15 files changed, 743 insertions, 145 deletions

diff --git a/lib/Kconfig b/lib/Kconfig
index 9960be04cbbe..bb1326d3839c 100644
--- a/lib/Kconfig
+++ b/lib/Kconfig
@@ -194,4 +194,10 @@ config DISABLE_OBSOLETE_CPUMASK_FUNCTIONS
 config NLATTR
         bool
 
+#
+# Generic 64-bit atomic support is selected if needed
+#
+config GENERIC_ATOMIC64
+       bool
+
 endmenu
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index 116a35051be6..12327b2bb785 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -300,7 +300,7 @@ config DEBUG_OBJECTS_ENABLE_DEFAULT
 
 config DEBUG_SLAB
         bool "Debug slab memory allocations"
-        depends on DEBUG_KERNEL && SLAB
+        depends on DEBUG_KERNEL && SLAB && !KMEMCHECK
         help
           Say Y here to have the kernel do limited verification on memory
           allocation as well as poisoning memory on free to catch use of freed
@@ -312,7 +312,7 @@ config DEBUG_SLAB_LEAK
 
 config SLUB_DEBUG_ON
         bool "SLUB debugging on by default"
-        depends on SLUB && SLUB_DEBUG
+        depends on SLUB && SLUB_DEBUG && !KMEMCHECK
         default n
         help
           Boot with debugging on by default. SLUB boots by default with
@@ -340,8 +340,6 @@ config DEBUG_KMEMLEAK
         bool "Kernel memory leak detector"
         depends on DEBUG_KERNEL && EXPERIMENTAL && (X86 || ARM) && \
                 !MEMORY_HOTPLUG
-        select DEBUG_SLAB if SLAB
-        select SLUB_DEBUG if SLUB
         select DEBUG_FS if SYSFS
         select STACKTRACE if STACKTRACE_SUPPORT
         select KALLSYMS
@@ -355,9 +353,24 @@ config DEBUG_KMEMLEAK
           allocations. See Documentation/kmemleak.txt for more
           details.
 
+          Enabling DEBUG_SLAB or SLUB_DEBUG may increase the chances
+          of finding leaks due to the slab objects poisoning.
+
           In order to access the kmemleak file, debugfs needs to be
           mounted (usually at /sys/kernel/debug).
 
+config DEBUG_KMEMLEAK_EARLY_LOG_SIZE
+        int "Maximum kmemleak early log entries"
+        depends on DEBUG_KMEMLEAK
+        range 200 2000
+        default 400
+        help
+          Kmemleak must track all the memory allocations to avoid
+          reporting false positives. Since memory may be allocated or
+          freed before kmemleak is initialised, an early log buffer is
+          used to store these actions. If kmemleak reports "early log
+          buffer exceeded", please increase this value.
+
 config DEBUG_KMEMLEAK_TEST
         tristate "Simple test for the kernel memory leak detector"
         depends on DEBUG_KMEMLEAK
@@ -472,7 +485,7 @@ config LOCKDEP
         bool
         depends on DEBUG_KERNEL && TRACE_IRQFLAGS_SUPPORT && STACKTRACE_SUPPORT && LOCKDEP_SUPPORT
         select STACKTRACE
-        select FRAME_POINTER if !X86 && !MIPS && !PPC && !ARM_UNWIND && !S390
+        select FRAME_POINTER if !MIPS && !PPC && !ARM_UNWIND && !S390
         select KALLSYMS
         select KALLSYMS_ALL
 
@@ -996,3 +1009,5 @@ config DMA_API_DEBUG
 source "samples/Kconfig"
 
 source "lib/Kconfig.kgdb"
+
+source "lib/Kconfig.kmemcheck"
diff --git a/lib/Kconfig.kmemcheck b/lib/Kconfig.kmemcheck
new file mode 100644
index 000000000000..603c81b66549
--- /dev/null
+++ b/lib/Kconfig.kmemcheck
@@ -0,0 +1,91 @@
+config HAVE_ARCH_KMEMCHECK
+        bool
+
+menuconfig KMEMCHECK
+        bool "kmemcheck: trap use of uninitialized memory"
+        depends on DEBUG_KERNEL
+        depends on !X86_USE_3DNOW
+        depends on SLUB || SLAB
+        depends on !CC_OPTIMIZE_FOR_SIZE
+        depends on !FUNCTION_TRACER
+        select FRAME_POINTER
+        select STACKTRACE
+        default n
+        help
+          This option enables tracing of dynamically allocated kernel memory
+          to see if memory is used before it has been given an initial value.
+          Be aware that this requires half of your memory for bookkeeping and
+          will insert extra code at *every* read and write to tracked memory
+          thus slow down the kernel code (but user code is unaffected).
+
+          The kernel may be started with kmemcheck=0 or kmemcheck=1 to disable
+          or enable kmemcheck at boot-time. If the kernel is started with
+          kmemcheck=0, the large memory and CPU overhead is not incurred.
+
+choice
+        prompt "kmemcheck: default mode at boot"
+        depends on KMEMCHECK
+        default KMEMCHECK_ONESHOT_BY_DEFAULT
+        help
+          This option controls the default behaviour of kmemcheck when the
+          kernel boots and no kmemcheck= parameter is given.
+
+config KMEMCHECK_DISABLED_BY_DEFAULT
+        bool "disabled"
+        depends on KMEMCHECK
+
+config KMEMCHECK_ENABLED_BY_DEFAULT
+        bool "enabled"
+        depends on KMEMCHECK
+
+config KMEMCHECK_ONESHOT_BY_DEFAULT
+        bool "one-shot"
+        depends on KMEMCHECK
+        help
+          In one-shot mode, only the first error detected is reported before
+          kmemcheck is disabled.
+
+endchoice
+
+config KMEMCHECK_QUEUE_SIZE
+        int "kmemcheck: error queue size"
+        depends on KMEMCHECK
+        default 64
+        help
+          Select the maximum number of errors to store in the queue. Since
+          errors can occur virtually anywhere and in any context, we need a
+          temporary storage area which is guarantueed not to generate any
+          other faults. The queue will be emptied as soon as a tasklet may
+          be scheduled. If the queue is full, new error reports will be
+          lost.
+
+config KMEMCHECK_SHADOW_COPY_SHIFT
+        int "kmemcheck: shadow copy size (5 => 32 bytes, 6 => 64 bytes)"
+        depends on KMEMCHECK
+        range 2 8
+        default 5
+        help
+          Select the number of shadow bytes to save along with each entry of
+          the queue. These bytes indicate what parts of an allocation are
+          initialized, uninitialized, etc. and will be displayed when an
+          error is detected to help the debugging of a particular problem.
+
+config KMEMCHECK_PARTIAL_OK
+        bool "kmemcheck: allow partially uninitialized memory"
+        depends on KMEMCHECK
+        default y
+        help
+          This option works around certain GCC optimizations that produce
+          32-bit reads from 16-bit variables where the upper 16 bits are
+          thrown away afterwards. This may of course also hide some real
+          bugs.
+
+config KMEMCHECK_BITOPS_OK
+        bool "kmemcheck: allow bit-field manipulation"
+        depends on KMEMCHECK
+        default n
+        help
+          This option silences warnings that would be generated for bit-field
+          accesses where not all the bits are initialized at the same time.
+          This may also hide some real bugs.
+
diff --git a/lib/Makefile b/lib/Makefile
index 1f6edefebffe..b6d1857bbf08 100644
--- a/lib/Makefile
+++ b/lib/Makefile
@@ -21,7 +21,7 @@ lib-y	+= kobject.o kref.o klist.o
 
 obj-y += bcd.o div64.o sort.o parser.o halfmd4.o debug_locks.o random32.o \
          bust_spinlocks.o hexdump.o kasprintf.o bitmap.o scatterlist.o \
-         string_helpers.o
+         string_helpers.o gcd.o
 
 ifeq ($(CONFIG_DEBUG_KOBJECT),y)
 CFLAGS_kobject.o += -DDEBUG
@@ -93,6 +93,10 @@ obj-$(CONFIG_NLATTR) += nlattr.o
 
 obj-$(CONFIG_DMA_API_DEBUG) += dma-debug.o
 
+obj-$(CONFIG_GENERIC_CSUM) += checksum.o
+
+obj-$(CONFIG_GENERIC_ATOMIC64) += atomic64.o
+
 hostprogs-y     := gen_crc32table
 clean-files     := crc32table.h
 
diff --git a/lib/atomic64.c b/lib/atomic64.c
new file mode 100644
index 000000000000..c5e725562416
--- /dev/null
+++ b/lib/atomic64.c
@@ -0,0 +1,175 @@
+/*
+ * Generic implementation of 64-bit atomics using spinlocks,
+ * useful on processors that don't have 64-bit atomic instructions.
+ *
+ * Copyright © 2009 Paul Mackerras, IBM Corp. <paulus@au1.ibm.com>
+ *
+ * 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/types.h>
+#include <linux/cache.h>
+#include <linux/spinlock.h>
+#include <linux/init.h>
+#include <asm/atomic.h>
+
+/*
+ * We use a hashed array of spinlocks to provide exclusive access
+ * to each atomic64_t variable.  Since this is expected to used on
+ * systems with small numbers of CPUs (<= 4 or so), we use a
+ * relatively small array of 16 spinlocks to avoid wasting too much
+ * memory on the spinlock array.
+ */
+#define NR_LOCKS        16
+
+/*
+ * Ensure each lock is in a separate cacheline.
+ */
+static union {
+        spinlock_t lock;
+        char pad[L1_CACHE_BYTES];
+} atomic64_lock[NR_LOCKS] __cacheline_aligned_in_smp;
+
+static inline spinlock_t *lock_addr(const atomic64_t *v)
+{
+        unsigned long addr = (unsigned long) v;
+
+        addr >>= L1_CACHE_SHIFT;
+        addr ^= (addr >> 8) ^ (addr >> 16);
+        return &atomic64_lock[addr & (NR_LOCKS - 1)].lock;
+}
+
+long long atomic64_read(const atomic64_t *v)
+{
+        unsigned long flags;
+        spinlock_t *lock = lock_addr(v);
+        long long val;
+
+        spin_lock_irqsave(lock, flags);
+        val = v->counter;
+        spin_unlock_irqrestore(lock, flags);
+        return val;
+}
+
+void atomic64_set(atomic64_t *v, long long i)
+{
+        unsigned long flags;
+        spinlock_t *lock = lock_addr(v);
+
+        spin_lock_irqsave(lock, flags);
+        v->counter = i;
+        spin_unlock_irqrestore(lock, flags);
+}
+
+void atomic64_add(long long a, atomic64_t *v)
+{
+        unsigned long flags;
+        spinlock_t *lock = lock_addr(v);
+
+        spin_lock_irqsave(lock, flags);
+        v->counter += a;
+        spin_unlock_irqrestore(lock, flags);
+}
+
+long long atomic64_add_return(long long a, atomic64_t *v)
+{
+        unsigned long flags;
+        spinlock_t *lock = lock_addr(v);
+        long long val;
+
+        spin_lock_irqsave(lock, flags);
+        val = v->counter += a;
+        spin_unlock_irqrestore(lock, flags);
+        return val;
+}
+
+void atomic64_sub(long long a, atomic64_t *v)
+{
+        unsigned long flags;
+        spinlock_t *lock = lock_addr(v);
+
+        spin_lock_irqsave(lock, flags);
+        v->counter -= a;
+        spin_unlock_irqrestore(lock, flags);
+}
+
+long long atomic64_sub_return(long long a, atomic64_t *v)
+{
+        unsigned long flags;
+        spinlock_t *lock = lock_addr(v);
+        long long val;
+
+        spin_lock_irqsave(lock, flags);
+        val = v->counter -= a;
+        spin_unlock_irqrestore(lock, flags);
+        return val;
+}
+
+long long atomic64_dec_if_positive(atomic64_t *v)
+{
+        unsigned long flags;
+        spinlock_t *lock = lock_addr(v);
+        long long val;
+
+        spin_lock_irqsave(lock, flags);
+        val = v->counter - 1;
+        if (val >= 0)
+                v->counter = val;
+        spin_unlock_irqrestore(lock, flags);
+        return val;
+}
+
+long long atomic64_cmpxchg(atomic64_t *v, long long o, long long n)
+{
+        unsigned long flags;
+        spinlock_t *lock = lock_addr(v);
+        long long val;
+
+        spin_lock_irqsave(lock, flags);
+        val = v->counter;
+        if (val == o)
+                v->counter = n;
+        spin_unlock_irqrestore(lock, flags);
+        return val;
+}
+
+long long atomic64_xchg(atomic64_t *v, long long new)
+{
+        unsigned long flags;
+        spinlock_t *lock = lock_addr(v);
+        long long val;
+
+        spin_lock_irqsave(lock, flags);
+        val = v->counter;
+        v->counter = new;
+        spin_unlock_irqrestore(lock, flags);
+        return val;
+}
+
+int atomic64_add_unless(atomic64_t *v, long long a, long long u)
+{
+        unsigned long flags;
+        spinlock_t *lock = lock_addr(v);
+        int ret = 1;
+
+        spin_lock_irqsave(lock, flags);
+        if (v->counter != u) {
+                v->counter += a;
+                ret = 0;
+        }
+        spin_unlock_irqrestore(lock, flags);
+        return ret;
+}
+
+static int init_atomic64_lock(void)
+{
+        int i;
+
+        for (i = 0; i < NR_LOCKS; ++i)
+                spin_lock_init(&atomic64_lock[i].lock);
+        return 0;
+}
+
+pure_initcall(init_atomic64_lock);
diff --git a/lib/checksum.c b/lib/checksum.c
new file mode 100644
index 000000000000..b2e2fd468461
--- /dev/null
+++ b/lib/checksum.c
@@ -0,0 +1,201 @@
+/*
+ *
+ * INET         An implementation of the TCP/IP protocol suite for the LINUX
+ *              operating system.  INET is implemented using the  BSD Socket
+ *              interface as the means of communication with the user level.
+ *
+ *              IP/TCP/UDP checksumming routines
+ *
+ * Authors:     Jorge Cwik, <jorge@laser.satlink.net>
+ *              Arnt Gulbrandsen, <agulbra@nvg.unit.no>
+ *              Tom May, <ftom@netcom.com>
+ *              Andreas Schwab, <schwab@issan.informatik.uni-dortmund.de>
+ *              Lots of code moved from tcp.c and ip.c; see those files
+ *              for more names.
+ *
+ * 03/02/96     Jes Sorensen, Andreas Schwab, Roman Hodek:
+ *              Fixed some nasty bugs, causing some horrible crashes.
+ *              A: At some points, the sum (%0) was used as
+ *              length-counter instead of the length counter
+ *              (%1). Thanks to Roman Hodek for pointing this out.
+ *              B: GCC seems to mess up if one uses too many
+ *              data-registers to hold input values and one tries to
+ *              specify d0 and d1 as scratch registers. Letting gcc
+ *              choose these registers itself solves the problem.
+ *
+ *              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.
+ */
+
+/* Revised by Kenneth Albanowski for m68knommu. Basic problem: unaligned access
+ kills, so most of the assembly has to go. */
+
+#include <linux/module.h>
+#include <net/checksum.h>
+
+#include <asm/byteorder.h>
+
+static inline unsigned short from32to16(unsigned long x)
+{
+        /* add up 16-bit and 16-bit for 16+c bit */
+        x = (x & 0xffff) + (x >> 16);
+        /* add up carry.. */
+        x = (x & 0xffff) + (x >> 16);
+        return x;
+}
+
+static unsigned int do_csum(const unsigned char *buff, int len)
+{
+        int odd, count;
+        unsigned long result = 0;
+
+        if (len <= 0)
+                goto out;
+        odd = 1 & (unsigned long) buff;
+        if (odd) {
+#ifdef __LITTLE_ENDIAN
+                result = *buff;
+#else
+                result += (*buff << 8);
+#endif
+                len--;
+                buff++;
+        }
+        count = len >> 1;               /* nr of 16-bit words.. */
+        if (count) {
+                if (2 & (unsigned long) buff) {
+                        result += *(unsigned short *) buff;
+                        count--;
+                        len -= 2;
+                        buff += 2;
+                }
+                count >>= 1;            /* nr of 32-bit words.. */
+                if (count) {
+                        unsigned long carry = 0;
+                        do {
+                                unsigned long w = *(unsigned int *) buff;
+                                count--;
+                                buff += 4;
+                                result += carry;
+                                result += w;
+                                carry = (w > result);
+                        } while (count);
+                        result += carry;
+                        result = (result & 0xffff) + (result >> 16);
+                }
+                if (len & 2) {
+                        result += *(unsigned short *) buff;
+                        buff += 2;
+                }
+        }
+        if (len & 1)
+#ifdef __LITTLE_ENDIAN
+                result += *buff;
+#else
+                result += (*buff << 8);
+#endif
+        result = from32to16(result);
+        if (odd)
+                result = ((result >> 8) & 0xff) | ((result & 0xff) << 8);
+out:
+        return result;
+}
+
+/*
+ *      This is a version of ip_compute_csum() optimized for IP headers,
+ *      which always checksum on 4 octet boundaries.
+ */
+__sum16 ip_fast_csum(const void *iph, unsigned int ihl)
+{
+        return (__force __sum16)~do_csum(iph, ihl*4);
+}
+EXPORT_SYMBOL(ip_fast_csum);
+
+/*
+ * computes the checksum of a memory block at buff, length len,
+ * and adds in "sum" (32-bit)
+ *
+ * returns a 32-bit number suitable for feeding into itself
+ * or csum_tcpudp_magic
+ *
+ * this function must be called with even lengths, except
+ * for the last fragment, which may be odd
+ *
+ * it's best to have buff aligned on a 32-bit boundary
+ */
+__wsum csum_partial(const void *buff, int len, __wsum wsum)
+{
+        unsigned int sum = (__force unsigned int)wsum;
+        unsigned int result = do_csum(buff, len);
+
+        /* add in old sum, and carry.. */
+        result += sum;
+        if (sum > result)
+                result += 1;
+        return (__force __wsum)result;
+}
+EXPORT_SYMBOL(csum_partial);
+
+/*
+ * this routine is used for miscellaneous IP-like checksums, mainly
+ * in icmp.c
+ */
+__sum16 ip_compute_csum(const void *buff, int len)
+{
+        return (__force __sum16)~do_csum(buff, len);
+}
+EXPORT_SYMBOL(ip_compute_csum);
+
+/*
+ * copy from fs while checksumming, otherwise like csum_partial
+ */
+__wsum
+csum_partial_copy_from_user(const void __user *src, void *dst, int len,
+                                                __wsum sum, int *csum_err)
+{
+        int missing;
+
+        missing = __copy_from_user(dst, src, len);
+        if (missing) {
+                memset(dst + len - missing, 0, missing);
+                *csum_err = -EFAULT;
+        } else
+                *csum_err = 0;
+
+        return csum_partial(dst, len, sum);
+}
+EXPORT_SYMBOL(csum_partial_copy_from_user);
+
+/*
+ * copy from ds while checksumming, otherwise like csum_partial
+ */
+__wsum
+csum_partial_copy(const void *src, void *dst, int len, __wsum sum)
+{
+        memcpy(dst, src, len);
+        return csum_partial(dst, len, sum);
+}
+EXPORT_SYMBOL(csum_partial_copy);
+
+#ifndef csum_tcpudp_nofold
+__wsum csum_tcpudp_nofold(__be32 saddr, __be32 daddr,
+                        unsigned short len,
+                        unsigned short proto,
+                        __wsum sum)
+{
+        unsigned long long s = (__force u32)sum;
+
+        s += (__force u32)saddr;
+        s += (__force u32)daddr;
+#ifdef __BIG_ENDIAN
+        s += proto + len;
+#else
+        s += (proto + len) << 8;
+#endif
+        s += (s >> 32);
+        return (__force __wsum)s;
+}
+EXPORT_SYMBOL(csum_tcpudp_nofold);
+#endif
diff --git a/lib/dec_and_lock.c b/lib/dec_and_lock.c
index a65c31455541..e73822aa6e9a 100644
--- a/lib/dec_and_lock.c
+++ b/lib/dec_and_lock.c
@@ -19,11 +19,10 @@
  */
 int _atomic_dec_and_lock(atomic_t *atomic, spinlock_t *lock)
 {
-#ifdef CONFIG_SMP
         /* Subtract 1 from counter unless that drops it to 0 (ie. it was 1) */
         if (atomic_add_unless(atomic, -1, 1))
                 return 0;
-#endif
+
         /* Otherwise do it the slow way */
         spin_lock(lock);
         if (atomic_dec_and_test(atomic))
diff --git a/lib/dma-debug.c b/lib/dma-debug.c
index ad65fc0317d9..65b0d99b6d0a 100644
--- a/lib/dma-debug.c
+++ b/lib/dma-debug.c
@@ -262,11 +262,12 @@ static struct dma_debug_entry *hash_bucket_find(struct hash_bucket *bucket,
                  */
                 matches += 1;
                 match_lvl = 0;
-                entry->size      == ref->size      ? ++match_lvl : match_lvl;
-                entry->type      == ref->type      ? ++match_lvl : match_lvl;
-                entry->direction == ref->direction ? ++match_lvl : match_lvl;
+                entry->size         == ref->size         ? ++match_lvl : 0;
+                entry->type         == ref->type         ? ++match_lvl : 0;
+                entry->direction    == ref->direction    ? ++match_lvl : 0;
+                entry->sg_call_ents == ref->sg_call_ents ? ++match_lvl : 0;
 
-                if (match_lvl == 3) {
+                if (match_lvl == 4) {
                         /* perfect-fit - return the result */
                         return entry;
                 } else if (match_lvl > last_lvl) {
@@ -715,7 +716,7 @@ void dma_debug_init(u32 num_entries)
 
         for (i = 0; i < HASH_SIZE; ++i) {
                 INIT_LIST_HEAD(&dma_entry_hash[i].list);
-                dma_entry_hash[i].lock = SPIN_LOCK_UNLOCKED;
+                spin_lock_init(&dma_entry_hash[i].lock);
         }
 
         if (dma_debug_fs_init() != 0) {
@@ -855,90 +856,85 @@ static void check_for_stack(struct device *dev, void *addr)
                                 "stack [addr=%p]\n", addr);
 }
 
-static inline bool overlap(void *addr, u64 size, void *start, void *end)
+static inline bool overlap(void *addr, unsigned long len, void *start, void *end)
 {
-        void *addr2 = (char *)addr + size;
+        unsigned long a1 = (unsigned long)addr;
+        unsigned long b1 = a1 + len;
+        unsigned long a2 = (unsigned long)start;
+        unsigned long b2 = (unsigned long)end;
 
-        return ((addr >= start && addr < end) ||
-                (addr2 >= start && addr2 < end) ||
-                ((addr < start) && (addr2 >= end)));
+        return !(b1 <= a2 || a1 >= b2);
 }
 
-static void check_for_illegal_area(struct device *dev, void *addr, u64 size)
+static void check_for_illegal_area(struct device *dev, void *addr, unsigned long len)
 {
-        if (overlap(addr, size, _text, _etext) ||
-            overlap(addr, size, __start_rodata, __end_rodata))
-                err_printk(dev, NULL, "DMA-API: device driver maps "
-                                "memory from kernel text or rodata "
-                                "[addr=%p] [size=%llu]\n", addr, size);
+        if (overlap(addr, len, _text, _etext) ||
+            overlap(addr, len, __start_rodata, __end_rodata))
+                err_printk(dev, NULL, "DMA-API: device driver maps memory from kernel text or rodata [addr=%p] [len=%lu]\n", addr, len);
 }
 
-static void check_sync(struct device *dev, dma_addr_t addr,
-                       u64 size, u64 offset, int direction, bool to_cpu)
+static void check_sync(struct device *dev,
+                       struct dma_debug_entry *ref,
+                       bool to_cpu)
 {
-        struct dma_debug_entry ref = {
-                .dev            = dev,
-                .dev_addr       = addr,
-                .size           = size,
-                .direction      = direction,
-        };
         struct dma_debug_entry *entry;
         struct hash_bucket *bucket;
         unsigned long flags;
 
-        bucket = get_hash_bucket(&ref, &flags);
+        bucket = get_hash_bucket(ref, &flags);
 
-        entry = hash_bucket_find(bucket, &ref);
+        entry = hash_bucket_find(bucket, ref);
 
         if (!entry) {
                 err_printk(dev, NULL, "DMA-API: device driver tries "
                                 "to sync DMA memory it has not allocated "
                                 "[device address=0x%016llx] [size=%llu bytes]\n",
-                                (unsigned long long)addr, size);
+                                (unsigned long long)ref->dev_addr, ref->size);
                 goto out;
         }
 
-        if ((offset + size) > entry->size) {
+        if (ref->size > entry->size) {
                 err_printk(dev, entry, "DMA-API: device driver syncs"
                                 " DMA memory outside allocated range "
                                 "[device address=0x%016llx] "
-                                "[allocation size=%llu bytes] [sync offset=%llu] "
-                                "[sync size=%llu]\n", entry->dev_addr, entry->size,
-                                offset, size);
+                                "[allocation size=%llu bytes] "
+                                "[sync offset+size=%llu]\n",
+                                entry->dev_addr, entry->size,
+                                ref->size);
         }
 
-        if (direction != entry->direction) {
+        if (ref->direction != entry->direction) {
                 err_printk(dev, entry, "DMA-API: device driver syncs "
                                 "DMA memory with different direction "
                                 "[device address=0x%016llx] [size=%llu bytes] "
                                 "[mapped with %s] [synced with %s]\n",
-                                (unsigned long long)addr, entry->size,
+                                (unsigned long long)ref->dev_addr, entry->size,
                                 dir2name[entry->direction],
-                                dir2name[direction]);
+                                dir2name[ref->direction]);
         }
 
         if (entry->direction == DMA_BIDIRECTIONAL)
                 goto out;
 
         if (to_cpu && !(entry->direction == DMA_FROM_DEVICE) &&
-                      !(direction == DMA_TO_DEVICE))
+                      !(ref->direction == DMA_TO_DEVICE))
                 err_printk(dev, entry, "DMA-API: device driver syncs "
                                 "device read-only DMA memory for cpu "
                                 "[device address=0x%016llx] [size=%llu bytes] "
                                 "[mapped with %s] [synced with %s]\n",
-                                (unsigned long long)addr, entry->size,
+                                (unsigned long long)ref->dev_addr, entry->size,
                                 dir2name[entry->direction],
-                                dir2name[direction]);
+                                dir2name[ref->direction]);
 
         if (!to_cpu && !(entry->direction == DMA_TO_DEVICE) &&
-                       !(direction == DMA_FROM_DEVICE))
+                       !(ref->direction == DMA_FROM_DEVICE))
                 err_printk(dev, entry, "DMA-API: device driver syncs "
                                 "device write-only DMA memory to device "
                                 "[device address=0x%016llx] [size=%llu bytes] "
                                 "[mapped with %s] [synced with %s]\n",
-                                (unsigned long long)addr, entry->size,
+                                (unsigned long long)ref->dev_addr, entry->size,
                                 dir2name[entry->direction],
-                                dir2name[direction]);
+                                dir2name[ref->direction]);
 
 out:
         put_hash_bucket(bucket, &flags);
@@ -972,7 +968,8 @@ void debug_dma_map_page(struct device *dev, struct page *page, size_t offset,
                 entry->type = dma_debug_single;
 
         if (!PageHighMem(page)) {
-                void *addr = ((char *)page_address(page)) + offset;
+                void *addr = page_address(page) + offset;
+
                 check_for_stack(dev, addr);
                 check_for_illegal_area(dev, addr, size);
         }
@@ -1036,19 +1033,16 @@ void debug_dma_map_sg(struct device *dev, struct scatterlist *sg,
 }
 EXPORT_SYMBOL(debug_dma_map_sg);
 
-static int get_nr_mapped_entries(struct device *dev, struct scatterlist *s)
+static int get_nr_mapped_entries(struct device *dev,
+                                 struct dma_debug_entry *ref)
 {
-        struct dma_debug_entry *entry, ref;
+        struct dma_debug_entry *entry;
         struct hash_bucket *bucket;
         unsigned long flags;
         int mapped_ents;
 
-        ref.dev      = dev;
-        ref.dev_addr = sg_dma_address(s);
-        ref.size     = sg_dma_len(s),
-
-        bucket       = get_hash_bucket(&ref, &flags);
-        entry        = hash_bucket_find(bucket, &ref);
+        bucket       = get_hash_bucket(ref, &flags);
+        entry        = hash_bucket_find(bucket, ref);
         mapped_ents  = 0;
 
         if (entry)
@@ -1076,16 +1070,14 @@ void debug_dma_unmap_sg(struct device *dev, struct scatterlist *sglist,
                         .dev_addr       = sg_dma_address(s),
                         .size           = sg_dma_len(s),
                         .direction      = dir,
-                        .sg_call_ents   = 0,
+                        .sg_call_ents   = nelems,
                 };
 
                 if (mapped_ents && i >= mapped_ents)
                         break;
 
-                if (!i) {
-                        ref.sg_call_ents = nelems;
-                        mapped_ents = get_nr_mapped_entries(dev, s);
-                }
+                if (!i)
+                        mapped_ents = get_nr_mapped_entries(dev, &ref);
 
                 check_unmap(&ref);
         }
@@ -1140,10 +1132,19 @@ EXPORT_SYMBOL(debug_dma_free_coherent);
 void debug_dma_sync_single_for_cpu(struct device *dev, dma_addr_t dma_handle,
                                    size_t size, int direction)
 {
+        struct dma_debug_entry ref;
+
         if (unlikely(global_disable))
                 return;
 
-        check_sync(dev, dma_handle, size, 0, direction, true);
+        ref.type         = dma_debug_single;
+        ref.dev          = dev;
+        ref.dev_addr     = dma_handle;
+        ref.size         = size;
+        ref.direction    = direction;
+        ref.sg_call_ents = 0;
+
+        check_sync(dev, &ref, true);
 }
 EXPORT_SYMBOL(debug_dma_sync_single_for_cpu);
 
@@ -1151,10 +1152,19 @@ void debug_dma_sync_single_for_device(struct device *dev,
                                       dma_addr_t dma_handle, size_t size,
                                       int direction)
 {
+        struct dma_debug_entry ref;
+
         if (unlikely(global_disable))
                 return;
 
-        check_sync(dev, dma_handle, size, 0, direction, false);
+        ref.type         = dma_debug_single;
+        ref.dev          = dev;
+        ref.dev_addr     = dma_handle;
+        ref.size         = size;
+        ref.direction    = direction;
+        ref.sg_call_ents = 0;
+
+        check_sync(dev, &ref, false);
 }
 EXPORT_SYMBOL(debug_dma_sync_single_for_device);
 
@@ -1163,10 +1173,19 @@ void debug_dma_sync_single_range_for_cpu(struct device *dev,
                                          unsigned long offset, size_t size,
                                          int direction)
 {
+        struct dma_debug_entry ref;
+
         if (unlikely(global_disable))
                 return;
 
-        check_sync(dev, dma_handle, size, offset, direction, true);
+        ref.type         = dma_debug_single;
+        ref.dev          = dev;
+        ref.dev_addr     = dma_handle;
+        ref.size         = offset + size;
+        ref.direction    = direction;
+        ref.sg_call_ents = 0;
+
+        check_sync(dev, &ref, true);
 }
 EXPORT_SYMBOL(debug_dma_sync_single_range_for_cpu);
 
@@ -1175,10 +1194,19 @@ void debug_dma_sync_single_range_for_device(struct device *dev,
                                             unsigned long offset,
                                             size_t size, int direction)
 {
+        struct dma_debug_entry ref;
+
         if (unlikely(global_disable))
                 return;
 
-        check_sync(dev, dma_handle, size, offset, direction, false);
+        ref.type         = dma_debug_single;
+        ref.dev          = dev;
+        ref.dev_addr     = dma_handle;
+        ref.size         = offset + size;
+        ref.direction    = direction;
+        ref.sg_call_ents = 0;
+
+        check_sync(dev, &ref, false);
 }
 EXPORT_SYMBOL(debug_dma_sync_single_range_for_device);
 
@@ -1192,14 +1220,24 @@ void debug_dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg,
                 return;
 
         for_each_sg(sg, s, nelems, i) {
+
+                struct dma_debug_entry ref = {
+                        .type           = dma_debug_sg,
+                        .dev            = dev,
+                        .paddr          = sg_phys(s),
+                        .dev_addr       = sg_dma_address(s),
+                        .size           = sg_dma_len(s),
+                        .direction      = direction,
+                        .sg_call_ents   = nelems,
+                };
+
                 if (!i)
-                        mapped_ents = get_nr_mapped_entries(dev, s);
+                        mapped_ents = get_nr_mapped_entries(dev, &ref);
 
                 if (i >= mapped_ents)
                         break;
 
-                check_sync(dev, sg_dma_address(s), sg_dma_len(s), 0,
-                           direction, true);
+                check_sync(dev, &ref, true);
         }
 }
 EXPORT_SYMBOL(debug_dma_sync_sg_for_cpu);
@@ -1214,14 +1252,23 @@ void debug_dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg,
                 return;
 
         for_each_sg(sg, s, nelems, i) {
+
+                struct dma_debug_entry ref = {
+                        .type           = dma_debug_sg,
+                        .dev            = dev,
+                        .paddr          = sg_phys(s),
+                        .dev_addr       = sg_dma_address(s),
+                        .size           = sg_dma_len(s),
+                        .direction      = direction,
+                        .sg_call_ents   = nelems,
+                };
                 if (!i)
-                        mapped_ents = get_nr_mapped_entries(dev, s);
+                        mapped_ents = get_nr_mapped_entries(dev, &ref);
 
                 if (i >= mapped_ents)
                         break;
 
-                check_sync(dev, sg_dma_address(s), sg_dma_len(s), 0,
-                           direction, false);
+                check_sync(dev, &ref, false);
         }
 }
 EXPORT_SYMBOL(debug_dma_sync_sg_for_device);
diff --git a/lib/extable.c b/lib/extable.c
index 179c08745595..4cac81ec225e 100644
--- a/lib/extable.c
+++ b/lib/extable.c
@@ -39,7 +39,26 @@ void sort_extable(struct exception_table_entry *start,
         sort(start, finish - start, sizeof(struct exception_table_entry),
              cmp_ex, NULL);
 }
-#endif
+
+#ifdef CONFIG_MODULES
+/*
+ * If the exception table is sorted, any referring to the module init
+ * will be at the beginning or the end.
+ */
+void trim_init_extable(struct module *m)
+{
+        /*trim the beginning*/
+        while (m->num_exentries && within_module_init(m->extable[0].insn, m)) {
+                m->extable++;
+                m->num_exentries--;
+        }
+        /*trim the end*/
+        while (m->num_exentries &&
+                within_module_init(m->extable[m->num_exentries-1].insn, m))
+                m->num_exentries--;
+}
+#endif /* CONFIG_MODULES */
+#endif /* !ARCH_HAS_SORT_EXTABLE */
 
 #ifndef ARCH_HAS_SEARCH_EXTABLE
 /*
diff --git a/lib/gcd.c b/lib/gcd.c
new file mode 100644
index 000000000000..f879033d9822
--- /dev/null
+++ b/lib/gcd.c
@@ -0,0 +1,18 @@
+#include <linux/kernel.h>
+#include <linux/gcd.h>
+#include <linux/module.h>
+
+/* Greatest common divisor */
+unsigned long gcd(unsigned long a, unsigned long b)
+{
+        unsigned long r;
+
+        if (a < b)
+                swap(a, b);
+        while ((r = a % b) != 0) {
+                a = b;
+                b = r;
+        }
+        return b;
+}
+EXPORT_SYMBOL_GPL(gcd);
diff --git a/lib/genalloc.c b/lib/genalloc.c
index f6d276db2d58..eed2bdb865e7 100644
--- a/lib/genalloc.c
+++ b/lib/genalloc.c
@@ -85,7 +85,6 @@ void gen_pool_destroy(struct gen_pool *pool)
         int bit, end_bit;
 
 
-        write_lock(&pool->lock);
         list_for_each_safe(_chunk, _next_chunk, &pool->chunks) {
                 chunk = list_entry(_chunk, struct gen_pool_chunk, next_chunk);
                 list_del(&chunk->next_chunk);
diff --git a/lib/hexdump.c b/lib/hexdump.c
index f07c0db81d26..39af2560f765 100644
--- a/lib/hexdump.c
+++ b/lib/hexdump.c
@@ -65,7 +65,8 @@ void hex_dump_to_buffer(const void *buf, size_t len, int rowsize,
 
                 for (j = 0; j < ngroups; j++)
                         lx += scnprintf(linebuf + lx, linebuflen - lx,
-                                "%16.16llx ", (unsigned long long)*(ptr8 + j));
+                                "%s%16.16llx", j ? " " : "",
+                                (unsigned long long)*(ptr8 + j));
                 ascii_column = 17 * ngroups + 2;
                 break;
         }
@@ -76,7 +77,7 @@ void hex_dump_to_buffer(const void *buf, size_t len, int rowsize,
 
                 for (j = 0; j < ngroups; j++)
                         lx += scnprintf(linebuf + lx, linebuflen - lx,
-                                "%8.8x ", *(ptr4 + j));
+                                "%s%8.8x", j ? " " : "", *(ptr4 + j));
                 ascii_column = 9 * ngroups + 2;
                 break;
         }
@@ -87,19 +88,21 @@ void hex_dump_to_buffer(const void *buf, size_t len, int rowsize,
 
                 for (j = 0; j < ngroups; j++)
                         lx += scnprintf(linebuf + lx, linebuflen - lx,
-                                "%4.4x ", *(ptr2 + j));
+                                "%s%4.4x", j ? " " : "", *(ptr2 + j));
                 ascii_column = 5 * ngroups + 2;
                 break;
         }
 
         default:
-                for (j = 0; (j < rowsize) && (j < len) && (lx + 4) < linebuflen;
-                     j++) {
+                for (j = 0; (j < len) && (lx + 3) <= linebuflen; j++) {
                         ch = ptr[j];
                         linebuf[lx++] = hex_asc_hi(ch);
                         linebuf[lx++] = hex_asc_lo(ch);
                         linebuf[lx++] = ' ';
                 }
+                if (j)
+                        lx--;
+
                 ascii_column = 3 * rowsize + 2;
                 break;
         }
@@ -108,7 +111,7 @@ void hex_dump_to_buffer(const void *buf, size_t len, int rowsize,
 
         while (lx < (linebuflen - 1) && lx < (ascii_column - 1))
                 linebuf[lx++] = ' ';
-        for (j = 0; (j < rowsize) && (j < len) && (lx + 2) < linebuflen; j++)
+        for (j = 0; (j < len) && (lx + 2) < linebuflen; j++)
                 linebuf[lx++] = (isascii(ptr[j]) && isprint(ptr[j])) ? ptr[j]
                                 : '.';
 nil:
diff --git a/lib/kobject.c b/lib/kobject.c
index bacf6fe4f7a0..b512b746d2af 100644
--- a/lib/kobject.c
+++ b/lib/kobject.c
@@ -793,11 +793,16 @@ static struct kset *kset_create(const char *name,
                                 struct kobject *parent_kobj)
 {
         struct kset *kset;
+        int retval;
 
         kset = kzalloc(sizeof(*kset), GFP_KERNEL);
         if (!kset)
                 return NULL;
-        kobject_set_name(&kset->kobj, name);
+        retval = kobject_set_name(&kset->kobj, name);
+        if (retval) {
+                kfree(kset);
+                return NULL;
+        }
         kset->uevent_ops = uevent_ops;
         kset->kobj.parent = parent_kobj;
 
diff --git a/lib/radix-tree.c b/lib/radix-tree.c
index 4bb42a0344ec..23abbd93cae1 100644
--- a/lib/radix-tree.c
+++ b/lib/radix-tree.c
@@ -351,20 +351,12 @@ int radix_tree_insert(struct radix_tree_root *root,
 }
 EXPORT_SYMBOL(radix_tree_insert);
 
-/**
- *      radix_tree_lookup_slot    -    lookup a slot in a radix tree
- *      @root:          radix tree root
- *      @index:         index key
- *
- *      Returns:  the slot corresponding to the position @index in the
- *      radix tree @root. This is useful for update-if-exists operations.
- *
- *      This function can be called under rcu_read_lock iff the slot is not
- *      modified by radix_tree_replace_slot, otherwise it must be called
- *      exclusive from other writers. Any dereference of the slot must be done
- *      using radix_tree_deref_slot.
+/*
+ * is_slot == 1 : search for the slot.
+ * is_slot == 0 : search for the node.
  */
-void **radix_tree_lookup_slot(struct radix_tree_root *root, unsigned long index)
+static void *radix_tree_lookup_element(struct radix_tree_root *root,
+                                unsigned long index, int is_slot)
 {
         unsigned int height, shift;
         struct radix_tree_node *node, **slot;
@@ -376,7 +368,7 @@ void **radix_tree_lookup_slot(struct radix_tree_root *root, unsigned long index)
         if (!radix_tree_is_indirect_ptr(node)) {
                 if (index > 0)
                         return NULL;
-                return (void **)&root->rnode;
+                return is_slot ? (void *)&root->rnode : node;
         }
         node = radix_tree_indirect_to_ptr(node);
 
@@ -397,7 +389,25 @@ void **radix_tree_lookup_slot(struct radix_tree_root *root, unsigned long index)
                 height--;
         } while (height > 0);
 
-        return (void **)slot;
+        return is_slot ? (void *)slot:node;
+}
+
+/**
+ *      radix_tree_lookup_slot    -    lookup a slot in a radix tree
+ *      @root:          radix tree root
+ *      @index:         index key
+ *
+ *      Returns:  the slot corresponding to the position @index in the
+ *      radix tree @root. This is useful for update-if-exists operations.
+ *
+ *      This function can be called under rcu_read_lock iff the slot is not
+ *      modified by radix_tree_replace_slot, otherwise it must be called
+ *      exclusive from other writers. Any dereference of the slot must be done
+ *      using radix_tree_deref_slot.
+ */
+void **radix_tree_lookup_slot(struct radix_tree_root *root, unsigned long index)
+{
+        return (void **)radix_tree_lookup_element(root, index, 1);
 }
 EXPORT_SYMBOL(radix_tree_lookup_slot);
 
@@ -415,38 +425,7 @@ EXPORT_SYMBOL(radix_tree_lookup_slot);
  */
 void *radix_tree_lookup(struct radix_tree_root *root, unsigned long index)
 {
-        unsigned int height, shift;
-        struct radix_tree_node *node, **slot;
-
-        node = rcu_dereference(root->rnode);
-        if (node == NULL)
-                return NULL;
-
-        if (!radix_tree_is_indirect_ptr(node)) {
-                if (index > 0)
-                        return NULL;
-                return node;
-        }
-        node = radix_tree_indirect_to_ptr(node);
-
-        height = node->height;
-        if (index > radix_tree_maxindex(height))
-                return NULL;
-
-        shift = (height-1) * RADIX_TREE_MAP_SHIFT;
-
-        do {
-                slot = (struct radix_tree_node **)
-                        (node->slots + ((index>>shift) & RADIX_TREE_MAP_MASK));
-                node = rcu_dereference(*slot);
-                if (node == NULL)
-                        return NULL;
-
-                shift -= RADIX_TREE_MAP_SHIFT;
-                height--;
-        } while (height > 0);
-
-        return node;
+        return radix_tree_lookup_element(root, index, 0);
 }
 EXPORT_SYMBOL(radix_tree_lookup);
 
@@ -666,6 +645,43 @@ unsigned long radix_tree_next_hole(struct radix_tree_root *root,
 }
 EXPORT_SYMBOL(radix_tree_next_hole);
 
+/**
+ *      radix_tree_prev_hole    -    find the prev hole (not-present entry)
+ *      @root:          tree root
+ *      @index:         index key
+ *      @max_scan:      maximum range to search
+ *
+ *      Search backwards in the range [max(index-max_scan+1, 0), index]
+ *      for the first hole.
+ *
+ *      Returns: the index of the hole if found, otherwise returns an index
+ *      outside of the set specified (in which case 'index - return >= max_scan'
+ *      will be true). In rare cases of wrap-around, LONG_MAX 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 10, then subsequently a hole is created at index 5,
+ *      radix_tree_prev_hole covering both indexes may return 5 if called under
+ *      rcu_read_lock.
+ */
+unsigned long radix_tree_prev_hole(struct radix_tree_root *root,
+                                   unsigned long index, unsigned long max_scan)
+{
+        unsigned long i;
+
+        for (i = 0; i < max_scan; i++) {
+                if (!radix_tree_lookup(root, index))
+                        break;
+                index--;
+                if (index == LONG_MAX)
+                        break;
+        }
+
+        return index;
+}
+EXPORT_SYMBOL(radix_tree_prev_hole);
+
 static unsigned int
 __lookup(struct radix_tree_node *slot, void ***results, unsigned long index,
         unsigned int max_items, unsigned long *next_index)
diff --git a/lib/rbtree.c b/lib/rbtree.c
index f653659e0bc1..e2aa3be29858 100644
--- a/lib/rbtree.c
+++ b/lib/rbtree.c
@@ -231,34 +231,34 @@ void rb_erase(struct rb_node *node, struct rb_root *root)
                 node = node->rb_right;
                 while ((left = node->rb_left) != NULL)
                         node = left;
+
+                if (rb_parent(old)) {
+                        if (rb_parent(old)->rb_left == old)
+                                rb_parent(old)->rb_left = node;
+                        else
+                                rb_parent(old)->rb_right = node;
+                } else
+                        root->rb_node = node;
+
                 child = node->rb_right;
                 parent = rb_parent(node);
                 color = rb_color(node);
 
-                if (child)
-                        rb_set_parent(child, parent);
                 if (parent == old) {
-                        parent->rb_right = child;
                         parent = node;
-                } else
+                } else {
+                        if (child)
+                                rb_set_parent(child, parent);
                         parent->rb_left = child;
 
+                        node->rb_right = old->rb_right;
+                        rb_set_parent(old->rb_right, node);
+                }
+
                 node->rb_parent_color = old->rb_parent_color;
-                node->rb_right = old->rb_right;
                 node->rb_left = old->rb_left;
-
-                if (rb_parent(old))
-                {
-                        if (rb_parent(old)->rb_left == old)
-                                rb_parent(old)->rb_left = node;
-                        else
-                                rb_parent(old)->rb_right = node;
-                } else
-                        root->rb_node = node;
-
                 rb_set_parent(old->rb_left, node);
-                if (old->rb_right)
-                        rb_set_parent(old->rb_right, node);
+
                 goto color;
         }