[PATCH] pi-futex: rt mutex core

Core functions for the rt-mutex subsystem.
Signed-off-by: Ingo Molnar <mingo@elte.hu>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Arjan van de Ven <arjan@linux.intel.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

include/linux/init_task.h

@@ -124,6 +124,7 @@ extern struct group_info init_groups;
 	.cpu_timers	= INIT_CPU_TIMERS(tsk.cpu_timers),		\
 	.fs_excl	= ATOMIC_INIT(0),				\
 	.pi_lock	= SPIN_LOCK_UNLOCKED,				\
+	INIT_RT_MUTEXES(tsk)						\
 }
 
 

include/linux/rtmutex.h

+/*
+ * RT Mutexes: blocking mutual exclusion locks with PI support
+ *
+ * started by Ingo Molnar and Thomas Gleixner:
+ *
+ *  Copyright (C) 2004-2006 Red Hat, Inc., Ingo Molnar <mingo@redhat.com>
+ *  Copyright (C) 2006, Timesys Corp., Thomas Gleixner <tglx@timesys.com>
+ *
+ * This file contains the public data structure and API definitions.
+ */
+
+#ifndef __LINUX_RT_MUTEX_H
+#define __LINUX_RT_MUTEX_H
+
+#include <linux/linkage.h>
+#include <linux/plist.h>
+#include <linux/spinlock_types.h>
+
+/*
+ * The rt_mutex structure
+ *
+ * @wait_lock:	spinlock to protect the structure
+ * @wait_list:	pilist head to enqueue waiters in priority order
+ * @owner:	the mutex owner
+ */
+struct rt_mutex {
+	spinlock_t		wait_lock;
+	struct plist_head	wait_list;
+	struct task_struct	*owner;
+#ifdef CONFIG_DEBUG_RT_MUTEXES
+	int			save_state;
+	struct list_head	held_list_entry;
+	unsigned long		acquire_ip;
+	const char 		*name, *file;
+	int			line;
+	void			*magic;
+#endif
+};
+
+struct rt_mutex_waiter;
+struct hrtimer_sleeper;
+
+#ifdef CONFIG_DEBUG_RT_MUTEXES
+# define __DEBUG_RT_MUTEX_INITIALIZER(mutexname) \
+	, .name = #mutexname, .file = __FILE__, .line = __LINE__
+# define rt_mutex_init(mutex)			__rt_mutex_init(mutex, __FUNCTION__)
+ extern void rt_mutex_debug_task_free(struct task_struct *tsk);
+#else
+# define __DEBUG_RT_MUTEX_INITIALIZER(mutexname)
+# define rt_mutex_init(mutex)			__rt_mutex_init(mutex, NULL)
+# define rt_mutex_debug_task_free(t)		do { } while (0)
+#endif
+
+#define __RT_MUTEX_INITIALIZER(mutexname) \
+	{ .wait_lock = SPIN_LOCK_UNLOCKED \
+	, .wait_list = PLIST_HEAD_INIT(mutexname.wait_list, mutexname.wait_lock) \
+	, .owner = NULL \
+	__DEBUG_RT_MUTEX_INITIALIZER(mutexname)}
+
+#define DEFINE_RT_MUTEX(mutexname) \
+	struct rt_mutex mutexname = __RT_MUTEX_INITIALIZER(mutexname)
+
+/***
+ * rt_mutex_is_locked - is the mutex locked
+ * @lock: the mutex to be queried
+ *
+ * Returns 1 if the mutex is locked, 0 if unlocked.
+ */
+static inline int rt_mutex_is_locked(struct rt_mutex *lock)
+{
+	return lock->owner != NULL;
+}
+
+extern void __rt_mutex_init(struct rt_mutex *lock, const char *name);
+extern void rt_mutex_destroy(struct rt_mutex *lock);
+
+extern void rt_mutex_lock(struct rt_mutex *lock);
+extern int rt_mutex_lock_interruptible(struct rt_mutex *lock,
+						int detect_deadlock);
+extern int rt_mutex_timed_lock(struct rt_mutex *lock,
+					struct hrtimer_sleeper *timeout,
+					int detect_deadlock);
+
+extern int rt_mutex_trylock(struct rt_mutex *lock);
+
+extern void rt_mutex_unlock(struct rt_mutex *lock);
+
+#ifdef CONFIG_DEBUG_RT_MUTEXES
+# define INIT_RT_MUTEX_DEBUG(tsk)					\
+	.held_list_head	= LIST_HEAD_INIT(tsk.held_list_head),		\
+	.held_list_lock	= SPIN_LOCK_UNLOCKED
+#else
+# define INIT_RT_MUTEX_DEBUG(tsk)
+#endif
+
+#ifdef CONFIG_RT_MUTEXES
+# define INIT_RT_MUTEXES(tsk)						\
+	.pi_waiters	= PLIST_HEAD_INIT(tsk.pi_waiters, tsk.pi_lock),	\
+	INIT_RT_MUTEX_DEBUG(tsk)
+#else
+# define INIT_RT_MUTEXES(tsk)
+#endif
+
+#endif

include/linux/sched.h

@@ -73,6 +73,7 @@ struct sched_param {
 #include <linux/seccomp.h>
 #include <linux/rcupdate.h>
 #include <linux/futex.h>
+#include <linux/rtmutex.h>
 
 #include <linux/time.h>
 #include <linux/param.h>
@@ -858,6 +859,17 @@ struct task_struct {
 	/* Protection of the PI data structures: */
 	spinlock_t pi_lock;
 
+#ifdef CONFIG_RT_MUTEXES
+	/* PI waiters blocked on a rt_mutex held by this task */
+	struct plist_head pi_waiters;
+	/* Deadlock detection and priority inheritance handling */
+	struct rt_mutex_waiter *pi_blocked_on;
+# ifdef CONFIG_DEBUG_RT_MUTEXES
+	spinlock_t held_list_lock;
+	struct list_head held_list_head;
+# endif
+#endif
+
 #ifdef CONFIG_DEBUG_MUTEXES
 	/* mutex deadlock detection */
 	struct mutex_waiter *blocked_on;

include/linux/sysctl.h

@@ -149,6 +149,7 @@ enum
 	KERN_ACPI_VIDEO_FLAGS=71, /* int: flags for setting up video after ACPI sleep */
 	KERN_IA64_UNALIGNED=72, /* int: ia64 unaligned userland trap enable */
 	KERN_COMPAT_LOG=73,	/* int: print compat layer  messages */
+	KERN_MAX_LOCK_DEPTH=74,
 };
 
 

init/Kconfig

@@ -339,9 +339,14 @@ config BASE_FULL
 	  kernel data structures. This saves memory on small machines,
 	  but may reduce performance.
 
+config RT_MUTEXES
+	boolean
+	select PLIST
+
 config FUTEX
 	bool "Enable futex support" if EMBEDDED
 	default y
+	select RT_MUTEXES
 	help
 	  Disabling this option will cause the kernel to be built without
 	  support for "fast userspace mutexes".  The resulting kernel may not

kernel/Makefile

@@ -16,6 +16,7 @@ obj-$(CONFIG_FUTEX) += futex.o
 ifeq ($(CONFIG_COMPAT),y)
 obj-$(CONFIG_FUTEX) += futex_compat.o
 endif
+obj-$(CONFIG_RT_MUTEXES) += rtmutex.o
 obj-$(CONFIG_GENERIC_ISA_DMA) += dma.o
 obj-$(CONFIG_SMP) += cpu.o spinlock.o
 obj-$(CONFIG_DEBUG_SPINLOCK) += spinlock.o

kernel/fork.c

@@ -104,6 +104,7 @@ static kmem_cache_t *mm_cachep;
 void free_task(struct task_struct *tsk)
 {
 	free_thread_info(tsk->thread_info);
+	rt_mutex_debug_task_free(tsk);
 	free_task_struct(tsk);
 }
 EXPORT_SYMBOL(free_task);
@@ -913,6 +914,19 @@ asmlinkage long sys_set_tid_address(int __user *tidptr)
 	return current->pid;
 }
 
+static inline void rt_mutex_init_task(struct task_struct *p)
+{
+#ifdef CONFIG_RT_MUTEXES
+	spin_lock_init(&p->pi_lock);
+	plist_head_init(&p->pi_waiters, &p->pi_lock);
+	p->pi_blocked_on = NULL;
+# ifdef CONFIG_DEBUG_RT_MUTEXES
+	spin_lock_init(&p->held_list_lock);
+	INIT_LIST_HEAD(&p->held_list_head);
+# endif
+#endif
+}
+
 /*
  * This creates a new process as a copy of the old one,
  * but does not actually start it yet.
@@ -1034,6 +1048,8 @@ static task_t *copy_process(unsigned long clone_flags,
 	mpol_fix_fork_child_flag(p);
 #endif
 
+	rt_mutex_init_task(p);
+
 #ifdef CONFIG_DEBUG_MUTEXES
 	p->blocked_on = NULL; /* not blocked yet */
 #endif

kernel/rtmutex.h

+/*
+ * RT-Mutexes: blocking mutual exclusion locks with PI support
+ *
+ * started by Ingo Molnar and Thomas Gleixner:
+ *
+ *  Copyright (C) 2004-2006 Red Hat, Inc., Ingo Molnar <mingo@redhat.com>
+ *  Copyright (C) 2006, Timesys Corp., Thomas Gleixner <tglx@timesys.com>
+ *
+ * This file contains macros used solely by rtmutex.c.
+ * Non-debug version.
+ */
+
+#define __IP_DECL__
+#define __IP__
+#define __RET_IP__
+#define rt_mutex_deadlock_check(l)			(0)
+#define rt_mutex_deadlock_account_lock(m, t)		do { } while (0)
+#define rt_mutex_deadlock_account_unlock(l)		do { } while (0)
+#define debug_rt_mutex_init_waiter(w)			do { } while (0)
+#define debug_rt_mutex_free_waiter(w)			do { } while (0)
+#define debug_rt_mutex_lock(l)				do { } while (0)
+#define debug_rt_mutex_proxy_lock(l,p)			do { } while (0)
+#define debug_rt_mutex_proxy_unlock(l)			do { } while (0)
+#define debug_rt_mutex_unlock(l)			do { } while (0)
+#define debug_rt_mutex_init(m, n)			do { } while (0)
+#define debug_rt_mutex_deadlock(d, a ,l)		do { } while (0)
+#define debug_rt_mutex_print_deadlock(w)		do { } while (0)
+#define debug_rt_mutex_detect_deadlock(w,d)		(d)
+#define debug_rt_mutex_reset_waiter(w)			do { } while (0)

kernel/rtmutex_common.h

+/*
+ * RT Mutexes: blocking mutual exclusion locks with PI support
+ *
+ * started by Ingo Molnar and Thomas Gleixner:
+ *
+ *  Copyright (C) 2004-2006 Red Hat, Inc., Ingo Molnar <mingo@redhat.com>
+ *  Copyright (C) 2006, Timesys Corp., Thomas Gleixner <tglx@timesys.com>
+ *
+ * This file contains the private data structure and API definitions.
+ */
+
+#ifndef __KERNEL_RTMUTEX_COMMON_H
+#define __KERNEL_RTMUTEX_COMMON_H
+
+#include <linux/rtmutex.h>
+
+/*
+ * This is the control structure for tasks blocked on a rt_mutex,
+ * which is allocated on the kernel stack on of the blocked task.
+ *
+ * @list_entry:		pi node to enqueue into the mutex waiters list
+ * @pi_list_entry:	pi node to enqueue into the mutex owner waiters list
+ * @task:		task reference to the blocked task
+ */
+struct rt_mutex_waiter {
+	struct plist_node	list_entry;
+	struct plist_node	pi_list_entry;
+	struct task_struct	*task;
+	struct rt_mutex		*lock;
+#ifdef CONFIG_DEBUG_RT_MUTEXES
+	unsigned long		ip;
+	pid_t			deadlock_task_pid;
+	struct rt_mutex		*deadlock_lock;
+#endif
+};
+
+/*
+ * Various helpers to access the waiters-plist:
+ */
+static inline int rt_mutex_has_waiters(struct rt_mutex *lock)
+{
+	return !plist_head_empty(&lock->wait_list);
+}
+
+static inline struct rt_mutex_waiter *
+rt_mutex_top_waiter(struct rt_mutex *lock)
+{
+	struct rt_mutex_waiter *w;
+
+	w = plist_first_entry(&lock->wait_list, struct rt_mutex_waiter,
+			       list_entry);
+	BUG_ON(w->lock != lock);
+
+	return w;
+}
+
+static inline int task_has_pi_waiters(struct task_struct *p)
+{
+	return !plist_head_empty(&p->pi_waiters);
+}
+
+static inline struct rt_mutex_waiter *
+task_top_pi_waiter(struct task_struct *p)
+{
+	return plist_first_entry(&p->pi_waiters, struct rt_mutex_waiter,
+				  pi_list_entry);
+}
+
+/*
+ * lock->owner state tracking:
+ */
+#define RT_MUTEX_OWNER_PENDING	1UL
+#define RT_MUTEX_HAS_WAITERS	2UL
+#define RT_MUTEX_OWNER_MASKALL	3UL
+
+static inline struct task_struct *rt_mutex_owner(struct rt_mutex *lock)
+{
+	return (struct task_struct *)
+		((unsigned long)lock->owner & ~RT_MUTEX_OWNER_MASKALL);
+}
+
+static inline struct task_struct *rt_mutex_real_owner(struct rt_mutex *lock)
+{
+ 	return (struct task_struct *)
+		((unsigned long)lock->owner & ~RT_MUTEX_HAS_WAITERS);
+}
+
+static inline unsigned long rt_mutex_owner_pending(struct rt_mutex *lock)
+{
+	return (unsigned long)lock->owner & RT_MUTEX_OWNER_PENDING;
+}
+
+#endif

kernel/sysctl.c

@@ -133,6 +133,10 @@ extern int acct_parm[];
 extern int no_unaligned_warning;
 #endif
 
+#ifdef CONFIG_RT_MUTEXES
+extern int max_lock_depth;
+#endif
+
 static int parse_table(int __user *, int, void __user *, size_t __user *, void __user *, size_t,
 		       ctl_table *, void **);
 static int proc_doutsstring(ctl_table *table, int write, struct file *filp,
@@ -688,6 +692,17 @@ static ctl_table kern_table[] = {
 		.proc_handler	= &proc_dointvec,
 	},
 #endif
+#ifdef CONFIG_RT_MUTEXES
+	{
+		.ctl_name	= KERN_MAX_LOCK_DEPTH,
+		.procname	= "max_lock_depth",
+		.data		= &max_lock_depth,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec,
+	},
+#endif
+
 	{ .ctl_name = 0 }
 };