1 files changed, 99 insertions, 20 deletions

diff --git a/include/linux/sched.h b/include/linux/sched.h
index 49e617fa0f66..b0ad6f30679e 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -107,13 +107,25 @@ extern unsigned long nr_iowait(void);
 
 #include <asm/processor.h>
 
+/*
+ * Task state bitmask. NOTE! These bits are also
+ * encoded in fs/proc/array.c: get_task_state().
+ *
+ * We have two separate sets of flags: task->state
+ * is about runnability, while task->exit_state are
+ * about the task exiting. Confusing, but this way
+ * modifying one set can't modify the other one by
+ * mistake.
+ */
 #define TASK_RUNNING            0
 #define TASK_INTERRUPTIBLE      1
 #define TASK_UNINTERRUPTIBLE    2
 #define TASK_STOPPED            4
 #define TASK_TRACED             8
+/* in tsk->exit_state */
 #define EXIT_ZOMBIE             16
 #define EXIT_DEAD               32
+/* in tsk->state again */
 #define TASK_NONINTERACTIVE     64
 
 #define __set_task_state(tsk, state_value)              \
@@ -237,6 +249,36 @@ arch_get_unmapped_area_topdown(struct file *filp, unsigned long addr,
 extern void arch_unmap_area(struct mm_struct *, unsigned long);
 extern void arch_unmap_area_topdown(struct mm_struct *, unsigned long);
 
+#if NR_CPUS >= CONFIG_SPLIT_PTLOCK_CPUS
+/*
+ * The mm counters are not protected by its page_table_lock,
+ * so must be incremented atomically.
+ */
+#ifdef ATOMIC64_INIT
+#define set_mm_counter(mm, member, value) atomic64_set(&(mm)->_##member, value)
+#define get_mm_counter(mm, member) ((unsigned long)atomic64_read(&(mm)->_##member))
+#define add_mm_counter(mm, member, value) atomic64_add(value, &(mm)->_##member)
+#define inc_mm_counter(mm, member) atomic64_inc(&(mm)->_##member)
+#define dec_mm_counter(mm, member) atomic64_dec(&(mm)->_##member)
+typedef atomic64_t mm_counter_t;
+#else /* !ATOMIC64_INIT */
+/*
+ * The counters wrap back to 0 at 2^32 * PAGE_SIZE,
+ * that is, at 16TB if using 4kB page size.
+ */
+#define set_mm_counter(mm, member, value) atomic_set(&(mm)->_##member, value)
+#define get_mm_counter(mm, member) ((unsigned long)atomic_read(&(mm)->_##member))
+#define add_mm_counter(mm, member, value) atomic_add(value, &(mm)->_##member)
+#define inc_mm_counter(mm, member) atomic_inc(&(mm)->_##member)
+#define dec_mm_counter(mm, member) atomic_dec(&(mm)->_##member)
+typedef atomic_t mm_counter_t;
+#endif /* !ATOMIC64_INIT */
+
+#else  /* NR_CPUS < CONFIG_SPLIT_PTLOCK_CPUS */
+/*
+ * The mm counters are protected by its page_table_lock,
+ * so can be incremented directly.
+ */
 #define set_mm_counter(mm, member, value) (mm)->_##member = (value)
 #define get_mm_counter(mm, member) ((mm)->_##member)
 #define add_mm_counter(mm, member, value) (mm)->_##member += (value)
@@ -244,6 +286,20 @@ extern void arch_unmap_area_topdown(struct mm_struct *, unsigned long);
 #define dec_mm_counter(mm, member) (mm)->_##member--
 typedef unsigned long mm_counter_t;
 
+#endif /* NR_CPUS < CONFIG_SPLIT_PTLOCK_CPUS */
+
+#define get_mm_rss(mm)                                  \
+        (get_mm_counter(mm, file_rss) + get_mm_counter(mm, anon_rss))
+#define update_hiwater_rss(mm)  do {                    \
+        unsigned long _rss = get_mm_rss(mm);            \
+        if ((mm)->hiwater_rss < _rss)                   \
+                (mm)->hiwater_rss = _rss;               \
+} while (0)
+#define update_hiwater_vm(mm)   do {                    \
+        if ((mm)->hiwater_vm < (mm)->total_vm)          \
+                (mm)->hiwater_vm = (mm)->total_vm;      \
+} while (0)
+
 struct mm_struct {
         struct vm_area_struct * mmap;           /* list of VMAs */
         struct rb_root mm_rb;
@@ -267,15 +323,20 @@ struct mm_struct {
                                                  * by mmlist_lock
                                                  */
 
+        /* Special counters, in some configurations protected by the
+         * page_table_lock, in other configurations by being atomic.
+         */
+        mm_counter_t _file_rss;
+        mm_counter_t _anon_rss;
+
+        unsigned long hiwater_rss;      /* High-watermark of RSS usage */
+        unsigned long hiwater_vm;       /* High-water virtual memory usage */
+
+        unsigned long total_vm, locked_vm, shared_vm, exec_vm;
+        unsigned long stack_vm, reserved_vm, def_flags, nr_ptes;
         unsigned long start_code, end_code, start_data, end_data;
         unsigned long start_brk, brk, start_stack;
         unsigned long arg_start, arg_end, env_start, env_end;
-        unsigned long total_vm, locked_vm, shared_vm;
-        unsigned long exec_vm, stack_vm, reserved_vm, def_flags, nr_ptes;
-
-        /* Special counters protected by the page_table_lock */
-        mm_counter_t _rss;
-        mm_counter_t _anon_rss;
 
         unsigned long saved_auxv[AT_VECTOR_SIZE]; /* for /proc/PID/auxv */
 
@@ -296,11 +357,6 @@ struct mm_struct {
         /* aio bits */
         rwlock_t                ioctx_list_lock;
         struct kioctx           *ioctx_list;
-
-        struct kioctx           default_kioctx;
-
-        unsigned long hiwater_rss;      /* High-water RSS usage */
-        unsigned long hiwater_vm;       /* High-water virtual memory usage */
 };
 
 struct sighand_struct {
@@ -883,7 +939,7 @@ extern int set_cpus_allowed(task_t *p, cpumask_t new_mask);
 #else
 static inline int set_cpus_allowed(task_t *p, cpumask_t new_mask)
 {
-        if (!cpus_intersects(new_mask, cpu_online_map))
+        if (!cpu_isset(0, new_mask))
                 return -EINVAL;
         return 0;
 }
@@ -1006,6 +1062,7 @@ extern int force_sig_info(int, struct siginfo *, struct task_struct *);
 extern int __kill_pg_info(int sig, struct siginfo *info, pid_t pgrp);
 extern int kill_pg_info(int, struct siginfo *, pid_t);
 extern int kill_proc_info(int, struct siginfo *, pid_t);
+extern int kill_proc_info_as_uid(int, struct siginfo *, pid_t, uid_t, uid_t);
 extern void do_notify_parent(struct task_struct *, int);
 extern void force_sig(int, struct task_struct *);
 extern void force_sig_specific(int, struct task_struct *);
@@ -1026,6 +1083,11 @@ extern int do_sigaltstack(const stack_t __user *, stack_t __user *, unsigned lon
 #define SEND_SIG_PRIV   ((struct siginfo *) 1)
 #define SEND_SIG_FORCED ((struct siginfo *) 2)
 
+static inline int is_si_special(const struct siginfo *info)
+{
+        return info <= SEND_SIG_FORCED;
+}
+
 /* True if we are on the alternate signal stack.  */
 
 static inline int on_sig_stack(unsigned long sp)
@@ -1153,7 +1215,7 @@ extern void unhash_process(struct task_struct *p);
 /*
  * Protects ->fs, ->files, ->mm, ->ptrace, ->group_info, ->comm, keyring
  * subscriptions and synchronises with wait4().  Also used in procfs.  Also
- * pins the final release of task.io_context.
+ * pins the final release of task.io_context.  Also protects ->cpuset.
  *
  * Nests both inside and outside of read_lock(&tasklist_lock).
  * It must not be nested with write_lock_irq(&tasklist_lock),
@@ -1169,32 +1231,49 @@ static inline void task_unlock(struct task_struct *p)
         spin_unlock(&p->alloc_lock);
 }
 
+#ifndef __HAVE_THREAD_FUNCTIONS
+
+#define task_thread_info(task) (task)->thread_info
+
+static inline void setup_thread_stack(struct task_struct *p, struct task_struct *org)
+{
+        *task_thread_info(p) = *task_thread_info(org);
+        task_thread_info(p)->task = p;
+}
+
+static inline unsigned long *end_of_stack(struct task_struct *p)
+{
+        return (unsigned long *)(p->thread_info + 1);
+}
+
+#endif
+
 /* set thread flags in other task's structures
  * - see asm/thread_info.h for TIF_xxxx flags available
  */
 static inline void set_tsk_thread_flag(struct task_struct *tsk, int flag)
 {
-        set_ti_thread_flag(tsk->thread_info,flag);
+        set_ti_thread_flag(task_thread_info(tsk), flag);
 }
 
 static inline void clear_tsk_thread_flag(struct task_struct *tsk, int flag)
 {
-        clear_ti_thread_flag(tsk->thread_info,flag);
+        clear_ti_thread_flag(task_thread_info(tsk), flag);
 }
 
 static inline int test_and_set_tsk_thread_flag(struct task_struct *tsk, int flag)
 {
-        return test_and_set_ti_thread_flag(tsk->thread_info,flag);
+        return test_and_set_ti_thread_flag(task_thread_info(tsk), flag);
 }
 
 static inline int test_and_clear_tsk_thread_flag(struct task_struct *tsk, int flag)
 {
-        return test_and_clear_ti_thread_flag(tsk->thread_info,flag);
+        return test_and_clear_ti_thread_flag(task_thread_info(tsk), flag);
 }
 
 static inline int test_tsk_thread_flag(struct task_struct *tsk, int flag)
 {
-        return test_ti_thread_flag(tsk->thread_info,flag);
+        return test_ti_thread_flag(task_thread_info(tsk), flag);
 }
 
 static inline void set_tsk_need_resched(struct task_struct *tsk)
@@ -1265,12 +1344,12 @@ extern void signal_wake_up(struct task_struct *t, int resume_stopped);
 
 static inline unsigned int task_cpu(const struct task_struct *p)
 {
-        return p->thread_info->cpu;
+        return task_thread_info(p)->cpu;
 }
 
 static inline void set_task_cpu(struct task_struct *p, unsigned int cpu)
 {
-        p->thread_info->cpu = cpu;
+        task_thread_info(p)->cpu = cpu;
 }
 
 #else