Merge branch 'irq/urgent' into irq/core

Reason: Further patches are conflicting with mainline fixes

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>

15 files changed, 105 insertions, 55 deletions

diff --git a/kernel/capability.c b/kernel/capability.c
index 2f05303715a..9e9385f132c 100644
--- a/kernel/capability.c
+++ b/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;
 	}
diff --git a/kernel/irq/internals.h b/kernel/irq/internals.h
index 4571ae7e085..99c3bc8a6fb 100644
--- a/kernel/irq/internals.h
+++ b/kernel/irq/internals.h
@@ -3,6 +3,12 @@
  */
 #include <linux/irqdesc.h>
 
+#ifdef CONFIG_SPARSE_IRQ
+# define IRQ_BITMAP_BITS	(NR_IRQS + 8196)
+#else
+# define IRQ_BITMAP_BITS	NR_IRQS
+#endif
+
 extern int noirqdebug;
 
 #define irq_data_to_desc(data)	container_of(data, struct irq_desc, irq_data)
diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c
index a7ac6e1e707..a250d3a0af1 100644
--- a/kernel/irq/irqdesc.c
+++ b/kernel/irq/irqdesc.c
@@ -94,7 +94,7 @@ int nr_irqs = NR_IRQS;
 EXPORT_SYMBOL_GPL(nr_irqs);
 
 static DEFINE_MUTEX(sparse_irq_lock);
-static DECLARE_BITMAP(allocated_irqs, NR_IRQS);
+static DECLARE_BITMAP(allocated_irqs, IRQ_BITMAP_BITS);
 
 #ifdef CONFIG_SPARSE_IRQ
 
@@ -217,6 +217,15 @@ int __init early_irq_init(void)
 	initcnt = arch_probe_nr_irqs();
 	printk(KERN_INFO "NR_IRQS:%d nr_irqs:%d %d\n", NR_IRQS, nr_irqs, initcnt);
 
+	if (WARN_ON(nr_irqs > IRQ_BITMAP_BITS))
+		nr_irqs = IRQ_BITMAP_BITS;
+
+	if (WARN_ON(initcnt > IRQ_BITMAP_BITS))
+		initcnt = IRQ_BITMAP_BITS;
+
+	if (initcnt > nr_irqs)
+		nr_irqs = initcnt;
+
 	for (i = 0; i < initcnt; i++) {
 		desc = alloc_desc(i, node);
 		set_bit(i, allocated_irqs);
diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
index 47b2bf10afb..ba84307fbf2 100644
--- a/kernel/irq/manage.c
+++ b/kernel/irq/manage.c
@@ -1196,7 +1196,7 @@ int request_threaded_irq(unsigned int irq, irq_handler_t handler,
 	if (retval)
 		kfree(action);
 
-#ifdef CONFIG_DEBUG_SHIRQ
+#ifdef CONFIG_DEBUG_SHIRQ_FIXME
 	if (!retval && (irqflags & IRQF_SHARED)) {
 		/*
 		 * It's a shared IRQ -- the driver ought to be prepared for it
diff --git a/kernel/irq/resend.c b/kernel/irq/resend.c
index 891115a929a..dc49358b73f 100644
--- a/kernel/irq/resend.c
+++ b/kernel/irq/resend.c
@@ -23,7 +23,7 @@
 #ifdef CONFIG_HARDIRQS_SW_RESEND
 
 /* Bitmap to handle software resend of interrupts: */
-static DECLARE_BITMAP(irqs_resend, NR_IRQS);
+static DECLARE_BITMAP(irqs_resend, IRQ_BITMAP_BITS);
 
 /*
  * Run software resends of IRQ's
diff --git a/kernel/power/main.c b/kernel/power/main.c
index 7b5db6a8561..701853042c2 100644
--- a/kernel/power/main.c
+++ b/kernel/power/main.c
@@ -326,7 +326,7 @@ EXPORT_SYMBOL_GPL(pm_wq);
 
 static int __init pm_start_workqueue(void)
 {
-	pm_wq = alloc_workqueue("pm", WQ_FREEZEABLE, 0);
+	pm_wq = alloc_workqueue("pm", WQ_FREEZABLE, 0);
 
 	return pm_wq ? 0 : -ENOMEM;
 }
diff --git a/kernel/power/process.c b/kernel/power/process.c
index d6d2a10320e..0cf3a27a6c9 100644
--- a/kernel/power/process.c
+++ b/kernel/power/process.c
@@ -22,7 +22,7 @@
  */
 #define TIMEOUT	(20 * HZ)
 
-static inline int freezeable(struct task_struct * p)
+static inline int freezable(struct task_struct * p)
 {
 	if ((p == current) ||
 	    (p->flags & PF_NOFREEZE) ||
@@ -53,7 +53,7 @@ static int try_to_freeze_tasks(bool sig_only)
 		todo = 0;
 		read_lock(&tasklist_lock);
 		do_each_thread(g, p) {
-			if (frozen(p) || !freezeable(p))
+			if (frozen(p) || !freezable(p))
 				continue;
 
 			if (!freeze_task(p, sig_only))
@@ -167,7 +167,7 @@ static void thaw_tasks(bool nosig_only)
 
 	read_lock(&tasklist_lock);
 	do_each_thread(g, p) {
-		if (!freezeable(p))
+		if (!freezable(p))
 			continue;
 
 		if (nosig_only && should_send_signal(p))
diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c
index 0dac75ea445..64db648ff91 100644
--- a/kernel/power/snapshot.c
+++ b/kernel/power/snapshot.c
@@ -1519,11 +1519,8 @@ static int
 swsusp_alloc(struct memory_bitmap *orig_bm, struct memory_bitmap *copy_bm,
 		unsigned int nr_pages, unsigned int nr_highmem)
 {
-	int error = 0;
-
 	if (nr_highmem > 0) {
-		error = get_highmem_buffer(PG_ANY);
-		if (error)
+		if (get_highmem_buffer(PG_ANY))
 			goto err_out;
 		if (nr_highmem > alloc_highmem) {
 			nr_highmem -= alloc_highmem;
@@ -1546,7 +1543,7 @@ swsusp_alloc(struct memory_bitmap *orig_bm, struct memory_bitmap *copy_bm,
 
  err_out:
 	swsusp_free();
-	return error;
+	return -ENOMEM;
 }
 
 asmlinkage int swsusp_save(void)
diff --git a/kernel/printk.c b/kernel/printk.c
index 2ddbdc73aad..36231525e22 100644
--- a/kernel/printk.c
+++ b/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)
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index 99bbaa3e5b0..1708b1e2972 100644
--- a/kernel/ptrace.c
+++ b/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);
 
diff --git a/kernel/time/timer_list.c b/kernel/time/timer_list.c
index 32a19f9397f..3258455549f 100644
--- a/kernel/time/timer_list.c
+++ b/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",
diff --git a/kernel/timer.c b/kernel/timer.c
index d53ce66daea..d6459923d24 100644
--- a/kernel/timer.c
+++ b/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.
@@ -971,12 +971,10 @@ int del_timer_sync(struct timer_list *timer)
 #ifdef CONFIG_LOCKDEP
 	unsigned long flags;
 
-	raw_local_irq_save(flags);
-	local_bh_disable();
+	local_irq_save(flags);
 	lock_map_acquire(&timer->lockdep_map);
 	lock_map_release(&timer->lockdep_map);
-	_local_bh_enable();
-	raw_local_irq_restore(flags);
+	local_irq_restore(flags);
 #endif
 	/*
 	 * don't use it in hardirq context, because it
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index 153562d0b93..d95721f3370 100644
--- a/kernel/trace/blktrace.c
+++ b/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);
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index f37f974aa81..18bb15776c5 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -363,8 +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 */
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 11869faa681..ee6578b578a 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -79,7 +79,9 @@ enum {
 	MAX_IDLE_WORKERS_RATIO	= 4,		/* 1/4 of busy can be idle */
 	IDLE_WORKER_TIMEOUT	= 300 * HZ,	/* keep idle ones for 5 mins */
 
-	MAYDAY_INITIAL_TIMEOUT	= HZ / 100,	/* call for help after 10ms */
+	MAYDAY_INITIAL_TIMEOUT  = HZ / 100 >= 2 ? HZ / 100 : 2,
+						/* call for help after 10ms
+						   (min two ticks) */
 	MAYDAY_INTERVAL		= HZ / 10,	/* and then every 100ms */
 	CREATE_COOLDOWN		= HZ,		/* time to breath after fail */
 	TRUSTEE_COOLDOWN	= HZ / 10,	/* for trustee draining */
@@ -2047,6 +2049,15 @@ repeat:
 				move_linked_works(work, scheduled, &n);
 
 		process_scheduled_works(rescuer);
+
+		/*
+		 * Leave this gcwq.  If keep_working() is %true, notify a
+		 * regular worker; otherwise, we end up with 0 concurrency
+		 * and stalling the execution.
+		 */
+		if (keep_working(gcwq))
+			wake_up_worker(gcwq);
+
 		spin_unlock_irq(&gcwq->lock);
 	}
 
@@ -2956,7 +2967,7 @@ struct workqueue_struct *__alloc_workqueue_key(const char *name,
 	 */
 	spin_lock(&workqueue_lock);
 
-	if (workqueue_freezing && wq->flags & WQ_FREEZEABLE)
+	if (workqueue_freezing && wq->flags & WQ_FREEZABLE)
 		for_each_cwq_cpu(cpu, wq)
 			get_cwq(cpu, wq)->max_active = 0;
 
@@ -3068,7 +3079,7 @@ void workqueue_set_max_active(struct workqueue_struct *wq, int max_active)
 
 		spin_lock_irq(&gcwq->lock);
 
-		if (!(wq->flags & WQ_FREEZEABLE) ||
+		if (!(wq->flags & WQ_FREEZABLE) ||
 		    !(gcwq->flags & GCWQ_FREEZING))
 			get_cwq(gcwq->cpu, wq)->max_active = max_active;
 
@@ -3318,7 +3329,7 @@ static int __cpuinit trustee_thread(void *__gcwq)
 	 * want to get it over with ASAP - spam rescuers, wake up as
 	 * many idlers as necessary and create new ones till the
 	 * worklist is empty.  Note that if the gcwq is frozen, there
-	 * may be frozen works in freezeable cwqs.  Don't declare
+	 * may be frozen works in freezable cwqs.  Don't declare
 	 * completion while frozen.
 	 */
 	while (gcwq->nr_workers != gcwq->nr_idle ||
@@ -3576,9 +3587,9 @@ EXPORT_SYMBOL_GPL(work_on_cpu);
 /**
  * freeze_workqueues_begin - begin freezing workqueues
  *
- * Start freezing workqueues.  After this function returns, all
- * freezeable workqueues will queue new works to their frozen_works
- * list instead of gcwq->worklist.
+ * Start freezing workqueues.  After this function returns, all freezable
+ * workqueues will queue new works to their frozen_works list instead of
+ * gcwq->worklist.
  *
  * CONTEXT:
  * Grabs and releases workqueue_lock and gcwq->lock's.
@@ -3604,7 +3615,7 @@ void freeze_workqueues_begin(void)
 		list_for_each_entry(wq, &workqueues, list) {
 			struct cpu_workqueue_struct *cwq = get_cwq(cpu, wq);
 
-			if (cwq && wq->flags & WQ_FREEZEABLE)
+			if (cwq && wq->flags & WQ_FREEZABLE)
 				cwq->max_active = 0;
 		}
 
@@ -3615,7 +3626,7 @@ void freeze_workqueues_begin(void)
 }
 
 /**
- * freeze_workqueues_busy - are freezeable workqueues still busy?
+ * freeze_workqueues_busy - are freezable workqueues still busy?
  *
  * Check whether freezing is complete.  This function must be called
  * between freeze_workqueues_begin() and thaw_workqueues().
@@ -3624,8 +3635,8 @@ void freeze_workqueues_begin(void)
  * Grabs and releases workqueue_lock.
  *
  * RETURNS:
- * %true if some freezeable workqueues are still busy.  %false if
- * freezing is complete.
+ * %true if some freezable workqueues are still busy.  %false if freezing
+ * is complete.
  */
 bool freeze_workqueues_busy(void)
 {
@@ -3645,7 +3656,7 @@ bool freeze_workqueues_busy(void)
 		list_for_each_entry(wq, &workqueues, list) {
 			struct cpu_workqueue_struct *cwq = get_cwq(cpu, wq);
 
-			if (!cwq || !(wq->flags & WQ_FREEZEABLE))
+			if (!cwq || !(wq->flags & WQ_FREEZABLE))
 				continue;
 
 			BUG_ON(cwq->nr_active < 0);
@@ -3690,7 +3701,7 @@ void thaw_workqueues(void)
 		list_for_each_entry(wq, &workqueues, list) {
 			struct cpu_workqueue_struct *cwq = get_cwq(cpu, wq);
 
-			if (!cwq || !(wq->flags & WQ_FREEZEABLE))
+			if (!cwq || !(wq->flags & WQ_FREEZABLE))
 				continue;
 
 			/* restore max_active and repopulate worklist */