Merge commit 'v2.6.36' into wip-merge-2.6.36

Conflicts:
	Makefile
	arch/x86/include/asm/unistd_32.h
	arch/x86/kernel/syscall_table_32.S
	kernel/sched.c
	kernel/time/tick-sched.c

Relevant API and functions changes (solved in this commit):
- (API) .enqueue_task() (enqueue_task_litmus),
  dequeue_task() (dequeue_task_litmus),
  [litmus/sched_litmus.c]
- (API) .select_task_rq() (select_task_rq_litmus)
  [litmus/sched_litmus.c]
- (API) sysrq_dump_trace_buffer() and sysrq_handle_kill_rt_tasks()
  [litmus/sched_trace.c]
- struct kfifo internal buffer name changed (buffer -> buf)
  [litmus/sched_trace.c]
- add_wait_queue_exclusive_locked -> __add_wait_queue_tail_exclusive
  [litmus/fmlp.c]
- syscall numbers for both x86_32 and x86_64

23 files changed, 425 insertions, 152 deletions

diff --git a/include/asm-generic/Kbuild b/include/asm-generic/Kbuild
index eb62334cda29..53f91b1ae53a 100644
--- a/include/asm-generic/Kbuild
+++ b/include/asm-generic/Kbuild
@@ -3,6 +3,8 @@ header-y += bitsperlong.h
 header-y += errno-base.h
 header-y += errno.h
 header-y += fcntl.h
+header-y += int-l64.h
+header-y += int-ll64.h
 header-y += ioctl.h
 header-y += ioctls.h
 header-y += ipcbuf.h
@@ -12,10 +14,12 @@ header-y += msgbuf.h
 header-y += param.h
 header-y += poll.h
 header-y += posix_types.h
+header-y += resource.h
 header-y += sembuf.h
 header-y += setup.h
 header-y += shmbuf.h
 header-y += shmparam.h
+header-y += siginfo.h
 header-y += signal-defs.h
 header-y += signal.h
 header-y += socket.h
@@ -28,8 +32,3 @@ header-y += termios.h
 header-y += types.h
 header-y += ucontext.h
 header-y += unistd.h
-
-unifdef-y += int-l64.h
-unifdef-y += int-ll64.h
-unifdef-y += resource.h
-unifdef-y += siginfo.h
diff --git a/include/asm-generic/Kbuild.asm b/include/asm-generic/Kbuild.asm
index 96d7c9804dc1..c5d2e5dd871b 100644
--- a/include/asm-generic/Kbuild.asm
+++ b/include/asm-generic/Kbuild.asm
@@ -1,5 +1,5 @@
 ifneq ($(wildcard $(srctree)/arch/$(SRCARCH)/include/asm/kvm.h \
-                  $(srctree)/include/asm-$(SRCARCH)/kvm.h),)
+                  $(srctree)/include/asm-$(SRCARCH)/kvm.h),)
 header-y  += kvm.h
 endif
 
@@ -9,36 +9,37 @@ header-y  += kvm_para.h
 endif
 
 ifneq ($(wildcard $(srctree)/arch/$(SRCARCH)/include/asm/a.out.h \
-                  $(srctree)/include/asm-$(SRCARCH)/a.out.h),)
-unifdef-y += a.out.h
+                  $(srctree)/include/asm-$(SRCARCH)/a.out.h),)
+header-y += a.out.h
 endif
-unifdef-y += auxvec.h
-unifdef-y += byteorder.h
-unifdef-y += bitsperlong.h
-unifdef-y += errno.h
-unifdef-y += fcntl.h
-unifdef-y += ioctl.h
-unifdef-y += ioctls.h
-unifdef-y += ipcbuf.h
-unifdef-y += mman.h
-unifdef-y += msgbuf.h
-unifdef-y += param.h
-unifdef-y += poll.h
-unifdef-y += posix_types.h
-unifdef-y += ptrace.h
-unifdef-y += resource.h
-unifdef-y += sembuf.h
-unifdef-y += setup.h
-unifdef-y += shmbuf.h
-unifdef-y += sigcontext.h
-unifdef-y += siginfo.h
-unifdef-y += signal.h
-unifdef-y += socket.h
-unifdef-y += sockios.h
-unifdef-y += stat.h
-unifdef-y += statfs.h
-unifdef-y += swab.h
-unifdef-y += termbits.h
-unifdef-y += termios.h
-unifdef-y += types.h
-unifdef-y += unistd.h
+
+header-y += auxvec.h
+header-y += bitsperlong.h
+header-y += byteorder.h
+header-y += errno.h
+header-y += fcntl.h
+header-y += ioctl.h
+header-y += ioctls.h
+header-y += ipcbuf.h
+header-y += mman.h
+header-y += msgbuf.h
+header-y += param.h
+header-y += poll.h
+header-y += posix_types.h
+header-y += ptrace.h
+header-y += resource.h
+header-y += sembuf.h
+header-y += setup.h
+header-y += shmbuf.h
+header-y += sigcontext.h
+header-y += siginfo.h
+header-y += signal.h
+header-y += socket.h
+header-y += sockios.h
+header-y += stat.h
+header-y += statfs.h
+header-y += swab.h
+header-y += termbits.h
+header-y += termios.h
+header-y += types.h
+header-y += unistd.h
diff --git a/include/asm-generic/atomic.h b/include/asm-generic/atomic.h
index c99c64dc5f3d..e53347fbf1da 100644
--- a/include/asm-generic/atomic.h
+++ b/include/asm-generic/atomic.h
@@ -30,18 +30,16 @@
  * atomic_read - read atomic variable
  * @v: pointer of type atomic_t
  *
- * Atomically reads the value of @v.  Note that the guaranteed
- * useful range of an atomic_t is only 24 bits.
+ * Atomically reads the value of @v.
  */
-#define atomic_read(v)  ((v)->counter)
+#define atomic_read(v)  (*(volatile int *)&(v)->counter)
 
 /**
  * atomic_set - set atomic variable
  * @v: pointer of type atomic_t
  * @i: required value
  *
- * Atomically sets the value of @v to @i.  Note that the guaranteed
- * useful range of an atomic_t is only 24 bits.
+ * Atomically sets the value of @v to @i.
  */
 #define atomic_set(v, i) (((v)->counter) = (i))
 
@@ -53,18 +51,17 @@
  * @v: pointer of type atomic_t
  *
  * Atomically adds @i to @v and returns the result
- * Note that the guaranteed useful range of an atomic_t is only 24 bits.
  */
 static inline int atomic_add_return(int i, atomic_t *v)
 {
         unsigned long flags;
         int temp;
 
-        local_irq_save(flags);
+        raw_local_irq_save(flags); /* Don't trace it in a irqsoff handler */
         temp = v->counter;
         temp += i;
         v->counter = temp;
-        local_irq_restore(flags);
+        raw_local_irq_restore(flags);
 
         return temp;
 }
@@ -75,18 +72,17 @@ static inline int atomic_add_return(int i, atomic_t *v)
  * @v: pointer of type atomic_t
  *
  * Atomically subtracts @i from @v and returns the result
- * Note that the guaranteed useful range of an atomic_t is only 24 bits.
  */
 static inline int atomic_sub_return(int i, atomic_t *v)
 {
         unsigned long flags;
         int temp;
 
-        local_irq_save(flags);
+        raw_local_irq_save(flags); /* Don't trace it in a irqsoff handler */
         temp = v->counter;
         temp -= i;
         v->counter = temp;
-        local_irq_restore(flags);
+        raw_local_irq_restore(flags);
 
         return temp;
 }
@@ -139,9 +135,9 @@ static inline void atomic_clear_mask(unsigned long mask, unsigned long *addr)
         unsigned long flags;
 
         mask = ~mask;
-        local_irq_save(flags);
+        raw_local_irq_save(flags); /* Don't trace it in a irqsoff handler */
         *addr &= mask;
-        local_irq_restore(flags);
+        raw_local_irq_restore(flags);
 }
 
 #define atomic_xchg(ptr, v)             (xchg(&(ptr)->counter, (v)))
diff --git a/include/asm-generic/bitops/arch_hweight.h b/include/asm-generic/bitops/arch_hweight.h
new file mode 100644
index 000000000000..6a211f40665c
--- /dev/null
+++ b/include/asm-generic/bitops/arch_hweight.h
@@ -0,0 +1,25 @@
+#ifndef _ASM_GENERIC_BITOPS_ARCH_HWEIGHT_H_
+#define _ASM_GENERIC_BITOPS_ARCH_HWEIGHT_H_
+
+#include <asm/types.h>
+
+static inline unsigned int __arch_hweight32(unsigned int w)
+{
+        return __sw_hweight32(w);
+}
+
+static inline unsigned int __arch_hweight16(unsigned int w)
+{
+        return __sw_hweight16(w);
+}
+
+static inline unsigned int __arch_hweight8(unsigned int w)
+{
+        return __sw_hweight8(w);
+}
+
+static inline unsigned long __arch_hweight64(__u64 w)
+{
+        return __sw_hweight64(w);
+}
+#endif /* _ASM_GENERIC_BITOPS_HWEIGHT_H_ */
diff --git a/include/asm-generic/bitops/const_hweight.h b/include/asm-generic/bitops/const_hweight.h
new file mode 100644
index 000000000000..fa2a50b7ee66
--- /dev/null
+++ b/include/asm-generic/bitops/const_hweight.h
@@ -0,0 +1,42 @@
+#ifndef _ASM_GENERIC_BITOPS_CONST_HWEIGHT_H_
+#define _ASM_GENERIC_BITOPS_CONST_HWEIGHT_H_
+
+/*
+ * Compile time versions of __arch_hweightN()
+ */
+#define __const_hweight8(w)             \
+      ( (!!((w) & (1ULL << 0))) +       \
+        (!!((w) & (1ULL << 1))) +       \
+        (!!((w) & (1ULL << 2))) +       \
+        (!!((w) & (1ULL << 3))) +       \
+        (!!((w) & (1ULL << 4))) +       \
+        (!!((w) & (1ULL << 5))) +       \
+        (!!((w) & (1ULL << 6))) +       \
+        (!!((w) & (1ULL << 7))) )
+
+#define __const_hweight16(w) (__const_hweight8(w)  + __const_hweight8((w)  >> 8 ))
+#define __const_hweight32(w) (__const_hweight16(w) + __const_hweight16((w) >> 16))
+#define __const_hweight64(w) (__const_hweight32(w) + __const_hweight32((w) >> 32))
+
+/*
+ * Generic interface.
+ */
+#define hweight8(w)  (__builtin_constant_p(w) ? __const_hweight8(w)  : __arch_hweight8(w))
+#define hweight16(w) (__builtin_constant_p(w) ? __const_hweight16(w) : __arch_hweight16(w))
+#define hweight32(w) (__builtin_constant_p(w) ? __const_hweight32(w) : __arch_hweight32(w))
+#define hweight64(w) (__builtin_constant_p(w) ? __const_hweight64(w) : __arch_hweight64(w))
+
+/*
+ * Interface for known constant arguments
+ */
+#define HWEIGHT8(w)  (BUILD_BUG_ON_ZERO(!__builtin_constant_p(w)) + __const_hweight8(w))
+#define HWEIGHT16(w) (BUILD_BUG_ON_ZERO(!__builtin_constant_p(w)) + __const_hweight16(w))
+#define HWEIGHT32(w) (BUILD_BUG_ON_ZERO(!__builtin_constant_p(w)) + __const_hweight32(w))
+#define HWEIGHT64(w) (BUILD_BUG_ON_ZERO(!__builtin_constant_p(w)) + __const_hweight64(w))
+
+/*
+ * Type invariant interface to the compile time constant hweight functions.
+ */
+#define HWEIGHT(w)   HWEIGHT64((u64)w)
+
+#endif /* _ASM_GENERIC_BITOPS_CONST_HWEIGHT_H_ */
diff --git a/include/asm-generic/bitops/hweight.h b/include/asm-generic/bitops/hweight.h
index fbbc383771da..a94d6519c7ed 100644
--- a/include/asm-generic/bitops/hweight.h
+++ b/include/asm-generic/bitops/hweight.h
@@ -1,11 +1,7 @@
 #ifndef _ASM_GENERIC_BITOPS_HWEIGHT_H_
 #define _ASM_GENERIC_BITOPS_HWEIGHT_H_
 
-#include <asm/types.h>
-
-extern unsigned int hweight32(unsigned int w);
-extern unsigned int hweight16(unsigned int w);
-extern unsigned int hweight8(unsigned int w);
-extern unsigned long hweight64(__u64 w);
+#include <asm-generic/bitops/arch_hweight.h>
+#include <asm-generic/bitops/const_hweight.h>
 
 #endif /* _ASM_GENERIC_BITOPS_HWEIGHT_H_ */
diff --git a/include/asm-generic/bug.h b/include/asm-generic/bug.h
index 18c435d7c082..c2c9ba032d46 100644
--- a/include/asm-generic/bug.h
+++ b/include/asm-generic/bug.h
@@ -25,7 +25,10 @@ struct bug_entry {
 };
 #endif          /* __ASSEMBLY__ */
 
-#define BUGFLAG_WARNING (1<<0)
+#define BUGFLAG_WARNING         (1 << 0)
+#define BUGFLAG_TAINT(taint)    (BUGFLAG_WARNING | ((taint) << 8))
+#define BUG_GET_TAINT(bug)      ((bug)->flags >> 8)
+
 #endif  /* CONFIG_GENERIC_BUG */
 
 /*
@@ -56,17 +59,25 @@ struct bug_entry {
  * appear at runtime.  Use the versions with printk format strings
  * to provide better diagnostics.
  */
-#ifndef __WARN
+#ifndef __WARN_TAINT
 #ifndef __ASSEMBLY__
 extern void warn_slowpath_fmt(const char *file, const int line,
                 const char *fmt, ...) __attribute__((format(printf, 3, 4)));
+extern void warn_slowpath_fmt_taint(const char *file, const int line,
+                                    unsigned taint, const char *fmt, ...)
+        __attribute__((format(printf, 4, 5)));
 extern void warn_slowpath_null(const char *file, const int line);
 #define WANT_WARN_ON_SLOWPATH
 #endif
 #define __WARN()                warn_slowpath_null(__FILE__, __LINE__)
 #define __WARN_printf(arg...)   warn_slowpath_fmt(__FILE__, __LINE__, arg)
+#define __WARN_printf_taint(taint, arg...)                              \
+        warn_slowpath_fmt_taint(__FILE__, __LINE__, taint, arg)
 #else
+#define __WARN()                __WARN_TAINT(TAINT_WARN)
 #define __WARN_printf(arg...)   do { printk(arg); __WARN(); } while (0)
+#define __WARN_printf_taint(taint, arg...)                              \
+        do { printk(arg); __WARN_TAINT(taint); } while (0)
 #endif
 
 #ifndef WARN_ON
@@ -87,6 +98,13 @@ extern void warn_slowpath_null(const char *file, const int line);
 })
 #endif
 
+#define WARN_TAINT(condition, taint, format...) ({                      \
+        int __ret_warn_on = !!(condition);                              \
+        if (unlikely(__ret_warn_on))                                    \
+                __WARN_printf_taint(taint, format);                     \
+        unlikely(__ret_warn_on);                                        \
+})
+
 #else /* !CONFIG_BUG */
 #ifndef HAVE_ARCH_BUG
 #define BUG() do {} while(0)
@@ -110,6 +128,8 @@ extern void warn_slowpath_null(const char *file, const int line);
 })
 #endif
 
+#define WARN_TAINT(condition, taint, format...) WARN_ON(condition)
+
 #endif
 
 #define WARN_ON_ONCE(condition) ({                              \
@@ -132,6 +152,16 @@ extern void warn_slowpath_null(const char *file, const int line);
         unlikely(__ret_warn_once);                              \
 })
 
+#define WARN_TAINT_ONCE(condition, taint, format...)    ({      \
+        static bool __warned;                                   \
+        int __ret_warn_once = !!(condition);                    \
+                                                                \
+        if (unlikely(__ret_warn_once))                          \
+                if (WARN_TAINT(!__warned, taint, format))       \
+                        __warned = true;                        \
+        unlikely(__ret_warn_once);                              \
+})
+
 #define WARN_ON_RATELIMIT(condition, state)                     \
                 WARN_ON((condition) && __ratelimit(state))
 
diff --git a/include/asm-generic/dma-mapping-broken.h b/include/asm-generic/dma-mapping-broken.h
index 82cd0cb1c3fe..ccf7b4f34a3c 100644
--- a/include/asm-generic/dma-mapping-broken.h
+++ b/include/asm-generic/dma-mapping-broken.h
@@ -72,9 +72,6 @@ dma_set_mask(struct device *dev, u64 mask);
 extern int
 dma_get_cache_alignment(void);
 
-extern int
-dma_is_consistent(struct device *dev, dma_addr_t dma_handle);
-
 extern void
 dma_cache_sync(struct device *dev, void *vaddr, size_t size,
                enum dma_data_direction direction);
diff --git a/include/asm-generic/dma-mapping-common.h b/include/asm-generic/dma-mapping-common.h
index 69206957b72c..0c80bb38773f 100644
--- a/include/asm-generic/dma-mapping-common.h
+++ b/include/asm-generic/dma-mapping-common.h
@@ -123,15 +123,7 @@ static inline void dma_sync_single_range_for_cpu(struct device *dev,
                                                  size_t size,
                                                  enum dma_data_direction dir)
 {
-        struct dma_map_ops *ops = get_dma_ops(dev);
-
-        BUG_ON(!valid_dma_direction(dir));
-        if (ops->sync_single_range_for_cpu) {
-                ops->sync_single_range_for_cpu(dev, addr, offset, size, dir);
-                debug_dma_sync_single_range_for_cpu(dev, addr, offset, size, dir);
-
-        } else
-                dma_sync_single_for_cpu(dev, addr + offset, size, dir);
+        dma_sync_single_for_cpu(dev, addr + offset, size, dir);
 }
 
 static inline void dma_sync_single_range_for_device(struct device *dev,
@@ -140,15 +132,7 @@ static inline void dma_sync_single_range_for_device(struct device *dev,
                                                     size_t size,
                                                     enum dma_data_direction dir)
 {
-        struct dma_map_ops *ops = get_dma_ops(dev);
-
-        BUG_ON(!valid_dma_direction(dir));
-        if (ops->sync_single_range_for_device) {
-                ops->sync_single_range_for_device(dev, addr, offset, size, dir);
-                debug_dma_sync_single_range_for_device(dev, addr, offset, size, dir);
-
-        } else
-                dma_sync_single_for_device(dev, addr + offset, size, dir);
+        dma_sync_single_for_device(dev, addr + offset, size, dir);
 }
 
 static inline void
diff --git a/include/asm-generic/fcntl.h b/include/asm-generic/fcntl.h
index fcd268ce0674..a70b2d2bfc14 100644
--- a/include/asm-generic/fcntl.h
+++ b/include/asm-generic/fcntl.h
@@ -3,6 +3,18 @@
 
 #include <linux/types.h>
 
+/*
+ * FMODE_EXEC is 0x20
+ * FMODE_NONOTIFY is 0x1000000
+ * These cannot be used by userspace O_* until internal and external open
+ * flags are split.
+ * -Eric Paris
+ */
+
+/*
+ * When introducing new O_* bits, please check its uniqueness in fcntl_init().
+ */
+
 #define O_ACCMODE       00000003
 #define O_RDONLY        00000000
 #define O_WRONLY        00000001
diff --git a/include/asm-generic/gpio.h b/include/asm-generic/gpio.h
index 979c6a57f2f1..8ca18e26d7e3 100644
--- a/include/asm-generic/gpio.h
+++ b/include/asm-generic/gpio.h
@@ -16,21 +16,34 @@
  * While the GPIO programming interface defines valid GPIO numbers
  * to be in the range 0..MAX_INT, this library restricts them to the
  * smaller range 0..ARCH_NR_GPIOS-1.
+ *
+ * ARCH_NR_GPIOS is somewhat arbitrary; it usually reflects the sum of
+ * builtin/SoC GPIOs plus a number of GPIOs on expanders; the latter is
+ * actually an estimate of a board-specific value.
  */
 
 #ifndef ARCH_NR_GPIOS
 #define ARCH_NR_GPIOS           256
 #endif
 
+/*
+ * "valid" GPIO numbers are nonnegative and may be passed to
+ * setup routines like gpio_request().  only some valid numbers
+ * can successfully be requested and used.
+ *
+ * Invalid GPIO numbers are useful for indicating no-such-GPIO in
+ * platform data and other tables.
+ */
+
 static inline int gpio_is_valid(int number)
 {
-        /* only some non-negative numbers are valid */
         return ((unsigned)number) < ARCH_NR_GPIOS;
 }
 
 struct device;
 struct seq_file;
 struct module;
+struct device_node;
 
 /**
  * struct gpio_chip - abstract a GPIO controller
@@ -60,7 +73,9 @@ struct module;
  * @names: if set, must be an array of strings to use as alternative
  *      names for the GPIOs in this chip. Any entry in the array
  *      may be NULL if there is no alias for the GPIO, however the
- *      array must be @ngpio entries long.
+ *      array must be @ngpio entries long.  A name can include a single printk
+ *      format specifier for an unsigned int.  It is substituted by the actual
+ *      number of the gpio.
  *
  * A gpio_chip can help platforms abstract various sources of GPIOs so
  * they can all be accessed through a common programing interface.
@@ -88,6 +103,9 @@ struct gpio_chip {
                                                 unsigned offset);
         int                     (*direction_output)(struct gpio_chip *chip,
                                                 unsigned offset, int value);
+        int                     (*set_debounce)(struct gpio_chip *chip,
+                                                unsigned offset, unsigned debounce);
+
         void                    (*set)(struct gpio_chip *chip,
                                                 unsigned offset, int value);
 
@@ -98,9 +116,20 @@ struct gpio_chip {
                                                 struct gpio_chip *chip);
         int                     base;
         u16                     ngpio;
-        char                    **names;
+        const char              *const *names;
         unsigned                can_sleep:1;
         unsigned                exported:1;
+
+#if defined(CONFIG_OF_GPIO)
+        /*
+         * If CONFIG_OF is enabled, then all GPIO controllers described in the
+         * device tree automatically may have an OF translation
+         */
+        struct device_node *of_node;
+        int of_gpio_n_cells;
+        int (*of_xlate)(struct gpio_chip *gc, struct device_node *np,
+                        const void *gpio_spec, u32 *flags);
+#endif
 };
 
 extern const char *gpiochip_is_requested(struct gpio_chip *chip,
@@ -110,6 +139,9 @@ extern int __must_check gpiochip_reserve(int start, int ngpio);
 /* add/remove chips */
 extern int gpiochip_add(struct gpio_chip *chip);
 extern int __must_check gpiochip_remove(struct gpio_chip *chip);
+extern struct gpio_chip *gpiochip_find(void *data,
+                                        int (*match)(struct gpio_chip *chip,
+                                                     void *data));
 
 
 /* Always use the library code for GPIO management calls,
@@ -121,6 +153,8 @@ extern void gpio_free(unsigned gpio);
 extern int gpio_direction_input(unsigned gpio);
 extern int gpio_direction_output(unsigned gpio, int value);
 
+extern int gpio_set_debounce(unsigned gpio, unsigned debounce);
+
 extern int gpio_get_value_cansleep(unsigned gpio);
 extern void gpio_set_value_cansleep(unsigned gpio, int value);
 
diff --git a/include/asm-generic/io.h b/include/asm-generic/io.h
index bcee6365dca0..118601fce92d 100644
--- a/include/asm-generic/io.h
+++ b/include/asm-generic/io.h
@@ -188,11 +188,15 @@ static inline void outsl(unsigned long addr, const void *buffer, int count)
 #ifndef CONFIG_GENERIC_IOMAP
 #define ioread8(addr)           readb(addr)
 #define ioread16(addr)          readw(addr)
+#define ioread16be(addr)        be16_to_cpu(ioread16(addr))
 #define ioread32(addr)          readl(addr)
+#define ioread32be(addr)        be32_to_cpu(ioread32(addr))
 
 #define iowrite8(v, addr)       writeb((v), (addr))
 #define iowrite16(v, addr)      writew((v), (addr))
+#define iowrite16be(v, addr)    iowrite16(be16_to_cpu(v), (addr))
 #define iowrite32(v, addr)      writel((v), (addr))
+#define iowrite32be(v, addr)    iowrite32(be32_to_cpu(v), (addr))
 
 #define ioread8_rep(p, dst, count) \
         insb((unsigned long) (p), (dst), (count))
diff --git a/include/asm-generic/ioctls.h b/include/asm-generic/ioctls.h
index a799e20a769e..8554cb6a81b9 100644
--- a/include/asm-generic/ioctls.h
+++ b/include/asm-generic/ioctls.h
@@ -69,6 +69,7 @@
 #define TCSETX          0x5433
 #define TCSETXF         0x5434
 #define TCSETXW         0x5435
+#define TIOCSIG         _IOW('T', 0x36, int)  /* pty: generate signal */
 
 #define FIONCLEX        0x5450
 #define FIOCLEX         0x5451
@@ -87,12 +88,10 @@
 #define TIOCGICOUNT     0x545D  /* read serial port inline interrupt counts */
 
 /*
- * some architectures define FIOQSIZE as 0x545E, which is used for
- * TIOCGHAYESESP on others
+ * Some arches already define FIOQSIZE due to a historical
+ * conflict with a Hayes modem-specific ioctl value.
  */
 #ifndef FIOQSIZE
-# define TIOCGHAYESESP  0x545E  /* Get Hayes ESP configuration */
-# define TIOCSHAYESESP  0x545F  /* Set Hayes ESP configuration */
 # define FIOQSIZE       0x5460
 #endif
 
@@ -104,6 +103,7 @@
 #define TIOCPKT_START            8
 #define TIOCPKT_NOSTOP          16
 #define TIOCPKT_DOSTOP          32
+#define TIOCPKT_IOCTL           64
 
 #define TIOCSER_TEMT    0x01    /* Transmitter physically empty */
 
diff --git a/include/asm-generic/kmap_types.h b/include/asm-generic/kmap_types.h
index e5f234a08540..0232ccb76f2b 100644
--- a/include/asm-generic/kmap_types.h
+++ b/include/asm-generic/kmap_types.h
@@ -28,7 +28,11 @@ KMAP_D(15)	KM_UML_USERCOPY,
 KMAP_D(16)      KM_IRQ_PTE,
 KMAP_D(17)      KM_NMI,
 KMAP_D(18)      KM_NMI_PTE,
-KMAP_D(19)      KM_TYPE_NR
+KMAP_D(19)      KM_KDB,
+/*
+ * Remember to update debug_kmap_atomic() when adding new kmap types!
+ */
+KMAP_D(20)      KM_TYPE_NR
 };
 
 #undef KMAP_D
diff --git a/include/asm-generic/local64.h b/include/asm-generic/local64.h
new file mode 100644
index 000000000000..02ac760c1a8b
--- /dev/null
+++ b/include/asm-generic/local64.h
@@ -0,0 +1,96 @@
+#ifndef _ASM_GENERIC_LOCAL64_H
+#define _ASM_GENERIC_LOCAL64_H
+
+#include <linux/percpu.h>
+#include <asm/types.h>
+
+/*
+ * A signed long type for operations which are atomic for a single CPU.
+ * Usually used in combination with per-cpu variables.
+ *
+ * This is the default implementation, which uses atomic64_t.  Which is
+ * rather pointless.  The whole point behind local64_t is that some processors
+ * can perform atomic adds and subtracts in a manner which is atomic wrt IRQs
+ * running on this CPU.  local64_t allows exploitation of such capabilities.
+ */
+
+/* Implement in terms of atomics. */
+
+#if BITS_PER_LONG == 64
+
+#include <asm/local.h>
+
+typedef struct {
+        local_t a;
+} local64_t;
+
+#define LOCAL64_INIT(i) { LOCAL_INIT(i) }
+
+#define local64_read(l)         local_read(&(l)->a)
+#define local64_set(l,i)        local_set((&(l)->a),(i))
+#define local64_inc(l)          local_inc(&(l)->a)
+#define local64_dec(l)          local_dec(&(l)->a)
+#define local64_add(i,l)        local_add((i),(&(l)->a))
+#define local64_sub(i,l)        local_sub((i),(&(l)->a))
+
+#define local64_sub_and_test(i, l) local_sub_and_test((i), (&(l)->a))
+#define local64_dec_and_test(l) local_dec_and_test(&(l)->a)
+#define local64_inc_and_test(l) local_inc_and_test(&(l)->a)
+#define local64_add_negative(i, l) local_add_negative((i), (&(l)->a))
+#define local64_add_return(i, l) local_add_return((i), (&(l)->a))
+#define local64_sub_return(i, l) local_sub_return((i), (&(l)->a))
+#define local64_inc_return(l)   local_inc_return(&(l)->a)
+
+#define local64_cmpxchg(l, o, n) local_cmpxchg((&(l)->a), (o), (n))
+#define local64_xchg(l, n)      local_xchg((&(l)->a), (n))
+#define local64_add_unless(l, _a, u) local_add_unless((&(l)->a), (_a), (u))
+#define local64_inc_not_zero(l) local_inc_not_zero(&(l)->a)
+
+/* Non-atomic variants, ie. preemption disabled and won't be touched
+ * in interrupt, etc.  Some archs can optimize this case well. */
+#define __local64_inc(l)        local64_set((l), local64_read(l) + 1)
+#define __local64_dec(l)        local64_set((l), local64_read(l) - 1)
+#define __local64_add(i,l)      local64_set((l), local64_read(l) + (i))
+#define __local64_sub(i,l)      local64_set((l), local64_read(l) - (i))
+
+#else /* BITS_PER_LONG != 64 */
+
+#include <asm/atomic.h>
+
+/* Don't use typedef: don't want them to be mixed with atomic_t's. */
+typedef struct {
+        atomic64_t a;
+} local64_t;
+
+#define LOCAL64_INIT(i) { ATOMIC_LONG_INIT(i) }
+
+#define local64_read(l)         atomic64_read(&(l)->a)
+#define local64_set(l,i)        atomic64_set((&(l)->a),(i))
+#define local64_inc(l)          atomic64_inc(&(l)->a)
+#define local64_dec(l)          atomic64_dec(&(l)->a)
+#define local64_add(i,l)        atomic64_add((i),(&(l)->a))
+#define local64_sub(i,l)        atomic64_sub((i),(&(l)->a))
+
+#define local64_sub_and_test(i, l) atomic64_sub_and_test((i), (&(l)->a))
+#define local64_dec_and_test(l) atomic64_dec_and_test(&(l)->a)
+#define local64_inc_and_test(l) atomic64_inc_and_test(&(l)->a)
+#define local64_add_negative(i, l) atomic64_add_negative((i), (&(l)->a))
+#define local64_add_return(i, l) atomic64_add_return((i), (&(l)->a))
+#define local64_sub_return(i, l) atomic64_sub_return((i), (&(l)->a))
+#define local64_inc_return(l)   atomic64_inc_return(&(l)->a)
+
+#define local64_cmpxchg(l, o, n) atomic64_cmpxchg((&(l)->a), (o), (n))
+#define local64_xchg(l, n)      atomic64_xchg((&(l)->a), (n))
+#define local64_add_unless(l, _a, u) atomic64_add_unless((&(l)->a), (_a), (u))
+#define local64_inc_not_zero(l) atomic64_inc_not_zero(&(l)->a)
+
+/* Non-atomic variants, ie. preemption disabled and won't be touched
+ * in interrupt, etc.  Some archs can optimize this case well. */
+#define __local64_inc(l)        local64_set((l), local64_read(l) + 1)
+#define __local64_dec(l)        local64_set((l), local64_read(l) - 1)
+#define __local64_add(i,l)      local64_set((l), local64_read(l) + (i))
+#define __local64_sub(i,l)      local64_set((l), local64_read(l) - (i))
+
+#endif /* BITS_PER_LONG != 64 */
+
+#endif /* _ASM_GENERIC_LOCAL64_H */
diff --git a/include/asm-generic/percpu.h b/include/asm-generic/percpu.h
index 04f91c2d3f7b..08923b684768 100644
--- a/include/asm-generic/percpu.h
+++ b/include/asm-generic/percpu.h
@@ -70,17 +70,22 @@ extern void setup_per_cpu_areas(void);
 
 #else /* ! SMP */
 
-#define per_cpu(var, cpu)                       (*((void)(cpu), &(var)))
-#define __get_cpu_var(var)                      (var)
-#define __raw_get_cpu_var(var)                  (var)
-#define this_cpu_ptr(ptr) per_cpu_ptr(ptr, 0)
-#define __this_cpu_ptr(ptr) this_cpu_ptr(ptr)
+#define VERIFY_PERCPU_PTR(__p) ({                       \
+        __verify_pcpu_ptr((__p));                       \
+        (typeof(*(__p)) __kernel __force *)(__p);       \
+})
+
+#define per_cpu(var, cpu)       (*((void)(cpu), VERIFY_PERCPU_PTR(&(var))))
+#define __get_cpu_var(var)      (*VERIFY_PERCPU_PTR(&(var)))
+#define __raw_get_cpu_var(var)  (*VERIFY_PERCPU_PTR(&(var)))
+#define this_cpu_ptr(ptr)       per_cpu_ptr(ptr, 0)
+#define __this_cpu_ptr(ptr)     this_cpu_ptr(ptr)
 
 #endif  /* SMP */
 
 #ifndef PER_CPU_BASE_SECTION
 #ifdef CONFIG_SMP
-#define PER_CPU_BASE_SECTION ".data.percpu"
+#define PER_CPU_BASE_SECTION ".data..percpu"
 #else
 #define PER_CPU_BASE_SECTION ".data"
 #endif
@@ -92,15 +97,15 @@ extern void setup_per_cpu_areas(void);
 #define PER_CPU_SHARED_ALIGNED_SECTION ""
 #define PER_CPU_ALIGNED_SECTION ""
 #else
-#define PER_CPU_SHARED_ALIGNED_SECTION ".shared_aligned"
-#define PER_CPU_ALIGNED_SECTION ".shared_aligned"
+#define PER_CPU_SHARED_ALIGNED_SECTION "..shared_aligned"
+#define PER_CPU_ALIGNED_SECTION "..shared_aligned"
 #endif
-#define PER_CPU_FIRST_SECTION ".first"
+#define PER_CPU_FIRST_SECTION "..first"
 
 #else
 
 #define PER_CPU_SHARED_ALIGNED_SECTION ""
-#define PER_CPU_ALIGNED_SECTION ".shared_aligned"
+#define PER_CPU_ALIGNED_SECTION "..shared_aligned"
 #define PER_CPU_FIRST_SECTION ""
 
 #endif
diff --git a/include/asm-generic/scatterlist.h b/include/asm-generic/scatterlist.h
index 8b9454496a7c..5de07355fad4 100644
--- a/include/asm-generic/scatterlist.h
+++ b/include/asm-generic/scatterlist.h
@@ -11,7 +11,9 @@ struct scatterlist {
         unsigned int    offset;
         unsigned int    length;
         dma_addr_t      dma_address;
+#ifdef CONFIG_NEED_SG_DMA_LENGTH
         unsigned int    dma_length;
+#endif
 };
 
 /*
@@ -22,22 +24,11 @@ struct scatterlist {
  * is 0.
  */
 #define sg_dma_address(sg)      ((sg)->dma_address)
-#ifndef sg_dma_len
-/*
- * Normally, you have an iommu on 64 bit machines, but not on 32 bit
- * machines. Architectures that are differnt should override this.
- */
-#if __BITS_PER_LONG == 64
+
+#ifdef CONFIG_NEED_SG_DMA_LENGTH
 #define sg_dma_len(sg)          ((sg)->dma_length)
 #else
 #define sg_dma_len(sg)          ((sg)->length)
-#endif /* 64 bit */
-#endif /* sg_dma_len */
-
-#ifndef ISA_DMA_THRESHOLD
-#define ISA_DMA_THRESHOLD       (~0UL)
 #endif
 
-#define ARCH_HAS_SG_CHAIN
-
 #endif /* __ASM_GENERIC_SCATTERLIST_H */
diff --git a/include/asm-generic/statfs.h b/include/asm-generic/statfs.h
index 3b4fb3e52f0d..0fd28e028de1 100644
--- a/include/asm-generic/statfs.h
+++ b/include/asm-generic/statfs.h
@@ -33,7 +33,8 @@ struct statfs {
         __kernel_fsid_t f_fsid;
         __statfs_word f_namelen;
         __statfs_word f_frsize;
-        __statfs_word f_spare[5];
+        __statfs_word f_flags;
+        __statfs_word f_spare[4];
 };
 
 /*
@@ -55,7 +56,8 @@ struct statfs64 {
         __kernel_fsid_t f_fsid;
         __statfs_word f_namelen;
         __statfs_word f_frsize;
-        __statfs_word f_spare[5];
+        __statfs_word f_flags;
+        __statfs_word f_spare[4];
 } ARCH_PACK_STATFS64;
 
 /* 
@@ -77,7 +79,8 @@ struct compat_statfs64 {
         __kernel_fsid_t f_fsid;
         __u32 f_namelen;
         __u32 f_frsize;
-        __u32 f_spare[5];
+        __u32 f_flags;
+        __u32 f_spare[4];
 } ARCH_PACK_COMPAT_STATFS64;
 
 #endif
diff --git a/include/asm-generic/syscalls.h b/include/asm-generic/syscalls.h
index df84e3b04555..d89dec864d42 100644
--- a/include/asm-generic/syscalls.h
+++ b/include/asm-generic/syscalls.h
@@ -23,8 +23,10 @@ asmlinkage long sys_vfork(struct pt_regs *regs);
 #endif
 
 #ifndef sys_execve
-asmlinkage long sys_execve(char __user *filename, char __user * __user *argv,
-                        char __user * __user *envp, struct pt_regs *regs);
+asmlinkage long sys_execve(const char __user *filename,
+                           const char __user *const __user *argv,
+                           const char __user *const __user *envp,
+                           struct pt_regs *regs);
 #endif
 
 #ifndef sys_mmap2
diff --git a/include/asm-generic/termbits.h b/include/asm-generic/termbits.h
index 1c9773d48cb0..232b4781aef3 100644
--- a/include/asm-generic/termbits.h
+++ b/include/asm-generic/termbits.h
@@ -178,6 +178,7 @@ struct ktermios {
 #define FLUSHO  0010000
 #define PENDIN  0040000
 #define IEXTEN  0100000
+#define EXTPROC 0200000
 
 /* tcflow() and TCXONC use these */
 #define TCOOFF          0
diff --git a/include/asm-generic/topology.h b/include/asm-generic/topology.h
index 510df36dd5d4..fc824e2828f3 100644
--- a/include/asm-generic/topology.h
+++ b/include/asm-generic/topology.h
@@ -5,7 +5,7 @@
  *
  * Copyright (C) 2002, IBM Corp.
  *
- * All rights reserved.          
+ * All rights reserved.
  *
  * 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
@@ -34,6 +34,16 @@
 #ifndef cpu_to_node
 #define cpu_to_node(cpu)        ((void)(cpu),0)
 #endif
+#ifndef set_numa_node
+#define set_numa_node(node)
+#endif
+#ifndef set_cpu_numa_node
+#define set_cpu_numa_node(cpu, node)
+#endif
+#ifndef cpu_to_mem
+#define cpu_to_mem(cpu)         ((void)(cpu),0)
+#endif
+
 #ifndef parent_node
 #define parent_node(node)       ((void)(node),0)
 #endif
@@ -52,4 +62,15 @@
 
 #endif  /* CONFIG_NUMA */
 
+#if !defined(CONFIG_NUMA) || !defined(CONFIG_HAVE_MEMORYLESS_NODES)
+
+#ifndef set_numa_mem
+#define set_numa_mem(node)
+#endif
+#ifndef set_cpu_numa_mem
+#define set_cpu_numa_mem(cpu, node)
+#endif
+
+#endif  /* !CONFIG_NUMA || !CONFIG_HAVE_MEMORYLESS_NODES */
+
 #endif /* _ASM_GENERIC_TOPOLOGY_H */
diff --git a/include/asm-generic/unistd.h b/include/asm-generic/unistd.h
index 6a0b30f78a62..b969770196c2 100644
--- a/include/asm-generic/unistd.h
+++ b/include/asm-generic/unistd.h
@@ -18,7 +18,7 @@
 #define __SYSCALL(x, y)
 #endif
 
-#if __BITS_PER_LONG == 32
+#if __BITS_PER_LONG == 32 || defined(__SYSCALL_COMPAT)
 #define __SC_3264(_nr, _32, _64) __SYSCALL(_nr, _32)
 #else
 #define __SC_3264(_nr, _32, _64) __SYSCALL(_nr, _64)
@@ -241,8 +241,13 @@ __SYSCALL(__NR_sync, sys_sync)
 __SYSCALL(__NR_fsync, sys_fsync)
 #define __NR_fdatasync 83
 __SYSCALL(__NR_fdatasync, sys_fdatasync)
+#ifdef __ARCH_WANT_SYNC_FILE_RANGE2
+#define __NR_sync_file_range2 84
+__SYSCALL(__NR_sync_file_range2, sys_sync_file_range2)
+#else
 #define __NR_sync_file_range 84
-__SYSCALL(__NR_sync_file_range, sys_sync_file_range) /* .long sys_sync_file_range2, */
+__SYSCALL(__NR_sync_file_range, sys_sync_file_range)
+#endif
 
 /* fs/timerfd.c */
 #define __NR_timerfd_create 85
@@ -580,7 +585,7 @@ __SYSCALL(__NR_execve, sys_execve)	/* .long sys_execve_wrapper */
 __SC_3264(__NR3264_mmap, sys_mmap2, sys_mmap)
 /* mm/fadvise.c */
 #define __NR3264_fadvise64 223
-__SC_3264(__NR3264_fadvise64, sys_fadvise64_64, sys_fadvise64)
+__SYSCALL(__NR3264_fadvise64, sys_fadvise64_64)
 
 /* mm/, CONFIG_MMU only */
 #ifndef __ARCH_NOMMU
@@ -627,8 +632,23 @@ __SYSCALL(__NR_accept4, sys_accept4)
 #define __NR_recvmmsg 243
 __SYSCALL(__NR_recvmmsg, sys_recvmmsg)
 
+/*
+ * Architectures may provide up to 16 syscalls of their own
+ * starting with this value.
+ */
+#define __NR_arch_specific_syscall 244
+
+#define __NR_wait4 260
+__SYSCALL(__NR_wait4, sys_wait4)
+#define __NR_prlimit64 261
+__SYSCALL(__NR_prlimit64, sys_prlimit64)
+#define __NR_fanotify_init 262
+__SYSCALL(__NR_fanotify_init, sys_fanotify_init)
+#define __NR_fanotify_mark 263
+__SYSCALL(__NR_fanotify_mark, sys_fanotify_mark)
+
 #undef __NR_syscalls
-#define __NR_syscalls 244
+#define __NR_syscalls 264
 
 /*
  * All syscalls below here should go away really,
@@ -694,7 +714,8 @@ __SYSCALL(__NR_signalfd, sys_signalfd)
 #define __NR_syscalls (__NR_signalfd+1)
 #endif /* __ARCH_WANT_SYSCALL_NO_FLAGS */
 
-#if __BITS_PER_LONG == 32 && defined(__ARCH_WANT_SYSCALL_OFF_T)
+#if (__BITS_PER_LONG == 32 || defined(__SYSCALL_COMPAT)) && \
+     defined(__ARCH_WANT_SYSCALL_OFF_T)
 #define __NR_sendfile 1046
 __SYSCALL(__NR_sendfile, sys_sendfile)
 #define __NR_ftruncate 1047
@@ -740,6 +761,7 @@ __SYSCALL(__NR_getpgrp, sys_getpgrp)
 __SYSCALL(__NR_pause, sys_pause)
 #define __NR_time 1062
 #define __ARCH_WANT_SYS_TIME
+#define __ARCH_WANT_COMPAT_SYS_TIME
 __SYSCALL(__NR_time, sys_time)
 #define __NR_utime 1063
 #define __ARCH_WANT_SYS_UTIME
@@ -763,8 +785,8 @@ __SYSCALL(__NR_epoll_wait, sys_epoll_wait)
 __SYSCALL(__NR_ustat, sys_ustat)
 #define __NR_vfork 1071
 __SYSCALL(__NR_vfork, sys_vfork)
-#define __NR_wait4 1072
-__SYSCALL(__NR_wait4, sys_wait4)
+#define __NR_oldwait4 1072
+__SYSCALL(__NR_oldwait4, sys_wait4)
 #define __NR_recv 1073
 __SYSCALL(__NR_recv, sys_recv)
 #define __NR_send 1074
@@ -801,7 +823,7 @@ __SYSCALL(__NR_fork, sys_ni_syscall)
  * Here we map the numbers so that both versions
  * use the same syscall table layout.
  */
-#if __BITS_PER_LONG == 64
+#if __BITS_PER_LONG == 64 && !defined(__SYSCALL_COMPAT)
 #define __NR_fcntl __NR3264_fcntl
 #define __NR_statfs __NR3264_statfs
 #define __NR_fstatfs __NR3264_fstatfs
@@ -848,6 +870,7 @@ __SYSCALL(__NR_fork, sys_ni_syscall)
 #endif
 #define __ARCH_WANT_SYS_RT_SIGACTION
 #define __ARCH_WANT_SYS_RT_SIGSUSPEND
+#define __ARCH_WANT_COMPAT_SYS_RT_SIGSUSPEND
 
 /*
  * "Conditional" syscalls
diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index 67e652068e0e..8a92a170fb7d 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -63,6 +63,12 @@
 /* Align . to a 8 byte boundary equals to maximum function alignment. */
 #define ALIGN_FUNCTION()  . = ALIGN(8)
 
+/*
+ * Align to a 32 byte boundary equal to the
+ * alignment gcc 4.5 uses for a struct
+ */
+#define STRUCT_ALIGN() . = ALIGN(32)
+
 /* The actual configuration determine if the init/exit sections
  * are handled as text/data or they can be discarded (which
  * often happens at runtime)
@@ -150,10 +156,6 @@
         CPU_KEEP(exit.data)                                             \
         MEM_KEEP(init.data)                                             \
         MEM_KEEP(exit.data)                                             \
-        . = ALIGN(8);                                                   \
-        VMLINUX_SYMBOL(__start___markers) = .;                          \
-        *(__markers)                                                    \
-        VMLINUX_SYMBOL(__stop___markers) = .;                           \
         . = ALIGN(32);                                                  \
         VMLINUX_SYMBOL(__start___tracepoints) = .;                      \
         *(__tracepoints)                                                \
@@ -166,7 +168,11 @@
         LIKELY_PROFILE()                                                \
         BRANCH_PROFILE()                                                \
         TRACE_PRINTKS()                                                 \
+                                                                        \
+        STRUCT_ALIGN();                                                 \
         FTRACE_EVENTS()                                                 \
+                                                                        \
+        STRUCT_ALIGN();                                                 \
         TRACE_SYSCALLS()
 
 /*
@@ -175,25 +181,25 @@
 #define NOSAVE_DATA                                                     \
         . = ALIGN(PAGE_SIZE);                                           \
         VMLINUX_SYMBOL(__nosave_begin) = .;                             \
-        *(.data.nosave)                                                 \
+        *(.data..nosave)                                                \
         . = ALIGN(PAGE_SIZE);                                           \
         VMLINUX_SYMBOL(__nosave_end) = .;
 
 #define PAGE_ALIGNED_DATA(page_align)                                   \
         . = ALIGN(page_align);                                          \
-        *(.data.page_aligned)
+        *(.data..page_aligned)
 
 #define READ_MOSTLY_DATA(align)                                         \
         . = ALIGN(align);                                               \
-        *(.data.read_mostly)
+        *(.data..read_mostly)
 
 #define CACHELINE_ALIGNED_DATA(align)                                   \
         . = ALIGN(align);                                               \
-        *(.data.cacheline_aligned)
+        *(.data..cacheline_aligned)
 
 #define INIT_TASK_DATA(align)                                           \
         . = ALIGN(align);                                               \
-        *(.data.init_task)
+        *(.data..init_task)
 
 /*
  * Read only Data
@@ -247,10 +253,10 @@
         }                                                               \
                                                                         \
         /* RapidIO route ops */                                         \
-        .rio_route        : AT(ADDR(.rio_route) - LOAD_OFFSET) {        \
-                VMLINUX_SYMBOL(__start_rio_route_ops) = .;              \
-                *(.rio_route_ops)                                       \
-                VMLINUX_SYMBOL(__end_rio_route_ops) = .;                \
+        .rio_ops        : AT(ADDR(.rio_ops) - LOAD_OFFSET) {            \
+                VMLINUX_SYMBOL(__start_rio_switch_ops) = .;             \
+                *(.rio_switch_ops)                                      \
+                VMLINUX_SYMBOL(__end_rio_switch_ops) = .;               \
         }                                                               \
                                                                         \
         TRACEDATA                                                       \
@@ -435,7 +441,7 @@
  */
 #define INIT_TASK_DATA_SECTION(align)                                   \
         . = ALIGN(align);                                               \
-        .data.init_task : {                                             \
+        .data..init_task :  AT(ADDR(.data..init_task) - LOAD_OFFSET) {  \
                 INIT_TASK_DATA(align)                                   \
         }
 
@@ -499,7 +505,7 @@
 #define BSS(bss_align)                                                  \
         . = ALIGN(bss_align);                                           \
         .bss : AT(ADDR(.bss) - LOAD_OFFSET) {                           \
-                *(.bss.page_aligned)                                    \
+                *(.bss..page_aligned)                                   \
                 *(.dynbss)                                              \
                 *(.bss)                                                 \
                 *(COMMON)                                               \
@@ -643,6 +649,7 @@
         EXIT_DATA                                                       \
         EXIT_CALL                                                       \
         *(.discard)                                                     \
+        *(.discard.*)                                                   \
         }
 
 /**
@@ -666,16 +673,16 @@
  */
 #define PERCPU_VADDR(vaddr, phdr)                                       \
         VMLINUX_SYMBOL(__per_cpu_load) = .;                             \
-        .data.percpu vaddr : AT(VMLINUX_SYMBOL(__per_cpu_load)          \
+        .data..percpu vaddr : AT(VMLINUX_SYMBOL(__per_cpu_load)         \
                                 - LOAD_OFFSET) {                        \
                 VMLINUX_SYMBOL(__per_cpu_start) = .;                    \
-                *(.data.percpu.first)                                   \
-                *(.data.percpu.page_aligned)                            \
-                *(.data.percpu)                                         \
-                *(.data.percpu.shared_aligned)                          \
+                *(.data..percpu..first)                                 \
+                *(.data..percpu..page_aligned)                          \
+                *(.data..percpu)                                        \
+                *(.data..percpu..shared_aligned)                        \
                 VMLINUX_SYMBOL(__per_cpu_end) = .;                      \
         } phdr                                                          \
-        . = VMLINUX_SYMBOL(__per_cpu_load) + SIZEOF(.data.percpu);
+        . = VMLINUX_SYMBOL(__per_cpu_load) + SIZEOF(.data..percpu);
 
 /**
  * PERCPU - define output section for percpu area, simple version
@@ -687,18 +694,18 @@
  *
  * This macro is equivalent to ALIGN(align); PERCPU_VADDR( , ) except
  * that __per_cpu_load is defined as a relative symbol against
- * .data.percpu which is required for relocatable x86_32
+ * .data..percpu which is required for relocatable x86_32
  * configuration.
  */
 #define PERCPU(align)                                                   \
         . = ALIGN(align);                                               \
-        .data.percpu    : AT(ADDR(.data.percpu) - LOAD_OFFSET) {        \
+        .data..percpu   : AT(ADDR(.data..percpu) - LOAD_OFFSET) {       \
                 VMLINUX_SYMBOL(__per_cpu_load) = .;                     \
                 VMLINUX_SYMBOL(__per_cpu_start) = .;                    \
-                *(.data.percpu.first)                                   \
-                *(.data.percpu.page_aligned)                            \
-                *(.data.percpu)                                         \
-                *(.data.percpu.shared_aligned)                          \
+                *(.data..percpu..first)                                 \
+                *(.data..percpu..page_aligned)                          \
+                *(.data..percpu)                                        \
+                *(.data..percpu..shared_aligned)                        \
                 VMLINUX_SYMBOL(__per_cpu_end) = .;                      \
         }