Merge branch 'master' into next

Conflicts:
	fs/namei.c

Manually merged per:

diff --cc fs/namei.c
index 734f2b5,bbc15c2..0000000
--- a/fs/namei.c
+++ b/fs/namei.c
@@@ -860,9 -848,8 +849,10 @@@ static int __link_path_walk(const char
  		nd->flags |= LOOKUP_CONTINUE;
  		err = exec_permission_lite(inode);
  		if (err == -EAGAIN)
- 			err = vfs_permission(nd, MAY_EXEC);
+ 			err = inode_permission(nd->path.dentry->d_inode,
+ 					       MAY_EXEC);
 +		if (!err)
 +			err = ima_path_check(&nd->path, MAY_EXEC);
   		if (err)
  			break;

@@@ -1525,14 -1506,9 +1509,14 @@@ int may_open(struct path *path, int acc
  		flag &= ~O_TRUNC;
  	}

- 	error = vfs_permission(nd, acc_mode);
+ 	error = inode_permission(inode, acc_mode);
  	if (error)
  		return error;
 +
- 	error = ima_path_check(&nd->path,
++	error = ima_path_check(path,
 +			       acc_mode & (MAY_READ | MAY_WRITE | MAY_EXEC));
 +	if (error)
 +		return error;
  	/*
  	 * An append-only file must be opened in append mode for writing.
  	 */

Signed-off-by: James Morris <jmorris@namei.org>

20 files changed, 382 insertions, 260 deletions

diff --git a/lib/Kconfig b/lib/Kconfig
index fd4118e097f0..03c2c24b9083 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
@@ -159,4 +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 2e75478e9c69..29044f500269 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -512,6 +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
@@ -563,17 +570,26 @@ config DEBUG_NOTIFIERS
           This is a relatively cheap check but if you care about maximum
           performance, say N.
 
+#
+# Select this config option from the architecture Kconfig, if it
+# it is preferred to always offer frame pointers as a config
+# option on the architecture (regardless of KERNEL_DEBUG):
+#
+config ARCH_WANT_FRAME_POINTERS
+        bool
+        help
+
 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"
@@ -626,19 +642,6 @@ config RCU_TORTURE_TEST_RUNNABLE
 
 config RCU_CPU_STALL_DETECTOR
         bool "Check for stalled CPUs delaying RCU grace periods"
-        depends on CLASSIC_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 RCU_CPU_STALL_DETECTOR
-        bool "Check for stalled CPUs delaying RCU grace periods"
         depends on CLASSIC_RCU || TREE_RCU
         default n
         help
diff --git a/lib/Makefile b/lib/Makefile
index 80fe8a3ec12a..32b0e64ded27 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -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/bust_spinlocks.c b/lib/bust_spinlocks.c
index 486da62b2b07..9681d54b95d1 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 8d03f22c6ced..3389e2440da0 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/dynamic_printk.c b/lib/dynamic_printk.c
index 8e30295e8566..165a19763dc9 100644
--- a/lib/dynamic_printk.c
+++ b/lib/dynamic_printk.c
@@ -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\n",
-                                               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\n", 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 a50a311554cc..f97af55bdd96 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 000000000000..5d202e36bdd8
--- /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 1c4f9281f412..c11c5765cdef 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);
@@ -292,7 +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)
 {
@@ -623,16 +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);
 }
 
 /**
@@ -723,7 +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/klist.c b/lib/klist.c
index bbdd3015c2c7..573d6068a42e 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 3f914725bda8..318328ddbd1c 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/percpu_counter.c b/lib/percpu_counter.c
index b255b939bc1b..aeaa6d734447 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)
 {
@@ -68,11 +66,11 @@ s64 __percpu_counter_sum(struct percpu_counter *fbc)
 }
 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)
@@ -84,17 +82,7 @@ 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)
 {
@@ -111,13 +99,24 @@ void percpu_counter_destroy(struct percpu_counter *fbc)
 }
 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;
 
@@ -134,13 +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 471944a54e23..a7af6f85eca8 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 4f387a643d72..d50746a79de2 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 be86b32bc874..4bb42a0344ec 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 48499c2d88cc..9956b99649f0 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/smp_processor_id.c b/lib/smp_processor_id.c
index 0f8fc22ed103..4689cb073da4 100644
--- a/lib/smp_processor_id.c
+++ b/lib/smp_processor_id.c
@@ -22,7 +22,7 @@ notrace unsigned int debug_smp_processor_id(void)
          * Kernel threads bound to a single CPU can safely use
          * smp_processor_id():
          */
-        if (cpus_equal(current->cpus_allowed, cpumask_of_cpu(this_cpu)))
+        if (cpumask_equal(&current->cpus_allowed, cpumask_of(this_cpu)))
                 goto out;
 
         /*
diff --git a/lib/sort.c b/lib/sort.c
index 6abbaf3d5858..926d00429ed2 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 fa2dc4e5f9ba..1f991acc2a05 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>
@@ -21,9 +22,9 @@
 #include <linux/mm.h>
 #include <linux/module.h>
 #include <linux/spinlock.h>
-#include <linux/swiotlb.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>
@@ -89,10 +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 struct swiotlb_phys_addr {
-        struct page *page;
-        unsigned int offset;
-} *io_tlb_orig_addr;
+static phys_addr_t *io_tlb_orig_addr;
 
 /*
  * Protect the above data structures in the map and unmap calls
@@ -116,7 +114,7 @@ setup_io_tlb_npages(char *str)
 __setup("swiotlb=", setup_io_tlb_npages);
 /* make io_tlb_overflow tunable too? */
 
-void * __weak swiotlb_alloc_boot(size_t size, unsigned long nslabs)
+void * __weak __init swiotlb_alloc_boot(size_t size, unsigned long nslabs)
 {
         return alloc_bootmem_low_pages(size);
 }
@@ -126,7 +124,7 @@ 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(phys_addr_t paddr)
+dma_addr_t __weak swiotlb_phys_to_bus(struct device *hwdev, phys_addr_t paddr)
 {
         return paddr;
 }
@@ -136,9 +134,10 @@ phys_addr_t __weak swiotlb_bus_to_phys(dma_addr_t baddr)
         return baddr;
 }
 
-static dma_addr_t swiotlb_virt_to_bus(volatile void *address)
+static dma_addr_t swiotlb_virt_to_bus(struct device *hwdev,
+                                      volatile void *address)
 {
-        return swiotlb_phys_to_bus(virt_to_phys(address));
+        return swiotlb_phys_to_bus(hwdev, virt_to_phys(address));
 }
 
 static void *swiotlb_bus_to_virt(dma_addr_t address)
@@ -151,35 +150,18 @@ int __weak swiotlb_arch_range_needs_mapping(void *ptr, size_t size)
         return 0;
 }
 
-static dma_addr_t swiotlb_sg_to_bus(struct scatterlist *sg)
-{
-        return swiotlb_phys_to_bus(page_to_phys(sg_page(sg)) + sg->offset);
-}
-
 static void swiotlb_print_info(unsigned long bytes)
 {
         phys_addr_t pstart, pend;
-        dma_addr_t bstart, bend;
 
         pstart = virt_to_phys(io_tlb_start);
         pend = virt_to_phys(io_tlb_end);
 
-        bstart = swiotlb_phys_to_bus(pstart);
-        bend = swiotlb_phys_to_bus(pend);
-
         printk(KERN_INFO "Placing %luMB software IO TLB between %p - %p\n",
                bytes >> 20, io_tlb_start, io_tlb_end);
-        if (pstart != bstart || pend != bend)
-                printk(KERN_INFO "software IO TLB at phys %#llx - %#llx"
-                       " bus %#llx - %#llx\n",
-                       (unsigned long long)pstart,
-                       (unsigned long long)pend,
-                       (unsigned long long)bstart,
-                       (unsigned long long)bend);
-        else
-                printk(KERN_INFO "software IO TLB at phys %#llx - %#llx\n",
-                       (unsigned long long)pstart,
-                       (unsigned long long)pend);
+        printk(KERN_INFO "software IO TLB at phys %#llx - %#llx\n",
+               (unsigned long long)pstart,
+               (unsigned long long)pend);
 }
 
 /*
@@ -215,7 +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(struct swiotlb_phys_addr));
+        io_tlb_orig_addr = alloc_bootmem(io_tlb_nslabs * sizeof(phys_addr_t));
 
         /*
          * Get the overflow emergency buffer
@@ -289,12 +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 = (struct swiotlb_phys_addr *)__get_free_pages(GFP_KERNEL,
-                                   get_order(io_tlb_nslabs * sizeof(struct swiotlb_phys_addr)));
+        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(struct swiotlb_phys_addr));
+        memset(io_tlb_orig_addr, 0, io_tlb_nslabs * sizeof(phys_addr_t));
 
         /*
          * Get the overflow emergency buffer
@@ -309,8 +293,8 @@ swiotlb_late_init_with_default_size(size_t default_size)
         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 *
@@ -341,51 +325,44 @@ static int is_swiotlb_buffer(char *addr)
         return addr >= io_tlb_start && addr < io_tlb_end;
 }
 
-static struct swiotlb_phys_addr swiotlb_bus_to_phys_addr(char *dma_addr)
-{
-        int index = (dma_addr - io_tlb_start) >> IO_TLB_SHIFT;
-        struct swiotlb_phys_addr buffer = io_tlb_orig_addr[index];
-        buffer.offset += (long)dma_addr & ((1 << IO_TLB_SHIFT) - 1);
-        buffer.page += buffer.offset >> PAGE_SHIFT;
-        buffer.offset &= PAGE_SIZE - 1;
-        return buffer;
-}
-
-static void
-__sync_single(struct swiotlb_phys_addr buffer, char *dma_addr, size_t size, int dir)
-{
-        if (PageHighMem(buffer.page)) {
-                size_t len, bytes;
-                char *dev, *host, *kmp;
-
-                len = size;
-                while (len != 0) {
-                        unsigned long flags;
-
-                        bytes = len;
-                        if ((bytes + buffer.offset) > PAGE_SIZE)
-                                bytes = PAGE_SIZE - buffer.offset;
-                        local_irq_save(flags); /* protects KM_BOUNCE_READ */
-                        kmp  = kmap_atomic(buffer.page, KM_BOUNCE_READ);
-                        dev  = dma_addr + size - len;
-                        host = kmp + buffer.offset;
-                        if (dir == DMA_FROM_DEVICE)
-                                memcpy(host, dev, bytes);
+/*
+ * 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(dev, host, bytes);
-                        kunmap_atomic(kmp, KM_BOUNCE_READ);
+                                memcpy(buffer + offset, dma_addr, sz);
+                        kunmap_atomic(buffer, KM_BOUNCE_READ);
                         local_irq_restore(flags);
-                        len -= bytes;
-                        buffer.page++;
-                        buffer.offset = 0;
+
+                        size -= sz;
+                        pfn++;
+                        dma_addr += sz;
+                        offset = 0;
                 }
         } else {
-                void *v = page_address(buffer.page) + buffer.offset;
-
                 if (dir == DMA_TO_DEVICE)
-                        memcpy(dma_addr, v, size);
+                        memcpy(dma_addr, phys_to_virt(phys), size);
                 else
-                        memcpy(v, dma_addr, size);
+                        memcpy(phys_to_virt(phys), dma_addr, size);
         }
 }
 
@@ -393,7 +370,7 @@ __sync_single(struct swiotlb_phys_addr buffer, char *dma_addr, size_t size, int
  * Allocates bounce buffer and returns its kernel virtual address.
  */
 static void *
-map_single(struct device *hwdev, struct swiotlb_phys_addr 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;
@@ -403,10 +380,9 @@ map_single(struct device *hwdev, struct swiotlb_phys_addr buffer, size_t size, i
         unsigned long mask;
         unsigned long offset_slots;
         unsigned long max_slots;
-        struct swiotlb_phys_addr slot_buf;
 
         mask = dma_get_seg_boundary(hwdev);
-        start_dma_addr = swiotlb_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;
 
@@ -488,15 +464,10 @@ found:
          * This is needed when we sync the memory.  Then we sync the buffer if
          * needed.
          */
-        slot_buf = buffer;
-        for (i = 0; i < nslots; i++) {
-                slot_buf.page += slot_buf.offset >> PAGE_SHIFT;
-                slot_buf.offset &= PAGE_SIZE - 1;
-                io_tlb_orig_addr[index+i] = slot_buf;
-                slot_buf.offset += 1 << IO_TLB_SHIFT;
-        }
+        for (i = 0; i < nslots; i++)
+                io_tlb_orig_addr[index+i] = phys + (i << IO_TLB_SHIFT);
         if (dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL)
-                __sync_single(buffer, dma_addr, size, DMA_TO_DEVICE);
+                swiotlb_bounce(phys, dma_addr, size, DMA_TO_DEVICE);
 
         return dma_addr;
 }
@@ -510,17 +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;
-        struct swiotlb_phys_addr buffer = swiotlb_bus_to_phys_addr(dma_addr);
+        phys_addr_t phys = io_tlb_orig_addr[index];
 
         /*
          * First, sync the memory before unmapping the entry
          */
-        if ((dir == DMA_FROM_DEVICE) || (dir == DMA_BIDIRECTIONAL))
-                /*
-                 * bounce... copy the data back into the original buffer * and
-                 * delete the bounce buffer.
-                 */
-                __sync_single(buffer, dma_addr, size, DMA_FROM_DEVICE);
+        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
@@ -552,18 +519,21 @@ static void
 sync_single(struct device *hwdev, char *dma_addr, size_t size,
             int dir, int target)
 {
-        struct swiotlb_phys_addr buffer = swiotlb_bus_to_phys_addr(dma_addr);
+        int index = (dma_addr - io_tlb_start) >> IO_TLB_SHIFT;
+        phys_addr_t phys = io_tlb_orig_addr[index];
+
+        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))
-                        __sync_single(buffer, dma_addr, size, DMA_FROM_DEVICE);
+                        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))
-                        __sync_single(buffer, dma_addr, size, DMA_TO_DEVICE);
+                        swiotlb_bounce(phys, dma_addr, size, DMA_TO_DEVICE);
                 else
                         BUG_ON(dir != DMA_FROM_DEVICE);
                 break;
@@ -585,7 +555,9 @@ swiotlb_alloc_coherent(struct device *hwdev, size_t size,
                 dma_mask = hwdev->coherent_dma_mask;
 
         ret = (void *)__get_free_pages(flags, order);
-        if (ret && !is_buffer_dma_capable(dma_mask, swiotlb_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().
@@ -600,16 +572,13 @@ swiotlb_alloc_coherent(struct device *hwdev, size_t size,
                  * swiotlb_map_single(), which will grab memory from
                  * the lowest available address range.
                  */
-                struct swiotlb_phys_addr buffer;
-                buffer.page = virt_to_page(NULL);
-                buffer.offset = 0;
-                ret = map_single(hwdev, buffer, size, DMA_FROM_DEVICE);
+                ret = map_single(hwdev, 0, size, DMA_FROM_DEVICE);
                 if (!ret)
                         return NULL;
         }
 
         memset(ret, 0, size);
-        dev_addr = swiotlb_virt_to_bus(ret);
+        dev_addr = swiotlb_virt_to_bus(hwdev, ret);
 
         /* Confirm address can be DMA'd by device */
         if (!is_buffer_dma_capable(dma_mask, dev_addr, size)) {
@@ -624,6 +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,
@@ -636,6 +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)
@@ -648,7 +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)
@@ -669,9 +640,8 @@ 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 = swiotlb_virt_to_bus(ptr);
+        dma_addr_t dev_addr = swiotlb_virt_to_bus(hwdev, ptr);
         void *map;
-        struct swiotlb_phys_addr buffer;
 
         BUG_ON(dir == DMA_NONE);
         /*
@@ -686,15 +656,13 @@ swiotlb_map_single_attrs(struct device *hwdev, void *ptr, size_t size,
         /*
          * Oh well, have to allocate and map a bounce buffer.
          */
-        buffer.page   = virt_to_page(ptr);
-        buffer.offset = (unsigned long)ptr & ~PAGE_MASK;
-        map = map_single(hwdev, buffer, 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 = swiotlb_virt_to_bus(map);
+        dev_addr = swiotlb_virt_to_bus(hwdev, map);
 
         /*
          * Ensure that the address returned is DMA'ble
@@ -711,6 +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
@@ -740,6 +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.
@@ -769,6 +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,
@@ -776,6 +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.
@@ -801,6 +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,
@@ -809,9 +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
@@ -833,20 +806,18 @@ swiotlb_map_sg_attrs(struct device *hwdev, struct scatterlist *sgl, int nelems,
                      int dir, struct dma_attrs *attrs)
 {
         struct scatterlist *sg;
-        struct swiotlb_phys_addr buffer;
-        dma_addr_t dev_addr;
         int i;
 
         BUG_ON(dir == DMA_NONE);
 
         for_each_sg(sgl, sg, nelems, i) {
-                dev_addr = swiotlb_sg_to_bus(sg);
-                if (range_needs_mapping(sg_virt(sg), sg->length) ||
+                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;
-                        buffer.page   = sg_page(sg);
-                        buffer.offset = sg->offset;
-                        map = map_single(hwdev, buffer, 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. */
@@ -856,7 +827,7 @@ swiotlb_map_sg_attrs(struct device *hwdev, struct scatterlist *sgl, int nelems,
                                 sgl[0].dma_length = 0;
                                 return 0;
                         }
-                        sg->dma_address = swiotlb_virt_to_bus(map);
+                        sg->dma_address = swiotlb_virt_to_bus(hwdev, map);
                 } else
                         sg->dma_address = dev_addr;
                 sg->dma_length = sg->length;
@@ -871,6 +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
@@ -886,11 +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 != swiotlb_sg_to_bus(sg))
+                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(swiotlb_bus_to_virt(sg->dma_address), sg->dma_length);
+                        dma_mark_clean(sg_virt(sg), sg->dma_length);
         }
 }
 EXPORT_SYMBOL(swiotlb_unmap_sg_attrs);
@@ -901,6 +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
@@ -919,11 +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 != swiotlb_sg_to_bus(sg))
+                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(swiotlb_bus_to_virt(sg->dma_address), sg->dma_length);
+                        dma_mark_clean(sg_virt(sg), sg->dma_length);
         }
 }
 
@@ -933,6 +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,
@@ -940,12 +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 == swiotlb_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
@@ -956,20 +932,6 @@ swiotlb_dma_mapping_error(struct device *hwdev, dma_addr_t dma_addr)
 int
 swiotlb_dma_supported(struct device *hwdev, u64 mask)
 {
-        return swiotlb_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 3b777025d876..0fbd0121d91d 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;
@@ -661,6 +665,9 @@ static char *ip4_addr_string(char *buf, char *end, u8 *addr, int field_width,
  */
 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);