Automerge with /usr/src/ntfs-2.6.git.

15 files changed, 718 insertions, 279 deletions

diff --git a/kernel/Kconfig.hz b/kernel/Kconfig.hz
new file mode 100644
index 00000000000..248e1c396f8
--- /dev/null
+++ b/kernel/Kconfig.hz
@@ -0,0 +1,46 @@
+#
+# Timer Interrupt Frequency Configuration
+#
+
+choice
+	prompt "Timer frequency"
+	default HZ_250
+	help
+	 Allows the configuration of the timer frequency. It is customary
+	 to have the timer interrupt run at 1000 HZ but 100 HZ may be more
+	 beneficial for servers and NUMA systems that do not need to have
+	 a fast response for user interaction and that may experience bus
+	 contention and cacheline bounces as a result of timer interrupts.
+	 Note that the timer interrupt occurs on each processor in an SMP
+	 environment leading to NR_CPUS * HZ number of timer interrupts
+	 per second.
+
+
+	config HZ_100
+		bool "100 HZ"
+	help
+	  100 HZ is a typical choice for servers, SMP and NUMA systems
+	  with lots of processors that may show reduced performance if
+	  too many timer interrupts are occurring.
+
+	config HZ_250
+		bool "250 HZ"
+	help
+	 250 HZ is a good compromise choice allowing server performance
+	 while also showing good interactive responsiveness even
+	 on SMP and NUMA systems.
+
+	config HZ_1000
+		bool "1000 HZ"
+	help
+	 1000 HZ is the preferred choice for desktop systems and other
+	 systems requiring fast interactive responses to events.
+
+endchoice
+
+config HZ
+	int
+	default 100 if HZ_100
+	default 250 if HZ_250
+	default 1000 if HZ_1000
+
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 00e8f257551..79dd929f408 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -228,13 +228,7 @@ static struct dentry_operations cpuset_dops = {
 
 static struct dentry *cpuset_get_dentry(struct dentry *parent, const char *name)
 {
-	struct qstr qstr;
-	struct dentry *d;
-
-	qstr.name = name;
-	qstr.len = strlen(name);
-	qstr.hash = full_name_hash(name, qstr.len);
-	d = lookup_hash(&qstr, parent);
+	struct dentry *d = lookup_one_len(name, parent, strlen(name));
 	if (!IS_ERR(d))
 		d->d_op = &cpuset_dops;
 	return d;
diff --git a/kernel/exit.c b/kernel/exit.c
index 2ef2ad54020..3ebcd60a19c 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -72,6 +72,11 @@ repeat:
 	BUG_ON(!list_empty(&p->ptrace_list) || !list_empty(&p->ptrace_children));
 	__exit_signal(p);
 	__exit_sighand(p);
+	/*
+	 * Note that the fastpath in sys_times depends on __exit_signal having
+	 * updated the counters before a task is removed from the tasklist of
+	 * the process by __unhash_process.
+	 */
 	__unhash_process(p);
 
 	/*
@@ -793,6 +798,17 @@ fastcall NORET_TYPE void do_exit(long code)
 		ptrace_notify((PTRACE_EVENT_EXIT << 8) | SIGTRAP);
 	}
 
+	/*
+	 * We're taking recursive faults here in do_exit. Safest is to just
+	 * leave this task alone and wait for reboot.
+	 */
+	if (unlikely(tsk->flags & PF_EXITING)) {
+		printk(KERN_ALERT
+			"Fixing recursive fault but reboot is needed!\n");
+		set_current_state(TASK_UNINTERRUPTIBLE);
+		schedule();
+	}
+
 	tsk->flags |= PF_EXITING;
 
 	/*
diff --git a/kernel/irq/spurious.c b/kernel/irq/spurious.c
index f6297c30690..ba039e827d5 100644
--- a/kernel/irq/spurious.c
+++ b/kernel/irq/spurious.c
@@ -45,7 +45,7 @@ __report_bad_irq(unsigned int irq, irq_desc_t *desc, irqreturn_t action_ret)
 	}
 }
 
-void report_bad_irq(unsigned int irq, irq_desc_t *desc, irqreturn_t action_ret)
+static void report_bad_irq(unsigned int irq, irq_desc_t *desc, irqreturn_t action_ret)
 {
 	static int count = 100;
 
diff --git a/kernel/kmod.c b/kernel/kmod.c
index eed53d4f523..44166e3bb8a 100644
--- a/kernel/kmod.c
+++ b/kernel/kmod.c
@@ -120,6 +120,7 @@ struct subprocess_info {
 	char *path;
 	char **argv;
 	char **envp;
+	struct key *ring;
 	int wait;
 	int retval;
 };
@@ -130,16 +131,21 @@ struct subprocess_info {
 static int ____call_usermodehelper(void *data)
 {
 	struct subprocess_info *sub_info = data;
+	struct key *old_session;
 	int retval;
 
-	/* Unblock all signals. */
+	/* Unblock all signals and set the session keyring. */
+	key_get(sub_info->ring);
 	flush_signals(current);
 	spin_lock_irq(&current->sighand->siglock);
+	old_session = __install_session_keyring(current, sub_info->ring);
 	flush_signal_handlers(current, 1);
 	sigemptyset(&current->blocked);
 	recalc_sigpending();
 	spin_unlock_irq(&current->sighand->siglock);
 
+	key_put(old_session);
+
 	/* We can run anywhere, unlike our parent keventd(). */
 	set_cpus_allowed(current, CPU_MASK_ALL);
 
@@ -211,10 +217,11 @@ static void __call_usermodehelper(void *data)
 }
 
 /**
- * call_usermodehelper - start a usermode application
+ * call_usermodehelper_keys - start a usermode application
  * @path: pathname for the application
  * @argv: null-terminated argument list
  * @envp: null-terminated environment list
+ * @session_keyring: session keyring for process (NULL for an empty keyring)
  * @wait: wait for the application to finish and return status.
  *
  * Runs a user-space application.  The application is started
@@ -224,7 +231,8 @@ static void __call_usermodehelper(void *data)
  * Must be called from process context.  Returns a negative error code
  * if program was not execed successfully, or 0.
  */
-int call_usermodehelper(char *path, char **argv, char **envp, int wait)
+int call_usermodehelper_keys(char *path, char **argv, char **envp,
+			     struct key *session_keyring, int wait)
 {
 	DECLARE_COMPLETION(done);
 	struct subprocess_info sub_info = {
@@ -232,6 +240,7 @@ int call_usermodehelper(char *path, char **argv, char **envp, int wait)
 		.path		= path,
 		.argv		= argv,
 		.envp		= envp,
+		.ring		= session_keyring,
 		.wait		= wait,
 		.retval		= 0,
 	};
@@ -247,7 +256,7 @@ int call_usermodehelper(char *path, char **argv, char **envp, int wait)
 	wait_for_completion(&done);
 	return sub_info.retval;
 }
-EXPORT_SYMBOL(call_usermodehelper);
+EXPORT_SYMBOL(call_usermodehelper_keys);
 
 void __init usermodehelper_init(void)
 {
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index 037142b72a4..334f37472c5 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -27,6 +27,9 @@
  *		interface to access function arguments.
  * 2004-Sep	Prasanna S Panchamukhi <prasanna@in.ibm.com> Changed Kprobes
  *		exceptions notifier to be first on the priority list.
+ * 2005-May	Hien Nguyen <hien@us.ibm.com>, Jim Keniston
+ *		<jkenisto@us.ibm.com> and Prasanna S Panchamukhi
+ *		<prasanna@in.ibm.com> added function-return probes.
  */
 #include <linux/kprobes.h>
 #include <linux/spinlock.h>
@@ -41,6 +44,7 @@
 #define KPROBE_TABLE_SIZE (1 << KPROBE_HASH_BITS)
 
 static struct hlist_head kprobe_table[KPROBE_TABLE_SIZE];
+static struct hlist_head kretprobe_inst_table[KPROBE_TABLE_SIZE];
 
 unsigned int kprobe_cpu = NR_CPUS;
 static DEFINE_SPINLOCK(kprobe_lock);
@@ -78,22 +82,23 @@ struct kprobe *get_kprobe(void *addr)
  * Aggregate handlers for multiple kprobes support - these handlers
  * take care of invoking the individual kprobe handlers on p->list
  */
-int aggr_pre_handler(struct kprobe *p, struct pt_regs *regs)
+static int aggr_pre_handler(struct kprobe *p, struct pt_regs *regs)
 {
 	struct kprobe *kp;
 
 	list_for_each_entry(kp, &p->list, list) {
 		if (kp->pre_handler) {
 			curr_kprobe = kp;
-			kp->pre_handler(kp, regs);
-			curr_kprobe = NULL;
+			if (kp->pre_handler(kp, regs))
+				return 1;
 		}
+		curr_kprobe = NULL;
 	}
 	return 0;
 }
 
-void aggr_post_handler(struct kprobe *p, struct pt_regs *regs,
-		unsigned long flags)
+static void aggr_post_handler(struct kprobe *p, struct pt_regs *regs,
+			      unsigned long flags)
 {
 	struct kprobe *kp;
 
@@ -107,7 +112,8 @@ void aggr_post_handler(struct kprobe *p, struct pt_regs *regs,
 	return;
 }
 
-int aggr_fault_handler(struct kprobe *p, struct pt_regs *regs, int trapnr)
+static int aggr_fault_handler(struct kprobe *p, struct pt_regs *regs,
+			      int trapnr)
 {
 	/*
 	 * if we faulted "during" the execution of a user specified
@@ -120,19 +126,191 @@ int aggr_fault_handler(struct kprobe *p, struct pt_regs *regs, int trapnr)
 	return 0;
 }
 
+static int aggr_break_handler(struct kprobe *p, struct pt_regs *regs)
+{
+	struct kprobe *kp = curr_kprobe;
+	if (curr_kprobe && kp->break_handler) {
+		if (kp->break_handler(kp, regs)) {
+			curr_kprobe = NULL;
+			return 1;
+		}
+	}
+	curr_kprobe = NULL;
+	return 0;
+}
+
+struct kprobe trampoline_p = {
+		.addr = (kprobe_opcode_t *) &kretprobe_trampoline,
+		.pre_handler = trampoline_probe_handler,
+		.post_handler = trampoline_post_handler
+};
+
+struct kretprobe_instance *get_free_rp_inst(struct kretprobe *rp)
+{
+	struct hlist_node *node;
+	struct kretprobe_instance *ri;
+	hlist_for_each_entry(ri, node, &rp->free_instances, uflist)
+		return ri;
+	return NULL;
+}
+
+static struct kretprobe_instance *get_used_rp_inst(struct kretprobe *rp)
+{
+	struct hlist_node *node;
+	struct kretprobe_instance *ri;
+	hlist_for_each_entry(ri, node, &rp->used_instances, uflist)
+		return ri;
+	return NULL;
+}
+
+struct kretprobe_instance *get_rp_inst(void *sara)
+{
+	struct hlist_head *head;
+	struct hlist_node *node;
+	struct task_struct *tsk;
+	struct kretprobe_instance *ri;
+
+	tsk = arch_get_kprobe_task(sara);
+	head = &kretprobe_inst_table[hash_ptr(tsk, KPROBE_HASH_BITS)];
+	hlist_for_each_entry(ri, node, head, hlist) {
+		if (ri->stack_addr == sara)
+			return ri;
+	}
+	return NULL;
+}
+
+void add_rp_inst(struct kretprobe_instance *ri)
+{
+	struct task_struct *tsk;
+	/*
+	 * Remove rp inst off the free list -
+	 * Add it back when probed function returns
+	 */
+	hlist_del(&ri->uflist);
+	tsk = arch_get_kprobe_task(ri->stack_addr);
+	/* Add rp inst onto table */
+	INIT_HLIST_NODE(&ri->hlist);
+	hlist_add_head(&ri->hlist,
+			&kretprobe_inst_table[hash_ptr(tsk, KPROBE_HASH_BITS)]);
+
+	/* Also add this rp inst to the used list. */
+	INIT_HLIST_NODE(&ri->uflist);
+	hlist_add_head(&ri->uflist, &ri->rp->used_instances);
+}
+
+void recycle_rp_inst(struct kretprobe_instance *ri)
+{
+	/* remove rp inst off the rprobe_inst_table */
+	hlist_del(&ri->hlist);
+	if (ri->rp) {
+		/* remove rp inst off the used list */
+		hlist_del(&ri->uflist);
+		/* put rp inst back onto the free list */
+		INIT_HLIST_NODE(&ri->uflist);
+		hlist_add_head(&ri->uflist, &ri->rp->free_instances);
+	} else
+		/* Unregistering */
+		kfree(ri);
+}
+
+struct hlist_head * kretprobe_inst_table_head(struct task_struct *tsk)
+{
+	return &kretprobe_inst_table[hash_ptr(tsk, KPROBE_HASH_BITS)];
+}
+
+struct kretprobe_instance *get_rp_inst_tsk(struct task_struct *tk)
+{
+	struct task_struct *tsk;
+	struct hlist_head *head;
+	struct hlist_node *node;
+	struct kretprobe_instance *ri;
+
+	head = &kretprobe_inst_table[hash_ptr(tk, KPROBE_HASH_BITS)];
+
+	hlist_for_each_entry(ri, node, head, hlist) {
+		tsk = arch_get_kprobe_task(ri->stack_addr);
+		if (tsk == tk)
+			return ri;
+	}
+	return NULL;
+}
+
+/*
+ * This function is called from do_exit or do_execv when task tk's stack is
+ * about to be recycled. Recycle any function-return probe instances
+ * associated with this task. These represent probed functions that have
+ * been called but may never return.
+ */
+void kprobe_flush_task(struct task_struct *tk)
+{
+	unsigned long flags = 0;
+	spin_lock_irqsave(&kprobe_lock, flags);
+	arch_kprobe_flush_task(tk);
+	spin_unlock_irqrestore(&kprobe_lock, flags);
+}
+
+/*
+ * This kprobe pre_handler is registered with every kretprobe. When probe
+ * hits it will set up the return probe.
+ */
+static int pre_handler_kretprobe(struct kprobe *p, struct pt_regs *regs)
+{
+	struct kretprobe *rp = container_of(p, struct kretprobe, kp);
+
+	/*TODO: consider to only swap the RA after the last pre_handler fired */
+	arch_prepare_kretprobe(rp, regs);
+	return 0;
+}
+
+static inline void free_rp_inst(struct kretprobe *rp)
+{
+	struct kretprobe_instance *ri;
+	while ((ri = get_free_rp_inst(rp)) != NULL) {
+		hlist_del(&ri->uflist);
+		kfree(ri);
+	}
+}
+
+/*
+ * Keep all fields in the kprobe consistent
+ */
+static inline void copy_kprobe(struct kprobe *old_p, struct kprobe *p)
+{
+	memcpy(&p->opcode, &old_p->opcode, sizeof(kprobe_opcode_t));
+	memcpy(&p->ainsn, &old_p->ainsn, sizeof(struct arch_specific_insn));
+}
+
+/*
+* Add the new probe to old_p->list. Fail if this is the
+* second jprobe at the address - two jprobes can't coexist
+*/
+static int add_new_kprobe(struct kprobe *old_p, struct kprobe *p)
+{
+        struct kprobe *kp;
+
+	if (p->break_handler) {
+		list_for_each_entry(kp, &old_p->list, list) {
+			if (kp->break_handler)
+				return -EEXIST;
+		}
+		list_add_tail(&p->list, &old_p->list);
+	} else
+		list_add(&p->list, &old_p->list);
+	return 0;
+}
+
 /*
  * Fill in the required fields of the "manager kprobe". Replace the
  * earlier kprobe in the hlist with the manager kprobe
  */
 static inline void add_aggr_kprobe(struct kprobe *ap, struct kprobe *p)
 {
+	copy_kprobe(p, ap);
 	ap->addr = p->addr;
-	ap->opcode = p->opcode;
-	memcpy(&ap->ainsn, &p->ainsn, sizeof(struct arch_specific_insn));
-
 	ap->pre_handler = aggr_pre_handler;
 	ap->post_handler = aggr_post_handler;
 	ap->fault_handler = aggr_fault_handler;
+	ap->break_handler = aggr_break_handler;
 
 	INIT_LIST_HEAD(&ap->list);
 	list_add(&p->list, &ap->list);
@@ -153,16 +331,16 @@ static int register_aggr_kprobe(struct kprobe *old_p, struct kprobe *p)
 	int ret = 0;
 	struct kprobe *ap;
 
-	if (old_p->break_handler || p->break_handler) {
-		ret = -EEXIST;	/* kprobe and jprobe can't (yet) coexist */
-	} else if (old_p->pre_handler == aggr_pre_handler) {
-		list_add(&p->list, &old_p->list);
+	if (old_p->pre_handler == aggr_pre_handler) {
+		copy_kprobe(old_p, p);
+		ret = add_new_kprobe(old_p, p);
 	} else {
 		ap = kcalloc(1, sizeof(struct kprobe), GFP_ATOMIC);
 		if (!ap)
 			return -ENOMEM;
 		add_aggr_kprobe(ap, old_p);
-		list_add(&p->list, &ap->list);
+		copy_kprobe(ap, p);
+		ret = add_new_kprobe(ap, p);
 	}
 	return ret;
 }
@@ -170,10 +348,8 @@ static int register_aggr_kprobe(struct kprobe *old_p, struct kprobe *p)
 /* kprobe removal house-keeping routines */
 static inline void cleanup_kprobe(struct kprobe *p, unsigned long flags)
 {
-	*p->addr = p->opcode;
+	arch_disarm_kprobe(p);
 	hlist_del(&p->hlist);
-	flush_icache_range((unsigned long) p->addr,
-		   (unsigned long) p->addr + sizeof(kprobe_opcode_t));
 	spin_unlock_irqrestore(&kprobe_lock, flags);
 	arch_remove_kprobe(p);
 }
@@ -200,6 +376,7 @@ int register_kprobe(struct kprobe *p)
 	}
 	spin_lock_irqsave(&kprobe_lock, flags);
 	old_p = get_kprobe(p->addr);
+	p->nmissed = 0;
 	if (old_p) {
 		ret = register_aggr_kprobe(old_p, p);
 		goto out;
@@ -210,10 +387,8 @@ int register_kprobe(struct kprobe *p)
 	hlist_add_head(&p->hlist,
 		       &kprobe_table[hash_ptr(p->addr, KPROBE_HASH_BITS)]);
 
-	p->opcode = *p->addr;
-	*p->addr = BREAKPOINT_INSTRUCTION;
-	flush_icache_range((unsigned long) p->addr,
-			   (unsigned long) p->addr + sizeof(kprobe_opcode_t));
+  	arch_arm_kprobe(p);
+
 out:
 	spin_unlock_irqrestore(&kprobe_lock, flags);
 rm_kprobe:
@@ -257,16 +432,82 @@ void unregister_jprobe(struct jprobe *jp)
 	unregister_kprobe(&jp->kp);
 }
 
+#ifdef ARCH_SUPPORTS_KRETPROBES
+
+int register_kretprobe(struct kretprobe *rp)
+{
+	int ret = 0;
+	struct kretprobe_instance *inst;
+	int i;
+
+	rp->kp.pre_handler = pre_handler_kretprobe;
+
+	/* Pre-allocate memory for max kretprobe instances */
+	if (rp->maxactive <= 0) {
+#ifdef CONFIG_PREEMPT
+		rp->maxactive = max(10, 2 * NR_CPUS);
+#else
+		rp->maxactive = NR_CPUS;
+#endif
+	}
+	INIT_HLIST_HEAD(&rp->used_instances);
+	INIT_HLIST_HEAD(&rp->free_instances);
+	for (i = 0; i < rp->maxactive; i++) {
+		inst = kmalloc(sizeof(struct kretprobe_instance), GFP_KERNEL);
+		if (inst == NULL) {
+			free_rp_inst(rp);
+			return -ENOMEM;
+		}
+		INIT_HLIST_NODE(&inst->uflist);
+		hlist_add_head(&inst->uflist, &rp->free_instances);
+	}
+
+	rp->nmissed = 0;
+	/* Establish function entry probe point */
+	if ((ret = register_kprobe(&rp->kp)) != 0)
+		free_rp_inst(rp);
+	return ret;
+}
+
+#else /* ARCH_SUPPORTS_KRETPROBES */
+
+int register_kretprobe(struct kretprobe *rp)
+{
+	return -ENOSYS;
+}
+
+#endif /* ARCH_SUPPORTS_KRETPROBES */
+
+void unregister_kretprobe(struct kretprobe *rp)
+{
+	unsigned long flags;
+	struct kretprobe_instance *ri;
+
+	unregister_kprobe(&rp->kp);
+	/* No race here */
+	spin_lock_irqsave(&kprobe_lock, flags);
+	free_rp_inst(rp);
+	while ((ri = get_used_rp_inst(rp)) != NULL) {
+		ri->rp = NULL;
+		hlist_del(&ri->uflist);
+	}
+	spin_unlock_irqrestore(&kprobe_lock, flags);
+}
+
 static int __init init_kprobes(void)
 {
 	int i, err = 0;
 
 	/* FIXME allocate the probe table, currently defined statically */
 	/* initialize all list heads */
-	for (i = 0; i < KPROBE_TABLE_SIZE; i++)
+	for (i = 0; i < KPROBE_TABLE_SIZE; i++) {
 		INIT_HLIST_HEAD(&kprobe_table[i]);
+		INIT_HLIST_HEAD(&kretprobe_inst_table[i]);
+	}
 
 	err = register_die_notifier(&kprobe_exceptions_nb);
+	/* Register the trampoline probe for return probe */
+	register_kprobe(&trampoline_p);
 	return err;
 }
 
@@ -277,3 +518,6 @@ EXPORT_SYMBOL_GPL(unregister_kprobe);
 EXPORT_SYMBOL_GPL(register_jprobe);
 EXPORT_SYMBOL_GPL(unregister_jprobe);
 EXPORT_SYMBOL_GPL(jprobe_return);
+EXPORT_SYMBOL_GPL(register_kretprobe);
+EXPORT_SYMBOL_GPL(unregister_kretprobe);
+
diff --git a/kernel/module.c b/kernel/module.c
index a566745dde6..068e271ab3a 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -35,6 +35,7 @@
 #include <linux/notifier.h>
 #include <linux/stop_machine.h>
 #include <linux/device.h>
+#include <linux/string.h>
 #include <asm/uaccess.h>
 #include <asm/semaphore.h>
 #include <asm/cacheflush.h>
@@ -370,6 +371,43 @@ static inline void percpu_modcopy(void *pcpudst, const void *src,
 #endif /* CONFIG_SMP */
 
 #ifdef CONFIG_MODULE_UNLOAD
+#define MODINFO_ATTR(field)	\
+static void setup_modinfo_##field(struct module *mod, const char *s)  \
+{                                                                     \
+	mod->field = kstrdup(s, GFP_KERNEL);                          \
+}                                                                     \
+static ssize_t show_modinfo_##field(struct module_attribute *mattr,   \
+	                struct module *mod, char *buffer)             \
+{                                                                     \
+	return sprintf(buffer, "%s\n", mod->field);                   \
+}                                                                     \
+static int modinfo_##field##_exists(struct module *mod)               \
+{                                                                     \
+	return mod->field != NULL;                                    \
+}                                                                     \
+static void free_modinfo_##field(struct module *mod)                  \
+{                                                                     \
+        kfree(mod->field);                                            \
+        mod->field = NULL;                                            \
+}                                                                     \
+static struct module_attribute modinfo_##field = {                    \
+	.attr = { .name = __stringify(field), .mode = 0444,           \
+		  .owner = THIS_MODULE },                             \
+	.show = show_modinfo_##field,                                 \
+	.setup = setup_modinfo_##field,                               \
+	.test = modinfo_##field##_exists,                             \
+	.free = free_modinfo_##field,                                 \
+};
+
+MODINFO_ATTR(version);
+MODINFO_ATTR(srcversion);
+
+static struct module_attribute *modinfo_attrs[] = {
+	&modinfo_version,
+	&modinfo_srcversion,
+	NULL,
+};
+
 /* Init the unload section of the module. */
 static void module_unload_init(struct module *mod)
 {
@@ -692,7 +730,7 @@ static int obsparm_copy_string(const char *val, struct kernel_param *kp)
 	return 0;
 }
 
-int set_obsolete(const char *val, struct kernel_param *kp)
+static int set_obsolete(const char *val, struct kernel_param *kp)
 {
 	unsigned int min, max;
 	unsigned int size, maxsize;
@@ -1031,6 +1069,32 @@ static void module_remove_refcnt_attr(struct module *mod)
 }
 #endif
 
+#ifdef CONFIG_MODULE_UNLOAD
+static int module_add_modinfo_attrs(struct module *mod)
+{
+	struct module_attribute *attr;
+	int error = 0;
+	int i;
+
+	for (i = 0; (attr = modinfo_attrs[i]) && !error; i++) {
+		if (!attr->test ||
+		    (attr->test && attr->test(mod)))
+			error = sysfs_create_file(&mod->mkobj.kobj,&attr->attr);
+	}
+	return error;
+}
+
+static void module_remove_modinfo_attrs(struct module *mod)
+{
+	struct module_attribute *attr;
+	int i;
+
+	for (i = 0; (attr = modinfo_attrs[i]); i++) {
+		sysfs_remove_file(&mod->mkobj.kobj,&attr->attr);
+		attr->free(mod);
+	}
+}
+#endif
 
 static int mod_sysfs_setup(struct module *mod,
 			   struct kernel_param *kparam,
@@ -1056,6 +1120,12 @@ static int mod_sysfs_setup(struct module *mod,
 	if (err)
 		goto out_unreg;
 
+#ifdef CONFIG_MODULE_UNLOAD
+	err = module_add_modinfo_attrs(mod);
+	if (err)
+		goto out_unreg;
+#endif
+
 	return 0;
 
 out_unreg:
@@ -1066,6 +1136,9 @@ out:
 
 static void mod_kobject_remove(struct module *mod)
 {
+#ifdef CONFIG_MODULE_UNLOAD
+	module_remove_modinfo_attrs(mod);
+#endif
 	module_remove_refcnt_attr(mod);
 	module_param_sysfs_remove(mod);
 
@@ -1311,6 +1384,23 @@ static char *get_modinfo(Elf_Shdr *sechdrs,
 	return NULL;
 }
 
+#ifdef CONFIG_MODULE_UNLOAD
+static void setup_modinfo(struct module *mod, Elf_Shdr *sechdrs,
+			  unsigned int infoindex)
+{
+	struct module_attribute *attr;
+	int i;
+
+	for (i = 0; (attr = modinfo_attrs[i]); i++) {
+		if (attr->setup)
+			attr->setup(mod,
+				    get_modinfo(sechdrs,
+						infoindex,
+						attr->attr.name));
+	}
+}
+#endif
+
 #ifdef CONFIG_KALLSYMS
 int is_exported(const char *name, const struct module *mod)
 {
@@ -1615,6 +1705,11 @@ static struct module *load_module(void __user *umod,
 	/* Set up license info based on the info section */
 	set_license(mod, get_modinfo(sechdrs, infoindex, "license"));
 
+#ifdef CONFIG_MODULE_UNLOAD
+	/* Set up MODINFO_ATTR fields */
+	setup_modinfo(mod, sechdrs, infoindex);
+#endif
+
 	/* Fix up syms, so that st_value is a pointer to location. */
 	err = simplify_symbols(sechdrs, symindex, strtab, versindex, pcpuindex,
 			       mod);
diff --git a/kernel/posix-timers.c b/kernel/posix-timers.c
index cabb63fc9e1..5b7b4736d82 100644
--- a/kernel/posix-timers.c
+++ b/kernel/posix-timers.c
@@ -89,23 +89,6 @@ static struct idr posix_timers_id;
 static DEFINE_SPINLOCK(idr_lock);
 
 /*
- * Just because the timer is not in the timer list does NOT mean it is
- * inactive.  It could be in the "fire" routine getting a new expire time.
- */
-#define TIMER_INACTIVE 1
-
-#ifdef CONFIG_SMP
-# define timer_active(tmr) \
-		((tmr)->it.real.timer.entry.prev != (void *)TIMER_INACTIVE)
-# define set_timer_inactive(tmr) \
-		do { \
-			(tmr)->it.real.timer.entry.prev = (void *)TIMER_INACTIVE; \
-		} while (0)
-#else
-# define timer_active(tmr) BARFY	// error to use outside of SMP
-# define set_timer_inactive(tmr) do { } while (0)
-#endif
-/*
  * we assume that the new SIGEV_THREAD_ID shares no bits with the other
  * SIGEV values.  Here we put out an error if this assumption fails.
  */
@@ -226,7 +209,6 @@ static inline int common_timer_create(struct k_itimer *new_timer)
 	init_timer(&new_timer->it.real.timer);
 	new_timer->it.real.timer.data = (unsigned long) new_timer;
 	new_timer->it.real.timer.function = posix_timer_fn;
-	set_timer_inactive(new_timer);
 	return 0;
 }
 
@@ -480,7 +462,6 @@ static void posix_timer_fn(unsigned long __data)
 	int do_notify = 1;
 
 	spin_lock_irqsave(&timr->it_lock, flags);
- 	set_timer_inactive(timr);
 	if (!list_empty(&timr->it.real.abs_timer_entry)) {
 		spin_lock(&abs_list.lock);
 		do {
@@ -983,8 +964,8 @@ common_timer_set(struct k_itimer *timr, int flags,
 	 * careful here.  If smp we could be in the "fire" routine which will
 	 * be spinning as we hold the lock.  But this is ONLY an SMP issue.
 	 */
+	if (try_to_del_timer_sync(&timr->it.real.timer) < 0) {
 #ifdef CONFIG_SMP
-	if (timer_active(timr) && !del_timer(&timr->it.real.timer))
 		/*
 		 * It can only be active if on an other cpu.  Since
 		 * we have cleared the interval stuff above, it should
@@ -994,11 +975,9 @@ common_timer_set(struct k_itimer *timr, int flags,
 		 * a "retry" exit status.
 		 */
 		return TIMER_RETRY;
-
-	set_timer_inactive(timr);
-#else
-	del_timer(&timr->it.real.timer);
 #endif
+	}
+
 	remove_from_abslist(timr);
 
 	timr->it_requeue_pending = (timr->it_requeue_pending + 2) & 
@@ -1083,8 +1062,9 @@ retry:
 static inline int common_timer_del(struct k_itimer *timer)
 {
 	timer->it.real.incr = 0;
+
+	if (try_to_del_timer_sync(&timer->it.real.timer) < 0) {
 #ifdef CONFIG_SMP
-	if (timer_active(timer) && !del_timer(&timer->it.real.timer))
 		/*
 		 * It can only be active if on an other cpu.  Since
 		 * we have cleared the interval stuff above, it should
@@ -1094,9 +1074,9 @@ static inline int common_timer_del(struct k_itimer *timer)
 		 * a "retry" exit status.
 		 */
 		return TIMER_RETRY;
-#else
-	del_timer(&timer->it.real.timer);
 #endif
+	}
+
 	remove_from_abslist(timer);
 
 	return 0;
diff --git a/kernel/power/swsusp.c b/kernel/power/swsusp.c
index 90b3b68dee3..53f9f8720ee 100644
--- a/kernel/power/swsusp.c
+++ b/kernel/power/swsusp.c
@@ -81,7 +81,7 @@ static int nr_copy_pages_check;
 extern char resume_file[];
 
 /* Local variables that should not be affected by save */
-unsigned int nr_copy_pages __nosavedata = 0;
+static unsigned int nr_copy_pages __nosavedata = 0;
 
 /* Suspend pagedir is allocated before final copy, therefore it
    must be freed after resume 
diff --git a/kernel/printk.c b/kernel/printk.c
index 01b58d7d17f..3a442bfb8be 100644
--- a/kernel/printk.c
+++ b/kernel/printk.c
@@ -876,8 +876,10 @@ void register_console(struct console * console)
 			break;
 		console->flags |= CON_ENABLED;
 		console->index = console_cmdline[i].index;
-		if (i == preferred_console)
+		if (i == selected_console) {
 			console->flags |= CON_CONSDEV;
+			preferred_console = selected_console;
+		}
 		break;
 	}
 
@@ -897,6 +899,8 @@ void register_console(struct console * console)
 	if ((console->flags & CON_CONSDEV) || console_drivers == NULL) {
 		console->next = console_drivers;
 		console_drivers = console;
+		if (console->next)
+			console->next->flags &= ~CON_CONSDEV;
 	} else {
 		console->next = console_drivers->next;
 		console_drivers->next = console;
@@ -937,10 +941,14 @@ int unregister_console(struct console * console)
 	/* If last console is removed, we re-enable picking the first
 	 * one that gets registered. Without that, pmac early boot console
 	 * would prevent fbcon from taking over.
+	 *
+	 * If this isn't the last console and it has CON_CONSDEV set, we
+	 * need to set it on the next preferred console.
 	 */
 	if (console_drivers == NULL)
 		preferred_console = selected_console;
-		
+	else if (console->flags & CON_CONSDEV)
+		console_drivers->flags |= CON_CONSDEV;
 
 	release_console_sem();
 	return res;
diff --git a/kernel/sched.c b/kernel/sched.c
index deca041fc36..76080d142e3 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -2576,7 +2576,7 @@ void fastcall add_preempt_count(int val)
 	/*
 	 * Underflow?
 	 */
-	BUG_ON(((int)preempt_count() < 0));
+	BUG_ON((preempt_count() < 0));
 	preempt_count() += val;
 	/*
 	 * Spinlock count overflowing soon?
@@ -2869,7 +2869,7 @@ need_resched:
 
 int default_wake_function(wait_queue_t *curr, unsigned mode, int sync, void *key)
 {
-	task_t *p = curr->task;
+	task_t *p = curr->private;
 	return try_to_wake_up(p, mode, sync);
 }
 
diff --git a/kernel/signal.c b/kernel/signal.c
index c89821b69ae..d1258729a5f 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -213,6 +213,7 @@ static inline int has_pending_signals(sigset_t *signal, sigset_t *blocked)
 fastcall void recalc_sigpending_tsk(struct task_struct *t)
 {
 	if (t->signal->group_stop_count > 0 ||
+	    (t->flags & PF_FREEZE) ||
 	    PENDING(&t->pending, &t->blocked) ||
 	    PENDING(&t->signal->shared_pending, &t->blocked))
 		set_tsk_thread_flag(t, TIF_SIGPENDING);
diff --git a/kernel/sys.c b/kernel/sys.c
index f006632c2ba..da24bc1292d 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -525,7 +525,7 @@ asmlinkage long sys_setregid(gid_t rgid, gid_t egid)
 	}
 	if (new_egid != old_egid)
 	{
-		current->mm->dumpable = 0;
+		current->mm->dumpable = suid_dumpable;
 		smp_wmb();
 	}
 	if (rgid != (gid_t) -1 ||
@@ -556,7 +556,7 @@ asmlinkage long sys_setgid(gid_t gid)
 	{
 		if(old_egid != gid)
 		{
-			current->mm->dumpable=0;
+			current->mm->dumpable = suid_dumpable;
 			smp_wmb();
 		}
 		current->gid = current->egid = current->sgid = current->fsgid = gid;
@@ -565,7 +565,7 @@ asmlinkage long sys_setgid(gid_t gid)
 	{
 		if(old_egid != gid)
 		{
-			current->mm->dumpable=0;
+			current->mm->dumpable = suid_dumpable;
 			smp_wmb();
 		}
 		current->egid = current->fsgid = gid;
@@ -596,7 +596,7 @@ static int set_user(uid_t new_ruid, int dumpclear)
 
 	if(dumpclear)
 	{
-		current->mm->dumpable = 0;
+		current->mm->dumpable = suid_dumpable;
 		smp_wmb();
 	}
 	current->uid = new_ruid;
@@ -653,7 +653,7 @@ asmlinkage long sys_setreuid(uid_t ruid, uid_t euid)
 
 	if (new_euid != old_euid)
 	{
-		current->mm->dumpable=0;
+		current->mm->dumpable = suid_dumpable;
 		smp_wmb();
 	}
 	current->fsuid = current->euid = new_euid;
@@ -703,7 +703,7 @@ asmlinkage long sys_setuid(uid_t uid)
 
 	if (old_euid != uid)
 	{
-		current->mm->dumpable = 0;
+		current->mm->dumpable = suid_dumpable;
 		smp_wmb();
 	}
 	current->fsuid = current->euid = uid;
@@ -748,7 +748,7 @@ asmlinkage long sys_setresuid(uid_t ruid, uid_t euid, uid_t suid)
 	if (euid != (uid_t) -1) {
 		if (euid != current->euid)
 		{
-			current->mm->dumpable = 0;
+			current->mm->dumpable = suid_dumpable;
 			smp_wmb();
 		}
 		current->euid = euid;
@@ -798,7 +798,7 @@ asmlinkage long sys_setresgid(gid_t rgid, gid_t egid, gid_t sgid)
 	if (egid != (gid_t) -1) {
 		if (egid != current->egid)
 		{
-			current->mm->dumpable = 0;
+			current->mm->dumpable = suid_dumpable;
 			smp_wmb();
 		}
 		current->egid = egid;
@@ -845,7 +845,7 @@ asmlinkage long sys_setfsuid(uid_t uid)
 	{
 		if (uid != old_fsuid)
 		{
-			current->mm->dumpable = 0;
+			current->mm->dumpable = suid_dumpable;
 			smp_wmb();
 		}
 		current->fsuid = uid;
@@ -875,7 +875,7 @@ asmlinkage long sys_setfsgid(gid_t gid)
 	{
 		if (gid != old_fsgid)
 		{
-			current->mm->dumpable = 0;
+			current->mm->dumpable = suid_dumpable;
 			smp_wmb();
 		}
 		current->fsgid = gid;
@@ -894,35 +894,69 @@ asmlinkage long sys_times(struct tms __user * tbuf)
 	 */
 	if (tbuf) {
 		struct tms tmp;
-		struct task_struct *tsk = current;
-		struct task_struct *t;
 		cputime_t utime, stime, cutime, cstime;
 
-		read_lock(&tasklist_lock);
-		utime = tsk->signal->utime;
-		stime = tsk->signal->stime;
-		t = tsk;
-		do {
-			utime = cputime_add(utime, t->utime);
-			stime = cputime_add(stime, t->stime);
-			t = next_thread(t);
-		} while (t != tsk);
-
-		/*
-		 * While we have tasklist_lock read-locked, no dying thread
-		 * can be updating current->signal->[us]time.  Instead,
-		 * we got their counts included in the live thread loop.
-		 * However, another thread can come in right now and
-		 * do a wait call that updates current->signal->c[us]time.
-		 * To make sure we always see that pair updated atomically,
-		 * we take the siglock around fetching them.
-		 */
-		spin_lock_irq(&tsk->sighand->siglock);
-		cutime = tsk->signal->cutime;
-		cstime = tsk->signal->cstime;
-		spin_unlock_irq(&tsk->sighand->siglock);
-		read_unlock(&tasklist_lock);
+#ifdef CONFIG_SMP
+		if (thread_group_empty(current)) {
+			/*
+			 * Single thread case without the use of any locks.
+			 *
+			 * We may race with release_task if two threads are
+			 * executing. However, release task first adds up the
+			 * counters (__exit_signal) before  removing the task
+			 * from the process tasklist (__unhash_process).
+			 * __exit_signal also acquires and releases the
+			 * siglock which results in the proper memory ordering
+			 * so that the list modifications are always visible
+			 * after the counters have been updated.
+			 *
+			 * If the counters have been updated by the second thread
+			 * but the thread has not yet been removed from the list
+			 * then the other branch will be executing which will
+			 * block on tasklist_lock until the exit handling of the
+			 * other task is finished.
+			 *
+			 * This also implies that the sighand->siglock cannot
+			 * be held by another processor. So we can also
+			 * skip acquiring that lock.
+			 */
+			utime = cputime_add(current->signal->utime, current->utime);
+			stime = cputime_add(current->signal->utime, current->stime);
+			cutime = current->signal->cutime;
+			cstime = current->signal->cstime;
+		} else
+#endif
+		{
+
+			/* Process with multiple threads */
+			struct task_struct *tsk = current;
+			struct task_struct *t;
 
+			read_lock(&tasklist_lock);
+			utime = tsk->signal->utime;
+			stime = tsk->signal->stime;
+			t = tsk;
+			do {
+				utime = cputime_add(utime, t->utime);
+				stime = cputime_add(stime, t->stime);
+				t = next_thread(t);
+			} while (t != tsk);
+
+			/*
+			 * While we have tasklist_lock read-locked, no dying thread
+			 * can be updating current->signal->[us]time.  Instead,
+			 * we got their counts included in the live thread loop.
+			 * However, another thread can come in right now and
+			 * do a wait call that updates current->signal->c[us]time.
+			 * To make sure we always see that pair updated atomically,
+			 * we take the siglock around fetching them.
+			 */
+			spin_lock_irq(&tsk->sighand->siglock);
+			cutime = tsk->signal->cutime;
+			cstime = tsk->signal->cstime;
+			spin_unlock_irq(&tsk->sighand->siglock);
+			read_unlock(&tasklist_lock);
+		}
 		tmp.tms_utime = cputime_to_clock_t(utime);
 		tmp.tms_stime = cputime_to_clock_t(stime);
 		tmp.tms_cutime = cputime_to_clock_t(cutime);
@@ -1225,7 +1259,7 @@ static void groups_sort(struct group_info *group_info)
 }
 
 /* a simple bsearch */
-static int groups_search(struct group_info *group_info, gid_t grp)
+int groups_search(struct group_info *group_info, gid_t grp)
 {
 	int left, right;
 
@@ -1652,7 +1686,7 @@ asmlinkage long sys_prctl(int option, unsigned long arg2, unsigned long arg3,
 				error = 1;
 			break;
 		case PR_SET_DUMPABLE:
-			if (arg2 != 0 && arg2 != 1) {
+			if (arg2 < 0 || arg2 > 2) {
 				error = -EINVAL;
 				break;
 			}
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 701d12c6306..24a4d12d5aa 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -58,6 +58,7 @@ extern int sysctl_overcommit_ratio;
 extern int max_threads;
 extern int sysrq_enabled;
 extern int core_uses_pid;
+extern int suid_dumpable;
 extern char core_pattern[];
 extern int cad_pid;
 extern int pid_max;
@@ -950,6 +951,14 @@ static ctl_table fs_table[] = {
 		.proc_handler	= &proc_dointvec,
 	},
 #endif
+	{
+		.ctl_name	= KERN_SETUID_DUMPABLE,
+		.procname	= "suid_dumpable",
+		.data		= &suid_dumpable,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec,
+	},
 	{ .ctl_name = 0 }
 };
 
diff --git a/kernel/timer.c b/kernel/timer.c
index 207aa4f0aa1..51ff917c959 100644
--- a/kernel/timer.c
+++ b/kernel/timer.c
@@ -57,6 +57,11 @@ static void time_interpolator_update(long delta_nsec);
 #define TVN_MASK (TVN_SIZE - 1)
 #define TVR_MASK (TVR_SIZE - 1)
 
+struct timer_base_s {
+	spinlock_t lock;
+	struct timer_list *running_timer;
+};
+
 typedef struct tvec_s {
 	struct list_head vec[TVN_SIZE];
 } tvec_t;
@@ -66,9 +71,8 @@ typedef struct tvec_root_s {
 } tvec_root_t;
 
 struct tvec_t_base_s {
-	spinlock_t lock;
+	struct timer_base_s t_base;
 	unsigned long timer_jiffies;
-	struct timer_list *running_timer;
 	tvec_root_t tv1;
 	tvec_t tv2;
 	tvec_t tv3;
@@ -77,18 +81,16 @@ struct tvec_t_base_s {
 } ____cacheline_aligned_in_smp;
 
 typedef struct tvec_t_base_s tvec_base_t;
+static DEFINE_PER_CPU(tvec_base_t, tvec_bases);
 
 static inline void set_running_timer(tvec_base_t *base,
 					struct timer_list *timer)
 {
 #ifdef CONFIG_SMP
-	base->running_timer = timer;
+	base->t_base.running_timer = timer;
 #endif
 }
 
-/* Fake initialization */
-static DEFINE_PER_CPU(tvec_base_t, tvec_bases) = { SPIN_LOCK_UNLOCKED };
-
 static void check_timer_failed(struct timer_list *timer)
 {
 	static int whine_count;
@@ -103,7 +105,6 @@ static void check_timer_failed(struct timer_list *timer)
 	/*
 	 * Now fix it up
 	 */
-	spin_lock_init(&timer->lock);
 	timer->magic = TIMER_MAGIC;
 }
 
@@ -156,65 +157,113 @@ static void internal_add_timer(tvec_base_t *base, struct timer_list *timer)
 	list_add_tail(&timer->entry, vec);
 }
 
+typedef struct timer_base_s timer_base_t;
+/*
+ * Used by TIMER_INITIALIZER, we can't use per_cpu(tvec_bases)
+ * at compile time, and we need timer->base to lock the timer.
+ */
+timer_base_t __init_timer_base
+	____cacheline_aligned_in_smp = { .lock = SPIN_LOCK_UNLOCKED };
+EXPORT_SYMBOL(__init_timer_base);
+
+/***
+ * init_timer - initialize a timer.
+ * @timer: the timer to be initialized
+ *
+ * init_timer() must be done to a timer prior calling *any* of the
+ * other timer functions.
+ */
+void fastcall init_timer(struct timer_list *timer)
+{
+	timer->entry.next = NULL;
+	timer->base = &per_cpu(tvec_bases, raw_smp_processor_id()).t_base;
+	timer->magic = TIMER_MAGIC;
+}
+EXPORT_SYMBOL(init_timer);
+
+static inline void detach_timer(struct timer_list *timer,
+					int clear_pending)
+{
+	struct list_head *entry = &timer->entry;
+
+	__list_del(entry->prev, entry->next);
+	if (clear_pending)
+		entry->next = NULL;
+	entry->prev = LIST_POISON2;
+}
+
+/*
+ * We are using hashed locking: holding per_cpu(tvec_bases).t_base.lock
+ * means that all timers which are tied to this base via timer->base are
+ * locked, and the base itself is locked too.
+ *
+ * So __run_timers/migrate_timers can safely modify all timers which could
+ * be found on ->tvX lists.
+ *
+ * When the timer's base is locked, and the timer removed from list, it is
+ * possible to set timer->base = NULL and drop the lock: the timer remains
+ * locked.
+ */
+static timer_base_t *lock_timer_base(struct timer_list *timer,
+					unsigned long *flags)
+{
+	timer_base_t *base;
+
+	for (;;) {
+		base = timer->base;
+		if (likely(base != NULL)) {
+			spin_lock_irqsave(&base->lock, *flags);
+			if (likely(base == timer->base))
+				return base;
+			/* The timer has migrated to another CPU */
+			spin_unlock_irqrestore(&base->lock, *flags);
+		}
+		cpu_relax();
+	}
+}
+
 int __mod_timer(struct timer_list *timer, unsigned long expires)
 {
-	tvec_base_t *old_base, *new_base;
+	timer_base_t *base;
+	tvec_base_t *new_base;
 	unsigned long flags;
 	int ret = 0;
 
 	BUG_ON(!timer->function);
-
 	check_timer(timer);
 
-	spin_lock_irqsave(&timer->lock, flags);
+	base = lock_timer_base(timer, &flags);
+
+	if (timer_pending(timer)) {
+		detach_timer(timer, 0);
+		ret = 1;
+	}
+
 	new_base = &__get_cpu_var(tvec_bases);
-repeat:
-	old_base = timer->base;
 
-	/*
-	 * Prevent deadlocks via ordering by old_base < new_base.
-	 */
-	if (old_base && (new_base != old_base)) {
-		if (old_base < new_base) {
-			spin_lock(&new_base->lock);
-			spin_lock(&old_base->lock);
-		} else {
-			spin_lock(&old_base->lock);
-			spin_lock(&new_base->lock);
-		}
+	if (base != &new_base->t_base) {
 		/*
-		 * The timer base might have been cancelled while we were
-		 * trying to take the lock(s):
+		 * We are trying to schedule the timer on the local CPU.
+		 * However we can't change timer's base while it is running,
+		 * otherwise del_timer_sync() can't detect that the timer's
+		 * handler yet has not finished. This also guarantees that
+		 * the timer is serialized wrt itself.
 		 */
-		if (timer->base != old_base) {
-			spin_unlock(&new_base->lock);
-			spin_unlock(&old_base->lock);
-			goto repeat;
-		}
-	} else {
-		spin_lock(&new_base->lock);
-		if (timer->base != old_base) {
-			spin_unlock(&new_base->lock);
-			goto repeat;
+		if (unlikely(base->running_timer == timer)) {
+			/* The timer remains on a former base */
+			new_base = container_of(base, tvec_base_t, t_base);
+		} else {
+			/* See the comment in lock_timer_base() */
+			timer->base = NULL;
+			spin_unlock(&base->lock);
+			spin_lock(&new_base->t_base.lock);
+			timer->base = &new_base->t_base;
 		}
 	}
 
-	/*
-	 * Delete the previous timeout (if there was any), and install
-	 * the new one:
-	 */
-	if (old_base) {
-		list_del(&timer->entry);
-		ret = 1;
-	}
 	timer->expires = expires;
 	internal_add_timer(new_base, timer);
-	timer->base = new_base;
-
-	if (old_base && (new_base != old_base))
-		spin_unlock(&old_base->lock);
-	spin_unlock(&new_base->lock);
-	spin_unlock_irqrestore(&timer->lock, flags);
+	spin_unlock_irqrestore(&new_base->t_base.lock, flags);
 
 	return ret;
 }
@@ -232,15 +281,15 @@ void add_timer_on(struct timer_list *timer, int cpu)
 {
 	tvec_base_t *base = &per_cpu(tvec_bases, cpu);
   	unsigned long flags;
-  
+
   	BUG_ON(timer_pending(timer) || !timer->function);
 
 	check_timer(timer);
 
-	spin_lock_irqsave(&base->lock, flags);
+	spin_lock_irqsave(&base->t_base.lock, flags);
+	timer->base = &base->t_base;
 	internal_add_timer(base, timer);
-	timer->base = base;
-	spin_unlock_irqrestore(&base->lock, flags);
+	spin_unlock_irqrestore(&base->t_base.lock, flags);
 }
 
 
@@ -295,109 +344,84 @@ EXPORT_SYMBOL(mod_timer);
  */
 int del_timer(struct timer_list *timer)
 {
+	timer_base_t *base;
 	unsigned long flags;
-	tvec_base_t *base;
+	int ret = 0;
 
 	check_timer(timer);
 
-repeat:
- 	base = timer->base;
-	if (!base)
-		return 0;
-	spin_lock_irqsave(&base->lock, flags);
-	if (base != timer->base) {
+	if (timer_pending(timer)) {
+		base = lock_timer_base(timer, &flags);
+		if (timer_pending(timer)) {
+			detach_timer(timer, 1);
+			ret = 1;
+		}
 		spin_unlock_irqrestore(&base->lock, flags);
-		goto repeat;
 	}
-	list_del(&timer->entry);
-	/* Need to make sure that anybody who sees a NULL base also sees the list ops */
-	smp_wmb();
-	timer->base = NULL;
-	spin_unlock_irqrestore(&base->lock, flags);
 
-	return 1;
+	return ret;
 }
 
 EXPORT_SYMBOL(del_timer);
 
 #ifdef CONFIG_SMP
-/***
- * del_timer_sync - deactivate a timer and wait for the handler to finish.
- * @timer: the timer to be deactivated
- *
- * This function only differs from del_timer() on SMP: besides deactivating
- * the timer it also makes sure the handler has finished executing on other
- * CPUs.
- *
- * Synchronization rules: callers must prevent restarting of the timer,
- * otherwise this function is meaningless. It must not be called from
- * interrupt contexts. The caller must not hold locks which would prevent
- * completion of the timer's handler.  Upon exit the timer is not queued and
- * the handler is not running on any CPU.
- *
- * The function returns whether it has deactivated a pending timer or not.
+/*
+ * This function tries to deactivate a timer. Upon successful (ret >= 0)
+ * exit the timer is not queued and the handler is not running on any CPU.
  *
- * del_timer_sync() is slow and complicated because it copes with timer
- * handlers which re-arm the timer (periodic timers).  If the timer handler
- * is known to not do this (a single shot timer) then use
- * del_singleshot_timer_sync() instead.
+ * It must not be called from interrupt contexts.
  */
-int del_timer_sync(struct timer_list *timer)
+int try_to_del_timer_sync(struct timer_list *timer)
 {
-	tvec_base_t *base;
-	int i, ret = 0;
+	timer_base_t *base;
+	unsigned long flags;
+	int ret = -1;
 
-	check_timer(timer);
+	base = lock_timer_base(timer, &flags);
 
-del_again:
-	ret += del_timer(timer);
+	if (base->running_timer == timer)
+		goto out;
 
-	for_each_online_cpu(i) {
-		base = &per_cpu(tvec_bases, i);
-		if (base->running_timer == timer) {
-			while (base->running_timer == timer) {
-				cpu_relax();
-				preempt_check_resched();
-			}
-			break;
-		}
+	ret = 0;
+	if (timer_pending(timer)) {
+		detach_timer(timer, 1);
+		ret = 1;
 	}
-	smp_rmb();
-	if (timer_pending(timer))
-		goto del_again;
+out:
+	spin_unlock_irqrestore(&base->lock, flags);
 
 	return ret;
 }
-EXPORT_SYMBOL(del_timer_sync);
 
 /***
- * del_singleshot_timer_sync - deactivate a non-recursive timer
+ * del_timer_sync - deactivate a timer and wait for the handler to finish.
  * @timer: the timer to be deactivated
  *
- * This function is an optimization of del_timer_sync for the case where the
- * caller can guarantee the timer does not reschedule itself in its timer
- * function.
+ * This function only differs from del_timer() on SMP: besides deactivating
+ * the timer it also makes sure the handler has finished executing on other
+ * CPUs.
  *
  * Synchronization rules: callers must prevent restarting of the timer,
  * otherwise this function is meaningless. It must not be called from
- * interrupt contexts. The caller must not hold locks which wold prevent
- * completion of the timer's handler.  Upon exit the timer is not queued and
- * the handler is not running on any CPU.
+ * interrupt contexts. The caller must not hold locks which would prevent
+ * completion of the timer's handler. The timer's handler must not call
+ * add_timer_on(). Upon exit the timer is not queued and the handler is
+ * not running on any CPU.
  *
  * The function returns whether it has deactivated a pending timer or not.
  */
-int del_singleshot_timer_sync(struct timer_list *timer)
+int del_timer_sync(struct timer_list *timer)
 {
-	int ret = del_timer(timer);
+	check_timer(timer);
 
-	if (!ret) {
-		ret = del_timer_sync(timer);
-		BUG_ON(ret);
+	for (;;) {
+		int ret = try_to_del_timer_sync(timer);
+		if (ret >= 0)
+			return ret;
 	}
-
-	return ret;
 }
-EXPORT_SYMBOL(del_singleshot_timer_sync);
+
+EXPORT_SYMBOL(del_timer_sync);
 #endif
 
 static int cascade(tvec_base_t *base, tvec_t *tv, int index)
@@ -415,7 +439,7 @@ static int cascade(tvec_base_t *base, tvec_t *tv, int index)
 		struct timer_list *tmp;
 
 		tmp = list_entry(curr, struct timer_list, entry);
-		BUG_ON(tmp->base != base);
+		BUG_ON(tmp->base != &base->t_base);
 		curr = curr->next;
 		internal_add_timer(base, tmp);
 	}
@@ -437,7 +461,7 @@ static inline void __run_timers(tvec_base_t *base)
 {
 	struct timer_list *timer;
 
-	spin_lock_irq(&base->lock);
+	spin_lock_irq(&base->t_base.lock);
 	while (time_after_eq(jiffies, base->timer_jiffies)) {
 		struct list_head work_list = LIST_HEAD_INIT(work_list);
 		struct list_head *head = &work_list;
@@ -453,8 +477,7 @@ static inline void __run_timers(tvec_base_t *base)
 			cascade(base, &base->tv5, INDEX(3));
 		++base->timer_jiffies; 
 		list_splice_init(base->tv1.vec + index, &work_list);
-repeat:
-		if (!list_empty(head)) {
+		while (!list_empty(head)) {
 			void (*fn)(unsigned long);
 			unsigned long data;
 
@@ -462,25 +485,26 @@ repeat:
  			fn = timer->function;
  			data = timer->data;
 
-			list_del(&timer->entry);
 			set_running_timer(base, timer);
-			smp_wmb();
-			timer->base = NULL;
-			spin_unlock_irq(&base->lock);
+			detach_timer(timer, 1);
+			spin_unlock_irq(&base->t_base.lock);
 			{
-				u32 preempt_count = preempt_count();
+				int preempt_count = preempt_count();
 				fn(data);
 				if (preempt_count != preempt_count()) {
-					printk("huh, entered %p with %08x, exited with %08x?\n", fn, preempt_count, preempt_count());
+					printk(KERN_WARNING "huh, entered %p "
+					       "with preempt_count %08x, exited"
+					       " with %08x?\n",
+					       fn, preempt_count,
+					       preempt_count());
 					BUG();
 				}
 			}
-			spin_lock_irq(&base->lock);
-			goto repeat;
+			spin_lock_irq(&base->t_base.lock);
 		}
 	}
 	set_running_timer(base, NULL);
-	spin_unlock_irq(&base->lock);
+	spin_unlock_irq(&base->t_base.lock);
 }
 
 #ifdef CONFIG_NO_IDLE_HZ
@@ -499,7 +523,7 @@ unsigned long next_timer_interrupt(void)
 	int i, j;
 
 	base = &__get_cpu_var(tvec_bases);
-	spin_lock(&base->lock);
+	spin_lock(&base->t_base.lock);
 	expires = base->timer_jiffies + (LONG_MAX >> 1);
 	list = 0;
 
@@ -547,7 +571,7 @@ found:
 				expires = nte->expires;
 		}
 	}
-	spin_unlock(&base->lock);
+	spin_unlock(&base->t_base.lock);
 	return expires;
 }
 #endif
@@ -1286,9 +1310,9 @@ static void __devinit init_timers_cpu(int cpu)
 {
 	int j;
 	tvec_base_t *base;
-       
+
 	base = &per_cpu(tvec_bases, cpu);
-	spin_lock_init(&base->lock);
+	spin_lock_init(&base->t_base.lock);
 	for (j = 0; j < TVN_SIZE; j++) {
 		INIT_LIST_HEAD(base->tv5.vec + j);
 		INIT_LIST_HEAD(base->tv4.vec + j);
@@ -1302,22 +1326,16 @@ static void __devinit init_timers_cpu(int cpu)
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
-static int migrate_timer_list(tvec_base_t *new_base, struct list_head *head)
+static void migrate_timer_list(tvec_base_t *new_base, struct list_head *head)
 {
 	struct timer_list *timer;
 
 	while (!list_empty(head)) {
 		timer = list_entry(head->next, struct timer_list, entry);
-		/* We're locking backwards from __mod_timer order here,
-		   beware deadlock. */
-		if (!spin_trylock(&timer->lock))
-			return 0;
-		list_del(&timer->entry);
+		detach_timer(timer, 0);
+		timer->base = &new_base->t_base;
 		internal_add_timer(new_base, timer);
-		timer->base = new_base;
-		spin_unlock(&timer->lock);
 	}
-	return 1;
 }
 
 static void __devinit migrate_timers(int cpu)
@@ -1331,39 +1349,24 @@ static void __devinit migrate_timers(int cpu)
 	new_base = &get_cpu_var(tvec_bases);
 
 	local_irq_disable();
-again:
-	/* Prevent deadlocks via ordering by old_base < new_base. */
-	if (old_base < new_base) {
-		spin_lock(&new_base->lock);
-		spin_lock(&old_base->lock);
-	} else {
-		spin_lock(&old_base->lock);
-		spin_lock(&new_base->lock);
-	}
+	spin_lock(&new_base->t_base.lock);
+	spin_lock(&old_base->t_base.lock);
 
-	if (old_base->running_timer)
+	if (old_base->t_base.running_timer)
 		BUG();
 	for (i = 0; i < TVR_SIZE; i++)
-		if (!migrate_timer_list(new_base, old_base->tv1.vec + i))
-			goto unlock_again;
-	for (i = 0; i < TVN_SIZE; i++)
-		if (!migrate_timer_list(new_base, old_base->tv2.vec + i)
-		    || !migrate_timer_list(new_base, old_base->tv3.vec + i)
-		    || !migrate_timer_list(new_base, old_base->tv4.vec + i)
-		    || !migrate_timer_list(new_base, old_base->tv5.vec + i))
-			goto unlock_again;
-	spin_unlock(&old_base->lock);
-	spin_unlock(&new_base->lock);
+		migrate_timer_list(new_base, old_base->tv1.vec + i);
+	for (i = 0; i < TVN_SIZE; i++) {
+		migrate_timer_list(new_base, old_base->tv2.vec + i);
+		migrate_timer_list(new_base, old_base->tv3.vec + i);
+		migrate_timer_list(new_base, old_base->tv4.vec + i);
+		migrate_timer_list(new_base, old_base->tv5.vec + i);
+	}
+
+	spin_unlock(&old_base->t_base.lock);
+	spin_unlock(&new_base->t_base.lock);
 	local_irq_enable();
 	put_cpu_var(tvec_bases);
-	return;
-
-unlock_again:
-	/* Avoid deadlock with __mod_timer, by backing off. */
-	spin_unlock(&old_base->lock);
-	spin_unlock(&new_base->lock);
-	cpu_relax();
-	goto again;
 }
 #endif /* CONFIG_HOTPLUG_CPU */