Merge commit 'v2.6.38-rc5' into core/locking

Merge reason: pick up upstream fixes.

Signed-off-by: Ingo Molnar <mingo@elte.hu>

kernel/capability.c

@@ -306,7 +306,7 @@ int capable(int cap)
 		BUG();
 	}
 
-	if (security_capable(cap) == 0) {
+	if (security_capable(current_cred(), cap) == 0) {
 		current->flags |= PF_SUPERPRIV;
 		return 1;
 	}

kernel/cred.c

@@ -252,13 +252,13 @@ struct cred *cred_alloc_blank(void)
 #endif
 
 	atomic_set(&new->usage, 1);
+#ifdef CONFIG_DEBUG_CREDENTIALS
+	new->magic = CRED_MAGIC;
+#endif
 
 	if (security_cred_alloc_blank(new, GFP_KERNEL) < 0)
 		goto error;
 
-#ifdef CONFIG_DEBUG_CREDENTIALS
-	new->magic = CRED_MAGIC;
-#endif
 	return new;
 
 error:
@@ -657,6 +657,8 @@ struct cred *prepare_kernel_cred(struct task_struct *daemon)
 	validate_creds(old);
 
 	*new = *old;
+	atomic_set(&new->usage, 1);
+	set_cred_subscribers(new, 0);
 	get_uid(new->user);
 	get_group_info(new->group_info);
 
@@ -674,8 +676,6 @@ struct cred *prepare_kernel_cred(struct task_struct *daemon)
 	if (security_prepare_creds(new, old, GFP_KERNEL) < 0)
 		goto error;
 
-	atomic_set(&new->usage, 1);
-	set_cred_subscribers(new, 0);
 	put_cred(old);
 	validate_creds(new);
 	return new;
@@ -748,7 +748,11 @@ bool creds_are_invalid(const struct cred *cred)
 	if (cred->magic != CRED_MAGIC)
 		return true;
 #ifdef CONFIG_SECURITY_SELINUX
-	if (selinux_is_enabled()) {
+	/*
+	 * cred->security == NULL if security_cred_alloc_blank() or
+	 * security_prepare_creds() returned an error.
+	 */
+	if (selinux_is_enabled() && cred->security) {
 		if ((unsigned long) cred->security < PAGE_SIZE)
 			return true;
 		if ((*(u32 *)cred->security & 0xffffff00) ==

kernel/irq/migration.c

@@ -56,6 +56,7 @@ void move_masked_irq(int irq)
 void move_native_irq(int irq)
 {
 	struct irq_desc *desc = irq_to_desc(irq);
+	bool masked;
 
 	if (likely(!(desc->status & IRQ_MOVE_PENDING)))
 		return;
@@ -63,8 +64,15 @@ void move_native_irq(int irq)
 	if (unlikely(desc->status & IRQ_DISABLED))
 		return;
 
-	desc->irq_data.chip->irq_mask(&desc->irq_data);
+	/*
+	 * Be careful vs. already masked interrupts. If this is a
+	 * threaded interrupt with ONESHOT set, we can end up with an
+	 * interrupt storm.
+	 */
+	masked = desc->status & IRQ_MASKED;
+	if (!masked)
+		desc->irq_data.chip->irq_mask(&desc->irq_data);
 	move_masked_irq(irq);
-	desc->irq_data.chip->irq_unmask(&desc->irq_data);
+	if (!masked)
+		desc->irq_data.chip->irq_unmask(&desc->irq_data);
 }
-

kernel/module.c

@@ -2460,9 +2460,9 @@ static void find_module_sections(struct module *mod, struct load_info *info)
 #endif
 
 #ifdef CONFIG_TRACEPOINTS
-	mod->tracepoints = section_objs(info, "__tracepoints",
-					sizeof(*mod->tracepoints),
-					&mod->num_tracepoints);
+	mod->tracepoints_ptrs = section_objs(info, "__tracepoints_ptrs",
+					     sizeof(*mod->tracepoints_ptrs),
+					     &mod->num_tracepoints);
 #endif
 #ifdef HAVE_JUMP_LABEL
 	mod->jump_entries = section_objs(info, "__jump_table",
@@ -3393,7 +3393,7 @@ void module_layout(struct module *mod,
 		   struct modversion_info *ver,
 		   struct kernel_param *kp,
 		   struct kernel_symbol *ks,
-		   struct tracepoint *tp)
+		   struct tracepoint * const *tp)
 {
 }
 EXPORT_SYMBOL(module_layout);
@@ -3407,8 +3407,8 @@ void module_update_tracepoints(void)
 	mutex_lock(&module_mutex);
 	list_for_each_entry(mod, &modules, list)
 		if (!mod->taints)
-			tracepoint_update_probe_range(mod->tracepoints,
-				mod->tracepoints + mod->num_tracepoints);
+			tracepoint_update_probe_range(mod->tracepoints_ptrs,
+				mod->tracepoints_ptrs + mod->num_tracepoints);
 	mutex_unlock(&module_mutex);
 }
 
@@ -3432,8 +3432,8 @@ int module_get_iter_tracepoints(struct tracepoint_iter *iter)
 			else if (iter_mod > iter->module)
 				iter->tracepoint = NULL;
 			found = tracepoint_get_iter_range(&iter->tracepoint,
-				iter_mod->tracepoints,
-				iter_mod->tracepoints
+				iter_mod->tracepoints_ptrs,
+				iter_mod->tracepoints_ptrs
 					+ iter_mod->num_tracepoints);
 			if (found) {
 				iter->module = iter_mod;

kernel/perf_event.c

@@ -1901,11 +1901,12 @@ static void __perf_event_read(void *info)
 		return;
 
 	raw_spin_lock(&ctx->lock);
-	update_context_time(ctx);
+	if (ctx->is_active)
+		update_context_time(ctx);
 	update_event_times(event);
+	if (event->state == PERF_EVENT_STATE_ACTIVE)
+		event->pmu->read(event);
 	raw_spin_unlock(&ctx->lock);
-
-	event->pmu->read(event);
 }
 
 static inline u64 perf_event_count(struct perf_event *event)
@@ -1999,8 +2000,7 @@ static int alloc_callchain_buffers(void)
 	 * accessed from NMI. Use a temporary manual per cpu allocation
 	 * until that gets sorted out.
 	 */
-	size = sizeof(*entries) + sizeof(struct perf_callchain_entry *) *
-		num_possible_cpus();
+	size = offsetof(struct callchain_cpus_entries, cpu_entries[nr_cpu_ids]);
 
 	entries = kzalloc(size, GFP_KERNEL);
 	if (!entries)

kernel/printk.c

@@ -262,25 +262,47 @@ int dmesg_restrict = 1;
 int dmesg_restrict;
 #endif
 
+static int syslog_action_restricted(int type)
+{
+	if (dmesg_restrict)
+		return 1;
+	/* Unless restricted, we allow "read all" and "get buffer size" for everybody */
+	return type != SYSLOG_ACTION_READ_ALL && type != SYSLOG_ACTION_SIZE_BUFFER;
+}
+
+static int check_syslog_permissions(int type, bool from_file)
+{
+	/*
+	 * If this is from /proc/kmsg and we've already opened it, then we've
+	 * already done the capabilities checks at open time.
+	 */
+	if (from_file && type != SYSLOG_ACTION_OPEN)
+		return 0;
+
+	if (syslog_action_restricted(type)) {
+		if (capable(CAP_SYSLOG))
+			return 0;
+		/* For historical reasons, accept CAP_SYS_ADMIN too, with a warning */
+		if (capable(CAP_SYS_ADMIN)) {
+			WARN_ONCE(1, "Attempt to access syslog with CAP_SYS_ADMIN "
+				 "but no CAP_SYSLOG (deprecated).\n");
+			return 0;
+		}
+		return -EPERM;
+	}
+	return 0;
+}
+
 int do_syslog(int type, char __user *buf, int len, bool from_file)
 {
 	unsigned i, j, limit, count;
 	int do_clear = 0;
 	char c;
-	int error = 0;
+	int error;
 
-	/*
-	 * If this is from /proc/kmsg we only do the capabilities checks
-	 * at open time.
-	 */
-	if (type == SYSLOG_ACTION_OPEN || !from_file) {
-		if (dmesg_restrict && !capable(CAP_SYSLOG))
-			goto warn; /* switch to return -EPERM after 2.6.39 */
-		if ((type != SYSLOG_ACTION_READ_ALL &&
-		     type != SYSLOG_ACTION_SIZE_BUFFER) &&
-		    !capable(CAP_SYSLOG))
-			goto warn; /* switch to return -EPERM after 2.6.39 */
-	}
+	error = check_syslog_permissions(type, from_file);
+	if (error)
+		goto out;
 
 	error = security_syslog(type);
 	if (error)
@@ -423,12 +445,6 @@ int do_syslog(int type, char __user *buf, int len, bool from_file)
 	}
 out:
 	return error;
-warn:
-	/* remove after 2.6.39 */
-	if (capable(CAP_SYS_ADMIN))
-		WARN_ONCE(1, "Attempt to access syslog with CAP_SYS_ADMIN "
-		  "but no CAP_SYSLOG (deprecated and denied).\n");
-	return -EPERM;
 }
 
 SYSCALL_DEFINE3(syslog, int, type, char __user *, buf, int, len)

kernel/ptrace.c

@@ -313,7 +313,7 @@ int ptrace_detach(struct task_struct *child, unsigned int data)
 		child->exit_code = data;
 		dead = __ptrace_detach(current, child);
 		if (!child->exit_state)
-			wake_up_process(child);
+			wake_up_state(child, TASK_TRACED | TASK_STOPPED);
 	}
 	write_unlock_irq(&tasklist_lock);
 

kernel/sched_fair.c

@@ -722,10 +722,10 @@ static void update_cfs_load(struct cfs_rq *cfs_rq, int global_update)
 	u64 now, delta;
 	unsigned long load = cfs_rq->load.weight;
 
-	if (!cfs_rq)
+	if (cfs_rq->tg == &root_task_group)
 		return;
 
-	now = rq_of(cfs_rq)->clock;
+	now = rq_of(cfs_rq)->clock_task;
 	delta = now - cfs_rq->load_stamp;
 
 	/* truncate load history at 4 idle periods */
@@ -830,9 +830,6 @@ static void update_cfs_shares(struct cfs_rq *cfs_rq, long weight_delta)
 	struct sched_entity *se;
 	long shares;
 
-	if (!cfs_rq)
-		return;
-
 	tg = cfs_rq->tg;
 	se = tg->se[cpu_of(rq_of(cfs_rq))];
 	if (!se)
@@ -1432,7 +1429,7 @@ static inline unsigned long effective_load(struct task_group *tg, int cpu,
 
 static int wake_affine(struct sched_domain *sd, struct task_struct *p, int sync)
 {
-	unsigned long this_load, load;
+	s64 this_load, load;
 	int idx, this_cpu, prev_cpu;
 	unsigned long tl_per_task;
 	struct task_group *tg;
@@ -1471,8 +1468,8 @@ static int wake_affine(struct sched_domain *sd, struct task_struct *p, int sync)
 	 * Otherwise check if either cpus are near enough in load to allow this
 	 * task to be woken on this_cpu.
 	 */
-	if (this_load) {
-		unsigned long this_eff_load, prev_eff_load;
+	if (this_load > 0) {
+		s64 this_eff_load, prev_eff_load;
 
 		this_eff_load = 100;
 		this_eff_load *= power_of(prev_cpu);

kernel/sched_rt.c

@@ -625,7 +625,7 @@ static void update_curr_rt(struct rq *rq)
 	struct rt_rq *rt_rq = rt_rq_of_se(rt_se);
 	u64 delta_exec;
 
-	if (!task_has_rt_policy(curr))
+	if (curr->sched_class != &rt_sched_class)
 		return;
 
 	delta_exec = rq->clock_task - curr->se.exec_start;

kernel/sys.c

@@ -1385,7 +1385,8 @@ static int check_prlimit_permission(struct task_struct *task)
 	const struct cred *cred = current_cred(), *tcred;
 
 	tcred = __task_cred(task);
-	if ((cred->uid != tcred->euid ||
+	if (current != task &&
+	    (cred->uid != tcred->euid ||
 	     cred->uid != tcred->suid ||
 	     cred->uid != tcred->uid  ||
 	     cred->gid != tcred->egid ||

kernel/time/timer_list.c

@@ -41,7 +41,7 @@ static void print_name_offset(struct seq_file *m, void *sym)
 	char symname[KSYM_NAME_LEN];
 
 	if (lookup_symbol_name((unsigned long)sym, symname) < 0)
-		SEQ_printf(m, "<%p>", sym);
+		SEQ_printf(m, "<%pK>", sym);
 	else
 		SEQ_printf(m, "%s", symname);
 }
@@ -112,7 +112,7 @@ next_one:
 static void
 print_base(struct seq_file *m, struct hrtimer_clock_base *base, u64 now)
 {
-	SEQ_printf(m, "  .base:       %p\n", base);
+	SEQ_printf(m, "  .base:       %pK\n", base);
 	SEQ_printf(m, "  .index:      %d\n",
 			base->index);
 	SEQ_printf(m, "  .resolution: %Lu nsecs\n",

kernel/timer.c

@@ -959,7 +959,7 @@ EXPORT_SYMBOL(try_to_del_timer_sync);
  *
  * Synchronization rules: Callers must prevent restarting of the timer,
  * otherwise this function is meaningless. It must not be called from
- * hardirq contexts. The caller must not hold locks which would prevent
+ * 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.
@@ -969,10 +969,12 @@ EXPORT_SYMBOL(try_to_del_timer_sync);
 int del_timer_sync(struct timer_list *timer)
 {
 #ifdef CONFIG_LOCKDEP
-	local_bh_disable();
+	unsigned long flags;
+
+	local_irq_save(flags);
 	lock_map_acquire(&timer->lockdep_map);
 	lock_map_release(&timer->lockdep_map);
-	local_bh_enable();
+	local_irq_restore(flags);
 #endif
 	/*
 	 * don't use it in hardirq context, because it

kernel/trace/blktrace.c

@@ -138,6 +138,13 @@ void __trace_note_message(struct blk_trace *bt, const char *fmt, ...)
 		     !blk_tracer_enabled))
 		return;
 
+	/*
+	 * If the BLK_TC_NOTIFY action mask isn't set, don't send any note
+	 * message to the trace.
+	 */
+	if (!(bt->act_mask & BLK_TC_NOTIFY))
+		return;
+
 	local_irq_save(flags);
 	buf = per_cpu_ptr(bt->msg_data, smp_processor_id());
 	va_start(args, fmt);

kernel/trace/trace_events.c

@@ -1284,7 +1284,7 @@ trace_create_file_ops(struct module *mod)
 static void trace_module_add_events(struct module *mod)
 {
 	struct ftrace_module_file_ops *file_ops = NULL;
-	struct ftrace_event_call *call, *start, *end;
+	struct ftrace_event_call **call, **start, **end;
 
 	start = mod->trace_events;
 	end = mod->trace_events + mod->num_trace_events;
@@ -1297,7 +1297,7 @@ static void trace_module_add_events(struct module *mod)
 		return;
 
 	for_each_event(call, start, end) {
-		__trace_add_event_call(call, mod,
+		__trace_add_event_call(*call, mod,
 				       &file_ops->id, &file_ops->enable,
 				       &file_ops->filter, &file_ops->format);
 	}
@@ -1367,8 +1367,8 @@ static struct notifier_block trace_module_nb = {
 	.priority = 0,
 };
 
-extern struct ftrace_event_call __start_ftrace_events[];
-extern struct ftrace_event_call __stop_ftrace_events[];
+extern struct ftrace_event_call *__start_ftrace_events[];
+extern struct ftrace_event_call *__stop_ftrace_events[];
 
 static char bootup_event_buf[COMMAND_LINE_SIZE] __initdata;
 
@@ -1384,7 +1384,7 @@ __setup("trace_event=", setup_trace_event);
 
 static __init int event_trace_init(void)
 {
-	struct ftrace_event_call *call;
+	struct ftrace_event_call **call;
 	struct dentry *d_tracer;
 	struct dentry *entry;
 	struct dentry *d_events;
@@ -1430,7 +1430,7 @@ static __init int event_trace_init(void)
 		pr_warning("tracing: Failed to allocate common fields");
 
 	for_each_event(call, __start_ftrace_events, __stop_ftrace_events) {
-		__trace_add_event_call(call, NULL, &ftrace_event_id_fops,
+		__trace_add_event_call(*call, NULL, &ftrace_event_id_fops,
 				       &ftrace_enable_fops,
 				       &ftrace_event_filter_fops,
 				       &ftrace_event_format_fops);

kernel/trace/trace_export.c

@@ -161,13 +161,13 @@ struct ftrace_event_class event_class_ftrace_##call = {			\
 	.fields			= LIST_HEAD_INIT(event_class_ftrace_##call.fields),\
 };									\
 									\
-struct ftrace_event_call __used						\
-__attribute__((__aligned__(4)))						\
-__attribute__((section("_ftrace_events"))) event_##call = {		\
+struct ftrace_event_call __used event_##call = {			\
 	.name			= #call,				\
 	.event.type		= etype,				\
 	.class			= &event_class_ftrace_##call,		\
 	.print_fmt		= print,				\
 };									\
+struct ftrace_event_call __used						\
+__attribute__((section("_ftrace_events"))) *__event_##call = &event_##call;
 
 #include "trace_entries.h"

kernel/trace/trace_syscalls.c

@@ -55,20 +55,21 @@ struct ftrace_event_class event_class_syscall_exit = {
 	.raw_init	= init_syscall_trace,
 };
 
-extern unsigned long __start_syscalls_metadata[];
-extern unsigned long __stop_syscalls_metadata[];
+extern struct syscall_metadata *__start_syscalls_metadata[];
+extern struct syscall_metadata *__stop_syscalls_metadata[];
 
 static struct syscall_metadata **syscalls_metadata;
 
-static struct syscall_metadata *find_syscall_meta(unsigned long syscall)
+static __init struct syscall_metadata *
+find_syscall_meta(unsigned long syscall)
 {
-	struct syscall_metadata *start;
-	struct syscall_metadata *stop;
+	struct syscall_metadata **start;
+	struct syscall_metadata **stop;
 	char str[KSYM_SYMBOL_LEN];
 
 
-	start = (struct syscall_metadata *)__start_syscalls_metadata;
-	stop = (struct syscall_metadata *)__stop_syscalls_metadata;
+	start = __start_syscalls_metadata;
+	stop = __stop_syscalls_metadata;
 	kallsyms_lookup(syscall, NULL, NULL, NULL, str);
 
 	for ( ; start < stop; start++) {
@@ -78,8 +79,8 @@ static struct syscall_metadata *find_syscall_meta(unsigned long syscall)
 		 * with "SyS" instead of "sys", leading to an unwanted
 		 * mismatch.
 		 */
-		if (start->name && !strcmp(start->name + 3, str + 3))
-			return start;
+		if ((*start)->name && !strcmp((*start)->name + 3, str + 3))
+			return *start;
 	}
 	return NULL;
 }

kernel/tracepoint.c

@@ -27,8 +27,8 @@
 #include <linux/sched.h>
 #include <linux/jump_label.h>
 
-extern struct tracepoint __start___tracepoints[];
-extern struct tracepoint __stop___tracepoints[];
+extern struct tracepoint * const __start___tracepoints_ptrs[];
+extern struct tracepoint * const __stop___tracepoints_ptrs[];
 
 /* Set to 1 to enable tracepoint debug output */
 static const int tracepoint_debug;
@@ -298,10 +298,10 @@ static void disable_tracepoint(struct tracepoint *elem)
  *
  * Updates the probe callback corresponding to a range of tracepoints.
  */
-void
-tracepoint_update_probe_range(struct tracepoint *begin, struct tracepoint *end)
+void tracepoint_update_probe_range(struct tracepoint * const *begin,
+				   struct tracepoint * const *end)
 {
-	struct tracepoint *iter;
+	struct tracepoint * const *iter;
 	struct tracepoint_entry *mark_entry;
 
 	if (!begin)
@@ -309,12 +309,12 @@ tracepoint_update_probe_range(struct tracepoint *begin, struct tracepoint *end)
 
 	mutex_lock(&tracepoints_mutex);
 	for (iter = begin; iter < end; iter++) {
-		mark_entry = get_tracepoint(iter->name);
+		mark_entry = get_tracepoint((*iter)->name);
 		if (mark_entry) {
-			set_tracepoint(&mark_entry, iter,
+			set_tracepoint(&mark_entry, *iter,
 					!!mark_entry->refcount);
 		} else {
-			disable_tracepoint(iter);
+			disable_tracepoint(*iter);
 		}
 	}
 	mutex_unlock(&tracepoints_mutex);
@@ -326,8 +326,8 @@ tracepoint_update_probe_range(struct tracepoint *begin, struct tracepoint *end)
 static void tracepoint_update_probes(void)
 {
 	/* Core kernel tracepoints */
-	tracepoint_update_probe_range(__start___tracepoints,
-		__stop___tracepoints);
+	tracepoint_update_probe_range(__start___tracepoints_ptrs,
+		__stop___tracepoints_ptrs);
 	/* tracepoints in modules. */
 	module_update_tracepoints();
 }
@@ -514,8 +514,8 @@ EXPORT_SYMBOL_GPL(tracepoint_probe_update_all);
  * Will return the first tracepoint in the range if the input tracepoint is
  * NULL.
  */
-int tracepoint_get_iter_range(struct tracepoint **tracepoint,
-	struct tracepoint *begin, struct tracepoint *end)
+int tracepoint_get_iter_range(struct tracepoint * const **tracepoint,
+	struct tracepoint * const *begin, struct tracepoint * const *end)
 {
 	if (!*tracepoint && begin != end) {
 		*tracepoint = begin;
@@ -534,7 +534,8 @@ static void tracepoint_get_iter(struct tracepoint_iter *iter)
 	/* Core kernel tracepoints */
 	if (!iter->module) {
 		found = tracepoint_get_iter_range(&iter->tracepoint,
-				__start___tracepoints, __stop___tracepoints);
+				__start___tracepoints_ptrs,
+				__stop___tracepoints_ptrs);
 		if (found)
 			goto end;
 	}
@@ -585,8 +586,8 @@ int tracepoint_module_notify(struct notifier_block *self,
 	switch (val) {
 	case MODULE_STATE_COMING:
 	case MODULE_STATE_GOING:
-		tracepoint_update_probe_range(mod->tracepoints,
-			mod->tracepoints + mod->num_tracepoints);
+		tracepoint_update_probe_range(mod->tracepoints_ptrs,
+			mod->tracepoints_ptrs + mod->num_tracepoints);
 		break;
 	}
 	return 0;

kernel/watchdog.c

@@ -27,7 +27,7 @@
 #include <asm/irq_regs.h>
 #include <linux/perf_event.h>
 
-int watchdog_enabled;
+int watchdog_enabled = 1;
 int __read_mostly softlockup_thresh = 60;
 
 static DEFINE_PER_CPU(unsigned long, watchdog_touch_ts);
@@ -43,9 +43,6 @@ static DEFINE_PER_CPU(unsigned long, hrtimer_interrupts_saved);
 static DEFINE_PER_CPU(struct perf_event *, watchdog_ev);
 #endif
 
-static int no_watchdog;
-
-
 /* boot commands */
 /*
  * Should we panic when a soft-lockup or hard-lockup occurs:
@@ -58,7 +55,7 @@ static int __init hardlockup_panic_setup(char *str)
 	if (!strncmp(str, "panic", 5))
 		hardlockup_panic = 1;
 	else if (!strncmp(str, "0", 1))
-		no_watchdog = 1;
+		watchdog_enabled = 0;
 	return 1;
 }
 __setup("nmi_watchdog=", hardlockup_panic_setup);
@@ -77,7 +74,7 @@ __setup("softlockup_panic=", softlockup_panic_setup);
 
 static int __init nowatchdog_setup(char *str)
 {
-	no_watchdog = 1;
+	watchdog_enabled = 0;
 	return 1;
 }
 __setup("nowatchdog", nowatchdog_setup);
@@ -85,7 +82,7 @@ __setup("nowatchdog", nowatchdog_setup);
 /* deprecated */
 static int __init nosoftlockup_setup(char *str)
 {
-	no_watchdog = 1;
+	watchdog_enabled = 0;
 	return 1;
 }
 __setup("nosoftlockup", nosoftlockup_setup);
@@ -366,8 +363,14 @@ static int watchdog_nmi_enable(int cpu)
 		goto out_save;
 	}
 
-	printk(KERN_ERR "NMI watchdog disabled for cpu%i: unable to create perf event: %ld\n",
-	       cpu, PTR_ERR(event));
+
+	/* vary the KERN level based on the returned errno */
+	if (PTR_ERR(event) == -EOPNOTSUPP)
+		printk(KERN_INFO "NMI watchdog disabled (cpu%i): not supported (no LAPIC?)\n", cpu);
+	else if (PTR_ERR(event) == -ENOENT)
+		printk(KERN_WARNING "NMI watchdog disabled (cpu%i): hardware events not enabled\n", cpu);
+	else
+		printk(KERN_ERR "NMI watchdog disabled (cpu%i): unable to create perf event: %ld\n", cpu, PTR_ERR(event));
 	return PTR_ERR(event);
 
 	/* success path */
@@ -432,9 +435,6 @@ static int watchdog_enable(int cpu)
 		wake_up_process(p);
 	}
 
-	/* if any cpu succeeds, watchdog is considered enabled for the system */
-	watchdog_enabled = 1;
-
 	return 0;
 }
 
@@ -462,12 +462,16 @@ static void watchdog_disable(int cpu)
 static void watchdog_enable_all_cpus(void)
 {
 	int cpu;
-	int result = 0;
+
+	watchdog_enabled = 0;
 
 	for_each_online_cpu(cpu)
-		result += watchdog_enable(cpu);
+		if (!watchdog_enable(cpu))
+			/* if any cpu succeeds, watchdog is considered
+			   enabled for the system */
+			watchdog_enabled = 1;
 
-	if (result)
+	if (!watchdog_enabled)
 		printk(KERN_ERR "watchdog: failed to be enabled on some cpus\n");
 
 }
@@ -476,9 +480,6 @@ static void watchdog_disable_all_cpus(void)
 {
 	int cpu;
 
-	if (no_watchdog)
-		return;
-
 	for_each_online_cpu(cpu)
 		watchdog_disable(cpu);
 
@@ -498,10 +499,12 @@ int proc_dowatchdog_enabled(struct ctl_table *table, int write,
 {
 	proc_dointvec(table, write, buffer, length, ppos);
 
-	if (watchdog_enabled)
-		watchdog_enable_all_cpus();
-	else
-		watchdog_disable_all_cpus();
+	if (write) {
+		if (watchdog_enabled)
+			watchdog_enable_all_cpus();
+		else
+			watchdog_disable_all_cpus();
+	}
 	return 0;
 }
 
@@ -530,7 +533,8 @@ cpu_callback(struct notifier_block *nfb, unsigned long action, void *hcpu)
 		break;
 	case CPU_ONLINE:
 	case CPU_ONLINE_FROZEN:
-		err = watchdog_enable(hotcpu);
+		if (watchdog_enabled)
+			err = watchdog_enable(hotcpu);
 		break;
 #ifdef CONFIG_HOTPLUG_CPU
 	case CPU_UP_CANCELED:
@@ -555,9 +559,6 @@ void __init lockup_detector_init(void)
 	void *cpu = (void *)(long)smp_processor_id();
 	int err;
 
-	if (no_watchdog)
-		return;
-
 	err = cpu_callback(&cpu_nfb, CPU_UP_PREPARE, cpu);
 	WARN_ON(notifier_to_errno(err));