7 files changed, 318 insertions, 34 deletions

diff --git a/kernel/Makefile b/kernel/Makefile
index 05c8003718ee..6c5f081132a4 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -8,7 +8,7 @@ obj-y     = sched.o fork.o exec_domain.o panic.o printk.o profile.o \
             signal.o sys.o kmod.o workqueue.o pid.o \
             rcupdate.o extable.o params.o posix-timers.o \
             kthread.o wait.o kfifo.o sys_ni.o posix-cpu-timers.o mutex.o \
-            hrtimer.o rwsem.o nsproxy.o srcu.o \
+            hrtimer.o rwsem.o nsproxy.o srcu.o semaphore.o \
             notifier.o ksysfs.o pm_qos_params.o
 
 obj-$(CONFIG_SYSCTL) += sysctl_check.o
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 2727f9238359..6d8de051382b 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -1722,7 +1722,12 @@ void cgroup_enable_task_cg_lists(void)
         use_task_css_set_links = 1;
         do_each_thread(g, p) {
                 task_lock(p);
-                if (list_empty(&p->cg_list))
+                /*
+                 * We should check if the process is exiting, otherwise
+                 * it will race with cgroup_exit() in that the list
+                 * entry won't be deleted though the process has exited.
+                 */
+                if (!(p->flags & PF_EXITING) && list_empty(&p->cg_list))
                         list_add(&p->cg_list, &p->cgroups->tasks);
                 task_unlock(p);
         } while_each_thread(g, p);
diff --git a/kernel/semaphore.c b/kernel/semaphore.c
new file mode 100644
index 000000000000..5c2942e768cd
--- /dev/null
+++ b/kernel/semaphore.c
@@ -0,0 +1,264 @@
+/*
+ * Copyright (c) 2008 Intel Corporation
+ * Author: Matthew Wilcox <willy@linux.intel.com>
+ *
+ * Distributed under the terms of the GNU GPL, version 2
+ *
+ * This file implements counting semaphores.
+ * A counting semaphore may be acquired 'n' times before sleeping.
+ * See mutex.c for single-acquisition sleeping locks which enforce
+ * rules which allow code to be debugged more easily.
+ */
+
+/*
+ * Some notes on the implementation:
+ *
+ * The spinlock controls access to the other members of the semaphore.
+ * down_trylock() and up() can be called from interrupt context, so we
+ * have to disable interrupts when taking the lock.  It turns out various
+ * parts of the kernel expect to be able to use down() on a semaphore in
+ * interrupt context when they know it will succeed, so we have to use
+ * irqsave variants for down(), down_interruptible() and down_killable()
+ * too.
+ *
+ * The ->count variable represents how many more tasks can acquire this
+ * semaphore.  If it's zero, there may be tasks waiting on the wait_list.
+ */
+
+#include <linux/compiler.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/sched.h>
+#include <linux/semaphore.h>
+#include <linux/spinlock.h>
+
+static noinline void __down(struct semaphore *sem);
+static noinline int __down_interruptible(struct semaphore *sem);
+static noinline int __down_killable(struct semaphore *sem);
+static noinline int __down_timeout(struct semaphore *sem, long jiffies);
+static noinline void __up(struct semaphore *sem);
+
+/**
+ * down - acquire the semaphore
+ * @sem: the semaphore to be acquired
+ *
+ * Acquires the semaphore.  If no more tasks are allowed to acquire the
+ * semaphore, calling this function will put the task to sleep until the
+ * semaphore is released.
+ *
+ * Use of this function is deprecated, please use down_interruptible() or
+ * down_killable() instead.
+ */
+void down(struct semaphore *sem)
+{
+        unsigned long flags;
+
+        spin_lock_irqsave(&sem->lock, flags);
+        if (likely(sem->count > 0))
+                sem->count--;
+        else
+                __down(sem);
+        spin_unlock_irqrestore(&sem->lock, flags);
+}
+EXPORT_SYMBOL(down);
+
+/**
+ * down_interruptible - acquire the semaphore unless interrupted
+ * @sem: the semaphore to be acquired
+ *
+ * Attempts to acquire the semaphore.  If no more tasks are allowed to
+ * acquire the semaphore, calling this function will put the task to sleep.
+ * If the sleep is interrupted by a signal, this function will return -EINTR.
+ * If the semaphore is successfully acquired, this function returns 0.
+ */
+int down_interruptible(struct semaphore *sem)
+{
+        unsigned long flags;
+        int result = 0;
+
+        spin_lock_irqsave(&sem->lock, flags);
+        if (likely(sem->count > 0))
+                sem->count--;
+        else
+                result = __down_interruptible(sem);
+        spin_unlock_irqrestore(&sem->lock, flags);
+
+        return result;
+}
+EXPORT_SYMBOL(down_interruptible);
+
+/**
+ * down_killable - acquire the semaphore unless killed
+ * @sem: the semaphore to be acquired
+ *
+ * Attempts to acquire the semaphore.  If no more tasks are allowed to
+ * acquire the semaphore, calling this function will put the task to sleep.
+ * If the sleep is interrupted by a fatal signal, this function will return
+ * -EINTR.  If the semaphore is successfully acquired, this function returns
+ * 0.
+ */
+int down_killable(struct semaphore *sem)
+{
+        unsigned long flags;
+        int result = 0;
+
+        spin_lock_irqsave(&sem->lock, flags);
+        if (likely(sem->count > 0))
+                sem->count--;
+        else
+                result = __down_killable(sem);
+        spin_unlock_irqrestore(&sem->lock, flags);
+
+        return result;
+}
+EXPORT_SYMBOL(down_killable);
+
+/**
+ * down_trylock - try to acquire the semaphore, without waiting
+ * @sem: the semaphore to be acquired
+ *
+ * Try to acquire the semaphore atomically.  Returns 0 if the mutex has
+ * been acquired successfully or 1 if it it cannot be acquired.
+ *
+ * NOTE: This return value is inverted from both spin_trylock and
+ * mutex_trylock!  Be careful about this when converting code.
+ *
+ * Unlike mutex_trylock, this function can be used from interrupt context,
+ * and the semaphore can be released by any task or interrupt.
+ */
+int down_trylock(struct semaphore *sem)
+{
+        unsigned long flags;
+        int count;
+
+        spin_lock_irqsave(&sem->lock, flags);
+        count = sem->count - 1;
+        if (likely(count >= 0))
+                sem->count = count;
+        spin_unlock_irqrestore(&sem->lock, flags);
+
+        return (count < 0);
+}
+EXPORT_SYMBOL(down_trylock);
+
+/**
+ * down_timeout - acquire the semaphore within a specified time
+ * @sem: the semaphore to be acquired
+ * @jiffies: how long to wait before failing
+ *
+ * Attempts to acquire the semaphore.  If no more tasks are allowed to
+ * acquire the semaphore, calling this function will put the task to sleep.
+ * If the semaphore is not released within the specified number of jiffies,
+ * this function returns -ETIME.  It returns 0 if the semaphore was acquired.
+ */
+int down_timeout(struct semaphore *sem, long jiffies)
+{
+        unsigned long flags;
+        int result = 0;
+
+        spin_lock_irqsave(&sem->lock, flags);
+        if (likely(sem->count > 0))
+                sem->count--;
+        else
+                result = __down_timeout(sem, jiffies);
+        spin_unlock_irqrestore(&sem->lock, flags);
+
+        return result;
+}
+EXPORT_SYMBOL(down_timeout);
+
+/**
+ * up - release the semaphore
+ * @sem: the semaphore to release
+ *
+ * Release the semaphore.  Unlike mutexes, up() may be called from any
+ * context and even by tasks which have never called down().
+ */
+void up(struct semaphore *sem)
+{
+        unsigned long flags;
+
+        spin_lock_irqsave(&sem->lock, flags);
+        if (likely(list_empty(&sem->wait_list)))
+                sem->count++;
+        else
+                __up(sem);
+        spin_unlock_irqrestore(&sem->lock, flags);
+}
+EXPORT_SYMBOL(up);
+
+/* Functions for the contended case */
+
+struct semaphore_waiter {
+        struct list_head list;
+        struct task_struct *task;
+        int up;
+};
+
+/*
+ * Because this function is inlined, the 'state' parameter will be
+ * constant, and thus optimised away by the compiler.  Likewise the
+ * 'timeout' parameter for the cases without timeouts.
+ */
+static inline int __sched __down_common(struct semaphore *sem, long state,
+                                                                long timeout)
+{
+        struct task_struct *task = current;
+        struct semaphore_waiter waiter;
+
+        list_add_tail(&waiter.list, &sem->wait_list);
+        waiter.task = task;
+        waiter.up = 0;
+
+        for (;;) {
+                if (state == TASK_INTERRUPTIBLE && signal_pending(task))
+                        goto interrupted;
+                if (state == TASK_KILLABLE && fatal_signal_pending(task))
+                        goto interrupted;
+                if (timeout <= 0)
+                        goto timed_out;
+                __set_task_state(task, state);
+                spin_unlock_irq(&sem->lock);
+                timeout = schedule_timeout(timeout);
+                spin_lock_irq(&sem->lock);
+                if (waiter.up)
+                        return 0;
+        }
+
+ timed_out:
+        list_del(&waiter.list);
+        return -ETIME;
+
+ interrupted:
+        list_del(&waiter.list);
+        return -EINTR;
+}
+
+static noinline void __sched __down(struct semaphore *sem)
+{
+        __down_common(sem, TASK_UNINTERRUPTIBLE, MAX_SCHEDULE_TIMEOUT);
+}
+
+static noinline int __sched __down_interruptible(struct semaphore *sem)
+{
+        return __down_common(sem, TASK_INTERRUPTIBLE, MAX_SCHEDULE_TIMEOUT);
+}
+
+static noinline int __sched __down_killable(struct semaphore *sem)
+{
+        return __down_common(sem, TASK_KILLABLE, MAX_SCHEDULE_TIMEOUT);
+}
+
+static noinline int __sched __down_timeout(struct semaphore *sem, long jiffies)
+{
+        return __down_common(sem, TASK_UNINTERRUPTIBLE, jiffies);
+}
+
+static noinline void __sched __up(struct semaphore *sem)
+{
+        struct semaphore_waiter *waiter = list_first_entry(&sem->wait_list,
+                                                struct semaphore_waiter, list);
+        list_del(&waiter->list);
+        waiter->up = 1;
+        wake_up_process(waiter->task);
+}
diff --git a/kernel/signal.c b/kernel/signal.c
index 6af1210092c3..cc8303cd093d 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -1757,6 +1757,45 @@ static int do_signal_stop(int signr)
         return 1;
 }
 
+static int ptrace_signal(int signr, siginfo_t *info,
+                         struct pt_regs *regs, void *cookie)
+{
+        if (!(current->ptrace & PT_PTRACED))
+                return signr;
+
+        ptrace_signal_deliver(regs, cookie);
+
+        /* Let the debugger run.  */
+        ptrace_stop(signr, 0, info);
+
+        /* We're back.  Did the debugger cancel the sig?  */
+        signr = current->exit_code;
+        if (signr == 0)
+                return signr;
+
+        current->exit_code = 0;
+
+        /* Update the siginfo structure if the signal has
+           changed.  If the debugger wanted something
+           specific in the siginfo structure then it should
+           have updated *info via PTRACE_SETSIGINFO.  */
+        if (signr != info->si_signo) {
+                info->si_signo = signr;
+                info->si_errno = 0;
+                info->si_code = SI_USER;
+                info->si_pid = task_pid_vnr(current->parent);
+                info->si_uid = current->parent->uid;
+        }
+
+        /* If the (new) signal is now blocked, requeue it.  */
+        if (sigismember(&current->blocked, signr)) {
+                specific_send_sig_info(signr, info, current);
+                signr = 0;
+        }
+
+        return signr;
+}
+
 int get_signal_to_deliver(siginfo_t *info, struct k_sigaction *return_ka,
                           struct pt_regs *regs, void *cookie)
 {
@@ -1785,36 +1824,10 @@ relock:
                 if (!signr)
                         break; /* will return 0 */
 
-                if ((current->ptrace & PT_PTRACED) && signr != SIGKILL) {
-                        ptrace_signal_deliver(regs, cookie);
-
-                        /* Let the debugger run.  */
-                        ptrace_stop(signr, 0, info);
-
-                        /* We're back.  Did the debugger cancel the sig?  */
-                        signr = current->exit_code;
-                        if (signr == 0)
-                                continue;
-
-                        current->exit_code = 0;
-
-                        /* Update the siginfo structure if the signal has
-                           changed.  If the debugger wanted something
-                           specific in the siginfo structure then it should
-                           have updated *info via PTRACE_SETSIGINFO.  */
-                        if (signr != info->si_signo) {
-                                info->si_signo = signr;
-                                info->si_errno = 0;
-                                info->si_code = SI_USER;
-                                info->si_pid = task_pid_vnr(current->parent);
-                                info->si_uid = current->parent->uid;
-                        }
-
-                        /* If the (new) signal is now blocked, requeue it.  */
-                        if (sigismember(&current->blocked, signr)) {
-                                specific_send_sig_info(signr, info, current);
+                if (signr != SIGKILL) {
+                        signr = ptrace_signal(signr, info, regs, cookie);
+                        if (!signr)
                                 continue;
-                        }
                 }
 
                 ka = &current->sighand->action[signr-1];
diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c
index e1bd50cbbf5d..fdfa0c745bb6 100644
--- a/kernel/time/tick-broadcast.c
+++ b/kernel/time/tick-broadcast.c
@@ -14,7 +14,7 @@
 #include <linux/cpu.h>
 #include <linux/err.h>
 #include <linux/hrtimer.h>
-#include <linux/irq.h>
+#include <linux/interrupt.h>
 #include <linux/percpu.h>
 #include <linux/profile.h>
 #include <linux/sched.h>
diff --git a/kernel/time/tick-common.c b/kernel/time/tick-common.c
index 1bea399a9ef0..4f3886562b8c 100644
--- a/kernel/time/tick-common.c
+++ b/kernel/time/tick-common.c
@@ -14,12 +14,14 @@
 #include <linux/cpu.h>
 #include <linux/err.h>
 #include <linux/hrtimer.h>
-#include <linux/irq.h>
+#include <linux/interrupt.h>
 #include <linux/percpu.h>
 #include <linux/profile.h>
 #include <linux/sched.h>
 #include <linux/tick.h>
 
+#include <asm/irq_regs.h>
+
 #include "tick-internal.h"
 
 /*
diff --git a/kernel/time/tick-oneshot.c b/kernel/time/tick-oneshot.c
index 0258d3115d54..450c04935b66 100644
--- a/kernel/time/tick-oneshot.c
+++ b/kernel/time/tick-oneshot.c
@@ -14,7 +14,7 @@
 #include <linux/cpu.h>
 #include <linux/err.h>
 #include <linux/hrtimer.h>
-#include <linux/irq.h>
+#include <linux/interrupt.h>
 #include <linux/percpu.h>
 #include <linux/profile.h>
 #include <linux/sched.h>