Merge commit 'v2.6.36-rc7' into core/rcu

Merge reason: Update from -rc3 to -rc7.

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

14 files changed, 161 insertions, 67 deletions

diff --git a/kernel/compat.c b/kernel/compat.c
index e167efc..c9e2ec0 100644
--- a/kernel/compat.c
+++ b/kernel/compat.c
@@ -1126,3 +1126,24 @@ compat_sys_sysinfo(struct compat_sysinfo __user *info)
 
 	return 0;
 }
+
+/*
+ * Allocate user-space memory for the duration of a single system call,
+ * in order to marshall parameters inside a compat thunk.
+ */
+void __user *compat_alloc_user_space(unsigned long len)
+{
+	void __user *ptr;
+
+	/* If len would occupy more than half of the entire compat space... */
+	if (unlikely(len > (((compat_uptr_t)~0) >> 1)))
+		return NULL;
+
+	ptr = arch_compat_alloc_user_space(len);
+
+	if (unlikely(!access_ok(VERIFY_WRITE, ptr, len)))
+		return NULL;
+
+	return ptr;
+}
+EXPORT_SYMBOL_GPL(compat_alloc_user_space);
diff --git a/kernel/fork.c b/kernel/fork.c
index b7e9d60..c445f8c 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -356,10 +356,10 @@ static int dup_mmap(struct mm_struct *mm, struct mm_struct *oldmm)
 		if (IS_ERR(pol))
 			goto fail_nomem_policy;
 		vma_set_policy(tmp, pol);
+		tmp->vm_mm = mm;
 		if (anon_vma_fork(tmp, mpnt))
 			goto fail_nomem_anon_vma_fork;
 		tmp->vm_flags &= ~VM_LOCKED;
-		tmp->vm_mm = mm;
 		tmp->vm_next = tmp->vm_prev = NULL;
 		file = tmp->vm_file;
 		if (file) {
diff --git a/kernel/hw_breakpoint.c b/kernel/hw_breakpoint.c
index d71a987..c7c2aed 100644
--- a/kernel/hw_breakpoint.c
+++ b/kernel/hw_breakpoint.c
@@ -433,7 +433,8 @@ register_user_hw_breakpoint(struct perf_event_attr *attr,
 			    perf_overflow_handler_t triggered,
 			    struct task_struct *tsk)
 {
-	return perf_event_create_kernel_counter(attr, -1, tsk->pid, triggered);
+	return perf_event_create_kernel_counter(attr, -1, task_pid_vnr(tsk),
+						triggered);
 }
 EXPORT_SYMBOL_GPL(register_user_hw_breakpoint);
 
diff --git a/kernel/kfifo.c b/kernel/kfifo.c
index 6b5580c..01a0700 100644
--- a/kernel/kfifo.c
+++ b/kernel/kfifo.c
@@ -365,8 +365,6 @@ static unsigned int setup_sgl(struct __kfifo *fifo, struct scatterlist *sgl,
 	n = setup_sgl_buf(sgl, fifo->data + off, nents, l);
 	n += setup_sgl_buf(sgl + n, fifo->data, nents - n, len - l);
 
-	if (n)
-		sg_mark_end(sgl + n - 1);
 	return n;
 }
 
diff --git a/kernel/module.c b/kernel/module.c
index d0b5f8d..ccd6419 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -1537,6 +1537,7 @@ static int __unlink_module(void *_mod)
 {
 	struct module *mod = _mod;
 	list_del(&mod->list);
+	module_bug_cleanup(mod);
 	return 0;
 }
 
@@ -2625,6 +2626,7 @@ static struct module *load_module(void __user *umod,
 	if (err < 0)
 		goto ddebug;
 
+	module_bug_finalize(info.hdr, info.sechdrs, mod);
 	list_add_rcu(&mod->list, &modules);
 	mutex_unlock(&module_mutex);
 
@@ -2650,6 +2652,8 @@ static struct module *load_module(void __user *umod,
 	mutex_lock(&module_mutex);
 	/* Unlink carefully: kallsyms could be walking list. */
 	list_del_rcu(&mod->list);
+	module_bug_cleanup(mod);
+
  ddebug:
 	if (!mod->taints)
 		dynamic_debug_remove(info.debug);
diff --git a/kernel/perf_event.c b/kernel/perf_event.c
index 657555a..db5b560 100644
--- a/kernel/perf_event.c
+++ b/kernel/perf_event.c
@@ -5761,15 +5761,15 @@ perf_cpu_notify(struct notifier_block *self, unsigned long action, void *hcpu)
 {
 	unsigned int cpu = (long)hcpu;
 
-	switch (action) {
+	switch (action & ~CPU_TASKS_FROZEN) {
 
 	case CPU_UP_PREPARE:
-	case CPU_UP_PREPARE_FROZEN:
+	case CPU_DOWN_FAILED:
 		perf_event_init_cpu(cpu);
 		break;
 
+	case CPU_UP_CANCELED:
 	case CPU_DOWN_PREPARE:
-	case CPU_DOWN_PREPARE_FROZEN:
 		perf_event_exit_cpu(cpu);
 		break;
 
diff --git a/kernel/pm_qos_params.c b/kernel/pm_qos_params.c
index b7e4c36..645e541 100644
--- a/kernel/pm_qos_params.c
+++ b/kernel/pm_qos_params.c
@@ -389,10 +389,12 @@ static ssize_t pm_qos_power_write(struct file *filp, const char __user *buf,
 	} else if (count == 11) { /* len('0x12345678/0') */
 		if (copy_from_user(ascii_value, buf, 11))
 			return -EFAULT;
+		if (strlen(ascii_value) != 10)
+			return -EINVAL;
 		x = sscanf(ascii_value, "%x", &value);
 		if (x != 1)
 			return -EINVAL;
-		pr_debug(KERN_ERR "%s, %d, 0x%x\n", ascii_value, x, value);
+		pr_debug("%s, %d, 0x%x\n", ascii_value, x, value);
 	} else
 		return -EINVAL;
 
diff --git a/kernel/power/snapshot.c b/kernel/power/snapshot.c
index f6cd6fa..d3f795f 100644
--- a/kernel/power/snapshot.c
+++ b/kernel/power/snapshot.c
@@ -1121,9 +1121,19 @@ static unsigned long preallocate_image_pages(unsigned long nr_pages, gfp_t mask)
 	return nr_alloc;
 }
 
-static unsigned long preallocate_image_memory(unsigned long nr_pages)
+static unsigned long preallocate_image_memory(unsigned long nr_pages,
+					      unsigned long avail_normal)
 {
-	return preallocate_image_pages(nr_pages, GFP_IMAGE);
+	unsigned long alloc;
+
+	if (avail_normal <= alloc_normal)
+		return 0;
+
+	alloc = avail_normal - alloc_normal;
+	if (nr_pages < alloc)
+		alloc = nr_pages;
+
+	return preallocate_image_pages(alloc, GFP_IMAGE);
 }
 
 #ifdef CONFIG_HIGHMEM
@@ -1169,15 +1179,22 @@ static inline unsigned long preallocate_highmem_fraction(unsigned long nr_pages,
  */
 static void free_unnecessary_pages(void)
 {
-	unsigned long save_highmem, to_free_normal, to_free_highmem;
+	unsigned long save, to_free_normal, to_free_highmem;
 
-	to_free_normal = alloc_normal - count_data_pages();
-	save_highmem = count_highmem_pages();
-	if (alloc_highmem > save_highmem) {
-		to_free_highmem = alloc_highmem - save_highmem;
+	save = count_data_pages();
+	if (alloc_normal >= save) {
+		to_free_normal = alloc_normal - save;
+		save = 0;
+	} else {
+		to_free_normal = 0;
+		save -= alloc_normal;
+	}
+	save += count_highmem_pages();
+	if (alloc_highmem >= save) {
+		to_free_highmem = alloc_highmem - save;
 	} else {
 		to_free_highmem = 0;
-		to_free_normal -= save_highmem - alloc_highmem;
+		to_free_normal -= save - alloc_highmem;
 	}
 
 	memory_bm_position_reset(&copy_bm);
@@ -1258,7 +1275,7 @@ int hibernate_preallocate_memory(void)
 {
 	struct zone *zone;
 	unsigned long saveable, size, max_size, count, highmem, pages = 0;
-	unsigned long alloc, save_highmem, pages_highmem;
+	unsigned long alloc, save_highmem, pages_highmem, avail_normal;
 	struct timeval start, stop;
 	int error;
 
@@ -1295,6 +1312,7 @@ int hibernate_preallocate_memory(void)
 		else
 			count += zone_page_state(zone, NR_FREE_PAGES);
 	}
+	avail_normal = count;
 	count += highmem;
 	count -= totalreserve_pages;
 
@@ -1309,12 +1327,21 @@ int hibernate_preallocate_memory(void)
 	 */
 	if (size >= saveable) {
 		pages = preallocate_image_highmem(save_highmem);
-		pages += preallocate_image_memory(saveable - pages);
+		pages += preallocate_image_memory(saveable - pages, avail_normal);
 		goto out;
 	}
 
 	/* Estimate the minimum size of the image. */
 	pages = minimum_image_size(saveable);
+	/*
+	 * To avoid excessive pressure on the normal zone, leave room in it to
+	 * accommodate an image of the minimum size (unless it's already too
+	 * small, in which case don't preallocate pages from it at all).
+	 */
+	if (avail_normal > pages)
+		avail_normal -= pages;
+	else
+		avail_normal = 0;
 	if (size < pages)
 		size = min_t(unsigned long, pages, max_size);
 
@@ -1335,16 +1362,34 @@ int hibernate_preallocate_memory(void)
 	 */
 	pages_highmem = preallocate_image_highmem(highmem / 2);
 	alloc = (count - max_size) - pages_highmem;
-	pages = preallocate_image_memory(alloc);
-	if (pages < alloc)
-		goto err_out;
-	size = max_size - size;
-	alloc = size;
-	size = preallocate_highmem_fraction(size, highmem, count);
-	pages_highmem += size;
-	alloc -= size;
-	pages += preallocate_image_memory(alloc);
-	pages += pages_highmem;
+	pages = preallocate_image_memory(alloc, avail_normal);
+	if (pages < alloc) {
+		/* We have exhausted non-highmem pages, try highmem. */
+		alloc -= pages;
+		pages += pages_highmem;
+		pages_highmem = preallocate_image_highmem(alloc);
+		if (pages_highmem < alloc)
+			goto err_out;
+		pages += pages_highmem;
+		/*
+		 * size is the desired number of saveable pages to leave in
+		 * memory, so try to preallocate (all memory - size) pages.
+		 */
+		alloc = (count - pages) - size;
+		pages += preallocate_image_highmem(alloc);
+	} else {
+		/*
+		 * There are approximately max_size saveable pages at this point
+		 * and we want to reduce this number down to size.
+		 */
+		alloc = max_size - size;
+		size = preallocate_highmem_fraction(alloc, highmem, count);
+		pages_highmem += size;
+		alloc -= size;
+		size = preallocate_image_memory(alloc, avail_normal);
+		pages_highmem += preallocate_image_highmem(alloc - size);
+		pages += pages_highmem + size;
+	}
 
 	/*
 	 * We only need as many page frames for the image as there are saveable
diff --git a/kernel/sched.c b/kernel/sched.c
index 09b574e..dc85ceb 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -1294,6 +1294,10 @@ static void resched_task(struct task_struct *p)
 static void sched_rt_avg_update(struct rq *rq, u64 rt_delta)
 {
 }
+
+static void sched_avg_update(struct rq *rq)
+{
+}
 #endif /* CONFIG_SMP */
 
 #if BITS_PER_LONG == 32
@@ -3182,6 +3186,8 @@ static void update_cpu_load(struct rq *this_rq)
 
 		this_rq->cpu_load[i] = (old_load * (scale - 1) + new_load) >> i;
 	}
+
+	sched_avg_update(this_rq);
 }
 
 static void update_cpu_load_active(struct rq *this_rq)
@@ -3507,9 +3513,9 @@ void task_times(struct task_struct *p, cputime_t *ut, cputime_t *st)
 	rtime = nsecs_to_cputime(p->se.sum_exec_runtime);
 
 	if (total) {
-		u64 temp;
+		u64 temp = rtime;
 
-		temp = (u64)(rtime * utime);
+		temp *= utime;
 		do_div(temp, total);
 		utime = (cputime_t)temp;
 	} else
@@ -3540,9 +3546,9 @@ void thread_group_times(struct task_struct *p, cputime_t *ut, cputime_t *st)
 	rtime = nsecs_to_cputime(cputime.sum_exec_runtime);
 
 	if (total) {
-		u64 temp;
+		u64 temp = rtime;
 
-		temp = (u64)(rtime * cputime.utime);
+		temp *= cputime.utime;
 		do_div(temp, total);
 		utime = (cputime_t)temp;
 	} else
diff --git a/kernel/sched_fair.c b/kernel/sched_fair.c
index 134f7ed..db3f674 100644
--- a/kernel/sched_fair.c
+++ b/kernel/sched_fair.c
@@ -54,13 +54,13 @@ enum sched_tunable_scaling sysctl_sched_tunable_scaling
  * Minimal preemption granularity for CPU-bound tasks:
  * (default: 2 msec * (1 + ilog(ncpus)), units: nanoseconds)
  */
-unsigned int sysctl_sched_min_granularity = 2000000ULL;
-unsigned int normalized_sysctl_sched_min_granularity = 2000000ULL;
+unsigned int sysctl_sched_min_granularity = 750000ULL;
+unsigned int normalized_sysctl_sched_min_granularity = 750000ULL;
 
 /*
  * is kept at sysctl_sched_latency / sysctl_sched_min_granularity
  */
-static unsigned int sched_nr_latency = 3;
+static unsigned int sched_nr_latency = 8;
 
 /*
  * After fork, child runs first. If set to 0 (default) then
@@ -2267,8 +2267,6 @@ unsigned long scale_rt_power(int cpu)
 	struct rq *rq = cpu_rq(cpu);
 	u64 total, available;
 
-	sched_avg_update(rq);
-
 	total = sched_avg_period() + (rq->clock - rq->age_stamp);
 	available = total - rq->rt_avg;
 
@@ -3632,7 +3630,7 @@ static inline int nohz_kick_needed(struct rq *rq, int cpu)
 	if (time_before(now, nohz.next_balance))
 		return 0;
 
-	if (!rq->nr_running)
+	if (rq->idle_at_tick)
 		return 0;
 
 	first_pick_cpu = atomic_read(&nohz.first_pick_cpu);
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 7cb1f45..fa7ece6 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -1510,6 +1510,8 @@ static void *t_start(struct seq_file *m, loff_t *pos)
 		if (*pos > 0)
 			return t_hash_start(m, pos);
 		iter->flags |= FTRACE_ITER_PRINTALL;
+		/* reset in case of seek/pread */
+		iter->flags &= ~FTRACE_ITER_HASH;
 		return iter;
 	}
 
@@ -2416,7 +2418,7 @@ static const struct file_operations ftrace_filter_fops = {
 	.open = ftrace_filter_open,
 	.read = seq_read,
 	.write = ftrace_filter_write,
-	.llseek = ftrace_regex_lseek,
+	.llseek = no_llseek,
 	.release = ftrace_filter_release,
 };
 
diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c
index 000e6e8..31cc4cb 100644
--- a/kernel/trace/trace_event_perf.c
+++ b/kernel/trace/trace_event_perf.c
@@ -91,6 +91,8 @@ int perf_trace_init(struct perf_event *p_event)
 		    tp_event->class && tp_event->class->reg &&
 		    try_module_get(tp_event->mod)) {
 			ret = perf_trace_event_init(tp_event, p_event);
+			if (ret)
+				module_put(tp_event->mod);
 			break;
 		}
 	}
@@ -146,6 +148,7 @@ void perf_trace_destroy(struct perf_event *p_event)
 		}
 	}
 out:
+	module_put(tp_event->mod);
 	mutex_unlock(&event_mutex);
 }
 
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index 8b27c98..544301d 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -514,8 +514,8 @@ static int kprobe_dispatcher(struct kprobe *kp, struct pt_regs *regs);
 static int kretprobe_dispatcher(struct kretprobe_instance *ri,
 				struct pt_regs *regs);
 
-/* Check the name is good for event/group */
-static int check_event_name(const char *name)
+/* Check the name is good for event/group/fields */
+static int is_good_name(const char *name)
 {
 	if (!isalpha(*name) && *name != '_')
 		return 0;
@@ -557,7 +557,7 @@ static struct trace_probe *alloc_trace_probe(const char *group,
 	else
 		tp->rp.kp.pre_handler = kprobe_dispatcher;
 
-	if (!event || !check_event_name(event)) {
+	if (!event || !is_good_name(event)) {
 		ret = -EINVAL;
 		goto error;
 	}
@@ -567,7 +567,7 @@ static struct trace_probe *alloc_trace_probe(const char *group,
 	if (!tp->call.name)
 		goto error;
 
-	if (!group || !check_event_name(group)) {
+	if (!group || !is_good_name(group)) {
 		ret = -EINVAL;
 		goto error;
 	}
@@ -883,7 +883,7 @@ static int create_trace_probe(int argc, char **argv)
 	int i, ret = 0;
 	int is_return = 0, is_delete = 0;
 	char *symbol = NULL, *event = NULL, *group = NULL;
-	char *arg, *tmp;
+	char *arg;
 	unsigned long offset = 0;
 	void *addr = NULL;
 	char buf[MAX_EVENT_NAME_LEN];
@@ -992,26 +992,36 @@ static int create_trace_probe(int argc, char **argv)
 	/* parse arguments */
 	ret = 0;
 	for (i = 0; i < argc && i < MAX_TRACE_ARGS; i++) {
+		/* Increment count for freeing args in error case */
+		tp->nr_args++;
+
 		/* Parse argument name */
 		arg = strchr(argv[i], '=');
-		if (arg)
+		if (arg) {
 			*arg++ = '\0';
-		else
+			tp->args[i].name = kstrdup(argv[i], GFP_KERNEL);
+		} else {
 			arg = argv[i];
+			/* If argument name is omitted, set "argN" */
+			snprintf(buf, MAX_EVENT_NAME_LEN, "arg%d", i + 1);
+			tp->args[i].name = kstrdup(buf, GFP_KERNEL);
+		}
 
-		tp->args[i].name = kstrdup(argv[i], GFP_KERNEL);
 		if (!tp->args[i].name) {
-			pr_info("Failed to allocate argument%d name '%s'.\n",
-				i, argv[i]);
+			pr_info("Failed to allocate argument[%d] name.\n", i);
 			ret = -ENOMEM;
 			goto error;
 		}
-		tmp = strchr(tp->args[i].name, ':');
-		if (tmp)
-			*tmp = '_';	/* convert : to _ */
+
+		if (!is_good_name(tp->args[i].name)) {
+			pr_info("Invalid argument[%d] name: %s\n",
+				i, tp->args[i].name);
+			ret = -EINVAL;
+			goto error;
+		}
 
 		if (conflict_field_name(tp->args[i].name, tp->args, i)) {
-			pr_info("Argument%d name '%s' conflicts with "
+			pr_info("Argument[%d] name '%s' conflicts with "
 				"another field.\n", i, argv[i]);
 			ret = -EINVAL;
 			goto error;
@@ -1020,12 +1030,9 @@ static int create_trace_probe(int argc, char **argv)
 		/* Parse fetch argument */
 		ret = parse_probe_arg(arg, tp, &tp->args[i], is_return);
 		if (ret) {
-			pr_info("Parse error at argument%d. (%d)\n", i, ret);
-			kfree(tp->args[i].name);
+			pr_info("Parse error at argument[%d]. (%d)\n", i, ret);
 			goto error;
 		}
-
-		tp->nr_args++;
 	}
 
 	ret = register_trace_probe(tp);
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 727f24e..f77afd9 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -1,19 +1,26 @@
 /*
- * linux/kernel/workqueue.c
+ * kernel/workqueue.c - generic async execution with shared worker pool
  *
- * Generic mechanism for defining kernel helper threads for running
- * arbitrary tasks in process context.
+ * Copyright (C) 2002		Ingo Molnar
  *
- * Started by Ingo Molnar, Copyright (C) 2002
+ *   Derived from the taskqueue/keventd code by:
+ *     David Woodhouse <dwmw2@infradead.org>
+ *     Andrew Morton
+ *     Kai Petzke <wpp@marie.physik.tu-berlin.de>
+ *     Theodore Ts'o <tytso@mit.edu>
  *
- * Derived from the taskqueue/keventd code by:
+ * Made to use alloc_percpu by Christoph Lameter.
  *
- *   David Woodhouse <dwmw2@infradead.org>
- *   Andrew Morton
- *   Kai Petzke <wpp@marie.physik.tu-berlin.de>
- *   Theodore Ts'o <tytso@mit.edu>
+ * Copyright (C) 2010		SUSE Linux Products GmbH
+ * Copyright (C) 2010		Tejun Heo <tj@kernel.org>
  *
- * Made to use alloc_percpu by Christoph Lameter.
+ * This is the generic async execution mechanism.  Work items as are
+ * executed in process context.  The worker pool is shared and
+ * automatically managed.  There is one worker pool for each CPU and
+ * one extra for works which are better served by workers which are
+ * not bound to any specific CPU.
+ *
+ * Please read Documentation/workqueue.txt for details.
  */
 
 #include <linux/module.h>