Merge branch 'master' into export-slabh

kernel/cgroup_freezer.c

@@ -48,17 +48,20 @@ static inline struct freezer *task_freezer(struct task_struct *task)
 			    struct freezer, css);
 }
 
-int cgroup_frozen(struct task_struct *task)
+int cgroup_freezing_or_frozen(struct task_struct *task)
 {
 	struct freezer *freezer;
 	enum freezer_state state;
 
 	task_lock(task);
 	freezer = task_freezer(task);
-	state = freezer->state;
+	if (!freezer->css.cgroup->parent)
+		state = CGROUP_THAWED; /* root cgroup can't be frozen */
+	else
+		state = freezer->state;
 	task_unlock(task);
 
-	return state == CGROUP_FROZEN;
+	return (state == CGROUP_FREEZING) || (state == CGROUP_FROZEN);
 }
 
 /*

kernel/cred.c

@@ -365,7 +365,7 @@ struct cred *prepare_usermodehelper_creds(void)
 
 	new = kmem_cache_alloc(cred_jar, GFP_ATOMIC);
 	if (!new)
-		return NULL;
+		goto free_tgcred;
 
 	kdebug("prepare_usermodehelper_creds() alloc %p", new);
 
@@ -398,6 +398,10 @@ struct cred *prepare_usermodehelper_creds(void)
 
 error:
 	put_cred(new);
+free_tgcred:
+#ifdef CONFIG_KEYS
+	kfree(tgcred);
+#endif
 	return NULL;
 }
 

kernel/early_res.c

@@ -333,6 +333,12 @@ void __init free_early_partial(u64 start, u64 end)
 	struct early_res *r;
 	int i;
 
+	if (start == end)
+		return;
+
+	if (WARN_ONCE(start > end, "  wrong range [%#llx, %#llx]\n", start, end))
+		return;
+
 try_next:
 	i = find_overlapped_early(start, end);
 	if (i >= max_early_res)

kernel/kgdb.c

@@ -69,9 +69,16 @@ struct kgdb_state {
 	struct pt_regs		*linux_regs;
 };
 
+/* Exception state values */
+#define DCPU_WANT_MASTER 0x1 /* Waiting to become a master kgdb cpu */
+#define DCPU_NEXT_MASTER 0x2 /* Transition from one master cpu to another */
+#define DCPU_IS_SLAVE    0x4 /* Slave cpu enter exception */
+#define DCPU_SSTEP       0x8 /* CPU is single stepping */
+
 static struct debuggerinfo_struct {
 	void			*debuggerinfo;
 	struct task_struct	*task;
+	int 			exception_state;
 } kgdb_info[NR_CPUS];
 
 /**
@@ -391,27 +398,22 @@ int kgdb_mem2hex(char *mem, char *buf, int count)
 
 /*
  * Copy the binary array pointed to by buf into mem.  Fix $, #, and
- * 0x7d escaped with 0x7d.  Return a pointer to the character after
- * the last byte written.
+ * 0x7d escaped with 0x7d. Return -EFAULT on failure or 0 on success.
+ * The input buf is overwitten with the result to write to mem.
  */
 static int kgdb_ebin2mem(char *buf, char *mem, int count)
 {
-	int err = 0;
-	char c;
+	int size = 0;
+	char *c = buf;
 
 	while (count-- > 0) {
-		c = *buf++;
-		if (c == 0x7d)
-			c = *buf++ ^ 0x20;
-
-		err = probe_kernel_write(mem, &c, 1);
-		if (err)
-			break;
-
-		mem++;
+		c[size] = *buf++;
+		if (c[size] == 0x7d)
+			c[size] = *buf++ ^ 0x20;
+		size++;
 	}
 
-	return err;
+	return probe_kernel_write(mem, c, size);
 }
 
 /*
@@ -562,49 +564,6 @@ static struct task_struct *getthread(struct pt_regs *regs, int tid)
 	return find_task_by_pid_ns(tid, &init_pid_ns);
 }
 
-/*
- * CPU debug state control:
- */
-
-#ifdef CONFIG_SMP
-static void kgdb_wait(struct pt_regs *regs)
-{
-	unsigned long flags;
-	int cpu;
-
-	local_irq_save(flags);
-	cpu = raw_smp_processor_id();
-	kgdb_info[cpu].debuggerinfo = regs;
-	kgdb_info[cpu].task = current;
-	/*
-	 * Make sure the above info reaches the primary CPU before
-	 * our cpu_in_kgdb[] flag setting does:
-	 */
-	smp_wmb();
-	atomic_set(&cpu_in_kgdb[cpu], 1);
-
-	/* Disable any cpu specific hw breakpoints */
-	kgdb_disable_hw_debug(regs);
-
-	/* Wait till primary CPU is done with debugging */
-	while (atomic_read(&passive_cpu_wait[cpu]))
-		cpu_relax();
-
-	kgdb_info[cpu].debuggerinfo = NULL;
-	kgdb_info[cpu].task = NULL;
-
-	/* fix up hardware debug registers on local cpu */
-	if (arch_kgdb_ops.correct_hw_break)
-		arch_kgdb_ops.correct_hw_break();
-
-	/* Signal the primary CPU that we are done: */
-	atomic_set(&cpu_in_kgdb[cpu], 0);
-	touch_softlockup_watchdog_sync();
-	clocksource_touch_watchdog();
-	local_irq_restore(flags);
-}
-#endif
-
 /*
  * Some architectures need cache flushes when we set/clear a
  * breakpoint:
@@ -1400,34 +1359,13 @@ static int kgdb_reenter_check(struct kgdb_state *ks)
 	return 1;
 }
 
-/*
- * kgdb_handle_exception() - main entry point from a kernel exception
- *
- * Locking hierarchy:
- *	interface locks, if any (begin_session)
- *	kgdb lock (kgdb_active)
- */
-int
-kgdb_handle_exception(int evector, int signo, int ecode, struct pt_regs *regs)
+static int kgdb_cpu_enter(struct kgdb_state *ks, struct pt_regs *regs)
 {
-	struct kgdb_state kgdb_var;
-	struct kgdb_state *ks = &kgdb_var;
 	unsigned long flags;
 	int sstep_tries = 100;
 	int error = 0;
 	int i, cpu;
-
-	ks->cpu			= raw_smp_processor_id();
-	ks->ex_vector		= evector;
-	ks->signo		= signo;
-	ks->ex_vector		= evector;
-	ks->err_code		= ecode;
-	ks->kgdb_usethreadid	= 0;
-	ks->linux_regs		= regs;
-
-	if (kgdb_reenter_check(ks))
-		return 0; /* Ouch, double exception ! */
-
+	int trace_on = 0;
 acquirelock:
 	/*
 	 * Interrupts will be restored by the 'trap return' code, except when
@@ -1435,13 +1373,43 @@ acquirelock:
 	 */
 	local_irq_save(flags);
 
-	cpu = raw_smp_processor_id();
+	cpu = ks->cpu;
+	kgdb_info[cpu].debuggerinfo = regs;
+	kgdb_info[cpu].task = current;
+	/*
+	 * Make sure the above info reaches the primary CPU before
+	 * our cpu_in_kgdb[] flag setting does:
+	 */
+	atomic_inc(&cpu_in_kgdb[cpu]);
 
 	/*
-	 * Acquire the kgdb_active lock:
+	 * CPU will loop if it is a slave or request to become a kgdb
+	 * master cpu and acquire the kgdb_active lock:
 	 */
-	while (atomic_cmpxchg(&kgdb_active, -1, cpu) != -1)
+	while (1) {
+		if (kgdb_info[cpu].exception_state & DCPU_WANT_MASTER) {
+			if (atomic_cmpxchg(&kgdb_active, -1, cpu) == cpu)
+				break;
+		} else if (kgdb_info[cpu].exception_state & DCPU_IS_SLAVE) {
+			if (!atomic_read(&passive_cpu_wait[cpu]))
+				goto return_normal;
+		} else {
+return_normal:
+			/* Return to normal operation by executing any
+			 * hw breakpoint fixup.
+			 */
+			if (arch_kgdb_ops.correct_hw_break)
+				arch_kgdb_ops.correct_hw_break();
+			if (trace_on)
+				tracing_on();
+			atomic_dec(&cpu_in_kgdb[cpu]);
+			touch_softlockup_watchdog_sync();
+			clocksource_touch_watchdog();
+			local_irq_restore(flags);
+			return 0;
+		}
 		cpu_relax();
+	}
 
 	/*
 	 * For single stepping, try to only enter on the processor
@@ -1475,9 +1443,6 @@ acquirelock:
 	if (kgdb_io_ops->pre_exception)
 		kgdb_io_ops->pre_exception();
 
-	kgdb_info[ks->cpu].debuggerinfo = ks->linux_regs;
-	kgdb_info[ks->cpu].task = current;
-
 	kgdb_disable_hw_debug(ks->linux_regs);
 
 	/*
@@ -1486,15 +1451,9 @@ acquirelock:
 	 */
 	if (!kgdb_single_step) {
 		for (i = 0; i < NR_CPUS; i++)
-			atomic_set(&passive_cpu_wait[i], 1);
+			atomic_inc(&passive_cpu_wait[i]);
 	}
 
-	/*
-	 * spin_lock code is good enough as a barrier so we don't
-	 * need one here:
-	 */
-	atomic_set(&cpu_in_kgdb[ks->cpu], 1);
-
 #ifdef CONFIG_SMP
 	/* Signal the other CPUs to enter kgdb_wait() */
 	if ((!kgdb_single_step) && kgdb_do_roundup)
@@ -1518,6 +1477,9 @@ acquirelock:
 	kgdb_single_step = 0;
 	kgdb_contthread = current;
 	exception_level = 0;
+	trace_on = tracing_is_on();
+	if (trace_on)
+		tracing_off();
 
 	/* Talk to debugger with gdbserial protocol */
 	error = gdb_serial_stub(ks);
@@ -1526,13 +1488,11 @@ acquirelock:
 	if (kgdb_io_ops->post_exception)
 		kgdb_io_ops->post_exception();
 
-	kgdb_info[ks->cpu].debuggerinfo = NULL;
-	kgdb_info[ks->cpu].task = NULL;
-	atomic_set(&cpu_in_kgdb[ks->cpu], 0);
+	atomic_dec(&cpu_in_kgdb[ks->cpu]);
 
 	if (!kgdb_single_step) {
 		for (i = NR_CPUS-1; i >= 0; i--)
-			atomic_set(&passive_cpu_wait[i], 0);
+			atomic_dec(&passive_cpu_wait[i]);
 		/*
 		 * Wait till all the CPUs have quit
 		 * from the debugger.
@@ -1551,6 +1511,8 @@ kgdb_restore:
 		else
 			kgdb_sstep_pid = 0;
 	}
+	if (trace_on)
+		tracing_on();
 	/* Free kgdb_active */
 	atomic_set(&kgdb_active, -1);
 	touch_softlockup_watchdog_sync();
@@ -1560,13 +1522,52 @@ kgdb_restore:
 	return error;
 }
 
+/*
+ * kgdb_handle_exception() - main entry point from a kernel exception
+ *
+ * Locking hierarchy:
+ *	interface locks, if any (begin_session)
+ *	kgdb lock (kgdb_active)
+ */
+int
+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;
+	ks->signo		= signo;
+	ks->ex_vector		= evector;
+	ks->err_code		= ecode;
+	ks->kgdb_usethreadid	= 0;
+	ks->linux_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;
+	return ret;
+}
+
 int kgdb_nmicallback(int cpu, void *regs)
 {
 #ifdef CONFIG_SMP
+	struct kgdb_state kgdb_var;
+	struct kgdb_state *ks = &kgdb_var;
+
+	memset(ks, 0, sizeof(struct kgdb_state));
+	ks->cpu			= cpu;
+	ks->linux_regs		= regs;
+
 	if (!atomic_read(&cpu_in_kgdb[cpu]) &&
-			atomic_read(&kgdb_active) != cpu &&
-			atomic_read(&cpu_in_kgdb[atomic_read(&kgdb_active)])) {
-		kgdb_wait((struct pt_regs *)regs);
+	    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;
 		return 0;
 	}
 #endif
@@ -1742,11 +1743,11 @@ EXPORT_SYMBOL_GPL(kgdb_unregister_io_module);
  */
 void kgdb_breakpoint(void)
 {
-	atomic_set(&kgdb_setting_breakpoint, 1);
+	atomic_inc(&kgdb_setting_breakpoint);
 	wmb(); /* Sync point before breakpoint */
 	arch_kgdb_breakpoint();
 	wmb(); /* Sync point after breakpoint */
-	atomic_set(&kgdb_setting_breakpoint, 0);
+	atomic_dec(&kgdb_setting_breakpoint);
 }
 EXPORT_SYMBOL_GPL(kgdb_breakpoint);
 

kernel/perf_event.c

@@ -1165,11 +1165,9 @@ void perf_event_task_sched_out(struct task_struct *task,
 	struct perf_event_context *ctx = task->perf_event_ctxp;
 	struct perf_event_context *next_ctx;
 	struct perf_event_context *parent;
-	struct pt_regs *regs;
 	int do_switch = 1;
 
-	regs = task_pt_regs(task);
-	perf_sw_event(PERF_COUNT_SW_CONTEXT_SWITCHES, 1, 1, regs, 0);
+	perf_sw_event(PERF_COUNT_SW_CONTEXT_SWITCHES, 1, 1, NULL, 0);
 
 	if (likely(!ctx || !cpuctx->task_ctx))
 		return;
@@ -2787,12 +2785,11 @@ __weak struct perf_callchain_entry *perf_callchain(struct pt_regs *regs)
 	return NULL;
 }
 
-#ifdef CONFIG_EVENT_TRACING
 __weak
 void perf_arch_fetch_caller_regs(struct pt_regs *regs, unsigned long ip, int skip)
 {
 }
-#endif
+
 
 /*
  * Output
@@ -3379,15 +3376,23 @@ static void perf_event_task_output(struct perf_event *event,
 				     struct perf_task_event *task_event)
 {
 	struct perf_output_handle handle;
-	int size;
 	struct task_struct *task = task_event->task;
-	int ret;
+	unsigned long flags;
+	int size, ret;
+
+	/*
+	 * If this CPU attempts to acquire an rq lock held by a CPU spinning
+	 * in perf_output_lock() from interrupt context, it's game over.
+	 */
+	local_irq_save(flags);
 
 	size  = task_event->event_id.header.size;
 	ret = perf_output_begin(&handle, event, size, 0, 0);
 
-	if (ret)
+	if (ret) {
+		local_irq_restore(flags);
 		return;
+	}
 
 	task_event->event_id.pid = perf_event_pid(event, task);
 	task_event->event_id.ppid = perf_event_pid(event, current);
@@ -3398,6 +3403,7 @@ static void perf_event_task_output(struct perf_event *event,
 	perf_output_put(&handle, task_event->event_id);
 
 	perf_output_end(&handle);
+	local_irq_restore(flags);
 }
 
 static int perf_event_task_match(struct perf_event *event)

kernel/power/process.c

@@ -88,12 +88,11 @@ static int try_to_freeze_tasks(bool sig_only)
 		printk(KERN_ERR "Freezing of tasks failed after %d.%02d seconds "
 				"(%d tasks refusing to freeze):\n",
 				elapsed_csecs / 100, elapsed_csecs % 100, todo);
-		show_state();
 		read_lock(&tasklist_lock);
 		do_each_thread(g, p) {
 			task_lock(p);
 			if (freezing(p) && !freezer_should_skip(p))
-				printk(KERN_ERR " %s\n", p->comm);
+				sched_show_task(p);
 			cancel_freezing(p);
 			task_unlock(p);
 		} while_each_thread(g, p);
@@ -145,7 +144,7 @@ static void thaw_tasks(bool nosig_only)
 		if (nosig_only && should_send_signal(p))
 			continue;
 
-		if (cgroup_frozen(p))
+		if (cgroup_freezing_or_frozen(p))
 			continue;
 
 		thaw_process(p);

kernel/sched.c

@@ -5388,7 +5388,7 @@ int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask)
 
 		get_task_struct(mt);
 		task_rq_unlock(rq, &flags);
-		wake_up_process(rq->migration_thread);
+		wake_up_process(mt);
 		put_task_struct(mt);
 		wait_for_completion(&req.done);
 		tlb_migrate_finish(p->mm);

kernel/sched_debug.c

@@ -518,8 +518,4 @@ void proc_sched_set_task(struct task_struct *p)
 	p->se.nr_wakeups_idle			= 0;
 	p->sched_info.bkl_count			= 0;
 #endif
-	p->se.sum_exec_runtime			= 0;
-	p->se.prev_sum_exec_runtime		= 0;
-	p->nvcsw				= 0;
-	p->nivcsw				= 0;
 }

kernel/trace/ring_buffer.c

@@ -1210,18 +1210,19 @@ rb_remove_pages(struct ring_buffer_per_cpu *cpu_buffer, unsigned nr_pages)
 
 	for (i = 0; i < nr_pages; i++) {
 		if (RB_WARN_ON(cpu_buffer, list_empty(cpu_buffer->pages)))
-			return;
+			goto out;
 		p = cpu_buffer->pages->next;
 		bpage = list_entry(p, struct buffer_page, list);
 		list_del_init(&bpage->list);
 		free_buffer_page(bpage);
 	}
 	if (RB_WARN_ON(cpu_buffer, list_empty(cpu_buffer->pages)))
-		return;
+		goto out;
 
 	rb_reset_cpu(cpu_buffer);
 	rb_check_pages(cpu_buffer);
 
+out:
 	spin_unlock_irq(&cpu_buffer->reader_lock);
 }
 
@@ -1238,7 +1239,7 @@ rb_insert_pages(struct ring_buffer_per_cpu *cpu_buffer,
 
 	for (i = 0; i < nr_pages; i++) {
 		if (RB_WARN_ON(cpu_buffer, list_empty(pages)))
-			return;
+			goto out;
 		p = pages->next;
 		bpage = list_entry(p, struct buffer_page, list);
 		list_del_init(&bpage->list);
@@ -1247,6 +1248,7 @@ rb_insert_pages(struct ring_buffer_per_cpu *cpu_buffer,
 	rb_reset_cpu(cpu_buffer);
 	rb_check_pages(cpu_buffer);
 
+out:
 	spin_unlock_irq(&cpu_buffer->reader_lock);
 }
 

kernel/trace/trace_clock.c

@@ -84,7 +84,7 @@ u64 notrace trace_clock_global(void)
 	int this_cpu;
 	u64 now;
 
-	raw_local_irq_save(flags);
+	local_irq_save(flags);
 
 	this_cpu = raw_smp_processor_id();
 	now = cpu_clock(this_cpu);
@@ -110,7 +110,7 @@ u64 notrace trace_clock_global(void)
 	arch_spin_unlock(&trace_clock_struct.lock);
 
  out:
-	raw_local_irq_restore(flags);
+	local_irq_restore(flags);
 
 	return now;
 }

kernel/trace/trace_event_perf.c

@@ -17,7 +17,12 @@ EXPORT_SYMBOL_GPL(perf_arch_fetch_caller_regs);
 static char *perf_trace_buf;
 static char *perf_trace_buf_nmi;
 
-typedef typeof(char [PERF_MAX_TRACE_SIZE]) perf_trace_t ;
+/*
+ * Force it to be aligned to unsigned long to avoid misaligned accesses
+ * suprises
+ */
+typedef typeof(unsigned long [PERF_MAX_TRACE_SIZE / sizeof(unsigned long)])
+	perf_trace_t;
 
 /* Count the events in use (per event id, not per instance) */
 static int	total_ref_count;
@@ -130,6 +135,8 @@ __kprobes void *perf_trace_buf_prepare(int size, unsigned short type,
 	char *trace_buf, *raw_data;
 	int pc, cpu;
 
+	BUILD_BUG_ON(PERF_MAX_TRACE_SIZE % sizeof(unsigned long));
+
 	pc = preempt_count();
 
 	/* Protect the per cpu buffer, begin the rcu read side */
@@ -152,7 +159,7 @@ __kprobes void *perf_trace_buf_prepare(int size, unsigned short type,
 	raw_data = per_cpu_ptr(trace_buf, cpu);
 
 	/* zero the dead bytes from align to not leak stack to user */
-	*(u64 *)(&raw_data[size - sizeof(u64)]) = 0ULL;
+	memset(&raw_data[size - sizeof(u64)], 0, sizeof(u64));
 
 	entry = (struct trace_entry *)raw_data;
 	tracing_generic_entry_update(entry, *irq_flags, pc);