Merge commit 'v2.6.27-rc3' into x86/prototypes

Conflicts:

	include/asm-x86/dma-mapping.h

Signed-off-by: Ingo Molnar <mingo@elte.hu>

27 files changed, 767 insertions, 279 deletions

diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index df27132a56f..800ac848554 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -74,6 +74,9 @@ config DEBUG_FS
 	  debugging files into.  Enable this option to be able to read and
 	  write to these files.
 
+	  For detailed documentation on the debugfs API, see
+	  Documentation/DocBook/filesystems.
+
 	  If unsure, say N.
 
 config HEADERS_CHECK
@@ -147,7 +150,7 @@ config DETECT_SOFTLOCKUP
 	help
 	  Say Y here to enable the kernel to detect "soft lockups",
 	  which are bugs that cause the kernel to loop in kernel
-	  mode for more than 10 seconds, without giving other tasks a
+	  mode for more than 60 seconds, without giving other tasks a
 	  chance to run.
 
 	  When a soft-lockup is detected, the kernel will print the
@@ -159,6 +162,30 @@ config DETECT_SOFTLOCKUP
 	   can be detected via the NMI-watchdog, on platforms that
 	   support it.)
 
+config BOOTPARAM_SOFTLOCKUP_PANIC
+	bool "Panic (Reboot) On Soft Lockups"
+	depends on DETECT_SOFTLOCKUP
+	help
+	  Say Y here to enable the kernel to panic on "soft lockups",
+	  which are bugs that cause the kernel to loop in kernel
+	  mode for more than 60 seconds, without giving other tasks a
+	  chance to run.
+
+	  The panic can be used in combination with panic_timeout,
+	  to cause the system to reboot automatically after a
+	  lockup has been detected. This feature is useful for
+	  high-availability systems that have uptime guarantees and
+	  where a lockup must be resolved ASAP.
+
+	  Say N if unsure.
+
+config BOOTPARAM_SOFTLOCKUP_PANIC_VALUE
+	int
+	depends on DETECT_SOFTLOCKUP
+	range 0 1
+	default 0 if !BOOTPARAM_SOFTLOCKUP_PANIC
+	default 1 if BOOTPARAM_SOFTLOCKUP_PANIC
+
 config SCHED_DEBUG
 	bool "Collect scheduler debugging info"
 	depends on DEBUG_KERNEL && PROC_FS
@@ -478,6 +505,18 @@ config DEBUG_WRITECOUNT
 
 	  If unsure, say N.
 
+config DEBUG_MEMORY_INIT
+	bool "Debug memory initialisation" if EMBEDDED
+	default !EMBEDDED
+	help
+	  Enable this for additional checks during memory initialisation.
+	  The sanity checks verify aspects of the VM such as the memory model
+	  and other information provided by the architecture. Verbose
+	  information will be printed at KERN_DEBUG loglevel depending
+	  on the mminit_loglevel= command-line option.
+
+	  If unsure, say Y
+
 config DEBUG_LIST
 	bool "Debug linked list manipulation"
 	depends on DEBUG_KERNEL
@@ -696,6 +735,15 @@ config FIREWIRE_OHCI_REMOTE_DMA
 
 	  If unsure, say N.
 
+menuconfig BUILD_DOCSRC
+	bool "Build targets in Documentation/ tree"
+	depends on HEADERS_CHECK
+	help
+	  This option attempts to build objects from the source files in the
+	  kernel Documentation/ tree.
+
+	  Say N if you are unsure.
+
 source "samples/Kconfig"
 
 source "lib/Kconfig.kgdb"
diff --git a/lib/Kconfig.kgdb b/lib/Kconfig.kgdb
index a5d4b1dac2a..9b5d1d7f2ef 100644
--- a/lib/Kconfig.kgdb
+++ b/lib/Kconfig.kgdb
@@ -1,20 +1,20 @@
 
-config HAVE_ARCH_KGDB_SHADOW_INFO
-	bool
-
 config HAVE_ARCH_KGDB
 	bool
 
 menuconfig KGDB
 	bool "KGDB: kernel debugging with remote gdb"
-	select FRAME_POINTER
 	depends on HAVE_ARCH_KGDB
 	depends on DEBUG_KERNEL && EXPERIMENTAL
 	help
 	  If you say Y here, it will be possible to remotely debug the
-	  kernel using gdb.  Documentation of kernel debugger is available
-	  at http://kgdb.sourceforge.net as well as in DocBook form
-	  in Documentation/DocBook/.  If unsure, say N.
+	  kernel using gdb.  It is recommended but not required, that
+	  you also turn on the kernel config option
+	  CONFIG_FRAME_POINTER to aid in producing more reliable stack
+	  backtraces in the external debugger.  Documentation of
+	  kernel debugger is available at http://kgdb.sourceforge.net
+	  as well as in DocBook form in Documentation/DocBook/.  If
+	  unsure, say N.
 
 if KGDB
 
diff --git a/lib/Makefile b/lib/Makefile
index 818c4d45551..3b1f94bbe9d 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -11,14 +11,14 @@ 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
+	 proportions.o prio_heap.o ratelimit.o show_mem.o
 
 lib-$(CONFIG_MMU) += ioremap.o
 lib-$(CONFIG_SMP) += cpumask.o
 
 lib-y	+= kobject.o kref.o klist.o
 
-obj-y += div64.o sort.o parser.o halfmd4.o debug_locks.o random32.o \
+obj-y += bcd.o div64.o sort.o parser.o halfmd4.o debug_locks.o random32.o \
 	 bust_spinlocks.o hexdump.o kasprintf.o bitmap.o scatterlist.o
 
 ifeq ($(CONFIG_DEBUG_KOBJECT),y)
@@ -78,6 +78,8 @@ lib-$(CONFIG_GENERIC_BUG) += bug.o
 
 obj-$(CONFIG_HAVE_LMB) += lmb.o
 
+obj-$(CONFIG_HAVE_ARCH_TRACEHOOK) += syscall.o
+
 hostprogs-y	:= gen_crc32table
 clean-files	:= crc32table.h
 
diff --git a/lib/bcd.c b/lib/bcd.c
new file mode 100644
index 00000000000..d74257fd0fe
--- /dev/null
+++ b/lib/bcd.c
@@ -0,0 +1,14 @@
+#include <linux/bcd.h>
+#include <linux/module.h>
+
+unsigned bcd2bin(unsigned char val)
+{
+	return (val & 0x0f) + (val >> 4) * 10;
+}
+EXPORT_SYMBOL(bcd2bin);
+
+unsigned char bin2bcd(unsigned val)
+{
+	return ((val / 10) << 4) + val % 10;
+}
+EXPORT_SYMBOL(bin2bcd);
diff --git a/lib/bitmap.c b/lib/bitmap.c
index 482df94ea21..06fb57c86de 100644
--- a/lib/bitmap.c
+++ b/lib/bitmap.c
@@ -316,6 +316,17 @@ int bitmap_scnprintf(char *buf, unsigned int buflen,
 EXPORT_SYMBOL(bitmap_scnprintf);
 
 /**
+ * bitmap_scnprintf_len - return buffer length needed to convert
+ * bitmap to an ASCII hex string
+ * @nr_bits: number of bits to be converted
+ */
+int bitmap_scnprintf_len(unsigned int nr_bits)
+{
+	unsigned int nr_nibbles = ALIGN(nr_bits, 4) / 4;
+	return nr_nibbles + ALIGN(nr_nibbles, CHUNKSZ / 4) / (CHUNKSZ / 4) - 1;
+}
+
+/**
  * __bitmap_parse - convert an ASCII hex string into a bitmap.
  * @buf: pointer to buffer containing string.
  * @buflen: buffer size in bytes.  If string is smaller than this
diff --git a/lib/cmdline.c b/lib/cmdline.c
index f596c08d213..5ba8a942a47 100644
--- a/lib/cmdline.c
+++ b/lib/cmdline.c
@@ -116,7 +116,7 @@ char *get_options(const char *str, int nints, int *ints)
 /**
  *	memparse - parse a string with mem suffixes into a number
  *	@ptr: Where parse begins
- *	@retptr: (output) Pointer to next char after parse completes
+ *	@retptr: (output) Optional pointer to next char after parse completes
  *
  *	Parses a string into a number.  The number stored at @ptr is
  *	potentially suffixed with %K (for kilobytes, or 1024 bytes),
@@ -126,11 +126,13 @@ char *get_options(const char *str, int nints, int *ints)
  *	megabyte, or one gigabyte, respectively.
  */
 
-unsigned long long memparse (char *ptr, char **retptr)
+unsigned long long memparse(char *ptr, char **retptr)
 {
-	unsigned long long ret = simple_strtoull (ptr, retptr, 0);
+	char *endptr;	/* local pointer to end of parsed string */
 
-	switch (**retptr) {
+	unsigned long long ret = simple_strtoull(ptr, &endptr, 0);
+
+	switch (*endptr) {
 	case 'G':
 	case 'g':
 		ret <<= 10;
@@ -140,10 +142,14 @@ unsigned long long memparse (char *ptr, char **retptr)
 	case 'K':
 	case 'k':
 		ret <<= 10;
-		(*retptr)++;
+		endptr++;
 	default:
 		break;
 	}
+
+	if (retptr)
+		*retptr = endptr;
+
 	return ret;
 }
 
diff --git a/lib/cpumask.c b/lib/cpumask.c
index bb4f76d3c3e..5f97dc25ef9 100644
--- a/lib/cpumask.c
+++ b/lib/cpumask.c
@@ -15,6 +15,15 @@ int __next_cpu(int n, const cpumask_t *srcp)
 }
 EXPORT_SYMBOL(__next_cpu);
 
+#if NR_CPUS > 64
+int __next_cpu_nr(int n, const cpumask_t *srcp)
+{
+	return min_t(int, nr_cpu_ids,
+				find_next_bit(srcp->bits, nr_cpu_ids, n+1));
+}
+EXPORT_SYMBOL(__next_cpu_nr);
+#endif
+
 int __any_online_cpu(const cpumask_t *mask)
 {
 	int cpu;
diff --git a/lib/debug_locks.c b/lib/debug_locks.c
index 0ef01d14727..0218b4693dd 100644
--- a/lib/debug_locks.c
+++ b/lib/debug_locks.c
@@ -8,6 +8,7 @@
  *
  *  Copyright (C) 2006 Red Hat, Inc., Ingo Molnar <mingo@redhat.com>
  */
+#include <linux/kernel.h>
 #include <linux/rwsem.h>
 #include <linux/mutex.h>
 #include <linux/module.h>
@@ -37,6 +38,7 @@ int debug_locks_off(void)
 {
 	if (xchg(&debug_locks, 0)) {
 		if (!debug_locks_silent) {
+			oops_in_progress = 1;
 			console_verbose();
 			return 1;
 		}
diff --git a/lib/debugobjects.c b/lib/debugobjects.c
index 85b18d79be8..45a6bde762d 100644
--- a/lib/debugobjects.c
+++ b/lib/debugobjects.c
@@ -205,9 +205,8 @@ static void debug_print_object(struct debug_obj *obj, char *msg)
 
 	if (limit < 5 && obj->descr != descr_test) {
 		limit++;
-		printk(KERN_ERR "ODEBUG: %s %s object type: %s\n", msg,
+		WARN(1, KERN_ERR "ODEBUG: %s %s object type: %s\n", msg,
 		       obj_states[obj->state], obj->descr->name);
-		WARN_ON(1);
 	}
 	debug_objects_warnings++;
 }
@@ -226,15 +225,13 @@ debug_object_fixup(int (*fixup)(void *addr, enum debug_obj_state state),
 
 static void debug_object_is_on_stack(void *addr, int onstack)
 {
-	void *stack = current->stack;
 	int is_on_stack;
 	static int limit;
 
 	if (limit > 4)
 		return;
 
-	is_on_stack = (addr >= stack && addr < (stack + THREAD_SIZE));
-
+	is_on_stack = object_is_on_stack(addr);
 	if (is_on_stack == onstack)
 		return;
 
@@ -735,26 +732,22 @@ check_results(void *addr, enum debug_obj_state state, int fixups, int warnings)
 
 	obj = lookup_object(addr, db);
 	if (!obj && state != ODEBUG_STATE_NONE) {
-		printk(KERN_ERR "ODEBUG: selftest object not found\n");
-		WARN_ON(1);
+		WARN(1, KERN_ERR "ODEBUG: selftest object not found\n");
 		goto out;
 	}
 	if (obj && obj->state != state) {
-		printk(KERN_ERR "ODEBUG: selftest wrong state: %d != %d\n",
+		WARN(1, KERN_ERR "ODEBUG: selftest wrong state: %d != %d\n",
 		       obj->state, state);
-		WARN_ON(1);
 		goto out;
 	}
 	if (fixups != debug_objects_fixups) {
-		printk(KERN_ERR "ODEBUG: selftest fixups failed %d != %d\n",
+		WARN(1, KERN_ERR "ODEBUG: selftest fixups failed %d != %d\n",
 		       fixups, debug_objects_fixups);
-		WARN_ON(1);
 		goto out;
 	}
 	if (warnings != debug_objects_warnings) {
-		printk(KERN_ERR "ODEBUG: selftest warnings failed %d != %d\n",
+		WARN(1, KERN_ERR "ODEBUG: selftest warnings failed %d != %d\n",
 		       warnings, debug_objects_warnings);
-		WARN_ON(1);
 		goto out;
 	}
 	res = 0;
diff --git a/lib/idr.c b/lib/idr.c
index 7a02e173f02..e728c7fccc4 100644
--- a/lib/idr.c
+++ b/lib/idr.c
@@ -6,6 +6,8 @@
  * Modified by George Anzinger to reuse immediately and to use
  * find bit instructions.  Also removed _irq on spinlocks.
  *
+ * Modified by Nadia Derbey to make it RCU safe.
+ *
  * Small id to pointer translation service.
  *
  * It uses a radix tree like structure as a sparse array indexed
@@ -35,7 +37,7 @@
 
 static struct kmem_cache *idr_layer_cache;
 
-static struct idr_layer *alloc_layer(struct idr *idp)
+static struct idr_layer *get_from_free_list(struct idr *idp)
 {
 	struct idr_layer *p;
 	unsigned long flags;
@@ -50,15 +52,28 @@ static struct idr_layer *alloc_layer(struct idr *idp)
 	return(p);
 }
 
+static void idr_layer_rcu_free(struct rcu_head *head)
+{
+	struct idr_layer *layer;
+
+	layer = container_of(head, struct idr_layer, rcu_head);
+	kmem_cache_free(idr_layer_cache, layer);
+}
+
+static inline void free_layer(struct idr_layer *p)
+{
+	call_rcu(&p->rcu_head, idr_layer_rcu_free);
+}
+
 /* only called when idp->lock is held */
-static void __free_layer(struct idr *idp, struct idr_layer *p)
+static void __move_to_free_list(struct idr *idp, struct idr_layer *p)
 {
 	p->ary[0] = idp->id_free;
 	idp->id_free = p;
 	idp->id_free_cnt++;
 }
 
-static void free_layer(struct idr *idp, struct idr_layer *p)
+static void move_to_free_list(struct idr *idp, struct idr_layer *p)
 {
 	unsigned long flags;
 
@@ -66,7 +81,7 @@ static void free_layer(struct idr *idp, struct idr_layer *p)
 	 * Depends on the return element being zeroed.
 	 */
 	spin_lock_irqsave(&idp->lock, flags);
-	__free_layer(idp, p);
+	__move_to_free_list(idp, p);
 	spin_unlock_irqrestore(&idp->lock, flags);
 }
 
@@ -96,7 +111,7 @@ static void idr_mark_full(struct idr_layer **pa, int id)
  * @gfp_mask:	memory allocation flags
  *
  * This function should be called prior to locking and calling the
- * following function.  It preallocates enough memory to satisfy
+ * idr_get_new* functions. It preallocates enough memory to satisfy
  * the worst possible allocation.
  *
  * If the system is REALLY out of memory this function returns 0,
@@ -109,7 +124,7 @@ int idr_pre_get(struct idr *idp, gfp_t gfp_mask)
 		new = kmem_cache_alloc(idr_layer_cache, gfp_mask);
 		if (new == NULL)
 			return (0);
-		free_layer(idp, new);
+		move_to_free_list(idp, new);
 	}
 	return 1;
 }
@@ -143,7 +158,7 @@ static int sub_alloc(struct idr *idp, int *starting_id, struct idr_layer **pa)
 			/* if already at the top layer, we need to grow */
 			if (!(p = pa[l])) {
 				*starting_id = id;
-				return -2;
+				return IDR_NEED_TO_GROW;
 			}
 
 			/* If we need to go up one layer, continue the
@@ -160,16 +175,17 @@ static int sub_alloc(struct idr *idp, int *starting_id, struct idr_layer **pa)
 			id = ((id >> sh) ^ n ^ m) << sh;
 		}
 		if ((id >= MAX_ID_BIT) || (id < 0))
-			return -3;
+			return IDR_NOMORE_SPACE;
 		if (l == 0)
 			break;
 		/*
 		 * Create the layer below if it is missing.
 		 */
 		if (!p->ary[m]) {
-			if (!(new = alloc_layer(idp)))
+			new = get_from_free_list(idp);
+			if (!new)
 				return -1;
-			p->ary[m] = new;
+			rcu_assign_pointer(p->ary[m], new);
 			p->count++;
 		}
 		pa[l--] = p;
@@ -192,7 +208,7 @@ build_up:
 	p = idp->top;
 	layers = idp->layers;
 	if (unlikely(!p)) {
-		if (!(p = alloc_layer(idp)))
+		if (!(p = get_from_free_list(idp)))
 			return -1;
 		layers = 1;
 	}
@@ -204,7 +220,7 @@ build_up:
 		layers++;
 		if (!p->count)
 			continue;
-		if (!(new = alloc_layer(idp))) {
+		if (!(new = get_from_free_list(idp))) {
 			/*
 			 * The allocation failed.  If we built part of
 			 * the structure tear it down.
@@ -214,7 +230,7 @@ build_up:
 				p = p->ary[0];
 				new->ary[0] = NULL;
 				new->bitmap = new->count = 0;
-				__free_layer(idp, new);
+				__move_to_free_list(idp, new);
 			}
 			spin_unlock_irqrestore(&idp->lock, flags);
 			return -1;
@@ -225,10 +241,10 @@ build_up:
 			__set_bit(0, &new->bitmap);
 		p = new;
 	}
-	idp->top = p;
+	rcu_assign_pointer(idp->top, p);
 	idp->layers = layers;
 	v = sub_alloc(idp, &id, pa);
-	if (v == -2)
+	if (v == IDR_NEED_TO_GROW)
 		goto build_up;
 	return(v);
 }
@@ -244,7 +260,8 @@ static int idr_get_new_above_int(struct idr *idp, void *ptr, int starting_id)
 		 * Successfully found an empty slot.  Install the user
 		 * pointer and mark the slot full.
 		 */
-		pa[0]->ary[id & IDR_MASK] = (struct idr_layer *)ptr;
+		rcu_assign_pointer(pa[0]->ary[id & IDR_MASK],
+				(struct idr_layer *)ptr);
 		pa[0]->count++;
 		idr_mark_full(pa, id);
 	}
@@ -277,12 +294,8 @@ int idr_get_new_above(struct idr *idp, void *ptr, int starting_id, int *id)
 	 * This is a cheap hack until the IDR code can be fixed to
 	 * return proper error values.
 	 */
-	if (rv < 0) {
-		if (rv == -1)
-			return -EAGAIN;
-		else /* Will be -3 */
-			return -ENOSPC;
-	}
+	if (rv < 0)
+		return _idr_rc_to_errno(rv);
 	*id = rv;
 	return 0;
 }
@@ -312,12 +325,8 @@ int idr_get_new(struct idr *idp, void *ptr, int *id)
 	 * This is a cheap hack until the IDR code can be fixed to
 	 * return proper error values.
 	 */
-	if (rv < 0) {
-		if (rv == -1)
-			return -EAGAIN;
-		else /* Will be -3 */
-			return -ENOSPC;
-	}
+	if (rv < 0)
+		return _idr_rc_to_errno(rv);
 	*id = rv;
 	return 0;
 }
@@ -325,7 +334,8 @@ EXPORT_SYMBOL(idr_get_new);
 
 static void idr_remove_warning(int id)
 {
-	printk("idr_remove called for id=%d which is not allocated.\n", id);
+	printk(KERN_WARNING
+		"idr_remove called for id=%d which is not allocated.\n", id);
 	dump_stack();
 }
 
@@ -334,6 +344,7 @@ static void sub_remove(struct idr *idp, int shift, int id)
 	struct idr_layer *p = idp->top;
 	struct idr_layer **pa[MAX_LEVEL];
 	struct idr_layer ***paa = &pa[0];
+	struct idr_layer *to_free;
 	int n;
 
 	*paa = NULL;
@@ -349,13 +360,18 @@ static void sub_remove(struct idr *idp, int shift, int id)
 	n = id & IDR_MASK;
 	if (likely(p != NULL && test_bit(n, &p->bitmap))){
 		__clear_bit(n, &p->bitmap);
-		p->ary[n] = NULL;
+		rcu_assign_pointer(p->ary[n], NULL);
+		to_free = NULL;
 		while(*paa && ! --((**paa)->count)){
-			free_layer(idp, **paa);
+			if (to_free)
+				free_layer(to_free);
+			to_free = **paa;
 			**paa-- = NULL;
 		}
 		if (!*paa)
 			idp->layers = 0;
+		if (to_free)
+			free_layer(to_free);
 	} else
 		idr_remove_warning(id);
 }
@@ -368,22 +384,34 @@ static void sub_remove(struct idr *idp, int shift, int id)
 void idr_remove(struct idr *idp, int id)
 {
 	struct idr_layer *p;
+	struct idr_layer *to_free;
 
 	/* Mask off upper bits we don't use for the search. */
 	id &= MAX_ID_MASK;
 
 	sub_remove(idp, (idp->layers - 1) * IDR_BITS, id);
 	if (idp->top && idp->top->count == 1 && (idp->layers > 1) &&
-	    idp->top->ary[0]) {  // We can drop a layer
-
+	    idp->top->ary[0]) {
+		/*
+		 * Single child at leftmost slot: we can shrink the tree.
+		 * This level is not needed anymore since when layers are
+		 * inserted, they are inserted at the top of the existing
+		 * tree.
+		 */
+		to_free = idp->top;
 		p = idp->top->ary[0];
-		idp->top->bitmap = idp->top->count = 0;
-		free_layer(idp, idp->top);
-		idp->top = p;
+		rcu_assign_pointer(idp->top, p);
 		--idp->layers;
+		to_free->bitmap = to_free->count = 0;
+		free_layer(to_free);
 	}
 	while (idp->id_free_cnt >= IDR_FREE_MAX) {
-		p = alloc_layer(idp);
+		p = get_from_free_list(idp);
+		/*
+		 * Note: we don't call the rcu callback here, since the only
+		 * layers that fall into the freelist are those that have been
+		 * preallocated.
+		 */
 		kmem_cache_free(idr_layer_cache, p);
 	}
 	return;
@@ -424,15 +452,13 @@ void idr_remove_all(struct idr *idp)
 
 		id += 1 << n;
 		while (n < fls(id)) {
-			if (p) {
-				memset(p, 0, sizeof *p);
-				free_layer(idp, p);
-			}
+			if (p)
+				free_layer(p);
 			n += IDR_BITS;
 			p = *--paa;
 		}
 	}
-	idp->top = NULL;
+	rcu_assign_pointer(idp->top, NULL);
 	idp->layers = 0;
 }
 EXPORT_SYMBOL(idr_remove_all);
@@ -444,7 +470,7 @@ EXPORT_SYMBOL(idr_remove_all);
 void idr_destroy(struct idr *idp)
 {
 	while (idp->id_free_cnt) {
-		struct idr_layer *p = alloc_layer(idp);
+		struct idr_layer *p = get_from_free_list(idp);
 		kmem_cache_free(idr_layer_cache, p);
 	}
 }
@@ -459,7 +485,8 @@ EXPORT_SYMBOL(idr_destroy);
  * return indicates that @id is not valid or you passed %NULL in
  * idr_get_new().
  *
- * The caller must serialize idr_find() vs idr_get_new() and idr_remove().
+ * This function can be called under rcu_read_lock(), given that the leaf
+ * pointers lifetimes are correctly managed.
  */
 void *idr_find(struct idr *idp, int id)
 {
@@ -467,7 +494,7 @@ void *idr_find(struct idr *idp, int id)
 	struct idr_layer *p;
 
 	n = idp->layers * IDR_BITS;
-	p = idp->top;
+	p = rcu_dereference(idp->top);
 
 	/* Mask off upper bits we don't use for the search. */
 	id &= MAX_ID_MASK;
@@ -477,7 +504,7 @@ void *idr_find(struct idr *idp, int id)
 
 	while (n > 0 && p) {
 		n -= IDR_BITS;
-		p = p->ary[(id >> n) & IDR_MASK];
+		p = rcu_dereference(p->ary[(id >> n) & IDR_MASK]);
 	}
 	return((void *)p);
 }
@@ -510,7 +537,7 @@ int idr_for_each(struct idr *idp,
 	struct idr_layer **paa = &pa[0];
 
 	n = idp->layers * IDR_BITS;
-	p = idp->top;
+	p = rcu_dereference(idp->top);
 	max = 1 << n;
 
 	id = 0;
@@ -518,7 +545,7 @@ int idr_for_each(struct idr *idp,
 		while (n > 0 && p) {
 			n -= IDR_BITS;
 			*paa++ = p;
-			p = p->ary[(id >> n) & IDR_MASK];
+			p = rcu_dereference(p->ary[(id >> n) & IDR_MASK]);
 		}
 
 		if (p) {
@@ -548,7 +575,7 @@ EXPORT_SYMBOL(idr_for_each);
  * A -ENOENT return indicates that @id was not found.
  * A -EINVAL return indicates that @id was not within valid constraints.
  *
- * The caller must serialize vs idr_find(), idr_get_new(), and idr_remove().
+ * The caller must serialize with writers.
  */
 void *idr_replace(struct idr *idp, void *ptr, int id)
 {
@@ -574,13 +601,13 @@ void *idr_replace(struct idr *idp, void *ptr, int id)
 		return ERR_PTR(-ENOENT);
 
 	old_p = p->ary[n];
-	p->ary[n] = ptr;
+	rcu_assign_pointer(p->ary[n], ptr);
 
 	return old_p;
 }
 EXPORT_SYMBOL(idr_replace);
 
-static void idr_cache_ctor(struct kmem_cache *idr_layer_cache, void *idr_layer)
+static void idr_cache_ctor(void *idr_layer)
 {
 	memset(idr_layer, 0, sizeof(struct idr_layer));
 }
@@ -694,12 +721,8 @@ int ida_get_new_above(struct ida *ida, int starting_id, int *p_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 < 0)
+		return _idr_rc_to_errno(t);
 
 	if (t * IDA_BITMAP_BITS >= MAX_ID_BIT)
 		return -ENOSPC;
@@ -720,7 +743,8 @@ int ida_get_new_above(struct ida *ida, int starting_id, int *p_id)
 			return -EAGAIN;
 
 		memset(bitmap, 0, sizeof(struct ida_bitmap));
-		pa[0]->ary[idr_id & IDR_MASK] = (void *)bitmap;
+		rcu_assign_pointer(pa[0]->ary[idr_id & IDR_MASK],
+				(void *)bitmap);
 		pa[0]->count++;
 	}
 
@@ -749,7 +773,7 @@ int ida_get_new_above(struct ida *ida, int starting_id, int *p_id)
 	 * allocation.
 	 */
 	if (ida->idr.id_free_cnt || ida->free_bitmap) {
-		struct idr_layer *p = alloc_layer(&ida->idr);
+		struct idr_layer *p = get_from_free_list(&ida->idr);
 		if (p)
 			kmem_cache_free(idr_layer_cache, p);
 	}
diff --git a/lib/inflate.c b/lib/inflate.c
index 9762294be06..1a8e8a97812 100644
--- a/lib/inflate.c
+++ b/lib/inflate.c
@@ -230,6 +230,45 @@ STATIC const ush mask_bits[] = {
 #define NEEDBITS(n) {while(k<(n)){b|=((ulg)NEXTBYTE())<<k;k+=8;}}
 #define DUMPBITS(n) {b>>=(n);k-=(n);}
 
+#ifndef NO_INFLATE_MALLOC
+/* A trivial malloc implementation, adapted from
+ *  malloc by Hannu Savolainen 1993 and Matthias Urlichs 1994
+ */
+
+static unsigned long malloc_ptr;
+static int malloc_count;
+
+static void *malloc(int size)
+{
+       void *p;
+
+       if (size < 0)
+		error("Malloc error");
+       if (!malloc_ptr)
+		malloc_ptr = free_mem_ptr;
+
+       malloc_ptr = (malloc_ptr + 3) & ~3;     /* Align */
+
+       p = (void *)malloc_ptr;
+       malloc_ptr += size;
+
+       if (free_mem_end_ptr && malloc_ptr >= free_mem_end_ptr)
+		error("Out of memory");
+
+       malloc_count++;
+       return p;
+}
+
+static void free(void *where)
+{
+       malloc_count--;
+       if (!malloc_count)
+		malloc_ptr = free_mem_ptr;
+}
+#else
+#define malloc(a) kmalloc(a, GFP_KERNEL)
+#define free(a) kfree(a)
+#endif
 
 /*
    Huffman code decoding is performed using a multi-level table lookup.
@@ -1045,7 +1084,6 @@ STATIC int INIT inflate(void)
   int e;                /* last block flag */
   int r;                /* result code */
   unsigned h;           /* maximum struct huft's malloc'ed */
-  void *ptr;
 
   /* initialize window, bit buffer */
   wp = 0;
@@ -1057,12 +1095,12 @@ STATIC int INIT inflate(void)
   h = 0;
   do {
     hufts = 0;
-    gzip_mark(&ptr);
-    if ((r = inflate_block(&e)) != 0) {
-      gzip_release(&ptr);	    
-      return r;
-    }
-    gzip_release(&ptr);
+#ifdef ARCH_HAS_DECOMP_WDOG
+    arch_decomp_wdog();
+#endif
+    r = inflate_block(&e);
+    if (r)
+	    return r;
     if (hufts > h)
       h = hufts;
   } while (!e);
diff --git a/lib/iomap.c b/lib/iomap.c
index 37a3ea4cac9..d3222938515 100644
--- a/lib/iomap.c
+++ b/lib/iomap.c
@@ -40,8 +40,7 @@ static void bad_io_access(unsigned long port, const char *access)
 	static int count = 10;
 	if (count) {
 		count--;
-		printk(KERN_ERR "Bad IO access at port %#lx (%s)\n", port, access);
-		WARN_ON(1);
+		WARN(1, KERN_ERR "Bad IO access at port %#lx (%s)\n", port, access);
 	}
 }
 
diff --git a/lib/kobject.c b/lib/kobject.c
index dcade0543bd..bd732ffebc8 100644
--- a/lib/kobject.c
+++ b/lib/kobject.c
@@ -164,9 +164,8 @@ static int kobject_add_internal(struct kobject *kobj)
 		return -ENOENT;
 
 	if (!kobj->name || !kobj->name[0]) {
-		pr_debug("kobject: (%p): attempted to be registered with empty "
+		WARN(1, "kobject: (%p): attempted to be registered with empty "
 			 "name!\n", kobj);
-		WARN_ON(1);
 		return -EINVAL;
 	}
 
@@ -216,13 +215,19 @@ static int kobject_add_internal(struct kobject *kobj)
 static int kobject_set_name_vargs(struct kobject *kobj, const char *fmt,
 				  va_list vargs)
 {
-	/* Free the old name, if necessary. */
-	kfree(kobj->name);
+	const char *old_name = kobj->name;
+	char *s;
 
 	kobj->name = kvasprintf(GFP_KERNEL, fmt, vargs);
 	if (!kobj->name)
 		return -ENOMEM;
 
+	/* ewww... some of these buggers have '/' in the name ... */
+	s = strchr(kobj->name, '/');
+	if (s)
+		s[0] = '!';
+
+	kfree(old_name);
 	return 0;
 }
 
@@ -577,12 +582,10 @@ static void kobject_release(struct kref *kref)
 void kobject_put(struct kobject *kobj)
 {
 	if (kobj) {
-		if (!kobj->state_initialized) {
-			printk(KERN_WARNING "kobject: '%s' (%p): is not "
+		if (!kobj->state_initialized)
+			WARN(1, KERN_WARNING "kobject: '%s' (%p): is not "
 			       "initialized, yet kobject_put() is being "
 			       "called.\n", kobject_name(kobj), kobj);
-			WARN_ON(1);
-		}
 		kref_put(&kobj->kref, kobject_release);
 	}
 }
diff --git a/lib/kobject_uevent.c b/lib/kobject_uevent.c
index 2fa545a6316..3f914725bda 100644
--- a/lib/kobject_uevent.c
+++ b/lib/kobject_uevent.c
@@ -245,7 +245,8 @@ int kobject_uevent_env(struct kobject *kobj, enum kobject_action action,
 		if (retval)
 			goto exit;
 
-		call_usermodehelper(argv[0], argv, env->envp, UMH_WAIT_EXEC);
+		retval = call_usermodehelper(argv[0], argv,
+					     env->envp, UMH_WAIT_EXEC);
 	}
 
 exit:
@@ -284,8 +285,7 @@ int add_uevent_var(struct kobj_uevent_env *env, const char *format, ...)
 	int len;
 
 	if (env->envp_idx >= ARRAY_SIZE(env->envp)) {
-		printk(KERN_ERR "add_uevent_var: too many keys\n");
-		WARN_ON(1);
+		WARN(1, KERN_ERR "add_uevent_var: too many keys\n");
 		return -ENOMEM;
 	}
 
@@ -296,8 +296,7 @@ int add_uevent_var(struct kobj_uevent_env *env, const char *format, ...)
 	va_end(args);
 
 	if (len >= (sizeof(env->buf) - env->buflen)) {
-		printk(KERN_ERR "add_uevent_var: buffer size too small\n");
-		WARN_ON(1);
+		WARN(1, KERN_ERR "add_uevent_var: buffer size too small\n");
 		return -ENOMEM;
 	}
 
diff --git a/lib/list_debug.c b/lib/list_debug.c
index 4350ba9655b..1a39f4e3ae1 100644
--- a/lib/list_debug.c
+++ b/lib/list_debug.c
@@ -20,18 +20,14 @@ void __list_add(struct list_head *new,
 			      struct list_head *prev,
 			      struct list_head *next)
 {
-	if (unlikely(next->prev != prev)) {
-		printk(KERN_ERR "list_add corruption. next->prev should be "
-			"prev (%p), but was %p. (next=%p).\n",
-			prev, next->prev, next);
-		BUG();
-	}
-	if (unlikely(prev->next != next)) {
-		printk(KERN_ERR "list_add corruption. prev->next should be "
-			"next (%p), but was %p. (prev=%p).\n",
-			next, prev->next, prev);
-		BUG();
-	}
+	WARN(next->prev != prev,
+		"list_add corruption. next->prev should be "
+		"prev (%p), but was %p. (next=%p).\n",
+		prev, next->prev, next);
+	WARN(prev->next != next,
+		"list_add corruption. prev->next should be "
+		"next (%p), but was %p. (prev=%p).\n",
+		next, prev->next, prev);
 	next->prev = new;
 	new->next = next;
 	new->prev = prev;
@@ -40,20 +36,6 @@ void __list_add(struct list_head *new,
 EXPORT_SYMBOL(__list_add);
 
 /**
- * list_add - add a new entry
- * @new: new entry to be added
- * @head: list head to add it after
- *
- * Insert a new entry after the specified head.
- * This is good for implementing stacks.
- */
-void list_add(struct list_head *new, struct list_head *head)
-{
-	__list_add(new, head, head->next);
-}
-EXPORT_SYMBOL(list_add);
-
-/**
  * list_del - deletes entry from list.
  * @entry: the element to delete from the list.
  * Note: list_empty on entry does not return true after this, the entry is
@@ -61,16 +43,12 @@ EXPORT_SYMBOL(list_add);
  */
 void list_del(struct list_head *entry)
 {
-	if (unlikely(entry->prev->next != entry)) {
-		printk(KERN_ERR "list_del corruption. prev->next should be %p, "
-				"but was %p\n", entry, entry->prev->next);
-		BUG();
-	}
-	if (unlikely(entry->next->prev != entry)) {
-		printk(KERN_ERR "list_del corruption. next->prev should be %p, "
-				"but was %p\n", entry, entry->next->prev);
-		BUG();
-	}
+	WARN(entry->prev->next != entry,
+		"list_del corruption. prev->next should be %p, "
+		"but was %p\n", entry, entry->prev->next);
+	WARN(entry->next->prev != entry,
+		"list_del corruption. next->prev should be %p, "
+		"but was %p\n", entry, entry->next->prev);
 	__list_del(entry->prev, entry->next);
 	entry->next = LIST_POISON1;
 	entry->prev = LIST_POISON2;
diff --git a/lib/lzo/lzo1x_decompress.c b/lib/lzo/lzo1x_decompress.c
index 77f0f9b775a..5dc6b29c157 100644
--- a/lib/lzo/lzo1x_decompress.c
+++ b/lib/lzo/lzo1x_decompress.c
@@ -138,8 +138,7 @@ match:
 					t += 31 + *ip++;
 				}
 				m_pos = op - 1;
-				m_pos -= le16_to_cpu(get_unaligned(
-					(const unsigned short *)ip)) >> 2;
+				m_pos -= get_unaligned_le16(ip) >> 2;
 				ip += 2;
 			} else if (t >= 16) {
 				m_pos = op;
@@ -157,8 +156,7 @@ match:
 					}
 					t += 7 + *ip++;
 				}
-				m_pos -= le16_to_cpu(get_unaligned(
-					(const unsigned short *)ip)) >> 2;
+				m_pos -= get_unaligned_le16(ip) >> 2;
 				ip += 2;
 				if (m_pos == op)
 					goto eof_found;
diff --git a/lib/plist.c b/lib/plist.c
index 3074a02272f..d6c64a824e1 100644
--- a/lib/plist.c
+++ b/lib/plist.c
@@ -31,12 +31,13 @@
 static void plist_check_prev_next(struct list_head *t, struct list_head *p,
 				  struct list_head *n)
 {
-	if (n->prev != p || p->next != n) {
-		printk("top: %p, n: %p, p: %p\n", t, t->next, t->prev);
-		printk("prev: %p, n: %p, p: %p\n", p, p->next, p->prev);
-		printk("next: %p, n: %p, p: %p\n", n, n->next, n->prev);
-		WARN_ON(1);
-	}
+	WARN(n->prev != p || p->next != n,
+			"top: %p, n: %p, p: %p\n"
+			"prev: %p, n: %p, p: %p\n"
+			"next: %p, n: %p, p: %p\n",
+			 t, t->next, t->prev,
+			p, p->next, p->prev,
+			n, n->next, n->prev);
 }
 
 static void plist_check_list(struct list_head *top)
diff --git a/lib/radix-tree.c b/lib/radix-tree.c
index 56ec21a7f73..be86b32bc87 100644
--- a/lib/radix-tree.c
+++ b/lib/radix-tree.c
@@ -359,18 +359,17 @@ EXPORT_SYMBOL(radix_tree_insert);
  *	Returns:  the slot corresponding to the position @index in the
  *	radix tree @root. This is useful for update-if-exists operations.
  *
- *	This function cannot be called under rcu_read_lock, it must be
- *	excluded from writers, as must the returned slot for subsequent
- *	use by radix_tree_deref_slot() and radix_tree_replace slot.
- *	Caller must hold tree write locked across slot lookup and
- *	replace.
+ *	This function can be called under rcu_read_lock iff the slot is not
+ *	modified by radix_tree_replace_slot, otherwise it must be called
+ *	exclusive from other writers. Any dereference of the slot must be done
+ *	using radix_tree_deref_slot.
  */
 void **radix_tree_lookup_slot(struct radix_tree_root *root, unsigned long index)
 {
 	unsigned int height, shift;
 	struct radix_tree_node *node, **slot;
 
-	node = root->rnode;
+	node = rcu_dereference(root->rnode);
 	if (node == NULL)
 		return NULL;
 
@@ -390,7 +389,7 @@ void **radix_tree_lookup_slot(struct radix_tree_root *root, unsigned long index)
 	do {
 		slot = (struct radix_tree_node **)
 			(node->slots + ((index>>shift) & RADIX_TREE_MAP_MASK));
-		node = *slot;
+		node = rcu_dereference(*slot);
 		if (node == NULL)
 			return NULL;
 
@@ -667,7 +666,7 @@ unsigned long radix_tree_next_hole(struct radix_tree_root *root,
 EXPORT_SYMBOL(radix_tree_next_hole);
 
 static unsigned int
-__lookup(struct radix_tree_node *slot, void **results, unsigned long index,
+__lookup(struct radix_tree_node *slot, void ***results, unsigned long index,
 	unsigned int max_items, unsigned long *next_index)
 {
 	unsigned int nr_found = 0;
@@ -701,11 +700,9 @@ __lookup(struct radix_tree_node *slot, void **results, unsigned long index,
 
 	/* Bottom level: grab some items */
 	for (i = index & RADIX_TREE_MAP_MASK; i < RADIX_TREE_MAP_SIZE; i++) {
-		struct radix_tree_node *node;
 		index++;
-		node = slot->slots[i];
-		if (node) {
-			results[nr_found++] = rcu_dereference(node);
+		if (slot->slots[i]) {
+			results[nr_found++] = &(slot->slots[i]);
 			if (nr_found == max_items)
 				goto out;
 		}
@@ -759,13 +756,22 @@ radix_tree_gang_lookup(struct radix_tree_root *root, void **results,
 
 	ret = 0;
 	while (ret < max_items) {
-		unsigned int nr_found;
+		unsigned int nr_found, slots_found, i;
 		unsigned long next_index;	/* Index of next search */
 
 		if (cur_index > max_index)
 			break;
-		nr_found = __lookup(node, results + ret, cur_index,
+		slots_found = __lookup(node, (void ***)results + ret, cur_index,
 					max_items - ret, &next_index);
+		nr_found = 0;
+		for (i = 0; i < slots_found; i++) {
+			struct radix_tree_node *slot;
+			slot = *(((void ***)results)[ret + i]);
+			if (!slot)
+				continue;
+			results[ret + nr_found] = rcu_dereference(slot);
+			nr_found++;
+		}
 		ret += nr_found;
 		if (next_index == 0)
 			break;
@@ -776,12 +782,71 @@ radix_tree_gang_lookup(struct radix_tree_root *root, void **results,
 }
 EXPORT_SYMBOL(radix_tree_gang_lookup);
 
+/**
+ *	radix_tree_gang_lookup_slot - perform multiple slot lookup on radix tree
+ *	@root:		radix tree root
+ *	@results:	where the results of the lookup are placed
+ *	@first_index:	start the lookup from this key
+ *	@max_items:	place up to this many items at *results
+ *
+ *	Performs an index-ascending scan of the tree for present items.  Places
+ *	their slots at *@results and returns the number of items which were
+ *	placed at *@results.
+ *
+ *	The implementation is naive.
+ *
+ *	Like radix_tree_gang_lookup as far as RCU and locking goes. Slots must
+ *	be dereferenced with radix_tree_deref_slot, and if using only RCU
+ *	protection, radix_tree_deref_slot may fail requiring a retry.
+ */
+unsigned int
+radix_tree_gang_lookup_slot(struct radix_tree_root *root, void ***results,
+			unsigned long first_index, unsigned int max_items)
+{
+	unsigned long max_index;
+	struct radix_tree_node *node;
+	unsigned long cur_index = first_index;
+	unsigned int ret;
+
+	node = rcu_dereference(root->rnode);
+	if (!node)
+		return 0;
+
+	if (!radix_tree_is_indirect_ptr(node)) {
+		if (first_index > 0)
+			return 0;
+		results[0] = (void **)&root->rnode;
+		return 1;
+	}
+	node = radix_tree_indirect_to_ptr(node);
+
+	max_index = radix_tree_maxindex(node->height);
+
+	ret = 0;
+	while (ret < max_items) {
+		unsigned int slots_found;
+		unsigned long next_index;	/* Index of next search */
+
+		if (cur_index > max_index)
+			break;
+		slots_found = __lookup(node, results + ret, cur_index,
+					max_items - ret, &next_index);
+		ret += slots_found;
+		if (next_index == 0)
+			break;
+		cur_index = next_index;
+	}
+
+	return ret;
+}
+EXPORT_SYMBOL(radix_tree_gang_lookup_slot);
+
 /*
  * FIXME: the two tag_get()s here should use find_next_bit() instead of
  * open-coding the search.
  */
 static unsigned int
-__lookup_tag(struct radix_tree_node *slot, void **results, unsigned long index,
+__lookup_tag(struct radix_tree_node *slot, void ***results, unsigned long index,
 	unsigned int max_items, unsigned long *next_index, unsigned int tag)
 {
 	unsigned int nr_found = 0;
@@ -811,11 +876,9 @@ __lookup_tag(struct radix_tree_node *slot, void **results, unsigned long index,
 			unsigned long j = index & RADIX_TREE_MAP_MASK;
 
 			for ( ; j < RADIX_TREE_MAP_SIZE; j++) {
-				struct radix_tree_node *node;
 				index++;
 				if (!tag_get(slot, tag, j))
 					continue;
-				node = slot->slots[j];
 				/*
 				 * Even though the tag was found set, we need to
 				 * recheck that we have a non-NULL node, because
@@ -826,9 +889,8 @@ __lookup_tag(struct radix_tree_node *slot, void **results, unsigned long index,
 				 * lookup ->slots[x] without a lock (ie. can't
 				 * rely on its value remaining the same).
 				 */
-				if (node) {
-					node = rcu_dereference(node);
-					results[nr_found++] = node;
+				if (slot->slots[j]) {
+					results[nr_found++] = &(slot->slots[j]);
 					if (nr_found == max_items)
 						goto out;
 				}
@@ -887,13 +949,22 @@ radix_tree_gang_lookup_tag(struct radix_tree_root *root, void **results,
 
 	ret = 0;
 	while (ret < max_items) {
-		unsigned int nr_found;
+		unsigned int nr_found, slots_found, i;
 		unsigned long next_index;	/* Index of next search */
 
 		if (cur_index > max_index)
 			break;
-		nr_found = __lookup_tag(node, results + ret, cur_index,
-					max_items - ret, &next_index, tag);
+		slots_found = __lookup_tag(node, (void ***)results + ret,
+				cur_index, max_items - ret, &next_index, tag);
+		nr_found = 0;
+		for (i = 0; i < slots_found; i++) {
+			struct radix_tree_node *slot;
+			slot = *(((void ***)results)[ret + i]);
+			if (!slot)
+				continue;
+			results[ret + nr_found] = rcu_dereference(slot);
+			nr_found++;
+		}
 		ret += nr_found;
 		if (next_index == 0)
 			break;
@@ -905,6 +976,67 @@ radix_tree_gang_lookup_tag(struct radix_tree_root *root, void **results,
 EXPORT_SYMBOL(radix_tree_gang_lookup_tag);
 
 /**
+ *	radix_tree_gang_lookup_tag_slot - perform multiple slot lookup on a
+ *					  radix tree based on a tag
+ *	@root:		radix tree root
+ *	@results:	where the results of the lookup are placed
+ *	@first_index:	start the lookup from this key
+ *	@max_items:	place up to this many items at *results
+ *	@tag:		the tag index (< RADIX_TREE_MAX_TAGS)
+ *
+ *	Performs an index-ascending scan of the tree for present items which
+ *	have the tag indexed by @tag set.  Places the slots at *@results and
+ *	returns the number of slots which were placed at *@results.
+ */
+unsigned int
+radix_tree_gang_lookup_tag_slot(struct radix_tree_root *root, void ***results,
+		unsigned long first_index, unsigned int max_items,
+		unsigned int tag)
+{
+	struct radix_tree_node *node;
+	unsigned long max_index;
+	unsigned long cur_index = first_index;
+	unsigned int ret;
+
+	/* check the root's tag bit */
+	if (!root_tag_get(root, tag))
+		return 0;
+
+	node = rcu_dereference(root->rnode);
+	if (!node)
+		return 0;
+
+	if (!radix_tree_is_indirect_ptr(node)) {
+		if (first_index > 0)
+			return 0;
+		results[0] = (void **)&root->rnode;
+		return 1;
+	}
+	node = radix_tree_indirect_to_ptr(node);
+
+	max_index = radix_tree_maxindex(node->height);
+
+	ret = 0;
+	while (ret < max_items) {
+		unsigned int slots_found;
+		unsigned long next_index;	/* Index of next search */
+
+		if (cur_index > max_index)
+			break;
+		slots_found = __lookup_tag(node, results + ret,
+				cur_index, max_items - ret, &next_index, tag);
+		ret += slots_found;
+		if (next_index == 0)
+			break;
+		cur_index = next_index;
+	}
+
+	return ret;
+}
+EXPORT_SYMBOL(radix_tree_gang_lookup_tag_slot);
+
+
+/**
  *	radix_tree_shrink    -    shrink height of a radix tree to minimal
  *	@root		radix tree root
  */
@@ -1051,7 +1183,7 @@ int radix_tree_tagged(struct radix_tree_root *root, unsigned int tag)
 EXPORT_SYMBOL(radix_tree_tagged);
 
 static void
-radix_tree_node_ctor(struct kmem_cache *cachep, void *node)
+radix_tree_node_ctor(void *node)
 {
 	memset(node, 0, sizeof(struct radix_tree_node));
 }
diff --git a/lib/random32.c b/lib/random32.c
index ca87d86992b..217d5c4b666 100644
--- a/lib/random32.c
+++ b/lib/random32.c
@@ -56,23 +56,12 @@ static u32 __random32(struct rnd_state *state)
 	return (state->s1 ^ state->s2 ^ state->s3);
 }
 
-static void __set_random32(struct rnd_state *state, unsigned long s)
+/*
+ * Handle minimum values for seeds
+ */
+static inline u32 __seed(u32 x, u32 m)
 {
-	if (s == 0)
-		s = 1;      /* default seed is 1 */
-
-#define LCG(n) (69069 * n)
-	state->s1 = LCG(s);
-	state->s2 = LCG(state->s1);
-	state->s3 = LCG(state->s2);
-
-	/* "warm it up" */
-	__random32(state);
-	__random32(state);
-	__random32(state);
-	__random32(state);
-	__random32(state);
-	__random32(state);
+	return (x < m) ? x + m : x;
 }
 
 /**
@@ -107,7 +96,7 @@ void srandom32(u32 entropy)
 	 */
 	for_each_possible_cpu (i) {
 		struct rnd_state *state = &per_cpu(net_rand_state, i);
-		__set_random32(state, state->s1 ^ entropy);
+		state->s1 = __seed(state->s1 ^ entropy, 1);
 	}
 }
 EXPORT_SYMBOL(srandom32);
@@ -122,7 +111,19 @@ static int __init random32_init(void)
 
 	for_each_possible_cpu(i) {
 		struct rnd_state *state = &per_cpu(net_rand_state,i);
-		__set_random32(state, i + jiffies);
+
+#define LCG(x)	((x) * 69069)	/* super-duper LCG */
+		state->s1 = __seed(LCG(i + jiffies), 1);
+		state->s2 = __seed(LCG(state->s1), 7);
+		state->s3 = __seed(LCG(state->s2), 15);
+
+		/* "warm it up" */
+		__random32(state);
+		__random32(state);
+		__random32(state);
+		__random32(state);
+		__random32(state);
+		__random32(state);
 	}
 	return 0;
 }
@@ -135,13 +136,18 @@ core_initcall(random32_init);
 static int __init random32_reseed(void)
 {
 	int i;
-	unsigned long seed;
 
 	for_each_possible_cpu(i) {
 		struct rnd_state *state = &per_cpu(net_rand_state,i);
+		u32 seeds[3];
+
+		get_random_bytes(&seeds, sizeof(seeds));
+		state->s1 = __seed(seeds[0], 1);
+		state->s2 = __seed(seeds[1], 7);
+		state->s3 = __seed(seeds[2], 15);
 
-		get_random_bytes(&seed, sizeof(seed));
-		__set_random32(state, seed);
+		/* mix it in */
+		__random32(state);
 	}
 	return 0;
 }
diff --git a/lib/ratelimit.c b/lib/ratelimit.c
index 485e3040dcd..26187edcc7e 100644
--- a/lib/ratelimit.c
+++ b/lib/ratelimit.c
@@ -3,6 +3,9 @@
  *
  * Isolated from kernel/printk.c by Dave Young <hidave.darkstar@gmail.com>
  *
+ * 2008-05-01 rewrite the function and use a ratelimit_state data struct as
+ * parameter. Now every user can use their own standalone ratelimit_state.
+ *
  * This file is released under the GPLv2.
  *
  */
@@ -11,41 +14,44 @@
 #include <linux/jiffies.h>
 #include <linux/module.h>
 
+static DEFINE_SPINLOCK(ratelimit_lock);
+
 /*
  * __ratelimit - rate limiting
- * @ratelimit_jiffies: minimum time in jiffies between two callbacks
- * @ratelimit_burst: number of callbacks we do before ratelimiting
+ * @rs: ratelimit_state data
  *
- * This enforces a rate limit: not more than @ratelimit_burst callbacks
- * in every ratelimit_jiffies
+ * This enforces a rate limit: not more than @rs->ratelimit_burst callbacks
+ * in every @rs->ratelimit_jiffies
  */
-int __ratelimit(int ratelimit_jiffies, int ratelimit_burst)
+int __ratelimit(struct ratelimit_state *rs)
 {
-	static DEFINE_SPINLOCK(ratelimit_lock);
-	static unsigned toks = 10 * 5 * HZ;
-	static unsigned long last_msg;
-	static int missed;
 	unsigned long flags;
-	unsigned long now = jiffies;
 
-	spin_lock_irqsave(&ratelimit_lock, flags);
-	toks += now - last_msg;
-	last_msg = now;
-	if (toks > (ratelimit_burst * ratelimit_jiffies))
-		toks = ratelimit_burst * ratelimit_jiffies;
-	if (toks >= ratelimit_jiffies) {
-		int lost = missed;
-
-		missed = 0;
-		toks -= ratelimit_jiffies;
-		spin_unlock_irqrestore(&ratelimit_lock, flags);
-		if (lost)
-			printk(KERN_WARNING "%s: %d messages suppressed\n",
-				__func__, lost);
+	if (!rs->interval)
 		return 1;
+
+	spin_lock_irqsave(&ratelimit_lock, flags);
+	if (!rs->begin)
+		rs->begin = jiffies;
+
+	if (time_is_before_jiffies(rs->begin + rs->interval)) {
+		if (rs->missed)
+			printk(KERN_WARNING "%s: %d callbacks suppressed\n",
+				__func__, rs->missed);
+		rs->begin = 0;
+		rs->printed = 0;
+		rs->missed = 0;
 	}
-	missed++;
+	if (rs->burst && rs->burst > rs->printed)
+		goto print;
+
+	rs->missed++;
 	spin_unlock_irqrestore(&ratelimit_lock, flags);
 	return 0;
+
+print:
+	rs->printed++;
+	spin_unlock_irqrestore(&ratelimit_lock, flags);
+	return 1;
 }
 EXPORT_SYMBOL(__ratelimit);
diff --git a/lib/scatterlist.c b/lib/scatterlist.c
index b80c21100d7..876ba6d5b67 100644
--- a/lib/scatterlist.c
+++ b/lib/scatterlist.c
@@ -295,6 +295,117 @@ int sg_alloc_table(struct sg_table *table, unsigned int nents, gfp_t gfp_mask)
 EXPORT_SYMBOL(sg_alloc_table);
 
 /**
+ * sg_miter_start - start mapping iteration over a sg list
+ * @miter: sg mapping iter to be started
+ * @sgl: sg list to iterate over
+ * @nents: number of sg entries
+ *
+ * Description:
+ *   Starts mapping iterator @miter.
+ *
+ * Context:
+ *   Don't care.
+ */
+void sg_miter_start(struct sg_mapping_iter *miter, struct scatterlist *sgl,
+		    unsigned int nents, unsigned int flags)
+{
+	memset(miter, 0, sizeof(struct sg_mapping_iter));
+
+	miter->__sg = sgl;
+	miter->__nents = nents;
+	miter->__offset = 0;
+	miter->__flags = flags;
+}
+EXPORT_SYMBOL(sg_miter_start);
+
+/**
+ * sg_miter_next - proceed mapping iterator to the next mapping
+ * @miter: sg mapping iter to proceed
+ *
+ * Description:
+ *   Proceeds @miter@ to the next mapping.  @miter@ should have been
+ *   started using sg_miter_start().  On successful return,
+ *   @miter@->page, @miter@->addr and @miter@->length point to the
+ *   current mapping.
+ *
+ * Context:
+ *   IRQ disabled if SG_MITER_ATOMIC.  IRQ must stay disabled till
+ *   @miter@ is stopped.  May sleep if !SG_MITER_ATOMIC.
+ *
+ * Returns:
+ *   true if @miter contains the next mapping.  false if end of sg
+ *   list is reached.
+ */
+bool sg_miter_next(struct sg_mapping_iter *miter)
+{
+	unsigned int off, len;
+
+	/* check for end and drop resources from the last iteration */
+	if (!miter->__nents)
+		return false;
+
+	sg_miter_stop(miter);
+
+	/* get to the next sg if necessary.  __offset is adjusted by stop */
+	if (miter->__offset == miter->__sg->length && --miter->__nents) {
+		miter->__sg = sg_next(miter->__sg);
+		miter->__offset = 0;
+	}
+
+	/* map the next page */
+	off = miter->__sg->offset + miter->__offset;
+	len = miter->__sg->length - miter->__offset;
+
+	miter->page = nth_page(sg_page(miter->__sg), off >> PAGE_SHIFT);
+	off &= ~PAGE_MASK;
+	miter->length = min_t(unsigned int, len, PAGE_SIZE - off);
+	miter->consumed = miter->length;
+
+	if (miter->__flags & SG_MITER_ATOMIC)
+		miter->addr = kmap_atomic(miter->page, KM_BIO_SRC_IRQ) + off;
+	else
+		miter->addr = kmap(miter->page) + off;
+
+	return true;
+}
+EXPORT_SYMBOL(sg_miter_next);
+
+/**
+ * sg_miter_stop - stop mapping iteration
+ * @miter: sg mapping iter to be stopped
+ *
+ * Description:
+ *   Stops mapping iterator @miter.  @miter should have been started
+ *   started using sg_miter_start().  A stopped iteration can be
+ *   resumed by calling sg_miter_next() on it.  This is useful when
+ *   resources (kmap) need to be released during iteration.
+ *
+ * Context:
+ *   IRQ disabled if the SG_MITER_ATOMIC is set.  Don't care otherwise.
+ */
+void sg_miter_stop(struct sg_mapping_iter *miter)
+{
+	WARN_ON(miter->consumed > miter->length);
+
+	/* drop resources from the last iteration */
+	if (miter->addr) {
+		miter->__offset += miter->consumed;
+
+		if (miter->__flags & SG_MITER_ATOMIC) {
+			WARN_ON(!irqs_disabled());
+			kunmap_atomic(miter->addr, KM_BIO_SRC_IRQ);
+		} else
+			kunmap(miter->addr);
+
+		miter->page = NULL;
+		miter->addr = NULL;
+		miter->length = 0;
+		miter->consumed = 0;
+	}
+}
+EXPORT_SYMBOL(sg_miter_stop);
+
+/**
  * sg_copy_buffer - Copy data between a linear buffer and an SG list
  * @sgl:		 The SG list
  * @nents:		 Number of SG entries
@@ -309,56 +420,29 @@ EXPORT_SYMBOL(sg_alloc_table);
 static size_t sg_copy_buffer(struct scatterlist *sgl, unsigned int nents,
 			     void *buf, size_t buflen, int to_buffer)
 {
-	struct scatterlist *sg;
-	size_t buf_off = 0;
-	int i;
-
-	WARN_ON(!irqs_disabled());
-
-	for_each_sg(sgl, sg, nents, i) {
-		struct page *page;
-		int n = 0;
-		unsigned int sg_off = sg->offset;
-		unsigned int sg_copy = sg->length;
-
-		if (sg_copy > buflen)
-			sg_copy = buflen;
-		buflen -= sg_copy;
-
-		while (sg_copy > 0) {
-			unsigned int page_copy;
-			void *p;
-
-			page_copy = PAGE_SIZE - sg_off;
-			if (page_copy > sg_copy)
-				page_copy = sg_copy;
-
-			page = nth_page(sg_page(sg), n);
-			p = kmap_atomic(page, KM_BIO_SRC_IRQ);
-
-			if (to_buffer)
-				memcpy(buf + buf_off, p + sg_off, page_copy);
-			else {
-				memcpy(p + sg_off, buf + buf_off, page_copy);
-				flush_kernel_dcache_page(page);
-			}
-
-			kunmap_atomic(p, KM_BIO_SRC_IRQ);
-
-			buf_off += page_copy;
-			sg_off += page_copy;
-			if (sg_off == PAGE_SIZE) {
-				sg_off = 0;
-				n++;
-			}
-			sg_copy -= page_copy;
+	unsigned int offset = 0;
+	struct sg_mapping_iter miter;
+
+	sg_miter_start(&miter, sgl, nents, SG_MITER_ATOMIC);
+
+	while (sg_miter_next(&miter) && offset < buflen) {
+		unsigned int len;
+
+		len = min(miter.length, buflen - offset);
+
+		if (to_buffer)
+			memcpy(buf + offset, miter.addr, len);
+		else {
+			memcpy(miter.addr, buf + offset, len);
+			flush_kernel_dcache_page(miter.page);
 		}
 
-		if (!buflen)
-			break;
+		offset += len;
 	}
 
-	return buf_off;
+	sg_miter_stop(&miter);
+
+	return offset;
 }
 
 /**
diff --git a/lib/show_mem.c b/lib/show_mem.c
new file mode 100644
index 00000000000..238e72a18ce
--- /dev/null
+++ b/lib/show_mem.c
@@ -0,0 +1,63 @@
+/*
+ * Generic show_mem() implementation
+ *
+ * Copyright (C) 2008 Johannes Weiner <hannes@saeurebad.de>
+ * All code subject to the GPL version 2.
+ */
+
+#include <linux/mm.h>
+#include <linux/nmi.h>
+#include <linux/quicklist.h>
+
+void show_mem(void)
+{
+	pg_data_t *pgdat;
+	unsigned long total = 0, reserved = 0, shared = 0,
+		nonshared = 0, highmem = 0;
+
+	printk(KERN_INFO "Mem-Info:\n");
+	show_free_areas();
+
+	for_each_online_pgdat(pgdat) {
+		unsigned long i, flags;
+
+		pgdat_resize_lock(pgdat, &flags);
+		for (i = 0; i < pgdat->node_spanned_pages; i++) {
+			struct page *page;
+			unsigned long pfn = pgdat->node_start_pfn + i;
+
+			if (unlikely(!(i % MAX_ORDER_NR_PAGES)))
+				touch_nmi_watchdog();
+
+			if (!pfn_valid(pfn))
+				continue;
+
+			page = pfn_to_page(pfn);
+
+			if (PageHighMem(page))
+				highmem++;
+
+			if (PageReserved(page))
+				reserved++;
+			else if (page_count(page) == 1)
+				nonshared++;
+			else if (page_count(page) > 1)
+				shared += page_count(page) - 1;
+
+			total++;
+		}
+		pgdat_resize_unlock(pgdat, &flags);
+	}
+
+	printk(KERN_INFO "%lu pages RAM\n", total);
+#ifdef CONFIG_HIGHMEM
+	printk(KERN_INFO "%lu pages HighMem\n", highmem);
+#endif
+	printk(KERN_INFO "%lu pages reserved\n", reserved);
+	printk(KERN_INFO "%lu pages shared\n", shared);
+	printk(KERN_INFO "%lu pages non-shared\n", nonshared);
+#ifdef CONFIG_QUICKLIST
+	printk(KERN_INFO "%lu pages in pagetable cache\n",
+		quicklist_total_size());
+#endif
+}
diff --git a/lib/smp_processor_id.c b/lib/smp_processor_id.c
index 3b4dc098181..0f8fc22ed10 100644
--- a/lib/smp_processor_id.c
+++ b/lib/smp_processor_id.c
@@ -11,7 +11,6 @@ notrace unsigned int debug_smp_processor_id(void)
 {
 	unsigned long preempt_count = preempt_count();
 	int this_cpu = raw_smp_processor_id();
-	cpumask_t this_mask;
 
 	if (likely(preempt_count))
 		goto out;
@@ -23,9 +22,7 @@ notrace unsigned int debug_smp_processor_id(void)
 	 * Kernel threads bound to a single CPU can safely use
 	 * smp_processor_id():
 	 */
-	this_mask = cpumask_of_cpu(this_cpu);
-
-	if (cpus_equal(current->cpus_allowed, this_mask))
+	if (cpus_equal(current->cpus_allowed, cpumask_of_cpu(this_cpu)))
 		goto out;
 
 	/*
diff --git a/lib/swiotlb.c b/lib/swiotlb.c
index d568894df8c..977edbdbc1d 100644
--- a/lib/swiotlb.c
+++ b/lib/swiotlb.c
@@ -492,7 +492,7 @@ swiotlb_alloc_coherent(struct device *hwdev, size_t size,
 		 */
 		dma_addr_t handle;
 		handle = swiotlb_map_single(NULL, NULL, size, DMA_FROM_DEVICE);
-		if (swiotlb_dma_mapping_error(handle))
+		if (swiotlb_dma_mapping_error(hwdev, handle))
 			return NULL;
 
 		ret = bus_to_virt(handle);
@@ -824,7 +824,7 @@ swiotlb_sync_sg_for_device(struct device *hwdev, struct scatterlist *sg,
 }
 
 int
-swiotlb_dma_mapping_error(dma_addr_t dma_addr)
+swiotlb_dma_mapping_error(struct device *hwdev, dma_addr_t dma_addr)
 {
 	return (dma_addr == virt_to_bus(io_tlb_overflow_buffer));
 }
diff --git a/lib/syscall.c b/lib/syscall.c
new file mode 100644
index 00000000000..a4f7067f72f
--- /dev/null
+++ b/lib/syscall.c
@@ -0,0 +1,75 @@
+#include <linux/ptrace.h>
+#include <linux/sched.h>
+#include <linux/module.h>
+#include <asm/syscall.h>
+
+static int collect_syscall(struct task_struct *target, long *callno,
+			   unsigned long args[6], unsigned int maxargs,
+			   unsigned long *sp, unsigned long *pc)
+{
+	struct pt_regs *regs = task_pt_regs(target);
+	if (unlikely(!regs))
+		return -EAGAIN;
+
+	*sp = user_stack_pointer(regs);
+	*pc = instruction_pointer(regs);
+
+	*callno = syscall_get_nr(target, regs);
+	if (*callno != -1L && maxargs > 0)
+		syscall_get_arguments(target, regs, 0, maxargs, args);
+
+	return 0;
+}
+
+/**
+ * task_current_syscall - Discover what a blocked task is doing.
+ * @target:		thread to examine
+ * @callno:		filled with system call number or -1
+ * @args:		filled with @maxargs system call arguments
+ * @maxargs:		number of elements in @args to fill
+ * @sp:			filled with user stack pointer
+ * @pc:			filled with user PC
+ *
+ * If @target is blocked in a system call, returns zero with *@callno
+ * set to the the call's number and @args filled in with its arguments.
+ * Registers not used for system call arguments may not be available and
+ * it is not kosher to use &struct user_regset calls while the system
+ * call is still in progress.  Note we may get this result if @target
+ * has finished its system call but not yet returned to user mode, such
+ * as when it's stopped for signal handling or syscall exit tracing.
+ *
+ * If @target is blocked in the kernel during a fault or exception,
+ * returns zero with *@callno set to -1 and does not fill in @args.
+ * If so, it's now safe to examine @target using &struct user_regset
+ * get() calls as long as we're sure @target won't return to user mode.
+ *
+ * Returns -%EAGAIN if @target does not remain blocked.
+ *
+ * Returns -%EINVAL if @maxargs is too large (maximum is six).
+ */
+int task_current_syscall(struct task_struct *target, long *callno,
+			 unsigned long args[6], unsigned int maxargs,
+			 unsigned long *sp, unsigned long *pc)
+{
+	long state;
+	unsigned long ncsw;
+
+	if (unlikely(maxargs > 6))
+		return -EINVAL;
+
+	if (target == current)
+		return collect_syscall(target, callno, args, maxargs, sp, pc);
+
+	state = target->state;
+	if (unlikely(!state))
+		return -EAGAIN;
+
+	ncsw = wait_task_inactive(target, state);
+	if (unlikely(!ncsw) ||
+	    unlikely(collect_syscall(target, callno, args, maxargs, sp, pc)) ||
+	    unlikely(wait_task_inactive(target, state) != ncsw))
+		return -EAGAIN;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(task_current_syscall);
diff --git a/lib/textsearch.c b/lib/textsearch.c
index 4b7c6075256..9fbcb44c554 100644
--- a/lib/textsearch.c
+++ b/lib/textsearch.c
@@ -267,7 +267,7 @@ struct ts_config *textsearch_prepare(const char *algo, const void *pattern,
 		return ERR_PTR(-EINVAL);
 
 	ops = lookup_ts_algo(algo);
-#ifdef CONFIG_KMOD
+#ifdef CONFIG_MODULES
 	/*
 	 * Why not always autoload you may ask. Some users are
 	 * in a situation where requesting a module may deadlock,
diff --git a/lib/vsprintf.c b/lib/vsprintf.c
index 1dc2d1d18fa..d8d1d114224 100644
--- a/lib/vsprintf.c
+++ b/lib/vsprintf.c
@@ -220,7 +220,7 @@ int strict_strtou##type(const char *cp, unsigned int base, valtype *res)\
 	if (len == 0)							\
 		return -EINVAL;						\
 									\
-	val = simple_strtoul(cp, &tail, base);				\
+	val = simple_strtou##type(cp, &tail, base);			\
 	if ((*tail == '\0') ||						\
 		((len == (size_t)(tail - cp) + 1) && (*tail == '\n'))) {\
 		*res = val;						\