Merge branch 'tip/perf/jump-label-2' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-2.6-trace into perf/urgent

45 files changed, 913 insertions, 645 deletions

diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index 291ba3d04bea..5cf366965d0c 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -52,7 +52,6 @@
 #include <linux/cgroupstats.h>
 #include <linux/hash.h>
 #include <linux/namei.h>
-#include <linux/smp_lock.h>
 #include <linux/pid_namespace.h>
 #include <linux/idr.h>
 #include <linux/vmalloc.h> /* TODO: replace with more sophisticated array */
@@ -244,6 +243,11 @@ static int notify_on_release(const struct cgroup *cgrp)
 	return test_bit(CGRP_NOTIFY_ON_RELEASE, &cgrp->flags);
 }
 
+static int clone_children(const struct cgroup *cgrp)
+{
+	return test_bit(CGRP_CLONE_CHILDREN, &cgrp->flags);
+}
+
 /*
  * for_each_subsys() allows you to iterate on each subsystem attached to
  * an active hierarchy
@@ -778,6 +782,7 @@ static struct inode *cgroup_new_inode(mode_t mode, struct super_block *sb)
 	struct inode *inode = new_inode(sb);
 
 	if (inode) {
+		inode->i_ino = get_next_ino();
 		inode->i_mode = mode;
 		inode->i_uid = current_fsuid();
 		inode->i_gid = current_fsgid();
@@ -1040,6 +1045,8 @@ static int cgroup_show_options(struct seq_file *seq, struct vfsmount *vfs)
 		seq_puts(seq, ",noprefix");
 	if (strlen(root->release_agent_path))
 		seq_printf(seq, ",release_agent=%s", root->release_agent_path);
+	if (clone_children(&root->top_cgroup))
+		seq_puts(seq, ",clone_children");
 	if (strlen(root->name))
 		seq_printf(seq, ",name=%s", root->name);
 	mutex_unlock(&cgroup_mutex);
@@ -1050,6 +1057,7 @@ struct cgroup_sb_opts {
 	unsigned long subsys_bits;
 	unsigned long flags;
 	char *release_agent;
+	bool clone_children;
 	char *name;
 	/* User explicitly requested empty subsystem */
 	bool none;
@@ -1066,7 +1074,8 @@ struct cgroup_sb_opts {
  */
 static int parse_cgroupfs_options(char *data, struct cgroup_sb_opts *opts)
 {
-	char *token, *o = data ?: "all";
+	char *token, *o = data;
+	bool all_ss = false, one_ss = false;
 	unsigned long mask = (unsigned long)-1;
 	int i;
 	bool module_pin_failed = false;
@@ -1082,22 +1091,27 @@ static int parse_cgroupfs_options(char *data, struct cgroup_sb_opts *opts)
 	while ((token = strsep(&o, ",")) != NULL) {
 		if (!*token)
 			return -EINVAL;
-		if (!strcmp(token, "all")) {
-			/* Add all non-disabled subsystems */
-			opts->subsys_bits = 0;
-			for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
-				struct cgroup_subsys *ss = subsys[i];
-				if (ss == NULL)
-					continue;
-				if (!ss->disabled)
-					opts->subsys_bits |= 1ul << i;
-			}
-		} else if (!strcmp(token, "none")) {
+		if (!strcmp(token, "none")) {
 			/* Explicitly have no subsystems */
 			opts->none = true;
-		} else if (!strcmp(token, "noprefix")) {
+			continue;
+		}
+		if (!strcmp(token, "all")) {
+			/* Mutually exclusive option 'all' + subsystem name */
+			if (one_ss)
+				return -EINVAL;
+			all_ss = true;
+			continue;
+		}
+		if (!strcmp(token, "noprefix")) {
 			set_bit(ROOT_NOPREFIX, &opts->flags);
-		} else if (!strncmp(token, "release_agent=", 14)) {
+			continue;
+		}
+		if (!strcmp(token, "clone_children")) {
+			opts->clone_children = true;
+			continue;
+		}
+		if (!strncmp(token, "release_agent=", 14)) {
 			/* Specifying two release agents is forbidden */
 			if (opts->release_agent)
 				return -EINVAL;
@@ -1105,7 +1119,9 @@ static int parse_cgroupfs_options(char *data, struct cgroup_sb_opts *opts)
 				kstrndup(token + 14, PATH_MAX - 1, GFP_KERNEL);
 			if (!opts->release_agent)
 				return -ENOMEM;
-		} else if (!strncmp(token, "name=", 5)) {
+			continue;
+		}
+		if (!strncmp(token, "name=", 5)) {
 			const char *name = token + 5;
 			/* Can't specify an empty name */
 			if (!strlen(name))
@@ -1127,20 +1143,44 @@ static int parse_cgroupfs_options(char *data, struct cgroup_sb_opts *opts)
 					      GFP_KERNEL);
 			if (!opts->name)
 				return -ENOMEM;
-		} else {
-			struct cgroup_subsys *ss;
-			for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
-				ss = subsys[i];
-				if (ss == NULL)
-					continue;
-				if (!strcmp(token, ss->name)) {
-					if (!ss->disabled)
-						set_bit(i, &opts->subsys_bits);
-					break;
-				}
-			}
-			if (i == CGROUP_SUBSYS_COUNT)
-				return -ENOENT;
+
+			continue;
+		}
+
+		for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
+			struct cgroup_subsys *ss = subsys[i];
+			if (ss == NULL)
+				continue;
+			if (strcmp(token, ss->name))
+				continue;
+			if (ss->disabled)
+				continue;
+
+			/* Mutually exclusive option 'all' + subsystem name */
+			if (all_ss)
+				return -EINVAL;
+			set_bit(i, &opts->subsys_bits);
+			one_ss = true;
+
+			break;
+		}
+		if (i == CGROUP_SUBSYS_COUNT)
+			return -ENOENT;
+	}
+
+	/*
+	 * If the 'all' option was specified select all the subsystems,
+	 * otherwise 'all, 'none' and a subsystem name options were not
+	 * specified, let's default to 'all'
+	 */
+	if (all_ss || (!all_ss && !one_ss && !opts->none)) {
+		for (i = 0; i < CGROUP_SUBSYS_COUNT; i++) {
+			struct cgroup_subsys *ss = subsys[i];
+			if (ss == NULL)
+				continue;
+			if (ss->disabled)
+				continue;
+			set_bit(i, &opts->subsys_bits);
 		}
 	}
 
@@ -1222,7 +1262,6 @@ static int cgroup_remount(struct super_block *sb, int *flags, char *data)
 	struct cgroup *cgrp = &root->top_cgroup;
 	struct cgroup_sb_opts opts;
 
-	lock_kernel();
 	mutex_lock(&cgrp->dentry->d_inode->i_mutex);
 	mutex_lock(&cgroup_mutex);
 
@@ -1255,7 +1294,6 @@ static int cgroup_remount(struct super_block *sb, int *flags, char *data)
 	kfree(opts.name);
 	mutex_unlock(&cgroup_mutex);
 	mutex_unlock(&cgrp->dentry->d_inode->i_mutex);
-	unlock_kernel();
 	return ret;
 }
 
@@ -1357,6 +1395,8 @@ static struct cgroupfs_root *cgroup_root_from_opts(struct cgroup_sb_opts *opts)
 		strcpy(root->release_agent_path, opts->release_agent);
 	if (opts->name)
 		strcpy(root->name, opts->name);
+	if (opts->clone_children)
+		set_bit(CGRP_CLONE_CHILDREN, &root->top_cgroup.flags);
 	return root;
 }
 
@@ -1568,7 +1608,6 @@ static int cgroup_get_sb(struct file_system_type *fs_type,
  out_err:
 	kfree(opts.release_agent);
 	kfree(opts.name);
-
 	return ret;
 }
 
@@ -1883,6 +1922,8 @@ static int cgroup_release_agent_write(struct cgroup *cgrp, struct cftype *cft,
 				      const char *buffer)
 {
 	BUILD_BUG_ON(sizeof(cgrp->root->release_agent_path) < PATH_MAX);
+	if (strlen(buffer) >= PATH_MAX)
+		return -EINVAL;
 	if (!cgroup_lock_live_group(cgrp))
 		return -ENODEV;
 	strcpy(cgrp->root->release_agent_path, buffer);
@@ -3176,6 +3217,23 @@ fail:
 	return ret;
 }
 
+static u64 cgroup_clone_children_read(struct cgroup *cgrp,
+				    struct cftype *cft)
+{
+	return clone_children(cgrp);
+}
+
+static int cgroup_clone_children_write(struct cgroup *cgrp,
+				     struct cftype *cft,
+				     u64 val)
+{
+	if (val)
+		set_bit(CGRP_CLONE_CHILDREN, &cgrp->flags);
+	else
+		clear_bit(CGRP_CLONE_CHILDREN, &cgrp->flags);
+	return 0;
+}
+
 /*
  * for the common functions, 'private' gives the type of file
  */
@@ -3206,6 +3264,11 @@ static struct cftype files[] = {
 		.write_string = cgroup_write_event_control,
 		.mode = S_IWUGO,
 	},
+	{
+		.name = "cgroup.clone_children",
+		.read_u64 = cgroup_clone_children_read,
+		.write_u64 = cgroup_clone_children_write,
+	},
 };
 
 static struct cftype cft_release_agent = {
@@ -3335,6 +3398,9 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry,
 	if (notify_on_release(parent))
 		set_bit(CGRP_NOTIFY_ON_RELEASE, &cgrp->flags);
 
+	if (clone_children(parent))
+		set_bit(CGRP_CLONE_CHILDREN, &cgrp->flags);
+
 	for_each_subsys(root, ss) {
 		struct cgroup_subsys_state *css = ss->create(ss, cgrp);
 
@@ -3349,6 +3415,8 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry,
 				goto err_destroy;
 		}
 		/* At error, ->destroy() callback has to free assigned ID. */
+		if (clone_children(parent) && ss->post_clone)
+			ss->post_clone(ss, cgrp);
 	}
 
 	cgroup_lock_hierarchy(root);
diff --git a/kernel/cgroup_freezer.c b/kernel/cgroup_freezer.c
index ce71ed53e88f..e7bebb7c6c38 100644
--- a/kernel/cgroup_freezer.c
+++ b/kernel/cgroup_freezer.c
@@ -48,20 +48,19 @@ static inline struct freezer *task_freezer(struct task_struct *task)
 			    struct freezer, css);
 }
 
-int cgroup_freezing_or_frozen(struct task_struct *task)
+static inline int __cgroup_freezing_or_frozen(struct task_struct *task)
 {
-	struct freezer *freezer;
-	enum freezer_state state;
+	enum freezer_state state = task_freezer(task)->state;
+	return (state == CGROUP_FREEZING) || (state == CGROUP_FROZEN);
+}
 
+int cgroup_freezing_or_frozen(struct task_struct *task)
+{
+	int result;
 	task_lock(task);
-	freezer = task_freezer(task);
-	if (!freezer->css.cgroup->parent)
-		state = CGROUP_THAWED; /* root cgroup can't be frozen */
-	else
-		state = freezer->state;
+	result = __cgroup_freezing_or_frozen(task);
 	task_unlock(task);
-
-	return (state == CGROUP_FREEZING) || (state == CGROUP_FROZEN);
+	return result;
 }
 
 /*
@@ -154,13 +153,6 @@ static void freezer_destroy(struct cgroup_subsys *ss,
 	kfree(cgroup_freezer(cgroup));
 }
 
-/* Task is frozen or will freeze immediately when next it gets woken */
-static bool is_task_frozen_enough(struct task_struct *task)
-{
-	return frozen(task) ||
-		(task_is_stopped_or_traced(task) && freezing(task));
-}
-
 /*
  * The call to cgroup_lock() in the freezer.state write method prevents
  * a write to that file racing against an attach, and hence the
@@ -174,24 +166,25 @@ static int freezer_can_attach(struct cgroup_subsys *ss,
 
 	/*
 	 * Anything frozen can't move or be moved to/from.
-	 *
-	 * Since orig_freezer->state == FROZEN means that @task has been
-	 * frozen, so it's sufficient to check the latter condition.
 	 */
 
-	if (is_task_frozen_enough(task))
+	freezer = cgroup_freezer(new_cgroup);
+	if (freezer->state != CGROUP_THAWED)
 		return -EBUSY;
 
-	freezer = cgroup_freezer(new_cgroup);
-	if (freezer->state == CGROUP_FROZEN)
+	rcu_read_lock();
+	if (__cgroup_freezing_or_frozen(task)) {
+		rcu_read_unlock();
 		return -EBUSY;
+	}
+	rcu_read_unlock();
 
 	if (threadgroup) {
 		struct task_struct *c;
 
 		rcu_read_lock();
 		list_for_each_entry_rcu(c, &task->thread_group, thread_group) {
-			if (is_task_frozen_enough(c)) {
+			if (__cgroup_freezing_or_frozen(c)) {
 				rcu_read_unlock();
 				return -EBUSY;
 			}
@@ -236,31 +229,30 @@ static void freezer_fork(struct cgroup_subsys *ss, struct task_struct *task)
 /*
  * caller must hold freezer->lock
  */
-static void update_freezer_state(struct cgroup *cgroup,
+static void update_if_frozen(struct cgroup *cgroup,
 				 struct freezer *freezer)
 {
 	struct cgroup_iter it;
 	struct task_struct *task;
 	unsigned int nfrozen = 0, ntotal = 0;
+	enum freezer_state old_state = freezer->state;
 
 	cgroup_iter_start(cgroup, &it);
 	while ((task = cgroup_iter_next(cgroup, &it))) {
 		ntotal++;
-		if (is_task_frozen_enough(task))
+		if (frozen(task))
 			nfrozen++;
 	}
 
-	/*
-	 * Transition to FROZEN when no new tasks can be added ensures
-	 * that we never exist in the FROZEN state while there are unfrozen
-	 * tasks.
-	 */
-	if (nfrozen == ntotal)
-		freezer->state = CGROUP_FROZEN;
-	else if (nfrozen > 0)
-		freezer->state = CGROUP_FREEZING;
-	else
-		freezer->state = CGROUP_THAWED;
+	if (old_state == CGROUP_THAWED) {
+		BUG_ON(nfrozen > 0);
+	} else if (old_state == CGROUP_FREEZING) {
+		if (nfrozen == ntotal)
+			freezer->state = CGROUP_FROZEN;
+	} else { /* old_state == CGROUP_FROZEN */
+		BUG_ON(nfrozen != ntotal);
+	}
+
 	cgroup_iter_end(cgroup, &it);
 }
 
@@ -279,7 +271,7 @@ static int freezer_read(struct cgroup *cgroup, struct cftype *cft,
 	if (state == CGROUP_FREEZING) {
 		/* We change from FREEZING to FROZEN lazily if the cgroup was
 		 * only partially frozen when we exitted write. */
-		update_freezer_state(cgroup, freezer);
+		update_if_frozen(cgroup, freezer);
 		state = freezer->state;
 	}
 	spin_unlock_irq(&freezer->lock);
@@ -301,7 +293,7 @@ static int try_to_freeze_cgroup(struct cgroup *cgroup, struct freezer *freezer)
 	while ((task = cgroup_iter_next(cgroup, &it))) {
 		if (!freeze_task(task, true))
 			continue;
-		if (is_task_frozen_enough(task))
+		if (frozen(task))
 			continue;
 		if (!freezing(task) && !freezer_should_skip(task))
 			num_cant_freeze_now++;
@@ -335,7 +327,7 @@ static int freezer_change_state(struct cgroup *cgroup,
 
 	spin_lock_irq(&freezer->lock);
 
-	update_freezer_state(cgroup, freezer);
+	update_if_frozen(cgroup, freezer);
 	if (goal_state == freezer->state)
 		goto out;
 
diff --git a/kernel/configs.c b/kernel/configs.c
index abaee684ecbf..b4066b44a99d 100644
--- a/kernel/configs.c
+++ b/kernel/configs.c
@@ -66,6 +66,7 @@ ikconfig_read_current(struct file *file, char __user *buf,
 static const struct file_operations ikconfig_file_ops = {
 	.owner = THIS_MODULE,
 	.read = ikconfig_read_current,
+	.llseek = default_llseek,
 };
 
 static int __init ikconfig_init(void)
diff --git a/kernel/cred.c b/kernel/cred.c
index 9a3e22641fe7..6a1aa004e376 100644
--- a/kernel/cred.c
+++ b/kernel/cred.c
@@ -325,7 +325,7 @@ EXPORT_SYMBOL(prepare_creds);
 
 /*
  * Prepare credentials for current to perform an execve()
- * - The caller must hold current->cred_guard_mutex
+ * - The caller must hold ->cred_guard_mutex
  */
 struct cred *prepare_exec_creds(void)
 {
@@ -384,8 +384,6 @@ int copy_creds(struct task_struct *p, unsigned long clone_flags)
 	struct cred *new;
 	int ret;
 
-	mutex_init(&p->cred_guard_mutex);
-
 	if (
 #ifdef CONFIG_KEYS
 		!p->cred->thread_keyring &&
diff --git a/kernel/debug/debug_core.c b/kernel/debug/debug_core.c
index de407c78178d..fec596da9bd0 100644
--- a/kernel/debug/debug_core.c
+++ b/kernel/debug/debug_core.c
@@ -47,6 +47,7 @@
 #include <linux/pid.h>
 #include <linux/smp.h>
 #include <linux/mm.h>
+#include <linux/rcupdate.h>
 
 #include <asm/cacheflush.h>
 #include <asm/byteorder.h>
@@ -109,13 +110,15 @@ static struct kgdb_bkpt		kgdb_break[KGDB_MAX_BREAKPOINTS] = {
  */
 atomic_t			kgdb_active = ATOMIC_INIT(-1);
 EXPORT_SYMBOL_GPL(kgdb_active);
+static DEFINE_RAW_SPINLOCK(dbg_master_lock);
+static DEFINE_RAW_SPINLOCK(dbg_slave_lock);
 
 /*
  * We use NR_CPUs not PERCPU, in case kgdb is used to debug early
  * bootup code (which might not have percpu set up yet):
  */
-static atomic_t			passive_cpu_wait[NR_CPUS];
-static atomic_t			cpu_in_kgdb[NR_CPUS];
+static atomic_t			masters_in_kgdb;
+static atomic_t			slaves_in_kgdb;
 static atomic_t			kgdb_break_tasklet_var;
 atomic_t			kgdb_setting_breakpoint;
 
@@ -457,26 +460,32 @@ static int kgdb_reenter_check(struct kgdb_state *ks)
 	return 1;
 }
 
-static void dbg_cpu_switch(int cpu, int next_cpu)
+static void dbg_touch_watchdogs(void)
 {
-	/* Mark the cpu we are switching away from as a slave when it
-	 * holds the kgdb_active token.  This must be done so that the
-	 * that all the cpus wait in for the debug core will not enter
-	 * again as the master. */
-	if (cpu == atomic_read(&kgdb_active)) {
-		kgdb_info[cpu].exception_state |= DCPU_IS_SLAVE;
-		kgdb_info[cpu].exception_state &= ~DCPU_WANT_MASTER;
-	}
-	kgdb_info[next_cpu].exception_state |= DCPU_NEXT_MASTER;
+	touch_softlockup_watchdog_sync();
+	clocksource_touch_watchdog();
+	rcu_cpu_stall_reset();
 }
 
-static int kgdb_cpu_enter(struct kgdb_state *ks, struct pt_regs *regs)
+static int kgdb_cpu_enter(struct kgdb_state *ks, struct pt_regs *regs,
+		int exception_state)
 {
 	unsigned long flags;
 	int sstep_tries = 100;
 	int error;
-	int i, cpu;
+	int cpu;
 	int trace_on = 0;
+	int online_cpus = num_online_cpus();
+
+	kgdb_info[ks->cpu].enter_kgdb++;
+	kgdb_info[ks->cpu].exception_state |= exception_state;
+
+	if (exception_state == DCPU_WANT_MASTER)
+		atomic_inc(&masters_in_kgdb);
+	else
+		atomic_inc(&slaves_in_kgdb);
+	kgdb_disable_hw_debug(ks->linux_regs);
+
 acquirelock:
 	/*
 	 * Interrupts will be restored by the 'trap return' code, except when
@@ -489,14 +498,15 @@ acquirelock:
 	kgdb_info[cpu].task = current;
 	kgdb_info[cpu].ret_state = 0;
 	kgdb_info[cpu].irq_depth = hardirq_count() >> HARDIRQ_SHIFT;
-	/*
-	 * Make sure the above info reaches the primary CPU before
-	 * our cpu_in_kgdb[] flag setting does:
-	 */
-	atomic_inc(&cpu_in_kgdb[cpu]);
 
-	if (exception_level == 1)
+	/* Make sure the above info reaches the primary CPU */
+	smp_mb();
+
+	if (exception_level == 1) {
+		if (raw_spin_trylock(&dbg_master_lock))
+			atomic_xchg(&kgdb_active, cpu);
 		goto cpu_master_loop;
+	}
 
 	/*
 	 * CPU will loop if it is a slave or request to become a kgdb
@@ -508,10 +518,12 @@ cpu_loop:
 			kgdb_info[cpu].exception_state &= ~DCPU_NEXT_MASTER;
 			goto cpu_master_loop;
 		} else if (kgdb_info[cpu].exception_state & DCPU_WANT_MASTER) {
-			if (atomic_cmpxchg(&kgdb_active, -1, cpu) == cpu)
+			if (raw_spin_trylock(&dbg_master_lock)) {
+				atomic_xchg(&kgdb_active, cpu);
 				break;
+			}
 		} else if (kgdb_info[cpu].exception_state & DCPU_IS_SLAVE) {
-			if (!atomic_read(&passive_cpu_wait[cpu]))
+			if (!raw_spin_is_locked(&dbg_slave_lock))
 				goto return_normal;
 		} else {
 return_normal:
@@ -522,9 +534,12 @@ return_normal:
 				arch_kgdb_ops.correct_hw_break();
 			if (trace_on)
 				tracing_on();
-			atomic_dec(&cpu_in_kgdb[cpu]);
-			touch_softlockup_watchdog_sync();
-			clocksource_touch_watchdog();
+			kgdb_info[cpu].exception_state &=
+				~(DCPU_WANT_MASTER | DCPU_IS_SLAVE);
+			kgdb_info[cpu].enter_kgdb--;
+			smp_mb__before_atomic_dec();
+			atomic_dec(&slaves_in_kgdb);
+			dbg_touch_watchdogs();
 			local_irq_restore(flags);
 			return 0;
 		}
@@ -541,8 +556,8 @@ return_normal:
 	    (kgdb_info[cpu].task &&
 	     kgdb_info[cpu].task->pid != kgdb_sstep_pid) && --sstep_tries) {
 		atomic_set(&kgdb_active, -1);
-		touch_softlockup_watchdog_sync();
-		clocksource_touch_watchdog();
+		raw_spin_unlock(&dbg_master_lock);
+		dbg_touch_watchdogs();
 		local_irq_restore(flags);
 
 		goto acquirelock;
@@ -563,16 +578,12 @@ return_normal:
 	if (dbg_io_ops->pre_exception)
 		dbg_io_ops->pre_exception();
 
-	kgdb_disable_hw_debug(ks->linux_regs);
-
 	/*
 	 * Get the passive CPU lock which will hold all the non-primary
 	 * CPU in a spin state while the debugger is active
 	 */
-	if (!kgdb_single_step) {
-		for (i = 0; i < NR_CPUS; i++)
-			atomic_inc(&passive_cpu_wait[i]);
-	}
+	if (!kgdb_single_step)
+		raw_spin_lock(&dbg_slave_lock);
 
 #ifdef CONFIG_SMP
 	/* Signal the other CPUs to enter kgdb_wait() */
@@ -583,10 +594,9 @@ return_normal:
 	/*
 	 * Wait for the other CPUs to be notified and be waiting for us:
 	 */
-	for_each_online_cpu(i) {
-		while (kgdb_do_roundup && !atomic_read(&cpu_in_kgdb[i]))
-			cpu_relax();
-	}
+	while (kgdb_do_roundup && (atomic_read(&masters_in_kgdb) +
+				atomic_read(&slaves_in_kgdb)) != online_cpus)
+		cpu_relax();
 
 	/*
 	 * At this point the primary processor is completely
@@ -615,7 +625,8 @@ cpu_master_loop:
 		if (error == DBG_PASS_EVENT) {
 			dbg_kdb_mode = !dbg_kdb_mode;
 		} else if (error == DBG_SWITCH_CPU_EVENT) {
-			dbg_cpu_switch(cpu, dbg_switch_cpu);
+			kgdb_info[dbg_switch_cpu].exception_state |=
+				DCPU_NEXT_MASTER;
 			goto cpu_loop;
 		} else {
 			kgdb_info[cpu].ret_state = error;
@@ -627,24 +638,11 @@ cpu_master_loop:
 	if (dbg_io_ops->post_exception)
 		dbg_io_ops->post_exception();
 
-	atomic_dec(&cpu_in_kgdb[ks->cpu]);
-
 	if (!kgdb_single_step) {
-		for (i = NR_CPUS-1; i >= 0; i--)
-			atomic_dec(&passive_cpu_wait[i]);
-		/*
-		 * Wait till all the CPUs have quit from the debugger,
-		 * but allow a CPU that hit an exception and is
-		 * waiting to become the master to remain in the debug
-		 * core.
-		 */
-		for_each_online_cpu(i) {
-			while (kgdb_do_roundup &&
-			       atomic_read(&cpu_in_kgdb[i]) &&
-			       !(kgdb_info[i].exception_state &
-				 DCPU_WANT_MASTER))
-				cpu_relax();
-		}
+		raw_spin_unlock(&dbg_slave_lock);
+		/* Wait till all the CPUs have quit from the debugger. */
+		while (kgdb_do_roundup && atomic_read(&slaves_in_kgdb))
+			cpu_relax();
 	}
 
 kgdb_restore:
@@ -655,12 +653,20 @@ kgdb_restore:
 		else
 			kgdb_sstep_pid = 0;
 	}
+	if (arch_kgdb_ops.correct_hw_break)
+		arch_kgdb_ops.correct_hw_break();
 	if (trace_on)
 		tracing_on();
+
+	kgdb_info[cpu].exception_state &=
+		~(DCPU_WANT_MASTER | DCPU_IS_SLAVE);
+	kgdb_info[cpu].enter_kgdb--;
+	smp_mb__before_atomic_dec();
+	atomic_dec(&masters_in_kgdb);
 	/* Free kgdb_active */
 	atomic_set(&kgdb_active, -1);
-	touch_softlockup_watchdog_sync();
-	clocksource_touch_watchdog();
+	raw_spin_unlock(&dbg_master_lock);
+	dbg_touch_watchdogs();
 	local_irq_restore(flags);
 
 	return kgdb_info[cpu].ret_state;
@@ -678,7 +684,6 @@ kgdb_handle_exception(int evector, int signo, int ecode, struct pt_regs *regs)
 {
 	struct kgdb_state kgdb_var;
 	struct kgdb_state *ks = &kgdb_var;
-	int ret;
 
 	ks->cpu			= raw_smp_processor_id();
 	ks->ex_vector		= evector;
@@ -689,11 +694,10 @@ kgdb_handle_exception(int evector, int signo, int ecode, struct pt_regs *regs)
 
 	if (kgdb_reenter_check(ks))
 		return 0; /* Ouch, double exception ! */
-	kgdb_info[ks->cpu].exception_state |= DCPU_WANT_MASTER;
-	ret = kgdb_cpu_enter(ks, regs);
-	kgdb_info[ks->cpu].exception_state &= ~(DCPU_WANT_MASTER |
-						DCPU_IS_SLAVE);
-	return ret;
+	if (kgdb_info[ks->cpu].enter_kgdb != 0)
+		return 0;
+
+	return kgdb_cpu_enter(ks, regs, DCPU_WANT_MASTER);
 }
 
 int kgdb_nmicallback(int cpu, void *regs)
@@ -706,12 +710,9 @@ int kgdb_nmicallback(int cpu, void *regs)
 	ks->cpu			= cpu;
 	ks->linux_regs		= regs;
 
-	if (!atomic_read(&cpu_in_kgdb[cpu]) &&
-	    atomic_read(&kgdb_active) != -1 &&
-	    atomic_read(&kgdb_active) != cpu) {
-		kgdb_info[cpu].exception_state |= DCPU_IS_SLAVE;
-		kgdb_cpu_enter(ks, regs);
-		kgdb_info[cpu].exception_state &= ~DCPU_IS_SLAVE;
+	if (kgdb_info[ks->cpu].enter_kgdb == 0 &&
+			raw_spin_is_locked(&dbg_master_lock)) {
+		kgdb_cpu_enter(ks, regs, DCPU_IS_SLAVE);
 		return 0;
 	}
 #endif
diff --git a/kernel/debug/debug_core.h b/kernel/debug/debug_core.h
index c5d753d80f67..3494c28a7e7a 100644
--- a/