aboutsummaryrefslogtreecommitdiff
path: root/kernel
diff options
context:
space:
mode:
authorLinus Torvalds <torvalds@linux-foundation.org>2012-03-31 13:34:04 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2012-03-31 13:34:04 -0700
commitf187e9fd68577cdd5f914659b6f7f11124e40485 (patch)
treead0e7422359724f7c7ffaaaa80dd3a7281f02a83 /kernel
parentadb3b1f3fc1c6edb501808ebf80a81e81c52eb73 (diff)
parent8ebfdf2babcda5a3b06cc67523bca1f9aed46009 (diff)
downloadlinux-f187e9fd68577cdd5f914659b6f7f11124e40485.tar.gz
Merge branch 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip
Pull perf updates and fixes from Ingo Molnar: "It's mostly fixes, but there's also two late items: - preliminary GTK GUI support for perf report - PMU raw event format descriptors in sysfs, to be parsed by tooling The raw event format in sysfs is a new ABI. For example for the 'CPU' PMU we have: aldebaran:~> ll /sys/bus/event_source/devices/cpu/format/* -r--r--r--. 1 root root 4096 Mar 31 10:29 /sys/bus/event_source/devices/cpu/format/any -r--r--r--. 1 root root 4096 Mar 31 10:29 /sys/bus/event_source/devices/cpu/format/cmask -r--r--r--. 1 root root 4096 Mar 31 10:29 /sys/bus/event_source/devices/cpu/format/edge -r--r--r--. 1 root root 4096 Mar 31 10:29 /sys/bus/event_source/devices/cpu/format/event -r--r--r--. 1 root root 4096 Mar 31 10:29 /sys/bus/event_source/devices/cpu/format/inv -r--r--r--. 1 root root 4096 Mar 31 10:29 /sys/bus/event_source/devices/cpu/format/offcore_rsp -r--r--r--. 1 root root 4096 Mar 31 10:29 /sys/bus/event_source/devices/cpu/format/pc -r--r--r--. 1 root root 4096 Mar 31 10:29 /sys/bus/event_source/devices/cpu/format/umask those lists of fields contain a specific format: aldebaran:~> cat /sys/bus/event_source/devices/cpu/format/offcore_rsp config1:0-63 So, those who wish to specify raw events can now use the following event format: -e cpu/cmask=1,event=2,umask=3 Most people will not want to specify any events (let alone raw events), they'll just use whatever default event the tools use. But for more obscure PMU events that have no cross-architecture generic events the above syntax is more usable and a bit more structured than specifying hex numbers." * 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (41 commits) perf tools: Remove auto-generated bison/flex files perf annotate: Fix off by one symbol hist size allocation and hit accounting perf tools: Add missing ref-cycles event back to event parser perf annotate: addr2line wants addresses in same format as objdump perf probe: Finder fails to resolve function name to address tracing: Fix ent_size in trace output perf symbols: Handle NULL dso in dso__name_len perf symbols: Do not include libgen.h perf tools: Fix bug in raw sample parsing perf tools: Fix display of first level of callchains perf tools: Switch module.h into export.h perf: Move mmap page data_head offset assertion out of header perf: Fix mmap_page capabilities and docs perf diff: Fix to work with new hists design perf tools: Fix modifier to be applied on correct events perf tools: Fix various casting issues for 32 bits perf tools: Simplify event_read_id exit path tracing: Fix ftrace stack trace entries tracing: Move the tracing_on/off() declarations into CONFIG_TRACING perf report: Add a simple GTK2-based 'perf report' browser ...
Diffstat (limited to 'kernel')
-rw-r--r--kernel/events/core.c11
-rw-r--r--kernel/trace/Kconfig2
-rw-r--r--kernel/trace/ftrace.c3
-rw-r--r--kernel/trace/ring_buffer.c157
-rw-r--r--kernel/trace/trace.c113
-rw-r--r--kernel/trace/trace.h3
-rw-r--r--kernel/trace/trace_entries.h16
-rw-r--r--kernel/trace/trace_export.c2
8 files changed, 199 insertions, 108 deletions
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 4b50357914f..a6a9ec4cd8f 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -3348,7 +3348,7 @@ static void calc_timer_values(struct perf_event *event,
*running = ctx_time - event->tstamp_running;
}
-void __weak perf_update_user_clock(struct perf_event_mmap_page *userpg, u64 now)
+void __weak arch_perf_update_userpage(struct perf_event_mmap_page *userpg, u64 now)
{
}
@@ -3398,7 +3398,7 @@ void perf_event_update_userpage(struct perf_event *event)
userpg->time_running = running +
atomic64_read(&event->child_total_time_running);
- perf_update_user_clock(userpg, now);
+ arch_perf_update_userpage(userpg, now);
barrier();
++userpg->lock;
@@ -7116,6 +7116,13 @@ void __init perf_event_init(void)
/* do not patch jump label more than once per second */
jump_label_rate_limit(&perf_sched_events, HZ);
+
+ /*
+ * Build time assertion that we keep the data_head at the intended
+ * location. IOW, validation we got the __reserved[] size right.
+ */
+ BUILD_BUG_ON((offsetof(struct perf_event_mmap_page, data_head))
+ != 1024);
}
static int __init perf_event_sysfs_init(void)
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index cd3134510f3..a1d2849f247 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -141,7 +141,7 @@ if FTRACE
config FUNCTION_TRACER
bool "Kernel Function Tracer"
depends on HAVE_FUNCTION_TRACER
- select FRAME_POINTER if !ARM_UNWIND && !S390 && !MICROBLAZE
+ select FRAME_POINTER if !ARM_UNWIND && !PPC && !S390 && !MICROBLAZE
select KALLSYMS
select GENERIC_TRACER
select CONTEXT_SWITCH_TRACER
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 867bd1dd2dd..0fa92f677c9 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -249,7 +249,8 @@ static void update_ftrace_function(void)
#else
__ftrace_trace_function = func;
#endif
- ftrace_trace_function = ftrace_test_stop_func;
+ ftrace_trace_function =
+ (func == ftrace_stub) ? func : ftrace_test_stop_func;
#endif
}
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index f5b7b5c1195..cf8d11e91ef 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -154,33 +154,10 @@ enum {
static unsigned long ring_buffer_flags __read_mostly = RB_BUFFERS_ON;
-#define BUF_PAGE_HDR_SIZE offsetof(struct buffer_data_page, data)
-
-/**
- * tracing_on - enable all tracing buffers
- *
- * This function enables all tracing buffers that may have been
- * disabled with tracing_off.
- */
-void tracing_on(void)
-{
- set_bit(RB_BUFFERS_ON_BIT, &ring_buffer_flags);
-}
-EXPORT_SYMBOL_GPL(tracing_on);
+/* Used for individual buffers (after the counter) */
+#define RB_BUFFER_OFF (1 << 20)
-/**
- * tracing_off - turn off all tracing buffers
- *
- * This function stops all tracing buffers from recording data.
- * It does not disable any overhead the tracers themselves may
- * be causing. This function simply causes all recording to
- * the ring buffers to fail.
- */
-void tracing_off(void)
-{
- clear_bit(RB_BUFFERS_ON_BIT, &ring_buffer_flags);
-}
-EXPORT_SYMBOL_GPL(tracing_off);
+#define BUF_PAGE_HDR_SIZE offsetof(struct buffer_data_page, data)
/**
* tracing_off_permanent - permanently disable ring buffers
@@ -193,15 +170,6 @@ void tracing_off_permanent(void)
set_bit(RB_BUFFERS_DISABLED_BIT, &ring_buffer_flags);
}
-/**
- * tracing_is_on - show state of ring buffers enabled
- */
-int tracing_is_on(void)
-{
- return ring_buffer_flags == RB_BUFFERS_ON;
-}
-EXPORT_SYMBOL_GPL(tracing_is_on);
-
#define RB_EVNT_HDR_SIZE (offsetof(struct ring_buffer_event, array))
#define RB_ALIGNMENT 4U
#define RB_MAX_SMALL_DATA (RB_ALIGNMENT * RINGBUF_TYPE_DATA_TYPE_LEN_MAX)
@@ -2619,6 +2587,63 @@ void ring_buffer_record_enable(struct ring_buffer *buffer)
EXPORT_SYMBOL_GPL(ring_buffer_record_enable);
/**
+ * ring_buffer_record_off - stop all writes into the buffer
+ * @buffer: The ring buffer to stop writes to.
+ *
+ * This prevents all writes to the buffer. Any attempt to write
+ * to the buffer after this will fail and return NULL.
+ *
+ * This is different than ring_buffer_record_disable() as
+ * it works like an on/off switch, where as the disable() verison
+ * must be paired with a enable().
+ */
+void ring_buffer_record_off(struct ring_buffer *buffer)
+{
+ unsigned int rd;
+ unsigned int new_rd;
+
+ do {
+ rd = atomic_read(&buffer->record_disabled);
+ new_rd = rd | RB_BUFFER_OFF;
+ } while (atomic_cmpxchg(&buffer->record_disabled, rd, new_rd) != rd);
+}
+EXPORT_SYMBOL_GPL(ring_buffer_record_off);
+
+/**
+ * ring_buffer_record_on - restart writes into the buffer
+ * @buffer: The ring buffer to start writes to.
+ *
+ * This enables all writes to the buffer that was disabled by
+ * ring_buffer_record_off().
+ *
+ * This is different than ring_buffer_record_enable() as
+ * it works like an on/off switch, where as the enable() verison
+ * must be paired with a disable().
+ */
+void ring_buffer_record_on(struct ring_buffer *buffer)
+{
+ unsigned int rd;
+ unsigned int new_rd;
+
+ do {
+ rd = atomic_read(&buffer->record_disabled);
+ new_rd = rd & ~RB_BUFFER_OFF;
+ } while (atomic_cmpxchg(&buffer->record_disabled, rd, new_rd) != rd);
+}
+EXPORT_SYMBOL_GPL(ring_buffer_record_on);
+
+/**
+ * ring_buffer_record_is_on - return true if the ring buffer can write
+ * @buffer: The ring buffer to see if write is enabled
+ *
+ * Returns true if the ring buffer is in a state that it accepts writes.
+ */
+int ring_buffer_record_is_on(struct ring_buffer *buffer)
+{
+ return !atomic_read(&buffer->record_disabled);
+}
+
+/**
* ring_buffer_record_disable_cpu - stop all writes into the cpu_buffer
* @buffer: The ring buffer to stop writes to.
* @cpu: The CPU buffer to stop
@@ -4039,68 +4064,6 @@ int ring_buffer_read_page(struct ring_buffer *buffer,
}
EXPORT_SYMBOL_GPL(ring_buffer_read_page);
-#ifdef CONFIG_TRACING
-static ssize_t
-rb_simple_read(struct file *filp, char __user *ubuf,
- size_t cnt, loff_t *ppos)
-{
- unsigned long *p = filp->private_data;
- char buf[64];
- int r;
-
- if (test_bit(RB_BUFFERS_DISABLED_BIT, p))
- r = sprintf(buf, "permanently disabled\n");
- else
- r = sprintf(buf, "%d\n", test_bit(RB_BUFFERS_ON_BIT, p));
-
- return simple_read_from_buffer(ubuf, cnt, ppos, buf, r);
-}
-
-static ssize_t
-rb_simple_write(struct file *filp, const char __user *ubuf,
- size_t cnt, loff_t *ppos)
-{
- unsigned long *p = filp->private_data;
- unsigned long val;
- int ret;
-
- ret = kstrtoul_from_user(ubuf, cnt, 10, &val);
- if (ret)
- return ret;
-
- if (val)
- set_bit(RB_BUFFERS_ON_BIT, p);
- else
- clear_bit(RB_BUFFERS_ON_BIT, p);
-
- (*ppos)++;
-
- return cnt;
-}
-
-static const struct file_operations rb_simple_fops = {
- .open = tracing_open_generic,
- .read = rb_simple_read,
- .write = rb_simple_write,
- .llseek = default_llseek,
-};
-
-
-static __init int rb_init_debugfs(void)
-{
- struct dentry *d_tracer;
-
- d_tracer = tracing_init_dentry();
-
- trace_create_file("tracing_on", 0644, d_tracer,
- &ring_buffer_flags, &rb_simple_fops);
-
- return 0;
-}
-
-fs_initcall(rb_init_debugfs);
-#endif
-
#ifdef CONFIG_HOTPLUG_CPU
static int rb_cpu_notify(struct notifier_block *self,
unsigned long action, void *hcpu)
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 10d5503f0d0..ed7b5d1e12f 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -36,6 +36,7 @@
#include <linux/ctype.h>
#include <linux/init.h>
#include <linux/poll.h>
+#include <linux/nmi.h>
#include <linux/fs.h>
#include "trace.h"
@@ -352,6 +353,59 @@ static void wakeup_work_handler(struct work_struct *work)
static DECLARE_DELAYED_WORK(wakeup_work, wakeup_work_handler);
/**
+ * tracing_on - enable tracing buffers
+ *
+ * This function enables tracing buffers that may have been
+ * disabled with tracing_off.
+ */
+void tracing_on(void)
+{
+ if (global_trace.buffer)
+ ring_buffer_record_on(global_trace.buffer);
+ /*
+ * This flag is only looked at when buffers haven't been
+ * allocated yet. We don't really care about the race
+ * between setting this flag and actually turning
+ * on the buffer.
+ */
+ global_trace.buffer_disabled = 0;
+}
+EXPORT_SYMBOL_GPL(tracing_on);
+
+/**
+ * tracing_off - turn off tracing buffers
+ *
+ * This function stops the tracing buffers from recording data.
+ * It does not disable any overhead the tracers themselves may
+ * be causing. This function simply causes all recording to
+ * the ring buffers to fail.
+ */
+void tracing_off(void)
+{
+ if (global_trace.buffer)
+ ring_buffer_record_on(global_trace.buffer);
+ /*
+ * This flag is only looked at when buffers haven't been
+ * allocated yet. We don't really care about the race
+ * between setting this flag and actually turning
+ * on the buffer.
+ */
+ global_trace.buffer_disabled = 1;
+}
+EXPORT_SYMBOL_GPL(tracing_off);
+
+/**
+ * tracing_is_on - show state of ring buffers enabled
+ */
+int tracing_is_on(void)
+{
+ if (global_trace.buffer)
+ return ring_buffer_record_is_on(global_trace.buffer);
+ return !global_trace.buffer_disabled;
+}
+EXPORT_SYMBOL_GPL(tracing_is_on);
+
+/**
* trace_wake_up - wake up tasks waiting for trace input
*
* Schedules a delayed work to wake up any task that is blocked on the
@@ -1644,6 +1698,7 @@ __find_next_entry(struct trace_iterator *iter, int *ent_cpu,
int cpu_file = iter->cpu_file;
u64 next_ts = 0, ts;
int next_cpu = -1;
+ int next_size = 0;
int cpu;
/*
@@ -1675,9 +1730,12 @@ __find_next_entry(struct trace_iterator *iter, int *ent_cpu,
next_cpu = cpu;
next_ts = ts;
next_lost = lost_events;
+ next_size = iter->ent_size;
}
}
+ iter->ent_size = next_size;
+
if (ent_cpu)
*ent_cpu = next_cpu;
@@ -4567,6 +4625,55 @@ static __init void create_trace_options_dir(void)
create_trace_option_core_file(trace_options[i], i);
}
+static ssize_t
+rb_simple_read(struct file *filp, char __user *ubuf,
+ size_t cnt, loff_t *ppos)
+{
+ struct ring_buffer *buffer = filp->private_data;
+ char buf[64];
+ int r;
+
+ if (buffer)
+ r = ring_buffer_record_is_on(buffer);
+ else
+ r = 0;
+
+ r = sprintf(buf, "%d\n", r);
+
+ return simple_read_from_buffer(ubuf, cnt, ppos, buf, r);
+}
+
+static ssize_t
+rb_simple_write(struct file *filp, const char __user *ubuf,
+ size_t cnt, loff_t *ppos)
+{
+ struct ring_buffer *buffer = filp->private_data;
+ unsigned long val;
+ int ret;
+
+ ret = kstrtoul_from_user(ubuf, cnt, 10, &val);
+ if (ret)
+ return ret;
+
+ if (buffer) {
+ if (val)
+ ring_buffer_record_on(buffer);
+ else
+ ring_buffer_record_off(buffer);
+ }
+
+ (*ppos)++;
+
+ return cnt;
+}
+
+static const struct file_operations rb_simple_fops = {
+ .open = tracing_open_generic,
+ .read = rb_simple_read,
+ .write = rb_simple_write,
+ .llseek = default_llseek,
+};
+
static __init int tracer_init_debugfs(void)
{
struct dentry *d_tracer;
@@ -4626,6 +4733,9 @@ static __init int tracer_init_debugfs(void)
trace_create_file("trace_clock", 0644, d_tracer, NULL,
&trace_clock_fops);
+ trace_create_file("tracing_on", 0644, d_tracer,
+ global_trace.buffer, &rb_simple_fops);
+
#ifdef CONFIG_DYNAMIC_FTRACE
trace_create_file("dyn_ftrace_total_info", 0444, d_tracer,
&ftrace_update_tot_cnt, &tracing_dyn_info_fops);
@@ -4798,6 +4908,7 @@ __ftrace_dump(bool disable_tracing, enum ftrace_dump_mode oops_dump_mode)
if (ret != TRACE_TYPE_NO_CONSUME)
trace_consume(&iter);
}
+ touch_nmi_watchdog();
trace_printk_seq(&iter.seq);
}
@@ -4863,6 +4974,8 @@ __init static int tracer_alloc_buffers(void)
goto out_free_cpumask;
}
global_trace.entries = ring_buffer_size(global_trace.buffer);
+ if (global_trace.buffer_disabled)
+ tracing_off();
#ifdef CONFIG_TRACER_MAX_TRACE
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index 54faec790bc..95059f091a2 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -154,6 +154,7 @@ struct trace_array {
struct ring_buffer *buffer;
unsigned long entries;
int cpu;
+ int buffer_disabled;
cycle_t time_start;
struct task_struct *waiter;
struct trace_array_cpu *data[NR_CPUS];
@@ -835,13 +836,11 @@ extern const char *__stop___trace_bprintk_fmt[];
filter)
#include "trace_entries.h"
-#ifdef CONFIG_PERF_EVENTS
#ifdef CONFIG_FUNCTION_TRACER
int perf_ftrace_event_register(struct ftrace_event_call *call,
enum trace_reg type, void *data);
#else
#define perf_ftrace_event_register NULL
#endif /* CONFIG_FUNCTION_TRACER */
-#endif /* CONFIG_PERF_EVENTS */
#endif /* _LINUX_KERNEL_TRACE_H */
diff --git a/kernel/trace/trace_entries.h b/kernel/trace/trace_entries.h
index d91eb0541b3..4108e1250ca 100644
--- a/kernel/trace/trace_entries.h
+++ b/kernel/trace/trace_entries.h
@@ -166,6 +166,12 @@ FTRACE_ENTRY_DUP(wakeup, ctx_switch_entry,
#define FTRACE_STACK_ENTRIES 8
+#ifndef CONFIG_64BIT
+# define IP_FMT "%08lx"
+#else
+# define IP_FMT "%016lx"
+#endif
+
FTRACE_ENTRY(kernel_stack, stack_entry,
TRACE_STACK,
@@ -175,8 +181,9 @@ FTRACE_ENTRY(kernel_stack, stack_entry,
__dynamic_array(unsigned long, caller )
),
- F_printk("\t=> (%08lx)\n\t=> (%08lx)\n\t=> (%08lx)\n\t=> (%08lx)\n"
- "\t=> (%08lx)\n\t=> (%08lx)\n\t=> (%08lx)\n\t=> (%08lx)\n",
+ F_printk("\t=> (" IP_FMT ")\n\t=> (" IP_FMT ")\n\t=> (" IP_FMT ")\n"
+ "\t=> (" IP_FMT ")\n\t=> (" IP_FMT ")\n\t=> (" IP_FMT ")\n"
+ "\t=> (" IP_FMT ")\n\t=> (" IP_FMT ")\n",
__entry->caller[0], __entry->caller[1], __entry->caller[2],
__entry->caller[3], __entry->caller[4], __entry->caller[5],
__entry->caller[6], __entry->caller[7]),
@@ -193,8 +200,9 @@ FTRACE_ENTRY(user_stack, userstack_entry,
__array( unsigned long, caller, FTRACE_STACK_ENTRIES )
),
- F_printk("\t=> (%08lx)\n\t=> (%08lx)\n\t=> (%08lx)\n\t=> (%08lx)\n"
- "\t=> (%08lx)\n\t=> (%08lx)\n\t=> (%08lx)\n\t=> (%08lx)\n",
+ F_printk("\t=> (" IP_FMT ")\n\t=> (" IP_FMT ")\n\t=> (" IP_FMT ")\n"
+ "\t=> (" IP_FMT ")\n\t=> (" IP_FMT ")\n\t=> (" IP_FMT ")\n"
+ "\t=> (" IP_FMT ")\n\t=> (" IP_FMT ")\n",
__entry->caller[0], __entry->caller[1], __entry->caller[2],
__entry->caller[3], __entry->caller[4], __entry->caller[5],
__entry->caller[6], __entry->caller[7]),
diff --git a/kernel/trace/trace_export.c b/kernel/trace/trace_export.c
index 7b46c9bd22a..3dd15e8bc85 100644
--- a/kernel/trace/trace_export.c
+++ b/kernel/trace/trace_export.c
@@ -162,7 +162,7 @@ ftrace_define_fields_##name(struct ftrace_event_call *event_call) \
#define __dynamic_array(type, item)
#undef F_printk
-#define F_printk(fmt, args...) #fmt ", " __stringify(args)
+#define F_printk(fmt, args...) __stringify(fmt) ", " __stringify(args)
#undef FTRACE_ENTRY_REG
#define FTRACE_ENTRY_REG(call, struct_name, etype, tstruct, print, filter,\