	case 'R':
 		return resource_string(buf, end, ptr, field_width, precision, flags);
+	case 'm':
+		flags |= SPECIAL;
+		/* Fallthrough */
+	case 'M':
+		return mac_address_string(buf, end, ptr, field_width, precision, flags);
+	case 'i':
+		flags |= SPECIAL;
+		/* Fallthrough */
+	case 'I':
+		if (fmt[1] == '6')
+			return ip6_addr_string(buf, end, ptr, field_width, precision, flags);
+		if (fmt[1] == '4')
+			return ip4_addr_string(buf, end, ptr, field_width, precision, flags);
+		flags &= ~SPECIAL;
+		break;
 	}
 	flags |= SMALL;
 	if (field_width == -1) {