16 files changed, 768 insertions, 79 deletions

diff --git a/lib/Kconfig b/lib/Kconfig
index bb1326d3839c..1cfe51628e1b 100644
--- a/lib/Kconfig
+++ b/lib/Kconfig
@@ -200,4 +200,7 @@ config NLATTR
 config GENERIC_ATOMIC64
        bool
 
+config LRU_CACHE
+        tristate
+
 endmenu
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 891155817bc6..2f22cf4576db 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -105,7 +105,7 @@ config DEBUG_SECTION_MISMATCH
         bool "Enable full Section mismatch analysis"
         depends on UNDEFINED
         # This option is on purpose disabled for now.
-        # It will be enabled when we are down to a resonable number
+        # It will be enabled when we are down to a reasonable number
         # of section mismatch warnings (< 10 for an allyesconfig build)
         help
           The section mismatch analysis checks if there are illegal
@@ -298,6 +298,14 @@ config DEBUG_OBJECTS_TIMERS
           timer routines to track the life time of timer objects and
           validate the timer operations.
 
+config DEBUG_OBJECTS_WORK
+        bool "Debug work objects"
+        depends on DEBUG_OBJECTS
+        help
+          If you say Y here, additional code will be inserted into the
+          work queue routines to track the life time of work objects and
+          validate the work operations.
+
 config DEBUG_OBJECTS_ENABLE_DEFAULT
         int "debug_objects bootup default value (0-1)"
         range 0 1
@@ -346,8 +354,9 @@ config SLUB_STATS
 
 config DEBUG_KMEMLEAK
         bool "Kernel memory leak detector"
-        depends on DEBUG_KERNEL && EXPERIMENTAL && (X86 || ARM || PPC) && \
-                !MEMORY_HOTPLUG
+        depends on DEBUG_KERNEL && EXPERIMENTAL && !MEMORY_HOTPLUG && \
+                (X86 || ARM || PPC || S390)
+
         select DEBUG_FS if SYSFS
         select STACKTRACE if STACKTRACE_SUPPORT
         select KALLSYMS
@@ -370,7 +379,7 @@ config DEBUG_KMEMLEAK
 config DEBUG_KMEMLEAK_EARLY_LOG_SIZE
         int "Maximum kmemleak early log entries"
         depends on DEBUG_KMEMLEAK
-        range 200 2000
+        range 200 40000
         default 400
         help
           Kmemleak must track all the memory allocations to avoid
@@ -391,7 +400,7 @@ config DEBUG_KMEMLEAK_TEST
 
 config DEBUG_PREEMPT
         bool "Debug preemptible kernel"
-        depends on DEBUG_KERNEL && PREEMPT && (TRACE_IRQFLAGS_SUPPORT || PPC64)
+        depends on DEBUG_KERNEL && PREEMPT && TRACE_IRQFLAGS_SUPPORT
         default y
         help
           If you say Y here then the kernel will use a debug variant of the
@@ -749,7 +758,7 @@ config RCU_TORTURE_TEST_RUNNABLE
 config RCU_CPU_STALL_DETECTOR
         bool "Check for stalled CPUs delaying RCU grace periods"
         depends on TREE_RCU || TREE_PREEMPT_RCU
-        default n
+        default y
         help
           This option causes RCU to printk information on which
           CPUs are delaying the current grace period, but only when
@@ -911,7 +920,7 @@ config LATENCYTOP
 
 config SYSCTL_SYSCALL_CHECK
         bool "Sysctl checks"
-        depends on SYSCTL_SYSCALL
+        depends on SYSCTL
         ---help---
           sys_sysctl uses binary paths that have been found challenging
           to properly maintain and use. This enables checks that help
diff --git a/lib/Makefile b/lib/Makefile
index 2e78277eff9d..347ad8db29d3 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -91,6 +91,8 @@ obj-$(CONFIG_DYNAMIC_DEBUG) += dynamic_debug.o
 
 obj-$(CONFIG_NLATTR) += nlattr.o
 
+obj-$(CONFIG_LRU_CACHE) += lru_cache.o
+
 obj-$(CONFIG_DMA_API_DEBUG) += dma-debug.o
 
 obj-$(CONFIG_GENERIC_CSUM) += checksum.o
diff --git a/lib/checksum.c b/lib/checksum.c
index b2e2fd468461..097508732f34 100644
--- a/lib/checksum.c
+++ b/lib/checksum.c
@@ -37,7 +37,8 @@
 
 #include <asm/byteorder.h>
 
-static inline unsigned short from32to16(unsigned long x)
+#ifndef do_csum
+static inline unsigned short from32to16(unsigned int x)
 {
         /* add up 16-bit and 16-bit for 16+c bit */
         x = (x & 0xffff) + (x >> 16);
@@ -49,16 +50,16 @@ static inline unsigned short from32to16(unsigned long x)
 static unsigned int do_csum(const unsigned char *buff, int len)
 {
         int odd, count;
-        unsigned long result = 0;
+        unsigned int result = 0;
 
         if (len <= 0)
                 goto out;
         odd = 1 & (unsigned long) buff;
         if (odd) {
 #ifdef __LITTLE_ENDIAN
-                result = *buff;
-#else
                 result += (*buff << 8);
+#else
+                result = *buff;
 #endif
                 len--;
                 buff++;
@@ -73,9 +74,9 @@ static unsigned int do_csum(const unsigned char *buff, int len)
                 }
                 count >>= 1;            /* nr of 32-bit words.. */
                 if (count) {
-                        unsigned long carry = 0;
+                        unsigned int carry = 0;
                         do {
-                                unsigned long w = *(unsigned int *) buff;
+                                unsigned int w = *(unsigned int *) buff;
                                 count--;
                                 buff += 4;
                                 result += carry;
@@ -102,6 +103,7 @@ static unsigned int do_csum(const unsigned char *buff, int len)
 out:
         return result;
 }
+#endif
 
 /*
  *      This is a version of ip_compute_csum() optimized for IP headers,
diff --git a/lib/debugobjects.c b/lib/debugobjects.c
index 2755a3bd16a1..eae56fddfa3b 100644
--- a/lib/debugobjects.c
+++ b/lib/debugobjects.c
@@ -9,6 +9,7 @@
  */
 #include <linux/debugobjects.h>
 #include <linux/interrupt.h>
+#include <linux/sched.h>
 #include <linux/seq_file.h>
 #include <linux/debugfs.h>
 #include <linux/hash.h>
diff --git a/lib/decompress_bunzip2.c b/lib/decompress_bunzip2.c
index 600f473a5610..76074209f9a2 100644
--- a/lib/decompress_bunzip2.c
+++ b/lib/decompress_bunzip2.c
@@ -299,7 +299,7 @@ static int INIT get_next_block(struct bunzip_data *bd)
                    again when using them (during symbol decoding).*/
                 base = hufGroup->base-1;
                 limit = hufGroup->limit-1;
-                /* Calculate permute[].  Concurently, initialize
+                /* Calculate permute[].  Concurrently, initialize
                  * temp[] and limit[]. */
                 pp = 0;
                 for (i = minLen; i <= maxLen; i++) {
diff --git a/lib/dma-debug.c b/lib/dma-debug.c
index 58a9f9fc609a..d9b08e0f7f55 100644
--- a/lib/dma-debug.c
+++ b/lib/dma-debug.c
@@ -259,7 +259,7 @@ static struct dma_debug_entry *hash_bucket_find(struct hash_bucket *bucket,
                  * times. Without a hardware IOMMU this results in the
                  * same device addresses being put into the dma-debug
                  * hash multiple times too. This can result in false
-                 * positives being reported. Therfore we implement a
+                 * positives being reported. Therefore we implement a
                  * best-fit algorithm here which returns the entry from
                  * the hash which fits best to the reference value
                  * instead of the first-fit.
@@ -819,9 +819,11 @@ static void check_unmap(struct dma_debug_entry *ref)
                 err_printk(ref->dev, entry, "DMA-API: device driver frees "
                            "DMA memory with different CPU address "
                            "[device address=0x%016llx] [size=%llu bytes] "
-                           "[cpu alloc address=%p] [cpu free address=%p]",
+                           "[cpu alloc address=0x%016llx] "
+                           "[cpu free address=0x%016llx]",
                            ref->dev_addr, ref->size,
-                           (void *)entry->paddr, (void *)ref->paddr);
+                           (unsigned long long)entry->paddr,
+                           (unsigned long long)ref->paddr);
         }
 
         if (ref->sg_call_ents && ref->type == dma_debug_sg &&
diff --git a/lib/fault-inject.c b/lib/fault-inject.c
index f97af55bdd96..7e65af70635e 100644
--- a/lib/fault-inject.c
+++ b/lib/fault-inject.c
@@ -1,6 +1,7 @@
 #include <linux/kernel.h>
 #include <linux/init.h>
 #include <linux/random.h>
+#include <linux/sched.h>
 #include <linux/stat.h>
 #include <linux/types.h>
 #include <linux/fs.h>
diff --git a/lib/idr.c b/lib/idr.c
index 80ca9aca038b..1cac726c44bc 100644
--- a/lib/idr.c
+++ b/lib/idr.c
@@ -281,7 +281,7 @@ static int idr_get_new_above_int(struct idr *idp, void *ptr, int starting_id)
 /**
  * idr_get_new_above - allocate new idr entry above or equal to a start id
  * @idp: idr handle
- * @ptr: pointer you want associated with the ide
+ * @ptr: pointer you want associated with the id
  * @start_id: id to start search at
  * @id: pointer to the allocated handle
  *
@@ -313,7 +313,7 @@ EXPORT_SYMBOL(idr_get_new_above);
 /**
  * idr_get_new - allocate new idr entry
  * @idp: idr handle
- * @ptr: pointer you want associated with the ide
+ * @ptr: pointer you want associated with the id
  * @id: pointer to the allocated handle
  *
  * This is the allocate id function.  It should be called with any
diff --git a/lib/kernel_lock.c b/lib/kernel_lock.c
index 39f1029e3525..5526b46aba94 100644
--- a/lib/kernel_lock.c
+++ b/lib/kernel_lock.c
@@ -5,10 +5,13 @@
  * relegated to obsolescence, but used by various less
  * important (or lazy) subsystems.
  */
-#include <linux/smp_lock.h>
 #include <linux/module.h>
 #include <linux/kallsyms.h>
 #include <linux/semaphore.h>
+#include <linux/smp_lock.h>
+
+#define CREATE_TRACE_POINTS
+#include <trace/events/bkl.h>
 
 /*
  * The 'big kernel lock'
@@ -113,21 +116,28 @@ static inline void __unlock_kernel(void)
  * This cannot happen asynchronously, so we only need to
  * worry about other CPU's.
  */
-void __lockfunc lock_kernel(void)
+void __lockfunc _lock_kernel(const char *func, const char *file, int line)
 {
-        int depth = current->lock_depth+1;
-        if (likely(!depth))
+        int depth = current->lock_depth + 1;
+
+        trace_lock_kernel(func, file, line);
+
+        if (likely(!depth)) {
+                might_sleep();
                 __lock_kernel();
+        }
         current->lock_depth = depth;
 }
 
-void __lockfunc unlock_kernel(void)
+void __lockfunc _unlock_kernel(const char *func, const char *file, int line)
 {
         BUG_ON(current->lock_depth < 0);
         if (likely(--current->lock_depth < 0))
                 __unlock_kernel();
+
+        trace_unlock_kernel(func, file, line);
 }
 
-EXPORT_SYMBOL(lock_kernel);
-EXPORT_SYMBOL(unlock_kernel);
+EXPORT_SYMBOL(_lock_kernel);
+EXPORT_SYMBOL(_unlock_kernel);
 
diff --git a/lib/lru_cache.c b/lib/lru_cache.c
new file mode 100644
index 000000000000..270de9d31b8c
--- /dev/null
+++ b/lib/lru_cache.c
@@ -0,0 +1,560 @@
+/*
+   lru_cache.c
+
+   This file is part of DRBD by Philipp Reisner and Lars Ellenberg.
+
+   Copyright (C) 2003-2008, LINBIT Information Technologies GmbH.
+   Copyright (C) 2003-2008, Philipp Reisner <philipp.reisner@linbit.com>.
+   Copyright (C) 2003-2008, Lars Ellenberg <lars.ellenberg@linbit.com>.
+
+   drbd 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, or (at your option)
+   any later version.
+
+   drbd is distributed in the hope that it will be useful,
+   but WITHOUT ANY WARRANTY; without even the implied warranty of
+   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+   GNU General Public License for more details.
+
+   You should have received a copy of the GNU General Public License
+   along with drbd; see the file COPYING.  If not, write to
+   the Free Software Foundation, 675 Mass Ave, Cambridge, MA 02139, USA.
+
+ */
+
+#include <linux/module.h>
+#include <linux/bitops.h>
+#include <linux/slab.h>
+#include <linux/string.h> /* for memset */
+#include <linux/seq_file.h> /* for seq_printf */
+#include <linux/lru_cache.h>
+
+MODULE_AUTHOR("Philipp Reisner <phil@linbit.com>, "
+              "Lars Ellenberg <lars@linbit.com>");
+MODULE_DESCRIPTION("lru_cache - Track sets of hot objects");
+MODULE_LICENSE("GPL");
+
+/* this is developers aid only.
+ * it catches concurrent access (lack of locking on the users part) */
+#define PARANOIA_ENTRY() do {           \
+        BUG_ON(!lc);                    \
+        BUG_ON(!lc->nr_elements);       \
+        BUG_ON(test_and_set_bit(__LC_PARANOIA, &lc->flags)); \
+} while (0)
+
+#define RETURN(x...)     do { \
+        clear_bit(__LC_PARANOIA, &lc->flags); \
+        smp_mb__after_clear_bit(); return x ; } while (0)
+
+/* BUG() if e is not one of the elements tracked by lc */
+#define PARANOIA_LC_ELEMENT(lc, e) do { \
+        struct lru_cache *lc_ = (lc);   \
+        struct lc_element *e_ = (e);    \
+        unsigned i = e_->lc_index;      \
+        BUG_ON(i >= lc_->nr_elements);  \
+        BUG_ON(lc_->lc_element[i] != e_); } while (0)
+
+/**
+ * lc_create - prepares to track objects in an active set
+ * @name: descriptive name only used in lc_seq_printf_stats and lc_seq_dump_details
+ * @e_count: number of elements allowed to be active simultaneously
+ * @e_size: size of the tracked objects
+ * @e_off: offset to the &struct lc_element member in a tracked object
+ *
+ * Returns a pointer to a newly initialized struct lru_cache on success,
+ * or NULL on (allocation) failure.
+ */
+struct lru_cache *lc_create(const char *name, struct kmem_cache *cache,
+                unsigned e_count, size_t e_size, size_t e_off)
+{
+        struct hlist_head *slot = NULL;
+        struct lc_element **element = NULL;
+        struct lru_cache *lc;
+        struct lc_element *e;
+        unsigned cache_obj_size = kmem_cache_size(cache);
+        unsigned i;
+
+        WARN_ON(cache_obj_size < e_size);
+        if (cache_obj_size < e_size)
+                return NULL;
+
+        /* e_count too big; would probably fail the allocation below anyways.
+         * for typical use cases, e_count should be few thousand at most. */
+        if (e_count > LC_MAX_ACTIVE)
+                return NULL;
+
+        slot = kzalloc(e_count * sizeof(struct hlist_head*), GFP_KERNEL);
+        if (!slot)
+                goto out_fail;
+        element = kzalloc(e_count * sizeof(struct lc_element *), GFP_KERNEL);
+        if (!element)
+                goto out_fail;
+
+        lc = kzalloc(sizeof(*lc), GFP_KERNEL);
+        if (!lc)
+                goto out_fail;
+
+        INIT_LIST_HEAD(&lc->in_use);
+        INIT_LIST_HEAD(&lc->lru);
+        INIT_LIST_HEAD(&lc->free);
+
+        lc->name = name;
+        lc->element_size = e_size;
+        lc->element_off = e_off;
+        lc->nr_elements = e_count;
+        lc->new_number = LC_FREE;
+        lc->lc_cache = cache;
+        lc->lc_element = element;
+        lc->lc_slot = slot;
+
+        /* preallocate all objects */
+        for (i = 0; i < e_count; i++) {
+                void *p = kmem_cache_alloc(cache, GFP_KERNEL);
+                if (!p)
+                        break;
+                memset(p, 0, lc->element_size);
+                e = p + e_off;
+                e->lc_index = i;
+                e->lc_number = LC_FREE;
+                list_add(&e->list, &lc->free);
+                element[i] = e;
+        }
+        if (i == e_count)
+                return lc;
+
+        /* else: could not allocate all elements, give up */
+        for (i--; i; i--) {
+                void *p = element[i];
+                kmem_cache_free(cache, p - e_off);
+        }
+        kfree(lc);
+out_fail:
+        kfree(element);
+        kfree(slot);
+        return NULL;
+}
+
+void lc_free_by_index(struct lru_cache *lc, unsigned i)
+{
+        void *p = lc->lc_element[i];
+        WARN_ON(!p);
+        if (p) {
+                p -= lc->element_off;
+                kmem_cache_free(lc->lc_cache, p);
+        }
+}
+
+/**
+ * lc_destroy - frees memory allocated by lc_create()
+ * @lc: the lru cache to destroy
+ */
+void lc_destroy(struct lru_cache *lc)
+{
+        unsigned i;
+        if (!lc)
+                return;
+        for (i = 0; i < lc->nr_elements; i++)
+                lc_free_by_index(lc, i);
+        kfree(lc->lc_element);
+        kfree(lc->lc_slot);
+        kfree(lc);
+}
+
+/**
+ * lc_reset - does a full reset for @lc and the hash table slots.
+ * @lc: the lru cache to operate on
+ *
+ * It is roughly the equivalent of re-allocating a fresh lru_cache object,
+ * basically a short cut to lc_destroy(lc); lc = lc_create(...);
+ */
+void lc_reset(struct lru_cache *lc)
+{
+        unsigned i;
+
+        INIT_LIST_HEAD(&lc->in_use);
+        INIT_LIST_HEAD(&lc->lru);
+        INIT_LIST_HEAD(&lc->free);
+        lc->used = 0;
+        lc->hits = 0;
+        lc->misses = 0;
+        lc->starving = 0;
+        lc->dirty = 0;
+        lc->changed = 0;
+        lc->flags = 0;
+        lc->changing_element = NULL;
+        lc->new_number = LC_FREE;
+        memset(lc->lc_slot, 0, sizeof(struct hlist_head) * lc->nr_elements);
+
+        for (i = 0; i < lc->nr_elements; i++) {
+                struct lc_element *e = lc->lc_element[i];
+                void *p = e;
+                p -= lc->element_off;
+                memset(p, 0, lc->element_size);
+                /* re-init it */
+                e->lc_index = i;
+                e->lc_number = LC_FREE;
+                list_add(&e->list, &lc->free);
+        }
+}
+
+/**
+ * lc_seq_printf_stats - print stats about @lc into @seq
+ * @seq: the seq_file to print into
+ * @lc: the lru cache to print statistics of
+ */
+size_t lc_seq_printf_stats(struct seq_file *seq, struct lru_cache *lc)
+{
+        /* NOTE:
+         * total calls to lc_get are
+         * (starving + hits + misses)
+         * misses include "dirty" count (update from an other thread in
+         * progress) and "changed", when this in fact lead to an successful
+         * update of the cache.
+         */
+        return seq_printf(seq, "\t%s: used:%u/%u "
+                "hits:%lu misses:%lu starving:%lu dirty:%lu changed:%lu\n",
+                lc->name, lc->used, lc->nr_elements,
+                lc->hits, lc->misses, lc->starving, lc->dirty, lc->changed);
+}
+
+static struct hlist_head *lc_hash_slot(struct lru_cache *lc, unsigned int enr)
+{
+        return  lc->lc_slot + (enr % lc->nr_elements);
+}
+
+
+/**
+ * lc_find - find element by label, if present in the hash table
+ * @lc: The lru_cache object
+ * @enr: element number
+ *
+ * Returns the pointer to an element, if the element with the requested
+ * "label" or element number is present in the hash table,
+ * or NULL if not found. Does not change the refcnt.
+ */
+struct lc_element *lc_find(struct lru_cache *lc, unsigned int enr)
+{
+        struct hlist_node *n;
+        struct lc_element *e;
+
+        BUG_ON(!lc);
+        BUG_ON(!lc->nr_elements);
+        hlist_for_each_entry(e, n, lc_hash_slot(lc, enr), colision) {
+                if (e->lc_number == enr)
+                        return e;
+        }
+        return NULL;
+}
+
+/* returned element will be "recycled" immediately */
+static struct lc_element *lc_evict(struct lru_cache *lc)
+{
+        struct list_head  *n;
+        struct lc_element *e;
+
+        if (list_empty(&lc->lru))
+                return NULL;
+
+        n = lc->lru.prev;
+        e = list_entry(n, struct lc_element, list);
+
+        PARANOIA_LC_ELEMENT(lc, e);
+
+        list_del(&e->list);
+        hlist_del(&e->colision);
+        return e;
+}
+
+/**
+ * lc_del - removes an element from the cache
+ * @lc: The lru_cache object
+ * @e: The element to remove
+ *
+ * @e must be unused (refcnt == 0). Moves @e from "lru" to "free" list,
+ * sets @e->enr to %LC_FREE.
+ */
+void lc_del(struct lru_cache *lc, struct lc_element *e)
+{
+        PARANOIA_ENTRY();
+        PARANOIA_LC_ELEMENT(lc, e);
+        BUG_ON(e->refcnt);
+
+        e->lc_number = LC_FREE;
+        hlist_del_init(&e->colision);
+        list_move(&e->list, &lc->free);
+        RETURN();
+}
+
+static struct lc_element *lc_get_unused_element(struct lru_cache *lc)
+{
+        struct list_head *n;
+
+        if (list_empty(&lc->free))
+                return lc_evict(lc);
+
+        n = lc->free.next;
+        list_del(n);
+        return list_entry(n, struct lc_element, list);
+}
+
+static int lc_unused_element_available(struct lru_cache *lc)
+{
+        if (!list_empty(&lc->free))
+                return 1; /* something on the free list */
+        if (!list_empty(&lc->lru))
+                return 1;  /* something to evict */
+
+        return 0;
+}
+
+
+/**
+ * lc_get - get element by label, maybe change the active set
+ * @lc: the lru cache to operate on
+ * @enr: the label to look up
+ *
+ * Finds an element in the cache, increases its usage count,
+ * "touches" and returns it.
+ *
+ * In case the requested number is not present, it needs to be added to the
+ * cache. Therefore it is possible that an other element becomes evicted from
+ * the cache. In either case, the user is notified so he is able to e.g. keep
+ * a persistent log of the cache changes, and therefore the objects in use.
+ *
+ * Return values:
+ *  NULL
+ *     The cache was marked %LC_STARVING,
+ *     or the requested label was not in the active set
+ *     and a changing transaction is still pending (@lc was marked %LC_DIRTY).
+ *     Or no unused or free element could be recycled (@lc will be marked as
+ *     %LC_STARVING, blocking further lc_get() operations).
+ *
+ *  pointer to the element with the REQUESTED element number.
+ *     In this case, it can be used right away
+ *
+ *  pointer to an UNUSED element with some different element number,
+ *          where that different number may also be %LC_FREE.
+ *
+ *          In this case, the cache is marked %LC_DIRTY (blocking further changes),
+ *          and the returned element pointer is removed from the lru list and
+ *          hash collision chains.  The user now should do whatever housekeeping
+ *          is necessary.
+ *          Then he must call lc_changed(lc,element_pointer), to finish
+ *          the change.
+ *
+ * NOTE: The user needs to check the lc_number on EACH use, so he recognizes
+ *       any cache set change.
+ */
+struct lc_element *lc_get(struct lru_cache *lc, unsigned int enr)
+{
+        struct lc_element *e;
+
+        PARANOIA_ENTRY();
+        if (lc->flags & LC_STARVING) {
+                ++lc->starving;
+                RETURN(NULL);
+        }
+
+        e = lc_find(lc, enr);
+        if (e) {
+                ++lc->hits;
+                if (e->refcnt++ == 0)
+                        lc->used++;
+                list_move(&e->list, &lc->in_use); /* Not evictable... */
+                RETURN(e);
+        }
+
+        ++lc->misses;
+
+        /* In case there is nothing available and we can not kick out
+         * the LRU element, we have to wait ...
+         */
+        if (!lc_unused_element_available(lc)) {
+                __set_bit(__LC_STARVING, &lc->flags);
+                RETURN(NULL);
+        }
+
+        /* it was not present in the active set.
+         * we are going to recycle an unused (or even "free") element.
+         * user may need to commit a transaction to record that change.
+         * we serialize on flags & TF_DIRTY */
+        if (test_and_set_bit(__LC_DIRTY, &lc->flags)) {
+                ++lc->dirty;
+                RETURN(NULL);
+        }
+
+        e = lc_get_unused_element(lc);
+        BUG_ON(!e);
+
+        clear_bit(__LC_STARVING, &lc->flags);
+        BUG_ON(++e->refcnt != 1);
+        lc->used++;
+
+        lc->changing_element = e;
+        lc->new_number = enr;
+
+        RETURN(e);
+}
+
+/* similar to lc_get,
+ * but only gets a new reference on an existing element.
+ * you either get the requested element, or NULL.
+ * will be consolidated into one function.
+ */
+struct lc_element *lc_try_get(struct lru_cache *lc, unsigned int enr)
+{
+        struct lc_element *e;
+
+        PARANOIA_ENTRY();
+        if (lc->flags & LC_STARVING) {
+                ++lc->starving;
+                RETURN(NULL);
+        }
+
+        e = lc_find(lc, enr);
+        if (e) {
+                ++lc->hits;
+                if (e->refcnt++ == 0)
+                        lc->used++;
+                list_move(&e->list, &lc->in_use); /* Not evictable... */
+        }
+        RETURN(e);
+}
+
+/**
+ * lc_changed - tell @lc that the change has been recorded
+ * @lc: the lru cache to operate on
+ * @e: the element pending label change
+ */
+void lc_changed(struct lru_cache *lc, struct lc_element *e)
+{
+        PARANOIA_ENTRY();
+        BUG_ON(e != lc->changing_element);
+        PARANOIA_LC_ELEMENT(lc, e);
+        ++lc->changed;
+        e->lc_number = lc->new_number;
+        list_add(&e->list, &lc->in_use);
+        hlist_add_head(&e->colision, lc_hash_slot(lc, lc->new_number));
+        lc->changing_element = NULL;
+        lc->new_number = LC_FREE;
+        clear_bit(__LC_DIRTY, &lc->flags);
+        smp_mb__after_clear_bit();
+        RETURN();
+}
+
+
+/**
+ * lc_put - give up refcnt of @e
+ * @lc: the lru cache to operate on
+ * @e: the element to put
+ *
+ * If refcnt reaches zero, the element is moved to the lru list,
+ * and a %LC_STARVING (if set) is cleared.
+ * Returns the new (post-decrement) refcnt.
+ */
+unsigned int lc_put(struct lru_cache *lc, struct lc_element *e)
+{
+        PARANOIA_ENTRY();
+        PARANOIA_LC_ELEMENT(lc, e);
+        BUG_ON(e->refcnt == 0);
+        BUG_ON(e == lc->changing_element);
+        if (--e->refcnt == 0) {
+                /* move it to the front of LRU. */
+                list_move(&e->list, &lc->lru);
+                lc->used--;
+                clear_bit(__LC_STARVING, &lc->flags);
+                smp_mb__after_clear_bit();
+        }
+        RETURN(e->refcnt);
+}
+
+/**
+ * lc_element_by_index
+ * @lc: the lru cache to operate on
+ * @i: the index of the element to return
+ */
+struct lc_element *lc_element_by_index(struct lru_cache *lc, unsigned i)
+{
+        BUG_ON(i >= lc->nr_elements);
+        BUG_ON(lc->lc_element[i] == NULL);
+        BUG_ON(lc->lc_element[i]->lc_index != i);
+        return lc->lc_element[i];
+}
+
+/**
+ * lc_index_of
+ * @lc: the lru cache to operate on
+ * @e: the element to query for its index position in lc->element
+ */
+unsigned int lc_index_of(struct lru_cache *lc, struct lc_element *e)
+{
+        PARANOIA_LC_ELEMENT(lc, e);
+        return e->lc_index;
+}
+
+/**
+ * lc_set - associate index with label
+ * @lc: the lru cache to operate on
+ * @enr: the label to set
+ * @index: the element index to associate label with.
+ *
+ * Used to initialize the active set to some previously recorded state.
+ */
+void lc_set(struct lru_cache *lc, unsigned int enr, int index)
+{
+        struct lc_element *e;
+
+        if (index < 0 || index >= lc->nr_elements)
+                return;
+
+        e = lc_element_by_index(lc, index);
+        e->lc_number = enr;
+
+        hlist_del_init(&e->colision);
+        hlist_add_head(&e->colision, lc_hash_slot(lc, enr));
+        list_move(&e->list, e->refcnt ? &lc->in_use : &lc->lru);
+}
+
+/**
+ * lc_dump - Dump a complete LRU cache to seq in textual form.
+ * @lc: the lru cache to operate on
+ * @seq: the &struct seq_file pointer to seq_printf into
+ * @utext: user supplied "heading" or other info
+ * @detail: function pointer the user may provide to dump further details
+ * of the object the lc_element is embedded in.
+ */
+void lc_seq_dump_details(struct seq_file *seq, struct lru_cache *lc, char *utext,
+             void (*detail) (struct seq_file *, struct lc_element *))
+{
+        unsigned int nr_elements = lc->nr_elements;
+        struct lc_element *e;
+        int i;
+
+        seq_printf(seq, "\tnn: lc_number refcnt %s\n ", utext);
+        for (i = 0; i < nr_elements; i++) {
+                e = lc_element_by_index(lc, i);
+                if (e->lc_number == LC_FREE) {
+                        seq_printf(seq, "\t%2d: FREE\n", i);
+                } else {
+                        seq_printf(seq, "\t%2d: %4u %4u    ", i,
+                                   e->lc_number, e->refcnt);
+                        detail(seq, e);
+                }
+        }
+}
+
+EXPORT_SYMBOL(lc_create);
+EXPORT_SYMBOL(lc_reset);
+EXPORT_SYMBOL(lc_destroy);
+EXPORT_SYMBOL(lc_set);
+EXPORT_SYMBOL(lc_del);
+EXPORT_SYMBOL(lc_try_get);
+EXPORT_SYMBOL(lc_find);
+EXPORT_SYMBOL(lc_get);
+EXPORT_SYMBOL(lc_put);
+EXPORT_SYMBOL(lc_changed);
+EXPORT_SYMBOL(lc_element_by_index);
+EXPORT_SYMBOL(lc_index_of);
+EXPORT_SYMBOL(lc_seq_printf_stats);
+EXPORT_SYMBOL(lc_seq_dump_details);
diff --git a/lib/radix-tree.c b/lib/radix-tree.c
index 23abbd93cae1..92cdd9936e3d 100644
--- a/lib/radix-tree.c
+++ b/lib/radix-tree.c
@@ -200,6 +200,9 @@ radix_tree_node_free(struct radix_tree_node *node)
  * ensure that the addition of a single element in the tree cannot fail.  On
  * success, return zero, with preemption disabled.  On error, return -ENOMEM
  * with preemption not disabled.
+ *
+ * To make use of this facility, the radix tree must be initialised without
+ * __GFP_WAIT being passed to INIT_RADIX_TREE().
  */
 int radix_tree_preload(gfp_t gfp_mask)
 {
@@ -543,7 +546,6 @@ out:
 }
 EXPORT_SYMBOL(radix_tree_tag_clear);
 
-#ifndef __KERNEL__      /* Only the test harness uses this at present */
 /**
  * radix_tree_tag_get - get a tag on a radix tree node
  * @root:               radix tree root
@@ -606,7 +608,6 @@ int radix_tree_tag_get(struct radix_tree_root *root,
         }
 }
 EXPORT_SYMBOL(radix_tree_tag_get);
-#endif
 
 /**
  *      radix_tree_next_hole    -    find the next hole (not-present entry)
diff --git a/lib/ratelimit.c b/lib/ratelimit.c
index 26187edcc7ea..09f5ce1810dc 100644
--- a/lib/ratelimit.c
+++ b/lib/ratelimit.c
@@ -7,15 +7,12 @@
  * parameter. Now every user can use their own standalone ratelimit_state.
  *
  * This file is released under the GPLv2.
- *
  */
 
-#include <linux/kernel.h>
+#include <linux/ratelimit.h>
 #include <linux/jiffies.h>
 #include <linux/module.h>
 
-static DEFINE_SPINLOCK(ratelimit_lock);
-
 /*
  * __ratelimit - rate limiting
  * @rs: ratelimit_state data
@@ -23,35 +20,43 @@ static DEFINE_SPINLOCK(ratelimit_lock);
  * This enforces a rate limit: not more than @rs->ratelimit_burst callbacks
  * in every @rs->ratelimit_jiffies
  */
-int __ratelimit(struct ratelimit_state *rs)
+int ___ratelimit(struct ratelimit_state *rs, const char *func)
 {
         unsigned long flags;
+        int ret;
 
         if (!rs->interval)
                 return 1;
 
-        spin_lock_irqsave(&ratelimit_lock, flags);
+        /*
+         * If we contend on this state's lock then almost
+         * by definition we are too busy to print a message,
+         * in addition to the one that will be printed by
+         * the entity that is holding the lock already:
+         */
+        if (!spin_trylock_irqsave(&rs->lock, flags))
+                return 1;
+
         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;
+                                func, rs->missed);
+                rs->begin   = 0;
                 rs->printed = 0;
-                rs->missed = 0;
+                rs->missed  = 0;
         }
-        if (rs->burst && rs->burst > rs->printed)
-                goto print;
-
-        rs->missed++;
-        spin_unlock_irqrestore(&ratelimit_lock, flags);
-        return 0;
+        if (rs->burst && rs->burst > rs->printed) {
+                rs->printed++;
+                ret = 1;
+        } else {
+                rs->missed++;
+                ret = 0;
+        }
+        spin_unlock_irqrestore(&rs->lock, flags);
 
-print:
-        rs->printed++;
-        spin_unlock_irqrestore(&ratelimit_lock, flags);
-        return 1;
+        return ret;
 }
-EXPORT_SYMBOL(__ratelimit);
+EXPORT_SYMBOL(___ratelimit);
diff --git a/lib/string.c b/lib/string.c
index b19b87af65a3..e96421ab9a9a 100644
--- a/lib/string.c
+++ b/lib/string.c
@@ -246,13 +246,17 @@ EXPORT_SYMBOL(strlcat);
 #undef strcmp
 int strcmp(const char *cs, const char *ct)
 {
-        signed char __res;
+        unsigned char c1, c2;
 
         while (1) {
-                if ((__res = *cs - *ct++) != 0 || !*cs++)
+                c1 = *cs++;
+                c2 = *ct++;
+                if (c1 != c2)
+                        return c1 < c2 ? -1 : 1;
+                if (!c1)
                         break;
         }
-        return __res;
+        return 0;
 }
 EXPORT_SYMBOL(strcmp);
 #endif
@@ -266,14 +270,18 @@ EXPORT_SYMBOL(strcmp);
  */
 int strncmp(const char *cs, const char *ct, size_t count)
 {
-        signed char __res = 0;
+        unsigned char c1, c2;
 
         while (count) {
-                if ((__res = *cs - *ct++) != 0 || !*cs++)
+                c1 = *cs++;
+                c2 = *ct++;
+                if (c1 != c2)
+                        return c1 < c2 ? -1 : 1;
+                if (!c1)
                         break;
                 count--;
         }
-        return __res;
+        return 0;
 }
 EXPORT_SYMBOL(strncmp);
 #endif
diff --git a/lib/swiotlb.c b/lib/swiotlb.c
index ac25cd28e807..5bc01803f8f8 100644
--- a/lib/swiotlb.c
+++ b/lib/swiotlb.c
@@ -97,6 +97,8 @@ static phys_addr_t *io_tlb_orig_addr;
  */
 static DEFINE_SPINLOCK(io_tlb_lock);
 
+static int late_alloc;
+
 static int __init
 setup_io_tlb_npages(char *str)
 {
@@ -109,6 +111,7 @@ setup_io_tlb_npages(char *str)
                 ++str;
         if (!strcmp(str, "force"))
                 swiotlb_force = 1;
+
         return 1;
 }
 __setup("swiotlb=", setup_io_tlb_npages);
@@ -121,8 +124,9 @@ static dma_addr_t swiotlb_virt_to_bus(struct device *hwdev,
         return phys_to_dma(hwdev, virt_to_phys(address));
 }
 
-static void swiotlb_print_info(unsigned long bytes)
+void swiotlb_print_info(void)
 {
+        unsigned long bytes = io_tlb_nslabs << IO_TLB_SHIFT;
         phys_addr_t pstart, pend;
 
         pstart = virt_to_phys(io_tlb_start);
@@ -140,7 +144,7 @@ static void swiotlb_print_info(unsigned long bytes)
  * structures for the software IO TLB used to implement the DMA API.
  */
 void __init
-swiotlb_init_with_default_size(size_t default_size)
+swiotlb_init_with_default_size(size_t default_size, int verbose)
 {
         unsigned long i, bytes;
 
@@ -176,14 +180,14 @@ swiotlb_init_with_default_size(size_t default_size)
         io_tlb_overflow_buffer = alloc_bootmem_low(io_tlb_overflow);
         if (!io_tlb_overflow_buffer)
                 panic("Cannot allocate SWIOTLB overflow buffer!\n");
-
-        swiotlb_print_info(bytes);
+        if (verbose)
+                swiotlb_print_info();
 }
 
 void __init
-swiotlb_init(void)
+swiotlb_init(int verbose)
 {
-        swiotlb_init_with_default_size(64 * (1<<20));   /* default to 64MB */
+        swiotlb_init_with_default_size(64 * (1<<20), verbose);  /* default to 64MB */
 }
 
 /*
@@ -260,7 +264,9 @@ swiotlb_late_init_with_default_size(size_t default_size)
         if (!io_tlb_overflow_buffer)
                 goto cleanup4;
 
-        swiotlb_print_info(bytes);
+        swiotlb_print_info();
+
+        late_alloc = 1;
 
         return 0;
 
@@ -281,6 +287,32 @@ cleanup1:
         return -ENOMEM;
 }
 
+void __init swiotlb_free(void)
+{
+        if (!io_tlb_overflow_buffer)
+                return;
+
+        if (late_alloc) {
+                free_pages((unsigned long)io_tlb_overflow_buffer,
+                           get_order(io_tlb_overflow));
+                free_pages((unsigned long)io_tlb_orig_addr,
+                           get_order(io_tlb_nslabs * sizeof(phys_addr_t)));
+                free_pages((unsigned long)io_tlb_list, get_order(io_tlb_nslabs *
+                                                                 sizeof(int)));
+                free_pages((unsigned long)io_tlb_start,
+                           get_order(io_tlb_nslabs << IO_TLB_SHIFT));
+        } else {
+                free_bootmem_late(__pa(io_tlb_overflow_buffer),
+                                  io_tlb_overflow);
+                free_bootmem_late(__pa(io_tlb_orig_addr),
+                                  io_tlb_nslabs * sizeof(phys_addr_t));
+                free_bootmem_late(__pa(io_tlb_list),
+                                  io_tlb_nslabs * sizeof(int));
+                free_bootmem_late(__pa(io_tlb_start),
+                                  io_tlb_nslabs << IO_TLB_SHIFT);
+        }
+}
+
 static int is_swiotlb_buffer(phys_addr_t paddr)
 {
         return paddr >= virt_to_phys(io_tlb_start) &&
@@ -453,7 +485,7 @@ do_unmap_single(struct device *hwdev, char *dma_addr, size_t size, int dir)
 
         /*
          * Return the buffer to the free list by setting the corresponding
-         * entries to indicate the number of contigous entries available.
+         * entries to indicate the number of contiguous entries available.
          * While returning the entries to the free list, we merge the entries
          * with slots below and above the pool being returned.
          */
diff --git a/lib/vsprintf.c b/lib/vsprintf.c
index 33bed5e67a21..6438cd5599ee 100644
--- a/lib/vsprintf.c
+++ b/lib/vsprintf.c
@@ -595,37 +595,89 @@ static char *symbol_string(char *buf, char *end, void *ptr,
 }
 
 static char *resource_string(char *buf, char *end, struct resource *res,
-                                struct printf_spec spec)
+                                struct printf_spec spec, const char *fmt)
 {
 #ifndef IO_RSRC_PRINTK_SIZE
-#define IO_RSRC_PRINTK_SIZE     4
+#define IO_RSRC_PRINTK_SIZE     6
 #endif
 
 #ifndef MEM_RSRC_PRINTK_SIZE
-#define MEM_RSRC_PRINTK_SIZE    8
+#define MEM_RSRC_PRINTK_SIZE    10
 #endif
-        struct printf_spec num_spec = {
+        struct printf_spec hex_spec = {
                 .base = 16,
                 .precision = -1,
                 .flags = SPECIAL | SMALL | ZEROPAD,
         };
-        /* room for the actual numbers, the two "0x", -, [, ] and the final zero */
-        char sym[4*sizeof(resource_size_t) + 8];
+        struct printf_spec dec_spec = {
+                .base = 10,
+                .precision = -1,
+                .flags = 0,
+        };
+        struct printf_spec str_spec = {
+                .field_width = -1,
+                .precision = 10,
+                .flags = LEFT,
+        };
+        struct printf_spec flag_spec = {
+                .base = 16,
+                .precision = -1,
+                .flags = SPECIAL | SMALL,
+        };
+
+        /* 32-bit res (sizeof==4): 10 chars in dec, 10 in hex ("0x" + 8)
+         * 64-bit res (sizeof==8): 20 chars in dec, 18 in hex ("0x" + 16) */
+#define RSRC_BUF_SIZE           ((2 * sizeof(resource_size_t)) + 4)
+#define FLAG_BUF_SIZE           (2 * sizeof(res->flags))
+#define DECODED_BUF_SIZE        sizeof("[mem - 64bit pref disabled]")
+#define RAW_BUF_SIZE            sizeof("[mem - flags 0x]")
+        char sym[max(2*RSRC_BUF_SIZE + DECODED_BUF_SIZE,
+                     2*RSRC_BUF_SIZE + FLAG_BUF_SIZE + RAW_BUF_SIZE)];
+
         char *p = sym, *pend = sym + sizeof(sym);
-        int size = -1;
+        int size = -1, addr = 0;
+        int decode = (fmt[0] == 'R') ? 1 : 0;
 
-        if (res->flags & IORESOURCE_IO)
+        if (res->flags & IORESOURCE_IO) {
                 size = IO_RSRC_PRINTK_SIZE;
-        else if (res->flags & IORESOURCE_MEM)
+                addr = 1;
+        } else if (res->flags & IORESOURCE_MEM) {
                 size = MEM_RSRC_PRINTK_SIZE;
+                addr = 1;
+        }
 
         *p++ = '[';
-        num_spec.field_width = size;
-        p = number(p, pend, res->start, num_spec);
-        *p++ = '-';
-        p = number(p, pend, res->end, num_spec);
+        if (res->flags & IORESOURCE_IO)
+                p = string(p, pend, "io  ", str_spec);
+        else if (res->flags & IORESOURCE_MEM)
+                p = string(p, pend, "mem ", str_spec);
+        else if (res->flags & IORESOURCE_IRQ)
+                p = string(p, pend, "irq ", str_spec);
+        else if (res->flags & IORESOURCE_DMA)
+                p = string(p, pend, "dma ", str_spec);
+        else {
+                p = string(p, pend, "??? ", str_spec);
+                decode = 0;
+        }
+        hex_spec.field_width = size;
+        p = number(p, pend, res->start, addr ? hex_spec : dec_spec);
+        if (res->start != res->end) {
+                *p++ = '-';
+                p = number(p, pend, res->end, addr ? hex_spec : dec_spec);
+        }
+        if (decode) {
+                if (res->flags & IORESOURCE_MEM_64)
+                        p = string(p, pend, " 64bit", str_spec);
+                if (res->flags & IORESOURCE_PREFETCH)
+                        p = string(p, pend, " pref", str_spec);
+                if (res->flags & IORESOURCE_DISABLED)
+                        p = string(p, pend, " disabled", str_spec);
+        } else {
+                p = string(p, pend, " flags ", str_spec);
+                p = number(p, pend, res->flags, flag_spec);
+        }
         *p++ = ']';
-        *p = 0;
+        *p = '\0';
 
         return string(buf, end, sym, spec);
 }
@@ -801,8 +853,8 @@ static char *ip4_addr_string(char *buf, char *end, const u8 *addr,
  * - 'f' For simple symbolic function names without offset
  * - 'S' For symbolic direct pointers with offset
  * - 's' For symbolic direct pointers without offset
- * - 'R' For a struct resource pointer, it prints the range of
- *       addresses (not the name nor the flags)
+ * - 'R' For decoded struct resource, e.g., [mem 0x0-0x1f 64bit pref]
+ * - 'r' For raw struct resource, e.g., [mem 0x0-0x1f flags 0x201]
  * - 'M' For a 6-byte MAC address, it prints the address in the
  *       usual colon-separated hex notation
  * - 'm' For a 6-byte MAC address, it prints the hex address without colons
@@ -833,7 +885,8 @@ static char *pointer(const char *fmt, char *buf, char *end, void *ptr,
         case 'S':
                 return symbol_string(buf, end, ptr, spec, *fmt);
         case 'R':
-                return resource_string(buf, end, ptr, spec);
+        case 'r':
+                return resource_string(buf, end, ptr, spec, fmt);
         case 'M':                       /* Colon separated: 00:01:02:03:04:05 */
         case 'm':                       /* Contiguous: 000102030405 */
                 return mac_address_string(buf, end, ptr, spec, fmt);