20 files changed, 1255 insertions, 243 deletions

diff --git a/lib/Kconfig b/lib/Kconfig
index 8ade0a7a91e0..bb1326d3839c 100644
--- a/lib/Kconfig
+++ b/lib/Kconfig
@@ -10,6 +10,9 @@ menu "Library routines"
 config BITREVERSE
         tristate
 
+config RATIONAL
+        boolean
+
 config GENERIC_FIND_FIRST_BIT
         bool
 
@@ -191,4 +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 c6e854f215fa..23067ab1a73c 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
@@ -336,6 +336,38 @@ config SLUB_STATS
           out which slabs are relevant to a particular load.
           Try running: slabinfo -DA
 
+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
+        help
+          Say Y here if you want to enable the memory leak
+          detector. The memory allocation/freeing is traced in a way
+          similar to the Boehm's conservative garbage collector, the
+          difference being that the orphan objects are not freed but
+          only shown in /sys/kernel/debug/kmemleak. Enabling this
+          feature will introduce an overhead to memory
+          allocations. See Documentation/kmemleak.txt for more
+          details.
+
+          In order to access the kmemleak file, debugfs needs to be
+          mounted (usually at /sys/kernel/debug).
+
+config DEBUG_KMEMLEAK_TEST
+        tristate "Simple test for the kernel memory leak detector"
+        depends on DEBUG_KMEMLEAK
+        help
+          Say Y or M here to build a test for the kernel memory leak
+          detector. This option enables a module that explicitly leaks
+          memory.
+
+          If unsure, say N.
+
 config DEBUG_PREEMPT
         bool "Debug preemptible kernel"
         depends on DEBUG_KERNEL && PREEMPT && (TRACE_IRQFLAGS_SUPPORT || PPC64)
@@ -440,7 +472,7 @@ 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
+        select FRAME_POINTER if !MIPS && !PPC && !ARM_UNWIND && !S390
         select KALLSYMS
         select KALLSYMS_ALL
 
@@ -620,7 +652,7 @@ config ARCH_WANT_FRAME_POINTERS
 config FRAME_POINTER
         bool "Compile the kernel with frame pointers"
         depends on DEBUG_KERNEL && \
-                (CRIS || M68K || M68KNOMMU || FRV || UML || S390 || \
+                (CRIS || M68K || M68KNOMMU || FRV || UML || \
                  AVR32 || SUPERH || BLACKFIN || MN10300) || \
                 ARCH_WANT_FRAME_POINTERS
         default y if (DEBUG_INFO && UML) || ARCH_WANT_FRAME_POINTERS
@@ -809,13 +841,13 @@ config FAULT_INJECTION_STACKTRACE_FILTER
         depends on FAULT_INJECTION_DEBUG_FS && STACKTRACE_SUPPORT
         depends on !X86_64
         select STACKTRACE
-        select FRAME_POINTER if !PPC
+        select FRAME_POINTER if !PPC && !S390
         help
           Provide stacktrace filter for fault-injection capabilities
 
 config LATENCYTOP
         bool "Latency measuring infrastructure"
-        select FRAME_POINTER if !MIPS && !PPC
+        select FRAME_POINTER if !MIPS && !PPC && !S390
         select KALLSYMS
         select KALLSYMS_ALL
         select STACKTRACE
@@ -891,7 +923,6 @@ config DYNAMIC_DEBUG
         default n
         depends on PRINTK
         depends on DEBUG_FS
-        select PRINTK_DEBUG
         help
 
           Compiles debug level messages into the kernel, which would not
@@ -965,3 +996,5 @@ 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 d6edd6753f40..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 ($(CONFIG_DEBUG_KOBJECT),y)
 CFLAGS_kobject.o += -DDEBUG
@@ -38,7 +38,7 @@ lib-$(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-$(CONFIG_GENERIC_FIND_LAST_BIT) += find_last_bit.o
 obj-$(CONFIG_GENERIC_HWEIGHT) += hweight.o
 obj-$(CONFIG_LOCK_KERNEL) += kernel_lock.o
 obj-$(CONFIG_DEBUG_PREEMPT) += smp_processor_id.o
@@ -50,6 +50,7 @@ ifneq ($(CONFIG_HAVE_DEC_LOCK),y)
 endif
 
 obj-$(CONFIG_BITREVERSE) += bitrev.o
+obj-$(CONFIG_RATIONAL)  += rational.o
 obj-$(CONFIG_CRC_CCITT) += crc-ccitt.o
 obj-$(CONFIG_CRC16)     += crc16.o
 obj-$(CONFIG_CRC_T10DIF)+= crc-t10dif.o
@@ -92,6 +93,10 @@ obj-$(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..12e5a1c91cda
--- /dev/null
+++ b/lib/checksum.c
@@ -0,0 +1,193 @@
+/*
+ *
+ * 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) {
+                result = *buff;
+                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 long *) 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)
+                result += (*buff << 8);
+        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/cpumask.c b/lib/cpumask.c
index 1f71b97de0f9..7bb4142a502f 100644
--- a/lib/cpumask.c
+++ b/lib/cpumask.c
@@ -92,15 +92,8 @@ int cpumask_any_but(const struct cpumask *mask, unsigned int cpu)
  */
 bool alloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node)
 {
-        if (likely(slab_is_available()))
-                *mask = kmalloc_node(cpumask_size(), flags, node);
-        else {
-#ifdef CONFIG_DEBUG_PER_CPU_MAPS
-                printk(KERN_ERR
-                        "=> alloc_cpumask_var: kmalloc not available!\n");
-#endif
-                *mask = NULL;
-        }
+        *mask = kmalloc_node(cpumask_size(), flags, node);
+
 #ifdef CONFIG_DEBUG_PER_CPU_MAPS
         if (!*mask) {
                 printk(KERN_ERR "=> alloc_cpumask_var: failed!\n");
@@ -119,6 +112,12 @@ bool alloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node)
 }
 EXPORT_SYMBOL(alloc_cpumask_var_node);
 
+bool zalloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node)
+{
+        return alloc_cpumask_var_node(mask, flags | __GFP_ZERO, node);
+}
+EXPORT_SYMBOL(zalloc_cpumask_var_node);
+
 /**
  * alloc_cpumask_var - allocate a struct cpumask
  * @mask: pointer to cpumask_var_t where the cpumask is returned
@@ -135,6 +134,12 @@ bool alloc_cpumask_var(cpumask_var_t *mask, gfp_t flags)
 }
 EXPORT_SYMBOL(alloc_cpumask_var);
 
+bool zalloc_cpumask_var(cpumask_var_t *mask, gfp_t flags)
+{
+        return alloc_cpumask_var(mask, flags | __GFP_ZERO);
+}
+EXPORT_SYMBOL(zalloc_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
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 d3da7edc034f..3b93129a968c 100644
--- a/lib/dma-debug.c
+++ b/lib/dma-debug.c
@@ -23,9 +23,11 @@
 #include <linux/dma-debug.h>
 #include <linux/spinlock.h>
 #include <linux/debugfs.h>
+#include <linux/uaccess.h>
 #include <linux/device.h>
 #include <linux/types.h>
 #include <linux/sched.h>
+#include <linux/ctype.h>
 #include <linux/list.h>
 #include <linux/slab.h>
 
@@ -85,6 +87,7 @@ static u32 show_num_errors = 1;
 
 static u32 num_free_entries;
 static u32 min_free_entries;
+static u32 nr_total_entries;
 
 /* number of preallocated entries requested by kernel cmdline */
 static u32 req_entries;
@@ -97,6 +100,16 @@ static struct dentry *show_all_errors_dent  __read_mostly;
 static struct dentry *show_num_errors_dent  __read_mostly;
 static struct dentry *num_free_entries_dent __read_mostly;
 static struct dentry *min_free_entries_dent __read_mostly;
+static struct dentry *filter_dent           __read_mostly;
+
+/* per-driver filter related state */
+
+#define NAME_MAX_LEN    64
+
+static char                  current_driver_name[NAME_MAX_LEN] __read_mostly;
+static struct device_driver *current_driver                    __read_mostly;
+
+static DEFINE_RWLOCK(driver_name_lock);
 
 static const char *type2name[4] = { "single", "page",
                                     "scather-gather", "coherent" };
@@ -104,6 +117,11 @@ static const char *type2name[4] = { "single", "page",
 static const char *dir2name[4] = { "DMA_BIDIRECTIONAL", "DMA_TO_DEVICE",
                                    "DMA_FROM_DEVICE", "DMA_NONE" };
 
+/* little merge helper - remove it after the merge window */
+#ifndef BUS_NOTIFY_UNBOUND_DRIVER
+#define BUS_NOTIFY_UNBOUND_DRIVER 0x0005
+#endif
+
 /*
  * The access to some variables in this macro is racy. We can't use atomic_t
  * here because all these variables are exported to debugfs. Some of them even
@@ -121,15 +139,54 @@ static inline void dump_entry_trace(struct dma_debug_entry *entry)
 {
 #ifdef CONFIG_STACKTRACE
         if (entry) {
-                printk(KERN_WARNING "Mapped at:\n");
+                pr_warning("Mapped at:\n");
                 print_stack_trace(&entry->stacktrace, 0);
         }
 #endif
 }
 
+static bool driver_filter(struct device *dev)
+{
+        struct device_driver *drv;
+        unsigned long flags;
+        bool ret;
+
+        /* driver filter off */
+        if (likely(!current_driver_name[0]))
+                return true;
+
+        /* driver filter on and initialized */
+        if (current_driver && dev->driver == current_driver)
+                return true;
+
+        if (current_driver || !current_driver_name[0])
+                return false;
+
+        /* driver filter on but not yet initialized */
+        drv = get_driver(dev->driver);
+        if (!drv)
+                return false;
+
+        /* lock to protect against change of current_driver_name */
+        read_lock_irqsave(&driver_name_lock, flags);
+
+        ret = false;
+        if (drv->name &&
+            strncmp(current_driver_name, drv->name, NAME_MAX_LEN - 1) == 0) {
+                current_driver = drv;
+                ret = true;
+        }
+
+        read_unlock_irqrestore(&driver_name_lock, flags);
+        put_driver(drv);
+
+        return ret;
+}
+
 #define err_printk(dev, entry, format, arg...) do {             \
                 error_count += 1;                               \
-                if (show_all_errors || show_num_errors > 0) {   \
+                if (driver_filter(dev) &&                       \
+                    (show_all_errors || show_num_errors > 0)) { \
                         WARN(1, "%s %s: " format,               \
                              dev_driver_string(dev),            \
                              dev_name(dev) , ## arg);           \
@@ -185,15 +242,51 @@ static void put_hash_bucket(struct hash_bucket *bucket,
 static struct dma_debug_entry *hash_bucket_find(struct hash_bucket *bucket,
                                                 struct dma_debug_entry *ref)
 {
-        struct dma_debug_entry *entry;
+        struct dma_debug_entry *entry, *ret = NULL;
+        int matches = 0, match_lvl, last_lvl = 0;
 
         list_for_each_entry(entry, &bucket->list, list) {
-                if ((entry->dev_addr == ref->dev_addr) &&
-                    (entry->dev == ref->dev))
+                if ((entry->dev_addr != ref->dev_addr) ||
+                    (entry->dev != ref->dev))
+                        continue;
+
+                /*
+                 * Some drivers map the same physical address multiple
+                 * 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
+                 * best-fit algorithm here which returns the entry from
+                 * the hash which fits best to the reference value
+                 * instead of the first-fit.
+                 */
+                matches += 1;
+                match_lvl = 0;
+                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 == 4) {
+                        /* perfect-fit - return the result */
                         return entry;
+                } else if (match_lvl > last_lvl) {
+                        /*
+                         * We found an entry that fits better then the
+                         * previous one
+                         */
+                        last_lvl = match_lvl;
+                        ret      = entry;
+                }
         }
 
-        return NULL;
+        /*
+         * If we have multiple matches but no perfect-fit, just return
+         * NULL.
+         */
+        ret = (matches == 1) ? ret : NULL;
+
+        return ret;
 }
 
 /*
@@ -257,6 +350,21 @@ static void add_dma_entry(struct dma_debug_entry *entry)
         put_hash_bucket(bucket, &flags);
 }
 
+static struct dma_debug_entry *__dma_entry_alloc(void)
+{
+        struct dma_debug_entry *entry;
+
+        entry = list_entry(free_entries.next, struct dma_debug_entry, list);
+        list_del(&entry->list);
+        memset(entry, 0, sizeof(*entry));
+
+        num_free_entries -= 1;
+        if (num_free_entries < min_free_entries)
+                min_free_entries = num_free_entries;
+
+        return entry;
+}
+
 /* struct dma_entry allocator
  *
  * The next two functions implement the allocator for
@@ -270,15 +378,12 @@ static struct dma_debug_entry *dma_entry_alloc(void)
         spin_lock_irqsave(&free_entries_lock, flags);
 
         if (list_empty(&free_entries)) {
-                printk(KERN_ERR "DMA-API: debugging out of memory "
-                                "- disabling\n");
+                pr_err("DMA-API: debugging out of memory - disabling\n");
                 global_disable = true;
                 goto out;
         }
 
-        entry = list_entry(free_entries.next, struct dma_debug_entry, list);
-        list_del(&entry->list);
-        memset(entry, 0, sizeof(*entry));
+        entry = __dma_entry_alloc();
 
 #ifdef CONFIG_STACKTRACE
         entry->stacktrace.max_entries = DMA_DEBUG_STACKTRACE_ENTRIES;
@@ -286,9 +391,6 @@ static struct dma_debug_entry *dma_entry_alloc(void)
         entry->stacktrace.skip = 2;
         save_stack_trace(&entry->stacktrace);
 #endif
-        num_free_entries -= 1;
-        if (num_free_entries < min_free_entries)
-                min_free_entries = num_free_entries;
 
 out:
         spin_unlock_irqrestore(&free_entries_lock, flags);
@@ -310,6 +412,53 @@ static void dma_entry_free(struct dma_debug_entry *entry)
         spin_unlock_irqrestore(&free_entries_lock, flags);
 }
 
+int dma_debug_resize_entries(u32 num_entries)
+{
+        int i, delta, ret = 0;
+        unsigned long flags;
+        struct dma_debug_entry *entry;
+        LIST_HEAD(tmp);
+
+        spin_lock_irqsave(&free_entries_lock, flags);
+
+        if (nr_total_entries < num_entries) {
+                delta = num_entries - nr_total_entries;
+
+                spin_unlock_irqrestore(&free_entries_lock, flags);
+
+                for (i = 0; i < delta; i++) {
+                        entry = kzalloc(sizeof(*entry), GFP_KERNEL);
+                        if (!entry)
+                                break;
+
+                        list_add_tail(&entry->list, &tmp);
+                }
+
+                spin_lock_irqsave(&free_entries_lock, flags);
+
+                list_splice(&tmp, &free_entries);
+                nr_total_entries += i;
+                num_free_entries += i;
+        } else {
+                delta = nr_total_entries - num_entries;
+
+                for (i = 0; i < delta && !list_empty(&free_entries); i++) {
+                        entry = __dma_entry_alloc();
+                        kfree(entry);
+                }
+
+                nr_total_entries -= i;
+        }
+
+        if (nr_total_entries != num_entries)
+                ret = 1;
+
+        spin_unlock_irqrestore(&free_entries_lock, flags);
+
+        return ret;
+}
+EXPORT_SYMBOL(dma_debug_resize_entries);
+
 /*
  * DMA-API debugging init code
  *
@@ -334,8 +483,7 @@ static int prealloc_memory(u32 num_entries)
         num_free_entries = num_entries;
         min_free_entries = num_entries;
 
-        printk(KERN_INFO "DMA-API: preallocated %d debug entries\n",
-                        num_entries);
+        pr_info("DMA-API: preallocated %d debug entries\n", num_entries);
 
         return 0;
 
@@ -349,11 +497,102 @@ out_err:
         return -ENOMEM;
 }
 
+static ssize_t filter_read(struct file *file, char __user *user_buf,
+                           size_t count, loff_t *ppos)
+{
+        char buf[NAME_MAX_LEN + 1];
+        unsigned long flags;
+        int len;
+
+        if (!current_driver_name[0])
+                return 0;
+
+        /*
+         * We can't copy to userspace directly because current_driver_name can
+         * only be read under the driver_name_lock with irqs disabled. So
+         * create a temporary copy first.
+         */
+        read_lock_irqsave(&driver_name_lock, flags);
+        len = scnprintf(buf, NAME_MAX_LEN + 1, "%s\n", current_driver_name);
+        read_unlock_irqrestore(&driver_name_lock, flags);
+
+        return simple_read_from_buffer(user_buf, count, ppos, buf, len);
+}
+
+static ssize_t filter_write(struct file *file, const char __user *userbuf,
+                            size_t count, loff_t *ppos)
+{
+        char buf[NAME_MAX_LEN];
+        unsigned long flags;
+        size_t len;
+        int i;
+
+        /*
+         * We can't copy from userspace directly. Access to
+         * current_driver_name is protected with a write_lock with irqs
+         * disabled. Since copy_from_user can fault and may sleep we
+         * need to copy to temporary buffer first
+         */
+        len = min(count, (size_t)(NAME_MAX_LEN - 1));
+        if (copy_from_user(buf, userbuf, len))
+                return -EFAULT;
+
+        buf[len] = 0;
+
+        write_lock_irqsave(&driver_name_lock, flags);
+
+        /*
+         * Now handle the string we got from userspace very carefully.
+         * The rules are:
+         *         - only use the first token we got
+         *         - token delimiter is everything looking like a space
+         *           character (' ', '\n', '\t' ...)
+         *
+         */
+        if (!isalnum(buf[0])) {
+                /*
+                 * If the first character userspace gave us is not
+                 * alphanumerical then assume the filter should be
+                 * switched off.
+                 */
+                if (current_driver_name[0])
+                        pr_info("DMA-API: switching off dma-debug driver filter\n");
+                current_driver_name[0] = 0;
+                current_driver = NULL;
+                goto out_unlock;
+        }
+
+        /*
+         * Now parse out the first token and use it as the name for the
+         * driver to filter for.
+         */
+        for (i = 0; i < NAME_MAX_LEN; ++i) {
+                current_driver_name[i] = buf[i];
+                if (isspace(buf[i]) || buf[i] == ' ' || buf[i] == 0)
+                        break;
+        }
+        current_driver_name[i] = 0;
+        current_driver = NULL;
+
+        pr_info("DMA-API: enable driver filter for driver [%s]\n",
+                current_driver_name);
+
+out_unlock:
+        write_unlock_irqrestore(&driver_name_lock, flags);
+
+        return count;
+}
+
+const struct file_operations filter_fops = {
+        .read  = filter_read,
+        .write = filter_write,
+};
+
 static int dma_debug_fs_init(void)
 {
         dma_debug_dent = debugfs_create_dir("dma-api", NULL);
         if (!dma_debug_dent) {
-                printk(KERN_ERR "DMA-API: can not create debugfs directory\n");
+                pr_err("DMA-API: can not create debugfs directory\n");
                 return -ENOMEM;
         }
 
@@ -392,6 +631,11 @@ static int dma_debug_fs_init(void)
         if (!min_free_entries_dent)
                 goto out_err;
 
+        filter_dent = debugfs_create_file("driver_filter", 0644,
+                                          dma_debug_dent, NULL, &filter_fops);
+        if (!filter_dent)
+                goto out_err;
+
         return 0;
 
 out_err:
@@ -406,15 +650,19 @@ static int device_dma_allocations(struct device *dev)
         unsigned long flags;
         int count = 0, i;
 
+        local_irq_save(flags);
+
         for (i = 0; i < HASH_SIZE; ++i) {
-                spin_lock_irqsave(&dma_entry_hash[i].lock, flags);
+                spin_lock(&dma_entry_hash[i].lock);
                 list_for_each_entry(entry, &dma_entry_hash[i].list, list) {
                         if (entry->dev == dev)
                                 count += 1;
                 }
-                spin_unlock_irqrestore(&dma_entry_hash[i].lock, flags);
+                spin_unlock(&dma_entry_hash[i].lock);
         }
 
+        local_irq_restore(flags);
+
         return count;
 }
 
@@ -426,7 +674,7 @@ static int dma_debug_device_change(struct notifier_block *nb,
 
 
         switch (action) {
-        case BUS_NOTIFY_UNBIND_DRIVER:
+        case BUS_NOTIFY_UNBOUND_DRIVER:
                 count = device_dma_allocations(dev);
                 if (count == 0)
                         break;
@@ -447,7 +695,7 @@ void dma_debug_add_bus(struct bus_type *bus)
 
         nb = kzalloc(sizeof(struct notifier_block), GFP_KERNEL);
         if (nb == NULL) {
-                printk(KERN_ERR "dma_debug_add_bus: out of memory\n");
+                pr_err("dma_debug_add_bus: out of memory\n");
                 return;
         }
 
@@ -472,8 +720,7 @@ void dma_debug_init(u32 num_entries)
         }
 
         if (dma_debug_fs_init() != 0) {
-                printk(KERN_ERR "DMA-API: error creating debugfs entries "
-                                "- disabling\n");
+                pr_err("DMA-API: error creating debugfs entries - disabling\n");
                 global_disable = true;
 
                 return;
@@ -483,14 +730,15 @@ void dma_debug_init(u32 num_entries)
                 num_entries = req_entries;
 
         if (prealloc_memory(num_entries) != 0) {
-                printk(KERN_ERR "DMA-API: debugging out of memory error "
-                                "- disabled\n");
+                pr_err("DMA-API: debugging out of memory error - disabled\n");
                 global_disable = true;
 
                 return;
         }
 
-        printk(KERN_INFO "DMA-API: debugging enabled by kernel config\n");
+        nr_total_entries = num_free_entries;
+
+        pr_info("DMA-API: debugging enabled by kernel config\n");
 }
 
 static __init int dma_debug_cmdline(char *str)
@@ -499,8 +747,7 @@ static __init int dma_debug_cmdline(char *str)
                 return -EINVAL;
 
         if (strncmp(str, "off", 3) == 0) {
-                printk(KERN_INFO "DMA-API: debugging disabled on kernel "
-                                 "command line\n");
+                pr_info("DMA-API: debugging disabled on kernel command line\n");
                 global_disable = true;
         }
 
@@ -627,72 +874,68 @@ static void check_for_illegal_area(struct device *dev, void *addr, u64 size)
                                 "[addr=%p] [size=%llu]\n", addr, size);
 }
 
-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);
@@ -774,15 +1017,15 @@ void debug_dma_map_sg(struct device *dev, struct scatterlist *sg,
                 entry->type           = dma_debug_sg;
                 entry->dev            = dev;
                 entry->paddr          = sg_phys(s);
-                entry->size           = s->length;
-                entry->dev_addr       = s->dma_address;
+                entry->size           = sg_dma_len(s);
+                entry->dev_addr       = sg_dma_address(s);
                 entry->direction      = direction;
                 entry->sg_call_ents   = nents;
                 entry->sg_mapped_ents = mapped_ents;
 
                 if (!PageHighMem(sg_page(s))) {
                         check_for_stack(dev, sg_virt(s));
-                        check_for_illegal_area(dev, sg_virt(s), s->length);
+                        check_for_illegal_area(dev, sg_virt(s), sg_dma_len(s));
                 }
 
                 add_dma_entry(entry);
@@ -790,13 +1033,30 @@ 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 dma_debug_entry *ref)
+{
+        struct dma_debug_entry *entry;
+        struct hash_bucket *bucket;
+        unsigned long flags;
+        int mapped_ents;
+
+        bucket       = get_hash_bucket(ref, &flags);
+        entry        = hash_bucket_find(bucket, ref);
+        mapped_ents  = 0;
+
+        if (entry)
+                mapped_ents = entry->sg_mapped_ents;
+        put_hash_bucket(bucket, &flags);
+
+        return mapped_ents;
+}
+
 void debug_dma_unmap_sg(struct device *dev, struct scatterlist *sglist,
                         int nelems, int dir)
 {
-        struct dma_debug_entry *entry;
         struct scatterlist *s;
         int mapped_ents = 0, i;
-        unsigned long flags;
 
         if (unlikely(global_disable))
                 return;
@@ -807,24 +1067,17 @@ void debug_dma_unmap_sg(struct device *dev, struct scatterlist *sglist,
                         .type           = dma_debug_sg,
                         .dev            = dev,
                         .paddr          = sg_phys(s),
-                        .dev_addr       = s->dma_address,
-                        .size           = s->length,
+                        .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 (mapped_ents == 0) {
-                        struct hash_bucket *bucket;
-                        ref.sg_call_ents = nelems;
-                        bucket = get_hash_bucket(&ref, &flags);
-                        entry = hash_bucket_find(bucket, &ref);
-                        if (entry)
-                                mapped_ents = entry->sg_mapped_ents;
-                        put_hash_bucket(bucket, &flags);
-                }
+                if (!i)
+                        mapped_ents = get_nr_mapped_entries(dev, &ref);
 
                 check_unmap(&ref);
         }
@@ -879,10 +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);
 
@@ -890,10 +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);
 
@@ -902,10 +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);
 
@@ -914,10 +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);
 
@@ -925,14 +1214,30 @@ void debug_dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg,
                                int nelems, int direction)
 {
         struct scatterlist *s;
-        int i;
+        int mapped_ents = 0, i;
 
         if (unlikely(global_disable))
                 return;
 
         for_each_sg(sg, s, nelems, i) {
-                check_sync(dev, s->dma_address, s->dma_length, 0,
-                                direction, true);
+
+                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, &ref);
+
+                if (i >= mapped_ents)
+                        break;
+
+                check_sync(dev, &ref, true);
         }
 }
 EXPORT_SYMBOL(debug_dma_sync_sg_for_cpu);
@@ -941,15 +1246,48 @@ void debug_dma_sync_sg_for_device(struct device *dev, struct scatterlist *sg,
                                   int nelems, int direction)
 {
         struct scatterlist *s;
-        int i;
+        int mapped_ents = 0, i;
 
         if (unlikely(global_disable))
                 return;
 
         for_each_sg(sg, s, nelems, i) {
-                check_sync(dev, s->dma_address, s->dma_length, 0,
-                                direction, false);
+
+                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, &ref);
+
+                if (i >= mapped_ents)
+                        break;
+
+                check_sync(dev, &ref, false);
         }
 }
 EXPORT_SYMBOL(debug_dma_sync_sg_for_device);
 
+static int __init dma_debug_driver_setup(char *str)
+{
+        int i;
+
+        for (i = 0; i < NAME_MAX_LEN - 1; ++i, ++str) {
+                current_driver_name[i] = *str;
+                if (*str == 0)
+                        break;
+        }
+
+        if (current_driver_name[0])
+                pr_info("DMA-API: enable driver filter for driver [%s]\n",
+                        current_driver_name);
+
+
+        return 1;
+}
+__setup("dma_debug_driver=", dma_debug_driver_setup);
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/rational.c b/lib/rational.c
new file mode 100644
index 000000000000..b3c099b5478e
--- /dev/null
+++ b/lib/rational.c
@@ -0,0 +1,62 @@
+/*
+ * rational fractions
+ *
+ * Copyright (C) 2009 emlix GmbH, Oskar Schirmer <os@emlix.com>
+ *
+ * helper functions when coping with rational numbers
+ */
+
+#include <linux/rational.h>
+
+/*
+ * calculate best rational approximation for a given fraction
+ * taking into account restricted register size, e.g. to find
+ * appropriate values for a pll with 5 bit denominator and
+ * 8 bit numerator register fields, trying to set up with a
+ * frequency ratio of 3.1415, one would say:
+ *
+ * rational_best_approximation(31415, 10000,
+ *              (1 << 8) - 1, (1 << 5) - 1, &n, &d);
+ *
+ * you may look at given_numerator as a fixed point number,
+ * with the fractional part size described in given_denominator.
+ *
+ * for theoretical background, see:
+ * http://en.wikipedia.org/wiki/Continued_fraction
+ */
+
+void rational_best_approximation(
+        unsigned long given_numerator, unsigned long given_denominator,
+        unsigned long max_numerator, unsigned long max_denominator,
+        unsigned long *best_numerator, unsigned long *best_denominator)
+{
+        unsigned long n, d, n0, d0, n1, d1;
+        n = given_numerator;
+        d = given_denominator;
+        n0 = d1 = 0;
+        n1 = d0 = 1;
+        for (;;) {
+                unsigned long t, a;
+                if ((n1 > max_numerator) || (d1 > max_denominator)) {
+                        n1 = n0;
+                        d1 = d0;
+                        break;
+                }
+                if (d == 0)
+                        break;
+                t = d;
+                a = n / d;
+                d = n % d;
+                n = t;
+                t = n0 + a * n1;
+                n0 = n1;
+                n1 = t;
+                t = d0 + a * d1;
+                d0 = d1;
+                d1 = t;
+        }
+        *best_numerator = n1;
+        *best_denominator = d1;
+}
+
+EXPORT_SYMBOL(rational_best_approximation);
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;
         }
 
diff --git a/lib/scatterlist.c b/lib/scatterlist.c
index b7b449dafbe5..a295e404e908 100644
--- a/lib/scatterlist.c
+++ b/lib/scatterlist.c
@@ -347,9 +347,12 @@ bool sg_miter_next(struct sg_mapping_iter *miter)
         sg_miter_stop(miter);
 
         /* get to the next sg if necessary.  __offset is adjusted by stop */
-        if (miter->__offset == miter->__sg->length && --miter->__nents) {
-                miter->__sg = sg_next(miter->__sg);
-                miter->__offset = 0;
+        while (miter->__offset == miter->__sg->length) {
+                if (--miter->__nents) {
+                        miter->__sg = sg_next(miter->__sg);
+                        miter->__offset = 0;
+                } else
+                        return false;
         }
 
         /* map the next page */
diff --git a/lib/swiotlb.c b/lib/swiotlb.c
index 2b0b5a7d2ced..bffe6d7ef9d9 100644
--- a/lib/swiotlb.c
+++ b/lib/swiotlb.c
@@ -60,8 +60,8 @@ enum dma_sync_target {
 int swiotlb_force;
 
 /*
- * Used to do a quick range check in swiotlb_unmap_single and
- * swiotlb_sync_single_*, to see if the memory was in fact allocated by this
+ * Used to do a quick range check in unmap_single and
+ * sync_single_*, to see if the memory was in fact allocated by this
  * API.
  */
 static char *io_tlb_start, *io_tlb_end;
@@ -129,7 +129,7 @@ dma_addr_t __weak swiotlb_phys_to_bus(struct device *hwdev, phys_addr_t paddr)
         return paddr;
 }
 
-phys_addr_t __weak swiotlb_bus_to_phys(dma_addr_t baddr)
+phys_addr_t __weak swiotlb_bus_to_phys(struct device *hwdev, dma_addr_t baddr)
 {
         return baddr;
 }
@@ -140,9 +140,15 @@ static dma_addr_t swiotlb_virt_to_bus(struct device *hwdev,
         return swiotlb_phys_to_bus(hwdev, virt_to_phys(address));
 }
 
-static void *swiotlb_bus_to_virt(dma_addr_t address)
+void * __weak swiotlb_bus_to_virt(struct device *hwdev, dma_addr_t address)
 {
-        return phys_to_virt(swiotlb_bus_to_phys(address));
+        return phys_to_virt(swiotlb_bus_to_phys(hwdev, address));
+}
+
+int __weak swiotlb_arch_address_needs_mapping(struct device *hwdev,
+                                               dma_addr_t addr, size_t size)
+{
+        return !is_buffer_dma_capable(dma_get_mask(hwdev), addr, size);
 }
 
 int __weak swiotlb_arch_range_needs_mapping(phys_addr_t paddr, size_t size)
@@ -309,10 +315,10 @@ cleanup1:
         return -ENOMEM;
 }
 
-static int
+static inline int
 address_needs_mapping(struct device *hwdev, dma_addr_t addr, size_t size)
 {
-        return !is_buffer_dma_capable(dma_get_mask(hwdev), addr, size);
+        return swiotlb_arch_address_needs_mapping(hwdev, addr, size);
 }
 
 static inline int range_needs_mapping(phys_addr_t paddr, size_t size)
@@ -341,7 +347,7 @@ static void swiotlb_bounce(phys_addr_t phys, char *dma_addr, size_t size,
                 unsigned long flags;
 
                 while (size) {
-                        sz = min(PAGE_SIZE - offset, size);
+                        sz = min_t(size_t, PAGE_SIZE - offset, size);
 
                         local_irq_save(flags);
                         buffer = kmap_atomic(pfn_to_page(pfn),
@@ -476,7 +482,7 @@ found:
  * dma_addr is the kernel virtual address of the bounce buffer to unmap.
  */
 static void
-unmap_single(struct device *hwdev, char *dma_addr, size_t size, int dir)
+do_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;
@@ -560,7 +566,6 @@ swiotlb_alloc_coherent(struct device *hwdev, size_t size,
                                    size)) {
                 /*
                  * The allocated memory isn't reachable by the device.
-                 * Fall back on swiotlb_map_single().
                  */
                 free_pages((unsigned long) ret, order);
                 ret = NULL;
@@ -568,9 +573,8 @@ swiotlb_alloc_coherent(struct device *hwdev, size_t size,
         if (!ret) {
                 /*
                  * We are either out of memory or the device can't DMA
-                 * to GFP_DMA memory; fall back on
-                 * swiotlb_map_single(), which will grab memory from
-                 * the lowest available address range.
+                 * to GFP_DMA memory; fall back on map_single(), which
+                 * will grab memory from the lowest available address range.
                  */
                 ret = map_single(hwdev, 0, size, DMA_FROM_DEVICE);
                 if (!ret)
@@ -587,7 +591,7 @@ swiotlb_alloc_coherent(struct device *hwdev, size_t size,
                        (unsigned long long)dev_addr);
 
                 /* DMA_TO_DEVICE to avoid memcpy in unmap_single */
-                unmap_single(hwdev, ret, size, DMA_TO_DEVICE);
+                do_unmap_single(hwdev, ret, size, DMA_TO_DEVICE);
                 return NULL;
         }
         *dma_handle = dev_addr;
@@ -604,7 +608,7 @@ swiotlb_free_coherent(struct device *hwdev, size_t size, void *vaddr,
                 free_pages((unsigned long) vaddr, get_order(size));
         else
                 /* DMA_TO_DEVICE to avoid memcpy in unmap_single */
-                unmap_single(hwdev, vaddr, size, DMA_TO_DEVICE);
+                do_unmap_single(hwdev, vaddr, size, DMA_TO_DEVICE);
 }
 EXPORT_SYMBOL(swiotlb_free_coherent);
 
@@ -634,7 +638,7 @@ swiotlb_full(struct device *dev, size_t size, int dir, int do_panic)
  * physical address to use is returned.
  *
  * Once the device is given the dma address, the device owns this memory until
- * either swiotlb_unmap_single or swiotlb_dma_sync_single is performed.
+ * either swiotlb_unmap_page or swiotlb_dma_sync_single is performed.
  */
 dma_addr_t swiotlb_map_page(struct device *dev, struct page *page,
                             unsigned long offset, size_t size,
@@ -642,18 +646,17 @@ dma_addr_t swiotlb_map_page(struct device *dev, struct page *page,
                             struct dma_attrs *attrs)
 {
         phys_addr_t phys = page_to_phys(page) + offset;
-        void *ptr = page_address(page) + offset;
         dma_addr_t dev_addr = swiotlb_phys_to_bus(dev, phys);
         void *map;
 
         BUG_ON(dir == DMA_NONE);
         /*
-         * If the pointer passed in happens to be in the device's DMA window,
+         * If the address happens to be in the device's DMA window,
          * we can safely return the device addr and not worry about bounce
          * buffering it.
          */
         if (!address_needs_mapping(dev, dev_addr, size) &&
-            !range_needs_mapping(virt_to_phys(ptr), size))
+            !range_needs_mapping(phys, size))
                 return dev_addr;
 
         /*
@@ -679,23 +682,35 @@ EXPORT_SYMBOL_GPL(swiotlb_map_page);
 
 /*
  * Unmap a single streaming mode DMA translation.  The dma_addr and size must
- * match what was provided for in a previous swiotlb_map_single call.  All
+ * match what was provided for in a previous swiotlb_map_page call.  All
  * other usages are undefined.
  *
  * After this call, reads by the cpu to the buffer are guaranteed to see
  * whatever the device wrote there.
  */
+static void unmap_single(struct device *hwdev, dma_addr_t dev_addr,
+                         size_t size, int dir)
+{
+        char *dma_addr = swiotlb_bus_to_virt(hwdev, dev_addr);
+
+        BUG_ON(dir == DMA_NONE);
+
+        if (is_swiotlb_buffer(dma_addr)) {
+                do_unmap_single(hwdev, dma_addr, size, dir);
+                return;
+        }
+
+        if (dir != DMA_FROM_DEVICE)
+                return;
+
+        dma_mark_clean(dma_addr, size);
+}
+
 void swiotlb_unmap_page(struct device *hwdev, dma_addr_t dev_addr,
                         size_t size, enum dma_data_direction dir,
                         struct dma_attrs *attrs)
 {
-        char *dma_addr = swiotlb_bus_to_virt(dev_addr);
-
-        BUG_ON(dir == DMA_NONE);
-        if (is_swiotlb_buffer(dma_addr))
-                unmap_single(hwdev, dma_addr, size, dir);
-        else if (dir == DMA_FROM_DEVICE)
-                dma_mark_clean(dma_addr, size);
+        unmap_single(hwdev, dev_addr, size, dir);
 }
 EXPORT_SYMBOL_GPL(swiotlb_unmap_page);
 
@@ -703,7 +718,7 @@ EXPORT_SYMBOL_GPL(swiotlb_unmap_page);
  * Make physical memory consistent for a single streaming mode DMA translation
  * after a transfer.
  *
- * If you perform a swiotlb_map_single() but wish to interrogate the buffer
+ * If you perform a swiotlb_map_page() but wish to interrogate the buffer
  * using the cpu, yet do not wish to teardown the dma mapping, you must
  * call this function before doing so.  At the next point you give the dma
  * address back to the card, you must first perform a
@@ -713,13 +728,19 @@ static void
 swiotlb_sync_single(struct device *hwdev, dma_addr_t dev_addr,
                     size_t size, int dir, int target)
 {
-        char *dma_addr = swiotlb_bus_to_virt(dev_addr);
+        char *dma_addr = swiotlb_bus_to_virt(hwdev, dev_addr);
 
         BUG_ON(dir == DMA_NONE);
-        if (is_swiotlb_buffer(dma_addr))
+
+        if (is_swiotlb_buffer(dma_addr)) {
                 sync_single(hwdev, dma_addr, size, dir, target);
-        else if (dir == DMA_FROM_DEVICE)
-                dma_mark_clean(dma_addr, size);
+                return;
+        }
+
+        if (dir != DMA_FROM_DEVICE)
+                return;
+
+        dma_mark_clean(dma_addr, size);
 }
 
 void
@@ -746,13 +767,7 @@ swiotlb_sync_single_range(struct device *hwdev, dma_addr_t dev_addr,
                           unsigned long offset, size_t size,
                           int dir, int target)
 {
-        char *dma_addr = swiotlb_bus_to_virt(dev_addr) + offset;
-
-        BUG_ON(dir == DMA_NONE);
-        if (is_swiotlb_buffer(dma_addr))
-                sync_single(hwdev, dma_addr, size, dir, target);
-        else if (dir == DMA_FROM_DEVICE)
-                dma_mark_clean(dma_addr, size);
+        swiotlb_sync_single(hwdev, dev_addr + offset, size, dir, target);
 }
 
 void
@@ -777,7 +792,7 @@ EXPORT_SYMBOL_GPL(swiotlb_sync_single_range_for_device);
 
 /*
  * 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
+ * This is the scatter-gather version of the above swiotlb_map_page
  * interface.  Here the scatter gather list elements are each tagged with the
  * appropriate dma address and length.  They are obtained via
  * sg_dma_{address,length}(SG).
@@ -788,7 +803,7 @@ EXPORT_SYMBOL_GPL(swiotlb_sync_single_range_for_device);
  *       The routine returns the number of addr/length pairs actually
  *       used, at most nents.
  *
- * Device ownership issues as mentioned above for swiotlb_map_single are the
+ * Device ownership issues as mentioned above for swiotlb_map_page are the
  * same here.
  */
 int
@@ -836,7 +851,7 @@ EXPORT_SYMBOL(swiotlb_map_sg);
 
 /*
  * Unmap a set of streaming mode DMA translations.  Again, cpu read rules
- * concerning calls here are the same as for swiotlb_unmap_single() above.
+ * concerning calls here are the same as for swiotlb_unmap_page() above.
  */
 void
 swiotlb_unmap_sg_attrs(struct device *hwdev, struct scatterlist *sgl,
@@ -847,13 +862,9 @@ 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_phys_to_bus(hwdev, sg_phys(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);
-        }
+        for_each_sg(sgl, sg, nelems, i)
+                unmap_single(hwdev, sg->dma_address, sg->dma_length, dir);
+
 }
 EXPORT_SYMBOL(swiotlb_unmap_sg_attrs);
 
@@ -879,15 +890,9 @@ swiotlb_sync_sg(struct device *hwdev, struct scatterlist *sgl,
         struct scatterlist *sg;
         int i;
 
-        BUG_ON(dir == DMA_NONE);
-
-        for_each_sg(sgl, sg, nelems, i) {
-                if (sg->dma_address != swiotlb_phys_to_bus(hwdev, sg_phys(sg)))
-                        sync_single(hwdev, swiotlb_bus_to_virt(sg->dma_address),
+        for_each_sg(sgl, sg, nelems, i)
+                swiotlb_sync_single(hwdev, 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);
-        }
 }
 
 void
diff --git a/lib/vsprintf.c b/lib/vsprintf.c
index 7536acea135b..756ccafa9cec 100644
--- a/lib/vsprintf.c
+++ b/lib/vsprintf.c
@@ -408,6 +408,8 @@ enum format_type {
         FORMAT_TYPE_LONG_LONG,
         FORMAT_TYPE_ULONG,
         FORMAT_TYPE_LONG,
+        FORMAT_TYPE_UBYTE,
+        FORMAT_TYPE_BYTE,
         FORMAT_TYPE_USHORT,
         FORMAT_TYPE_SHORT,
         FORMAT_TYPE_UINT,
@@ -573,12 +575,15 @@ static char *string(char *buf, char *end, char *s, struct printf_spec spec)
 }
 
 static char *symbol_string(char *buf, char *end, void *ptr,
-                                struct printf_spec spec)
+                                struct printf_spec spec, char ext)
 {
         unsigned long value = (unsigned long) ptr;
 #ifdef CONFIG_KALLSYMS
         char sym[KSYM_SYMBOL_LEN];
-        sprint_symbol(sym, value);
+        if (ext != 'f')
+                sprint_symbol(sym, value);
+        else
+                kallsyms_lookup(value, NULL, NULL, NULL, sym);
         return string(buf, end, sym, spec);
 #else
         spec.field_width = 2*sizeof(void *);
@@ -690,7 +695,8 @@ static char *ip4_addr_string(char *buf, char *end, u8 *addr,
  *
  * Right now we handle:
  *
- * - 'F' For symbolic function descriptor pointers
+ * - 'F' For symbolic function descriptor pointers with offset
+ * - 'f' For simple symbolic function names without offset
  * - 'S' For symbolic direct pointers
  * - 'R' For a struct resource pointer, it prints the range of
  *       addresses (not the name nor the flags)
@@ -713,10 +719,11 @@ static char *pointer(const char *fmt, char *buf, char *end, void *ptr,
 
         switch (*fmt) {
         case 'F':
+        case 'f':
                 ptr = dereference_function_descriptor(ptr);
                 /* Fallthrough */
         case 'S':
-                return symbol_string(buf, end, ptr, spec);
+                return symbol_string(buf, end, ptr, spec, *fmt);
         case 'R':
                 return resource_string(buf, end, ptr, spec);
         case 'm':
@@ -853,11 +860,15 @@ qualifier:
         spec->qualifier = -1;
         if (*fmt == 'h' || *fmt == 'l' || *fmt == 'L' ||
             *fmt == 'Z' || *fmt == 'z' || *fmt == 't') {
-                spec->qualifier = *fmt;
-                ++fmt;
-                if (spec->qualifier == 'l' && *fmt == 'l') {
-                        spec->qualifier = 'L';
-                        ++fmt;
+                spec->qualifier = *fmt++;
+                if (unlikely(spec->qualifier == *fmt)) {
+                        if (spec->qualifier == 'l') {
+                                spec->qualifier = 'L';
+                                ++fmt;
+                        } else if (spec->qualifier == 'h') {
+                                spec->qualifier = 'H';
+                                ++fmt;
+                        }
                 }
         }
 
@@ -919,6 +930,11 @@ qualifier:
                 spec->type = FORMAT_TYPE_SIZE_T;
         } else if (spec->qualifier == 't') {
                 spec->type = FORMAT_TYPE_PTRDIFF;
+        } else if (spec->qualifier == 'H') {
+                if (spec->flags & SIGN)
+                        spec->type = FORMAT_TYPE_BYTE;
+                else
+                        spec->type = FORMAT_TYPE_UBYTE;
         } else if (spec->qualifier == 'h') {
                 if (spec->flags & SIGN)
                         spec->type = FORMAT_TYPE_SHORT;
@@ -943,7 +959,8 @@ qualifier:
  *
  * This function follows C99 vsnprintf, but has some extensions:
  * %pS output the name of a text symbol
- * %pF output the name of a function pointer
+ * %pF output the name of a function pointer with its offset
+ * %pf output the name of a function pointer without its offset
  * %pR output the address range in a struct resource
  *
  * The return value is the number of characters which would
@@ -1087,6 +1104,12 @@ int vsnprintf(char *buf, size_t size, const char *fmt, va_list args)
                         case FORMAT_TYPE_PTRDIFF:
                                 num = va_arg(args, ptrdiff_t);
                                 break;
+                        case FORMAT_TYPE_UBYTE:
+                                num = (unsigned char) va_arg(args, int);
+                                break;
+                        case FORMAT_TYPE_BYTE:
+                                num = (signed char) va_arg(args, int);
+                                break;
                         case FORMAT_TYPE_USHORT:
                                 num = (unsigned short) va_arg(args, int);
                                 break;
@@ -1363,6 +1386,10 @@ do {									\
                         case FORMAT_TYPE_PTRDIFF:
                                 save_arg(ptrdiff_t);
                                 break;
+                        case FORMAT_TYPE_UBYTE:
+                        case FORMAT_TYPE_BYTE:
+                                save_arg(char);
+                                break;
                         case FORMAT_TYPE_USHORT:
                         case FORMAT_TYPE_SHORT:
                                 save_arg(short);
@@ -1391,7 +1418,8 @@ EXPORT_SYMBOL_GPL(vbin_printf);
  *
  * The format follows C99 vsnprintf, but has some extensions:
  * %pS output the name of a text symbol
- * %pF output the name of a function pointer
+ * %pF output the name of a function pointer with its offset
+ * %pf output the name of a function pointer without its offset
  * %pR output the address range in a struct resource
  * %n is ignored
  *
@@ -1538,6 +1566,12 @@ int bstr_printf(char *buf, size_t size, const char *fmt, const u32 *bin_buf)
                         case FORMAT_TYPE_PTRDIFF:
                                 num = get_arg(ptrdiff_t);
                                 break;
+                        case FORMAT_TYPE_UBYTE:
+                                num = get_arg(unsigned char);
+                                break;
+                        case FORMAT_TYPE_BYTE:
+                                num = get_arg(signed char);
+                                break;
                         case FORMAT_TYPE_USHORT:
                                 num = get_arg(unsigned short);
                                 break;