ftrace update patches

Index: linux-sched-devel.git/kernel/trace/trace.c
===================================================================
@@ -36,8 +36,7 @@ unsigned long __read_mostly	tracing_max_
 unsigned long __read_mostly	tracing_thresh;
 
 /* dummy trace to disable tracing */
-static struct tracer no_tracer __read_mostly =
-{
+static struct tracer no_tracer __read_mostly = {
 	.name		= "none",
 };
 

@@ -1961,8 +1960,8 @@ tracing_iter_ctrl_write(struct file *fil
 	int neg = 0;
 	int i;
 
-	if (cnt > 63)
-		cnt = 63;
+	if (cnt >= sizeof(buf))
+		return -EINVAL;
 
 	if (copy_from_user(&buf, ubuf, cnt))
 		return -EFAULT;

@@ -2054,8 +2053,8 @@ tracing_ctrl_write(struct file *filp, co
 	long val;
 	char buf[64];
 
-	if (cnt > 63)
-		cnt = 63;
+	if (cnt >= sizeof(buf))
+		return -EINVAL;
 
 	if (copy_from_user(&buf, ubuf, cnt))
 		return -EFAULT;

@@ -2154,10 +2153,10 @@ tracing_max_lat_read(struct file *filp, 
 	char buf[64];
 	int r;
 
-	r = snprintf(buf, 64, "%ld\n",
+	r = snprintf(buf, sizeof(buf), "%ld\n",
 		     *ptr == (unsigned long)-1 ? -1 : nsecs_to_usecs(*ptr));
-	if (r > 64)
-		r = 64;
+	if (r > sizeof(buf))
+		r = sizeof(buf);
 	return simple_read_from_buffer(ubuf, cnt, ppos, buf, r);
 }
 

@@ -2169,8 +2168,8 @@ tracing_max_lat_write(struct file *filp,
 	long val;
 	char buf[64];
 
-	if (cnt > 63)
-		cnt = 63;
+	if (cnt >= sizeof(buf))
+		return -EINVAL;
 
 	if (copy_from_user(&buf, ubuf, cnt))
 		return -EFAULT;

@@ -2434,8 +2433,8 @@ tracing_entries_write(struct file *filp,
 	unsigned long val;
 	char buf[64];
 
-	if (cnt > 63)
-		cnt = 63;
+	if (cnt >= sizeof(buf))
+		return -EINVAL;
 
 	if (copy_from_user(&buf, ubuf, cnt))
 		return -EFAULT;

Index: linux-sched-devel.git/kernel/trace/trace.c
===================================================================
@@ -92,9 +92,16 @@ void trace_wake_up(void)
 
 static int __init set_nr_entries(char *str)
 {
+	unsigned long nr_entries;
+	int ret;
+
 	if (!str)
 		return 0;
-	trace_nr_entries = simple_strtoul(str, &str, 0);
+	ret = strict_strtoul(str, 0, &nr_entries);
+	/* nr_entries can not be zero */
+	if (ret < 0 || nr_entries == 0)
+		return 0;
+	trace_nr_entries = nr_entries;
 	return 1;
 }
 __setup("trace_entries=", set_nr_entries);

@@ -2050,8 +2057,9 @@ tracing_ctrl_write(struct file *filp, co
 		   size_t cnt, loff_t *ppos)
 {
 	struct trace_array *tr = filp->private_data;
-	long val;
 	char buf[64];
+	long val;
+	int ret;
 
 	if (cnt >= sizeof(buf))
 		return -EINVAL;

@@ -2061,7 +2069,9 @@ tracing_ctrl_write(struct file *filp, co
 
 	buf[cnt] = 0;
 
-	val = simple_strtoul(buf, NULL, 10);
+	ret = strict_strtoul(buf, 10, &val);
+	if (ret < 0)
+		return ret;
 
 	val = !!val;
 

@@ -2165,8 +2175,9 @@ tracing_max_lat_write(struct file *filp,
 		      size_t cnt, loff_t *ppos)
 {
 	long *ptr = filp->private_data;
-	long val;
 	char buf[64];
+	long val;
+	int ret;
 
 	if (cnt >= sizeof(buf))
 		return -EINVAL;

@@ -2176,7 +2187,9 @@ tracing_max_lat_write(struct file *filp,
 
 	buf[cnt] = 0;
 
-	val = simple_strtoul(buf, NULL, 10);
+	ret = strict_strtoul(buf, 10, &val);
+	if (ret < 0)
+		return ret;
 
 	*ptr = val * 1000;
 

@@ -2432,6 +2445,7 @@ tracing_entries_write(struct file *filp,
 {
 	unsigned long val;
 	char buf[64];
+	int ret;
 
 	if (cnt >= sizeof(buf))
 		return -EINVAL;

@@ -2441,7 +2455,9 @@ tracing_entries_write(struct file *filp,
 
 	buf[cnt] = 0;
 
-	val = simple_strtoul(buf, NULL, 10);
+	ret = strict_strtoul(buf, 10, &val);
+	if (ret < 0)
+		return ret;
 
 	/* must have at least 1 entry */
 	if (!val)

Index: linux-sched-devel.git/kernel/trace/trace.c
===================================================================
@@ -35,6 +35,12 @@
 unsigned long __read_mostly	tracing_max_latency = (cycle_t)ULONG_MAX;
 unsigned long __read_mostly	tracing_thresh;
 
+static unsigned long __read_mostly	tracing_nr_buffers;
+static cpumask_t __read_mostly		tracing_buffer_mask;
+
+#define for_each_tracing_cpu(cpu)	\
+	for_each_cpu_mask(cpu, tracing_buffer_mask)
+
 /* dummy trace to disable tracing */
 static struct tracer no_tracer __read_mostly = {
 	.name		= "none",

@@ -341,7 +347,7 @@ update_max_tr(struct trace_array *tr, st
 	WARN_ON_ONCE(!irqs_disabled());
 	__raw_spin_lock(&ftrace_max_lock);
 	/* clear out all the previous traces */
-	for_each_possible_cpu(i) {
+	for_each_tracing_cpu(i) {
 		data = tr->data[i];
 		flip_trace(max_tr.data[i], data);
 		tracing_reset(data);

@@ -365,7 +371,7 @@ update_max_tr_single(struct trace_array 
 
 	WARN_ON_ONCE(!irqs_disabled());
 	__raw_spin_lock(&ftrace_max_lock);
-	for_each_possible_cpu(i)
+	for_each_tracing_cpu(i)
 		tracing_reset(max_tr.data[i]);
 
 	flip_trace(max_tr.data[cpu], data);

@@ -411,7 +417,7 @@ int register_tracer(struct tracer *type)
 		 * internal tracing to verify that everything is in order.
 		 * If we fail, we do not register this tracer.
 		 */
-		for_each_possible_cpu(i) {
+		for_each_tracing_cpu(i) {
 			data = tr->data[i];
 			if (!head_page(data))
 				continue;

@@ -430,7 +436,7 @@ int register_tracer(struct tracer *type)
 			goto out;
 		}
 		/* Only reset on passing, to avoid touching corrupted buffers */
-		for_each_possible_cpu(i) {
+		for_each_tracing_cpu(i) {
 			data = tr->data[i];
 			if (!head_page(data))
 				continue;

@@ -902,7 +908,7 @@ find_next_entry(struct trace_iterator *i
 	int next_cpu = -1;
 	int cpu;
 
-	for_each_possible_cpu(cpu) {
+	for_each_tracing_cpu(cpu) {
 		if (!head_page(tr->data[cpu]))
 			continue;
 		ent = trace_entry_idx(tr, tr->data[cpu], iter, cpu);

@@ -1027,7 +1033,7 @@ static void *s_start(struct seq_file *m,
 		iter->prev_ent = NULL;
 		iter->prev_cpu = -1;
 
-		for_each_possible_cpu(i) {
+		for_each_tracing_cpu(i) {
 			iter->next_idx[i] = 0;
 			iter->next_page[i] = NULL;
 		}

@@ -1144,7 +1150,7 @@ print_trace_header(struct seq_file *m, s
 	if (type)
 		name = type->name;
 
-	for_each_possible_cpu(cpu) {
+	for_each_tracing_cpu(cpu) {
 		if (head_page(tr->data[cpu])) {
 			total += tr->data[cpu]->trace_idx;
 			if (tr->data[cpu]->trace_idx > tr->entries)

@@ -1574,7 +1580,7 @@ static int trace_empty(struct trace_iter
 	struct trace_array_cpu *data;
 	int cpu;
 
-	for_each_possible_cpu(cpu) {
+	for_each_tracing_cpu(cpu) {
 		data = iter->tr->data[cpu];
 
 		if (head_page(data) && data->trace_idx &&

@@ -1886,7 +1892,7 @@ tracing_cpumask_write(struct file *filp,
 
 	raw_local_irq_disable();
 	__raw_spin_lock(&ftrace_max_lock);
-	for_each_possible_cpu(cpu) {
+	for_each_tracing_cpu(cpu) {
 		/*
 		 * Increase/decrease the disabled counter if we are
 		 * about to flip a bit in the cpumask:

@@ -2364,7 +2370,7 @@ tracing_read_pipe(struct file *filp, cha
 	ftrace_enabled = 0;
 #endif
 	smp_wmb();
-	for_each_possible_cpu(cpu) {
+	for_each_tracing_cpu(cpu) {
 		data = iter->tr->data[cpu];
 
 		if (!head_page(data) || !data->trace_idx)

@@ -2664,7 +2670,7 @@ static int trace_alloc_page(void)
 	int i;
 
 	/* first allocate a page for each CPU */
-	for_each_possible_cpu(i) {
+	for_each_tracing_cpu(i) {
 		array = (void *)__get_free_page(GFP_KERNEL);
 		if (array == NULL) {
 			printk(KERN_ERR "tracer: failed to allocate page"

@@ -2689,7 +2695,7 @@ static int trace_alloc_page(void)
 	}
 
 	/* Now that we successfully allocate a page per CPU, add them */
-	for_each_possible_cpu(i) {
+	for_each_tracing_cpu(i) {
 		data = global_trace.data[i];
 		page = list_entry(pages.next, struct page, lru);
 		list_del_init(&page->lru);

@@ -2725,7 +2731,7 @@ static int trace_free_page(void)
 	int ret = 0;
 
 	/* free one page from each buffer */
-	for_each_possible_cpu(i) {
+	for_each_tracing_cpu(i) {
 		data = global_trace.data[i];
 		p = data->trace_pages.next;
 		if (p == &data->trace_pages) {

@@ -2776,8 +2782,12 @@ __init static int tracer_alloc_buffers(v
 
 	global_trace.ctrl = tracer_enabled;
 
+	/* TODO: make the number of buffers hot pluggable with CPUS */
+	tracing_nr_buffers = num_possible_cpus();
+	tracing_buffer_mask = cpu_possible_map;
+
 	/* Allocate the first page for all buffers */
-	for_each_possible_cpu(i) {
+	for_each_tracing_cpu(i) {
 		data = global_trace.data[i] = &per_cpu(global_trace_cpu, i);
 		max_tr.data[i] = &per_cpu(max_data, i);
 

Index: linux-sched-devel.git/kernel/trace/trace.c
===================================================================
@@ -67,26 +67,79 @@ cycle_t ftrace_now(int cpu)
 	return cpu_clock(cpu);
 }
 
+/*
+ * The global_trace is the descriptor that holds the tracing
+ * buffers for the live tracing. For each CPU, it contains
+ * a link list of pages that will store trace entries. The
+ * page descriptor of the pages in the memory is used to hold
+ * the link list by linking the lru item in the page descriptor
+ * to each of the pages in the buffer per CPU.
+ *
+ * For each active CPU there is a data field that holds the
+ * pages for the buffer for that CPU. Each CPU has the same number
+ * of pages allocated for its buffer.
+ */
 static struct trace_array	global_trace;
 
 static DEFINE_PER_CPU(struct trace_array_cpu, global_trace_cpu);
 
+/*
+ * The max_tr is used to snapshot the global_trace when a maximum
+ * latency is reached. Some tracers will use this to store a maximum
+ * trace while it continues examining live traces.
+ *
+ * The buffers for the max_tr are set up the same as the global_trace.
+ * When a snapshot is taken, the link list of the max_tr is swapped
+ * with the link list of the global_trace and the buffers are reset for
+ * the global_trace so the tracing can continue.
+ */
 static struct trace_array	max_tr;
 
 static DEFINE_PER_CPU(struct trace_array_cpu, max_data);
 
+/* tracer_enabled is used to toggle activation of a tracer */
 static int			tracer_enabled = 1;
+
+/*
+ * trace_nr_entries is the number of entries that is allocated
+ * for a buffer. Note, the number of entries is always rounded
+ * to ENTRIES_PER_PAGE.
+ */
 static unsigned long		trace_nr_entries = 65536UL;
 
+/* trace_types holds a link list of available tracers. */
 static struct tracer		*trace_types __read_mostly;
+
+/* current_trace points to the tracer that is currently active */
 static struct tracer		*current_trace __read_mostly;
+
+/*
+ * max_tracer_type_len is used to simplify the allocating of
+ * buffers to read userspace tracer names. We keep track of
+ * the longest tracer name registered.
+ */
 static int			max_tracer_type_len;
 
+/*
+ * trace_types_lock is used to protect the trace_types list.
+ * This lock is also used to keep user access serialized.
+ * Accesses from userspace will grab this lock while userspace
+ * activities happen inside the kernel.
+ */
 static DEFINE_MUTEX(trace_types_lock);
+
+/* trace_wait is a waitqueue for tasks blocked on trace_poll */
 static DECLARE_WAIT_QUEUE_HEAD(trace_wait);
 
+/* trace_flags holds iter_ctrl options */
 unsigned long trace_flags = TRACE_ITER_PRINT_PARENT;
 
+/**
+ * trace_wake_up - wake up tasks waiting for trace input
+ *
+ * Simply wakes up any task that is blocked on the trace_wait
+ * queue. These is used with trace_poll for tasks polling the trace.
+ */
 void trace_wake_up(void)
 {
 	/*

@@ -120,6 +173,14 @@ unsigned long nsecs_to_usecs(unsigned lo
 	return nsecs / 1000;
 }
 
+/*
+ * trace_flag_type is an enumeration that holds different
+ * states when a trace occurs. These are:
+ *  IRQS_OFF	- interrupts were disabled
+ *  NEED_RESCED - reschedule is requested
+ *  HARDIRQ	- inside an interrupt handler
+ *  SOFTIRQ	- inside a softirq handler
+ */
 enum trace_flag_type {
 	TRACE_FLAG_IRQS_OFF		= 0x01,
 	TRACE_FLAG_NEED_RESCHED		= 0x02,

@@ -127,10 +188,14 @@ enum trace_flag_type {
 	TRACE_FLAG_SOFTIRQ		= 0x08,
 };
 
+/*
+ * TRACE_ITER_SYM_MASK masks the options in trace_flags that
+ * control the output of kernel symbols.
+ */
 #define TRACE_ITER_SYM_MASK \
 	(TRACE_ITER_PRINT_PARENT|TRACE_ITER_SYM_OFFSET|TRACE_ITER_SYM_ADDR)
 
-/* These must match the bit postions above */
+/* These must match the bit postions in trace_iterator_flags */
 static const char *trace_options[] = {
 	"print-parent",
 	"sym-offset",

@@ -145,6 +210,15 @@ static const char *trace_options[] = {
 	NULL
 };
 
+/*
+ * ftrace_max_lock is used to protect the swapping of buffers
+ * when taking a max snapshot. The buffers themselves are
+ * protected by per_cpu spinlocks. But the action of the swap
+ * needs its own lock.
+ *
+ * This is defined as a raw_spinlock_t in order to help
+ * with performance when lockdep debugging is enabled.
+ */
 static raw_spinlock_t ftrace_max_lock =
 	(raw_spinlock_t)__RAW_SPIN_LOCK_UNLOCKED;
 

@@ -175,6 +249,13 @@ __update_max_tr(struct trace_array *tr, 
 	tracing_record_cmdline(current);
 }
 
+/**
+ * check_pages - integrity check of trace buffers
+ *
+ * As a safty measure we check to make sure the data pages have not
+ * been corrupted. TODO: configure to disable this because it adds
+ * a bit of overhead.
+ */
 void check_pages(struct trace_array_cpu *data)
 {
 	struct page *page, *tmp;

@@ -188,6 +269,13 @@ void check_pages(struct trace_array_cpu 
 	}
 }
 
+/**
+ * head_page - page address of the first page in per_cpu buffer.
+ *
+ * head_page returns the page address of the first page in
+ * a per_cpu buffer. This also preforms various consistency
+ * checks to make sure the buffer has not been corrupted.
+ */
 void *head_page(struct trace_array_cpu *data)
 {
 	struct page *page;

@@ -202,6 +290,17 @@ void *head_page(struct trace_array_cpu *
 	return page_address(page);
 }
 
+/**
+ * trace_seq_printf - sequence printing of trace information
+ * @s: trace sequence descriptor
+ * @fmt: printf format string
+ *
+ * The tracer may use either sequence operations or its own
+ * copy to user routines. To simplify formating of a trace
+ * trace_seq_printf is used to store strings into a special
+ * buffer (@s). Then the output may be either used by
+ * the sequencer or pulled into another buffer.
+ */
 int
 trace_seq_printf(struct trace_seq *s, const char *fmt, ...)
 {

@@ -225,6 +324,16 @@ trace_seq_printf(struct trace_seq *s, co
 	return len;
 }
 
+/**
+ * trace_seq_puts - trace sequence printing of simple string
+ * @s: trace sequence descriptor
+ * @str: simple string to record
+ *
+ * The tracer may use either the sequence operations or its own
+ * copy to user routines. This function records a simple string
+ * into a special buffer (@s) for later retrieval by a sequencer
+ * or other mechanism.
+ */
 static int
 trace_seq_puts(struct trace_seq *s, const char *str)
 {

@@ -320,6 +429,13 @@ trace_print_seq(struct seq_file *m, stru
 	trace_seq_reset(s);
 }
 
+/*
+ * flip the trace buffers between two trace descriptors.
+ * This usually is the buffers between the global_trace and
+ * the max_tr to record a snapshot of a current trace.
+ *
+ * The ftrace_max_lock must be held.
+ */
 static void
 flip_trace(struct trace_array_cpu *tr1, struct trace_array_cpu *tr2)
 {

@@ -341,6 +457,15 @@ flip_trace(struct trace_array_cpu *tr1, 
 	check_pages(tr2);
 }
 
+/**
+ * update_max_tr - snapshot all trace buffers from global_trace to max_tr
+ * @tr: tracer
+ * @tsk: the task with the latency
+ * @cpu: The cpu that initiated the trace.
+ *
+ * Flip the buffers between the @tr and the max_tr and record information
+ * about which task was the cause of this latency.
+ */
 void
 update_max_tr(struct trace_array *tr, struct task_struct *tsk, int cpu)
 {

@@ -365,6 +490,8 @@ update_max_tr(struct trace_array *tr, st
  * @tr - tracer
  * @tsk - task with the latency
  * @cpu - the cpu of the buffer to copy.
+ *
+ * Flip the trace of a single CPU buffer between the @tr and the max_tr.
  */
 void
 update_max_tr_single(struct trace_array *tr, struct task_struct *tsk, int cpu)

@@ -384,6 +511,12 @@ update_max_tr_single(struct trace_array 
 	__raw_spin_unlock(&ftrace_max_lock);
 }
 
+/**
+ * register_tracer - register a tracer with the ftrace system.
+ * @type - the plugin for the tracer
+ *
+ * Register a new plugin tracer.
+ */
 int register_tracer(struct tracer *type)
 {
 	struct tracer *t;

Index: linux-sched-devel.git/kernel/trace/trace.h
===================================================================
@@ -314,6 +314,13 @@ extern long ns2usecs(cycle_t nsec);
 
 extern unsigned long trace_flags;
 
+/*
+ * trace_iterator_flags is an enumeration that defines bit
+ * positions into trace_flags that controls the output.
+ *
+ * NOTE: These bits must match the trace_options array in
+ *       trace.c.
+ */
 enum trace_iterator_flags {
 	TRACE_ITER_PRINT_PARENT		= 0x01,
 	TRACE_ITER_SYM_OFFSET		= 0x02,

Index: linux-sched-devel.git/include/linux/writeback.h
===================================================================
@@ -105,6 +105,8 @@ extern int vm_highmem_is_dirtyable;
 extern int block_dump;
 extern int laptop_mode;
 
+extern unsigned long determine_dirtyable_memory(void);
+
 extern int dirty_ratio_handler(struct ctl_table *table, int write,
 		struct file *filp, void __user *buffer, size_t *lenp,
 		loff_t *ppos);

Index: linux-sched-devel.git/kernel/trace/trace.c
===================================================================
@@ -27,6 +27,7 @@
 #include <linux/poll.h>
 #include <linux/gfp.h>
 #include <linux/fs.h>
+#include <linux/writeback.h>
 
 #include <linux/stacktrace.h>
 

@@ -51,6 +52,8 @@ static int trace_free_page(void);
 
 static int tracing_disabled = 1;
 
+static unsigned long tracing_pages_allocated;
+
 long
 ns2usecs(cycle_t nsec)
 {

@@ -2479,12 +2482,41 @@ tracing_entries_write(struct file *filp,
 	}
 
 	if (val > global_trace.entries) {
+		long pages_requested;
+		unsigned long freeable_pages;
+
+		/* make sure we have enough memory before mapping */
+		pages_requested =
+			(val + (ENTRIES_PER_PAGE-1)) / ENTRIES_PER_PAGE;
+
+		/* account for each buffer (and max_tr) */
+		pages_requested *= tracing_nr_buffers * 2;
+
+		/* Check for overflow */
+		if (pages_requested < 0) {
+			cnt = -ENOMEM;
+			goto out;
+		}
+
+		freeable_pages = determine_dirtyable_memory();
+
+		/* we only allow to request 1/4 of useable memory */
+		if (pages_requested >
+		    ((freeable_pages + tracing_pages_allocated) / 4)) {
+			cnt = -ENOMEM;
+			goto out;
+		}
+
 		while (global_trace.entries < val) {
 			if (trace_alloc_page()) {
 				cnt = -ENOMEM;
 				goto out;
 			}
+			/* double check that we don't go over the known pages */
+			if (tracing_pages_allocated > pages_requested)
+				break;
 		}
+
 	} else {
 		/* include the number of entries in val (inc of page entries) */
 		while (global_trace.entries > val + (ENTRIES_PER_PAGE - 1))

@@ -2667,6 +2699,7 @@ static int trace_alloc_page(void)
 	struct page *page, *tmp;
 	LIST_HEAD(pages);
 	void *array;
+	unsigned pages_allocated = 0;
 	int i;
 
 	/* first allocate a page for each CPU */

@@ -2678,6 +2711,7 @@ static int trace_alloc_page(void)
 			goto free_pages;
 		}
 
+		pages_allocated++;
 		page = virt_to_page(array);
 		list_add(&page->lru, &pages);
 

@@ -2689,6 +2723,7 @@ static int trace_alloc_page(void)
 			       "for trace buffer!\n");
 			goto free_pages;
 		}
+		pages_allocated++;
 		page = virt_to_page(array);
 		list_add(&page->lru, &pages);
 #endif

@@ -2710,6 +2745,7 @@ static int trace_alloc_page(void)
 		SetPageLRU(page);
 #endif
 	}
+	tracing_pages_allocated += pages_allocated;
 	global_trace.entries += ENTRIES_PER_PAGE;
 
 	return 0;

@@ -2744,6 +2780,7 @@ static int trace_free_page(void)
 		page = list_entry(p, struct page, lru);
 		ClearPageLRU(page);
 		list_del(&page->lru);
+		tracing_pages_allocated--;
 		__free_page(page);
 
 		tracing_reset(data);

@@ -2761,6 +2798,7 @@ static int trace_free_page(void)
 		page = list_entry(p, struct page, lru);
 		ClearPageLRU(page);
 		list_del(&page->lru);
+		tracing_pages_allocated--;
 		__free_page(page);
 
 		tracing_reset(data);

Index: linux-sched-devel.git/mm/page-writeback.c
===================================================================
@@ -126,8 +126,6 @@ static void background_writeout(unsigned
 static struct prop_descriptor vm_completions;
 static struct prop_descriptor vm_dirties;
 
-static unsigned long determine_dirtyable_memory(void);
-
 /*
  * couple the period to the dirty_ratio:
  *

@@ -286,7 +284,13 @@ static unsigned long highmem_dirtyable_m
 #endif
 }
 
-static unsigned long determine_dirtyable_memory(void)
+/**
+ * detremine_dirtyable_memory - amount of memory that may be used
+ *
+ * Returns the numebr of pages that can currently be freed and used
+ * by the kernel for direct mappings.
+ */
+unsigned long determine_dirtyable_memory(void)
 {
 	unsigned long x;
 

Index: linux-sched-devel.git/kernel/trace/trace.c
===================================================================
@@ -36,8 +36,7 @@ unsigned long __read_mostly	tracing_max_
 unsigned long __read_mostly	tracing_thresh;
 
 /* dummy trace to disable tracing */
-static struct tracer no_tracer __read_mostly =
-{
+static struct tracer no_tracer __read_mostly = {
 	.name		= "none",
 };
 

@@ -1961,8 +1960,8 @@ tracing_iter_ctrl_write(struct file *fil
 	int neg = 0;
 	int i;
 
-	if (cnt > 63)
-		cnt = 63;
+	if (cnt >= sizeof(buf))
+		return -EINVAL;
 
 	if (copy_from_user(&buf, ubuf, cnt))
 		return -EFAULT;

@@ -2054,8 +2053,8 @@ tracing_ctrl_write(struct file *filp, co
 	long val;
 	char buf[64];
 
-	if (cnt > 63)
-		cnt = 63;
+	if (cnt >= sizeof(buf))
+		return -EINVAL;
 
 	if (copy_from_user(&buf, ubuf, cnt))
 		return -EFAULT;

@@ -2154,10 +2153,8 @@ tracing_max_lat_read(struct file *filp,
 	char buf[64];
 	int r;
 
-	r = snprintf(buf, 64, "%ld\n",
+	r = scnprintf(buf, sizeof(buf), "%ld\n",
 		     *ptr == (unsigned long)-1 ? -1 : nsecs_to_usecs(*ptr));
-	if (r > 64)
-		r = 64;
 	return simple_read_from_buffer(ubuf, cnt, ppos, buf, r);
 }
 

@@ -2169,8 +2166,8 @@ tracing_max_lat_write(struct file *filp,
 	long val;
 	char buf[64];
 
-	if (cnt > 63)
-		cnt = 63;
+	if (cnt >= sizeof(buf))
+		return -EINVAL;
 
 	if (copy_from_user(&buf, ubuf, cnt))
 		return -EFAULT;

@@ -2434,8 +2431,8 @@ tracing_entries_write(struct file *filp,
 	unsigned long val;
 	char buf[64];
 
-	if (cnt > 63)
-		cnt = 63;
+	if (cnt >= sizeof(buf))
+		return -EINVAL;
 
 	if (copy_from_user(&buf, ubuf, cnt))
 		return -EFAULT;

Index: linux-sched-devel.git/include/linux/writeback.h
===================================================================
@@ -105,6 +105,8 @@ extern int vm_highmem_is_dirtyable;
 extern int block_dump;
 extern int laptop_mode;
 
+extern unsigned long determine_dirtyable_memory(void);
+
 extern int dirty_ratio_handler(struct ctl_table *table, int write,
 		struct file *filp, void __user *buffer, size_t *lenp,
 		loff_t *ppos);

Index: linux-sched-devel.git/kernel/trace/trace.c
===================================================================
@@ -27,6 +27,7 @@
 #include <linux/poll.h>
 #include <linux/gfp.h>
 #include <linux/fs.h>
+#include <linux/writeback.h>
 
 #include <linux/stacktrace.h>
 

@@ -51,6 +52,8 @@ static int trace_free_page(void);
 
 static int tracing_disabled = 1;
 
+static unsigned long tracing_pages_allocated;
+
 long
 ns2usecs(cycle_t nsec)
 {

@@ -2477,12 +2480,41 @@ tracing_entries_write(struct file *filp,
 	}
 
 	if (val > global_trace.entries) {
+		long pages_requested;
+		unsigned long freeable_pages;
+
+		/* make sure we have enough memory before mapping */
+		pages_requested =
+			(val + (ENTRIES_PER_PAGE-1)) / ENTRIES_PER_PAGE;
+
+		/* account for each buffer (and max_tr) */
+		pages_requested *= tracing_nr_buffers * 2;
+
+		/* Check for overflow */
+		if (pages_requested < 0) {
+			cnt = -ENOMEM;
+			goto out;
+		}
+
+		freeable_pages = determine_dirtyable_memory();
+
+		/* we only allow to request 1/4 of useable memory */
+		if (pages_requested >
+		    ((freeable_pages + tracing_pages_allocated) / 4)) {
+			cnt = -ENOMEM;
+			goto out;
+		}
+
 		while (global_trace.entries < val) {
 			if (trace_alloc_page()) {
 				cnt = -ENOMEM;
 				goto out;
 			}
+			/* double check that we don't go over the known pages */
+			if (tracing_pages_allocated > pages_requested)
+				break;
 		}
+
 	} else {
 		/* include the number of entries in val (inc of page entries) */
 		while (global_trace.entries > val + (ENTRIES_PER_PAGE - 1))

@@ -2665,6 +2697,7 @@ static int trace_alloc_page(void)
 	struct page *page, *tmp;
 	LIST_HEAD(pages);
 	void *array;
+	unsigned pages_allocated = 0;
 	int i;
 
 	/* first allocate a page for each CPU */

@@ -2676,6 +2709,7 @@ static int trace_alloc_page(void)
 			goto free_pages;
 		}
 
+		pages_allocated++;
 		page = virt_to_page(array);
 		list_add(&page->lru, &pages);
 

@@ -2687,6 +2721,7 @@ static int trace_alloc_page(void)
 			       "for trace buffer!\n");
 			goto free_pages;
 		}
+		pages_allocated++;
 		page = virt_to_page(array);
 		list_add(&page->lru, &pages);
 #endif

@@ -2708,6 +2743,7 @@ static int trace_alloc_page(void)
 		SetPageLRU(page);
 #endif
 	}
+	tracing_pages_allocated += pages_allocated;
 	global_trace.entries += ENTRIES_PER_PAGE;
 
 	return 0;

@@ -2742,6 +2778,7 @@ static int trace_free_page(void)
 		page = list_entry(p, struct page, lru);
 		ClearPageLRU(page);
 		list_del(&page->lru);
+		tracing_pages_allocated--;
 		__free_page(page);
 
 		tracing_reset(data);

@@ -2759,6 +2796,7 @@ static int trace_free_page(void)
 		page = list_entry(p, struct page, lru);
 		ClearPageLRU(page);
 		list_del(&page->lru);
+		tracing_pages_allocated--;
 		__free_page(page);
 
 		tracing_reset(data);

Index: linux-sched-devel.git/mm/page-writeback.c
===================================================================
@@ -126,8 +126,6 @@ static void background_writeout(unsigned
 static struct prop_descriptor vm_completions;
 static struct prop_descriptor vm_dirties;
 
-static unsigned long determine_dirtyable_memory(void);
-
 /*
  * couple the period to the dirty_ratio:
  *

@@ -286,7 +284,13 @@ static unsigned long highmem_dirtyable_m
 #endif
 }
 
-static unsigned long determine_dirtyable_memory(void)
+/**
+ * determine_dirtyable_memory - amount of memory that may be used
+ *
+ * Returns the numebr of pages that can currently be freed and used
+ * by the kernel for direct mappings.
+ */
+unsigned long determine_dirtyable_memory(void)
 {
 	unsigned long x;