9 files changed, 192 insertions, 24 deletions

diff --git a/include/asm-generic/atomic.h b/include/asm-generic/atomic.h
index 058129e9b04c..e53347fbf1da 100644
--- a/include/asm-generic/atomic.h
+++ b/include/asm-generic/atomic.h
@@ -57,11 +57,11 @@ 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;
 }
@@ -78,11 +78,11 @@ 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;
 }
@@ -135,9 +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/fcntl.h b/include/asm-generic/fcntl.h
index fcd268ce0674..e3cbc38bdcc2 100644
--- a/include/asm-generic/fcntl.h
+++ b/include/asm-generic/fcntl.h
@@ -3,6 +3,14 @@
 
 #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
+ */
+
 #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 4f3d75e1ad39..c7376bf80b06 100644
--- a/include/asm-generic/gpio.h
+++ b/include/asm-generic/gpio.h
@@ -31,6 +31,7 @@ static inline int gpio_is_valid(int number)
 struct device;
 struct seq_file;
 struct module;
+struct device_node;
 
 /**
  * struct gpio_chip - abstract a GPIO controller
@@ -106,6 +107,17 @@ struct gpio_chip {
         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,
@@ -115,6 +127,9 @@ 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,
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/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/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/topology.h b/include/asm-generic/topology.h
index fd60700503c8..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
@@ -34,9 +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
@@ -55,4 +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 0dfd517e5ec9..e1898090f22c 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
@@ -626,11 +631,20 @@ __SYSCALL(__NR_perf_event_open, sys_perf_event_open)
 __SYSCALL(__NR_accept4, sys_accept4)
 #define __NR_recvmmsg 243
 __SYSCALL(__NR_recvmmsg, sys_recvmmsg)
-#define __NR_prlimit64 244
+
+/*
+ * 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)
 
 #undef __NR_syscalls
-#define __NR_syscalls 245
+#define __NR_syscalls 262
 
 /*
  * All syscalls below here should go away really,
@@ -696,7 +710,8 @@ __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
@@ -742,6 +757,7 @@ __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
@@ -765,8 +781,8 @@ __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
@@ -803,7 +819,7 @@ __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
@@ -850,6 +866,7 @@ __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 48c5299cbf26..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()
 
 /*
@@ -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)                                   \
         }
 
@@ -643,6 +649,7 @@
         EXIT_DATA                                                       \
         EXIT_CALL                                                       \
         *(.discard)                                                     \
+        *(.discard.*)                                                   \
         }
 
 /**