summaryrefslogtreecommitdiff
path: root/kernel/trace
diff options
context:
space:
mode:
Diffstat (limited to 'kernel/trace')
-rw-r--r--kernel/trace/Kconfig17
-rw-r--r--kernel/trace/Makefile2
-rw-r--r--kernel/trace/blktrace.c44
-rw-r--r--kernel/trace/power-traces.c5
-rw-r--r--kernel/trace/ring_buffer.c9
-rw-r--r--kernel/trace/trace.c30
-rw-r--r--kernel/trace/trace_entries.h2
-rw-r--r--kernel/trace/trace_event_perf.c31
-rw-r--r--kernel/trace/trace_events.c18
-rw-r--r--kernel/trace/trace_export.c20
-rw-r--r--kernel/trace/trace_irqsoff.c8
-rw-r--r--kernel/trace/trace_selftest.c2
-rw-r--r--kernel/trace/trace_syscalls.c52
13 files changed, 163 insertions, 77 deletions
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index e04b8bcdef88..14674dce77a6 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -69,6 +69,21 @@ config EVENT_TRACING
select CONTEXT_SWITCH_TRACER
bool
+config EVENT_POWER_TRACING_DEPRECATED
+ depends on EVENT_TRACING
+ bool "Deprecated power event trace API, to be removed"
+ default y
+ help
+ Provides old power event types:
+ C-state/idle accounting events:
+ power:power_start
+ power:power_end
+ and old cpufreq accounting event:
+ power:power_frequency
+ This is for userspace compatibility
+ and will vanish after 5 kernel iterations,
+ namely 2.6.41.
+
config CONTEXT_SWITCH_TRACER
bool
@@ -126,7 +141,7 @@ if FTRACE
config FUNCTION_TRACER
bool "Kernel Function Tracer"
depends on HAVE_FUNCTION_TRACER
- select FRAME_POINTER if (!ARM_UNWIND)
+ select FRAME_POINTER if !ARM_UNWIND && !S390
select KALLSYMS
select GENERIC_TRACER
select CONTEXT_SWITCH_TRACER
diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile
index 53f338190b26..761c510a06c5 100644
--- a/kernel/trace/Makefile
+++ b/kernel/trace/Makefile
@@ -52,7 +52,7 @@ obj-$(CONFIG_EVENT_TRACING) += trace_event_perf.o
endif
obj-$(CONFIG_EVENT_TRACING) += trace_events_filter.o
obj-$(CONFIG_KPROBE_EVENT) += trace_kprobe.o
-obj-$(CONFIG_EVENT_TRACING) += power-traces.o
+obj-$(CONFIG_TRACEPOINTS) += power-traces.o
ifeq ($(CONFIG_TRACING),y)
obj-$(CONFIG_KGDB_KDB) += trace_kdb.o
endif
diff --git a/kernel/trace/blktrace.c b/kernel/trace/blktrace.c
index 7b8ec0281548..d95721f33702 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);
@@ -758,53 +765,58 @@ static void blk_add_trace_rq_complete(void *ignore,
* @q: queue the io is for
* @bio: the source bio
* @what: the action
+ * @error: error, if any
*
* Description:
* Records an action against a bio. Will log the bio offset + size.
*
**/
static void blk_add_trace_bio(struct request_queue *q, struct bio *bio,
- u32 what)
+ u32 what, int error)
{
struct blk_trace *bt = q->blk_trace;
if (likely(!bt))
return;
+ if (!error && !bio_flagged(bio, BIO_UPTODATE))
+ error = EIO;
+
__blk_add_trace(bt, bio->bi_sector, bio->bi_size, bio->bi_rw, what,
- !bio_flagged(bio, BIO_UPTODATE), 0, NULL);
+ error, 0, NULL);
}
static void blk_add_trace_bio_bounce(void *ignore,
struct request_queue *q, struct bio *bio)
{
- blk_add_trace_bio(q, bio, BLK_TA_BOUNCE);
+ blk_add_trace_bio(q, bio, BLK_TA_BOUNCE, 0);
}
static void blk_add_trace_bio_complete(void *ignore,
- struct request_queue *q, struct bio *bio)
+ struct request_queue *q, struct bio *bio,
+ int error)
{
- blk_add_trace_bio(q, bio, BLK_TA_COMPLETE);
+ blk_add_trace_bio(q, bio, BLK_TA_COMPLETE, error);
}
static void blk_add_trace_bio_backmerge(void *ignore,
struct request_queue *q,
struct bio *bio)
{
- blk_add_trace_bio(q, bio, BLK_TA_BACKMERGE);
+ blk_add_trace_bio(q, bio, BLK_TA_BACKMERGE, 0);
}
static void blk_add_trace_bio_frontmerge(void *ignore,
struct request_queue *q,
struct bio *bio)
{
- blk_add_trace_bio(q, bio, BLK_TA_FRONTMERGE);
+ blk_add_trace_bio(q, bio, BLK_TA_FRONTMERGE, 0);
}
static void blk_add_trace_bio_queue(void *ignore,
struct request_queue *q, struct bio *bio)
{
- blk_add_trace_bio(q, bio, BLK_TA_QUEUE);
+ blk_add_trace_bio(q, bio, BLK_TA_QUEUE, 0);
}
static void blk_add_trace_getrq(void *ignore,
@@ -812,7 +824,7 @@ static void blk_add_trace_getrq(void *ignore,
struct bio *bio, int rw)
{
if (bio)
- blk_add_trace_bio(q, bio, BLK_TA_GETRQ);
+ blk_add_trace_bio(q, bio, BLK_TA_GETRQ, 0);
else {
struct blk_trace *bt = q->blk_trace;
@@ -827,7 +839,7 @@ static void blk_add_trace_sleeprq(void *ignore,
struct bio *bio, int rw)
{
if (bio)
- blk_add_trace_bio(q, bio, BLK_TA_SLEEPRQ);
+ blk_add_trace_bio(q, bio, BLK_TA_SLEEPRQ, 0);
else {
struct blk_trace *bt = q->blk_trace;
@@ -887,7 +899,7 @@ static void blk_add_trace_split(void *ignore,
}
/**
- * blk_add_trace_remap - Add a trace for a remap operation
+ * blk_add_trace_bio_remap - Add a trace for a bio-remap operation
* @ignore: trace callback data parameter (not used)
* @q: queue the io is for
* @bio: the source bio
@@ -899,9 +911,9 @@ static void blk_add_trace_split(void *ignore,
* it spans a stripe (or similar). Add a trace for that action.
*
**/
-static void blk_add_trace_remap(void *ignore,
- struct request_queue *q, struct bio *bio,
- dev_t dev, sector_t from)
+static void blk_add_trace_bio_remap(void *ignore,
+ struct request_queue *q, struct bio *bio,
+ dev_t dev, sector_t from)
{
struct blk_trace *bt = q->blk_trace;
struct blk_io_trace_remap r;
@@ -1016,7 +1028,7 @@ static void blk_register_tracepoints(void)
WARN_ON(ret);
ret = register_trace_block_split(blk_add_trace_split, NULL);
WARN_ON(ret);
- ret = register_trace_block_remap(blk_add_trace_remap, NULL);
+ ret = register_trace_block_bio_remap(blk_add_trace_bio_remap, NULL);
WARN_ON(ret);
ret = register_trace_block_rq_remap(blk_add_trace_rq_remap, NULL);
WARN_ON(ret);
@@ -1025,7 +1037,7 @@ static void blk_register_tracepoints(void)
static void blk_unregister_tracepoints(void)
{
unregister_trace_block_rq_remap(blk_add_trace_rq_remap, NULL);
- unregister_trace_block_remap(blk_add_trace_remap, NULL);
+ unregister_trace_block_bio_remap(blk_add_trace_bio_remap, NULL);
unregister_trace_block_split(blk_add_trace_split, NULL);
unregister_trace_block_unplug_io(blk_add_trace_unplug_io, NULL);
unregister_trace_block_unplug_timer(blk_add_trace_unplug_timer, NULL);
diff --git a/kernel/trace/power-traces.c b/kernel/trace/power-traces.c
index a22582a06161..f55fcf61b223 100644
--- a/kernel/trace/power-traces.c
+++ b/kernel/trace/power-traces.c
@@ -13,5 +13,8 @@
#define CREATE_TRACE_POINTS
#include <trace/events/power.h>
-EXPORT_TRACEPOINT_SYMBOL_GPL(power_frequency);
+#ifdef EVENT_POWER_TRACING_DEPRECATED
+EXPORT_TRACEPOINT_SYMBOL_GPL(power_start);
+#endif
+EXPORT_TRACEPOINT_SYMBOL_GPL(cpu_idle);
diff --git a/kernel/trace/ring_buffer.c b/kernel/trace/ring_buffer.c
index 9ed509a015d8..bd1c35a4fbcc 100644
--- a/kernel/trace/ring_buffer.c
+++ b/kernel/trace/ring_buffer.c
@@ -3853,6 +3853,13 @@ int ring_buffer_read_page(struct ring_buffer *buffer,
/* Need to copy one event at a time */
do {
+ /* We need the size of one event, because
+ * rb_advance_reader only advances by one event,
+ * whereas rb_event_ts_length may include the size of
+ * one or two events.
+ * We have already ensured there's enough space if this
+ * is a time extend. */
+ size = rb_event_length(event);
memcpy(bpage->data + pos, rpage->data + rpos, size);
len -= size;
@@ -3867,7 +3874,7 @@ int ring_buffer_read_page(struct ring_buffer *buffer,
event = rb_reader_event(cpu_buffer);
/* Always keep the time extend and data together */
size = rb_event_ts_length(event);
- } while (len > size);
+ } while (len >= size);
/* update bpage */
local_set(&bpage->commit, pos);
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index 82d9b8106cd0..dc53ecb80589 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -17,7 +17,6 @@
#include <linux/writeback.h>
#include <linux/kallsyms.h>
#include <linux/seq_file.h>
-#include <linux/smp_lock.h>
#include <linux/notifier.h>
#include <linux/irqflags.h>
#include <linux/debugfs.h>
@@ -1284,6 +1283,8 @@ void trace_dump_stack(void)
__ftrace_trace_stack(global_trace.buffer, flags, 3, preempt_count());
}
+static DEFINE_PER_CPU(int, user_stack_count);
+
void
ftrace_trace_userstack(struct ring_buffer *buffer, unsigned long flags, int pc)
{
@@ -1302,10 +1303,20 @@ ftrace_trace_userstack(struct ring_buffer *buffer, unsigned long flags, int pc)
if (unlikely(in_nmi()))
return;
+ /*
+ * prevent recursion, since the user stack tracing may
+ * trigger other kernel events.
+ */
+ preempt_disable();
+ if (__this_cpu_read(user_stack_count))
+ goto out;
+
+ __this_cpu_inc(user_stack_count);
+
event = trace_buffer_lock_reserve(buffer, TRACE_USER_STACK,
sizeof(*entry), flags, pc);
if (!event)
- return;
+ goto out_drop_count;
entry = ring_buffer_event_data(event);
entry->tgid = current->tgid;
@@ -1319,6 +1330,11 @@ ftrace_trace_userstack(struct ring_buffer *buffer, unsigned long flags, int pc)
save_stack_trace_user(&trace);
if (!filter_check_discard(call, entry, buffer, event))
ring_buffer_unlock_commit(buffer, event);
+
+ out_drop_count:
+ __this_cpu_dec(user_stack_count);
+ out:
+ preempt_enable();
}
#ifdef UNUSED
@@ -2320,11 +2336,19 @@ tracing_write_stub(struct file *filp, const char __user *ubuf,
return count;
}
+static loff_t tracing_seek(struct file *file, loff_t offset, int origin)
+{
+ if (file->f_mode & FMODE_READ)
+ return seq_lseek(file, offset, origin);
+ else
+ return 0;
+}
+
static const struct file_operations tracing_fops = {
.open = tracing_open,
.read = seq_read,
.write = tracing_write_stub,
- .llseek = seq_lseek,
+ .llseek = tracing_seek,
.release = tracing_release,
};
diff --git a/kernel/trace/trace_entries.h b/kernel/trace/trace_entries.h
index e3dfecaf13e6..6cf223764be8 100644
--- a/kernel/trace/trace_entries.h
+++ b/kernel/trace/trace_entries.h
@@ -53,7 +53,7 @@
*/
/*
- * Function trace entry - function address and parent function addres:
+ * Function trace entry - function address and parent function address:
*/
FTRACE_ENTRY(function, ftrace_entry,
diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c
index 39c059ca670e..19a359d5e6d5 100644
--- a/kernel/trace/trace_event_perf.c
+++ b/kernel/trace/trace_event_perf.c
@@ -21,17 +21,46 @@ typedef typeof(unsigned long [PERF_MAX_TRACE_SIZE / sizeof(unsigned long)])
/* Count the events in use (per event id, not per instance) */
static int total_ref_count;
+static int perf_trace_event_perm(struct ftrace_event_call *tp_event,
+ struct perf_event *p_event)
+{
+ /* No tracing, just counting, so no obvious leak */
+ if (!(p_event->attr.sample_type & PERF_SAMPLE_RAW))
+ return 0;
+
+ /* Some events are ok to be traced by non-root users... */
+ if (p_event->attach_state == PERF_ATTACH_TASK) {
+ if (tp_event->flags & TRACE_EVENT_FL_CAP_ANY)
+ return 0;
+ }
+
+ /*
+ * ...otherwise raw tracepoint data can be a severe data leak,
+ * only allow root to have these.
+ */
+ if (perf_paranoid_tracepoint_raw() && !capable(CAP_SYS_ADMIN))
+ return -EPERM;
+
+ return 0;
+}
+
static int perf_trace_event_init(struct ftrace_event_call *tp_event,
struct perf_event *p_event)
{
struct hlist_head __percpu *list;
- int ret = -ENOMEM;
+ int ret;
int cpu;
+ ret = perf_trace_event_perm(tp_event, p_event);
+ if (ret)
+ return ret;
+
p_event->tp_event = tp_event;
if (tp_event->perf_refcount++ > 0)
return 0;
+ ret = -ENOMEM;
+
list = alloc_percpu(struct hlist_head);
if (!list)
goto fail;
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index 0725eeab1937..5f499e0438a4 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -27,6 +27,12 @@
DEFINE_MUTEX(event_mutex);
+DEFINE_MUTEX(event_storage_mutex);
+EXPORT_SYMBOL_GPL(event_storage_mutex);
+
+char event_storage[EVENT_STORAGE_SIZE];
+EXPORT_SYMBOL_GPL(event_storage);
+
LIST_HEAD(ftrace_events);
LIST_HEAD(ftrace_common_fields);
@@ -1278,7 +1284,7 @@ trace_create_file_ops(struct module *mod)
static void trace_module_add_events(struct module *mod)
{
struct ftrace_module_file_ops *file_ops = NULL;
- struct ftrace_event_call *call, *start, *end;
+ struct ftrace_event_call **call, **start, **end;
start = mod->trace_events;
end = mod->trace_events + mod->num_trace_events;
@@ -1291,7 +1297,7 @@ static void trace_module_add_events(struct module *mod)
return;
for_each_event(call, start, end) {
- __trace_add_event_call(call, mod,
+ __trace_add_event_call(*call, mod,
&file_ops->id, &file_ops->enable,
&file_ops->filter, &file_ops->format);
}
@@ -1361,8 +1367,8 @@ static struct notifier_block trace_module_nb = {
.priority = 0,
};
-extern struct ftrace_event_call __start_ftrace_events[];
-extern struct ftrace_event_call __stop_ftrace_events[];
+extern struct ftrace_event_call *__start_ftrace_events[];
+extern struct ftrace_event_call *__stop_ftrace_events[];
static char bootup_event_buf[COMMAND_LINE_SIZE] __initdata;
@@ -1378,7 +1384,7 @@ __setup("trace_event=", setup_trace_event);
static __init int event_trace_init(void)
{
- struct ftrace_event_call *call;
+ struct ftrace_event_call **call;
struct dentry *d_tracer;
struct dentry *entry;
struct dentry *d_events;
@@ -1424,7 +1430,7 @@ static __init int event_trace_init(void)
pr_warning("tracing: Failed to allocate common fields");
for_each_event(call, __start_ftrace_events, __stop_ftrace_events) {
- __trace_add_event_call(call, NULL, &ftrace_event_id_fops,
+ __trace_add_event_call(*call, NULL, &ftrace_event_id_fops,
&ftrace_enable_fops,
&ftrace_event_filter_fops,
&ftrace_event_format_fops);
diff --git a/kernel/trace/trace_export.c b/kernel/trace/trace_export.c
index 4ba44deaac25..bbeec31e0ae3 100644
--- a/kernel/trace/trace_export.c
+++ b/kernel/trace/trace_export.c
@@ -83,13 +83,19 @@ static void __always_unused ____ftrace_check_##name(void) \
#undef __array
#define __array(type, item, len) \
- BUILD_BUG_ON(len > MAX_FILTER_STR_VAL); \
- ret = trace_define_field(event_call, #type "[" #len "]", #item, \
+ do { \
+ BUILD_BUG_ON(len > MAX_FILTER_STR_VAL); \
+ mutex_lock(&event_storage_mutex); \
+ snprintf(event_storage, sizeof(event_storage), \
+ "%s[%d]", #type, len); \
+ ret = trace_define_field(event_call, event_storage, #item, \
offsetof(typeof(field), item), \
sizeof(field.item), \
is_signed_type(type), FILTER_OTHER); \
- if (ret) \
- return ret;
+ mutex_unlock(&event_storage_mutex); \
+ if (ret) \
+ return ret; \
+ } while (0);
#undef __array_desc
#define __array_desc(type, container, item, len) \
@@ -155,13 +161,13 @@ struct ftrace_event_class event_class_ftrace_##call = { \
.fields = LIST_HEAD_INIT(event_class_ftrace_##call.fields),\
}; \
\
-struct ftrace_event_call __used \
-__attribute__((__aligned__(4))) \
-__attribute__((section("_ftrace_events"))) event_##call = { \
+struct ftrace_event_call __used event_##call = { \
.name = #call, \
.event.type = etype, \
.class = &event_class_ftrace_##call, \
.print_fmt = print, \
}; \
+struct ftrace_event_call __used \
+__attribute__((section("_ftrace_events"))) *__event_##call = &event_##call;
#include "trace_entries.h"
diff --git a/kernel/trace/trace_irqsoff.c b/kernel/trace/trace_irqsoff.c
index 5cf8c602b880..92b6e1e12d98 100644
--- a/kernel/trace/trace_irqsoff.c
+++ b/kernel/trace/trace_irqsoff.c
@@ -453,14 +453,6 @@ void time_hardirqs_off(unsigned long a0, unsigned long a1)
* Stubs:
*/
-void early_boot_irqs_off(void)
-{
-}
-
-void early_boot_irqs_on(void)
-{
-}
-
void trace_softirqs_on(unsigned long ip)
{
}
diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c
index 155a415b3209..659732eba07c 100644
--- a/kernel/trace/trace_selftest.c
+++ b/kernel/trace/trace_selftest.c
@@ -558,7 +558,7 @@ trace_selftest_startup_nop(struct tracer *trace, struct trace_array *tr)
static int trace_wakeup_test_thread(void *data)
{
/* Make this a RT thread, doesn't need to be too high */
- struct sched_param param = { .sched_priority = 5 };
+ static const struct sched_param param = { .sched_priority = 5 };
struct completion *x = data;
sched_setscheduler(current, SCHED_FIFO, &param);
diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c
index bac752f0cfb5..5c9fe08d2093 100644
--- a/kernel/trace/trace_syscalls.c
+++ b/kernel/trace/trace_syscalls.c
@@ -23,9 +23,6 @@ static int syscall_exit_register(struct ftrace_event_call *event,
static int syscall_enter_define_fields(struct ftrace_event_call *call);
static int syscall_exit_define_fields(struct ftrace_event_call *call);
-/* All syscall exit events have the same fields */
-static LIST_HEAD(syscall_exit_fields);
-
static struct list_head *
syscall_get_enter_fields(struct ftrace_event_call *call)
{
@@ -34,50 +31,45 @@ syscall_get_enter_fields(struct ftrace_event_call *call)
return &entry->enter_fields;
}
-static struct list_head *
-syscall_get_exit_fields(struct ftrace_event_call *call)
-{
- return &syscall_exit_fields;
-}
-
struct trace_event_functions enter_syscall_print_funcs = {
- .trace = print_syscall_enter,
+ .trace = print_syscall_enter,
};
struct trace_event_functions exit_syscall_print_funcs = {
- .trace = print_syscall_exit,
+ .trace = print_syscall_exit,
};
struct ftrace_event_class event_class_syscall_enter = {
- .system = "syscalls",
- .reg = syscall_enter_register,
- .define_fields = syscall_enter_define_fields,
- .get_fields = syscall_get_enter_fields,
- .raw_init = init_syscall_trace,
+ .system = "syscalls",
+ .reg = syscall_enter_register,
+ .define_fields = syscall_enter_define_fields,
+ .get_fields = syscall_get_enter_fields,
+ .raw_init = init_syscall_trace,
};
struct ftrace_event_class event_class_syscall_exit = {
- .system = "syscalls",
- .reg = syscall_exit_register,
- .define_fields = syscall_exit_define_fields,
- .get_fields = syscall_get_exit_fields,
- .raw_init = init_syscall_trace,
+ .system = "syscalls",
+ .reg = syscall_exit_register,
+ .define_fields = syscall_exit_define_fields,
+ .fields = LIST_HEAD_INIT(event_class_syscall_exit.fields),
+ .raw_init = init_syscall_trace,
};
-extern unsigned long __start_syscalls_metadata[];
-extern unsigned long __stop_syscalls_metadata[];
+extern struct syscall_metadata *__start_syscalls_metadata[];
+extern struct syscall_metadata *__stop_syscalls_metadata[];
static struct syscall_metadata **syscalls_metadata;
-static struct syscall_metadata *find_syscall_meta(unsigned long syscall)
+static __init struct syscall_metadata *
+find_syscall_meta(unsigned long syscall)
{
- struct syscall_metadata *start;
- struct syscall_metadata *stop;
+ struct syscall_metadata **start;
+ struct syscall_metadata **stop;
char str[KSYM_SYMBOL_LEN];
- start = (struct syscall_metadata *)__start_syscalls_metadata;
- stop = (struct syscall_metadata *)__stop_syscalls_metadata;
+ start = __start_syscalls_metadata;
+ stop = __stop_syscalls_metadata;
kallsyms_lookup(syscall, NULL, NULL, NULL, str);
for ( ; start < stop; start++) {
@@ -87,8 +79,8 @@ static struct syscall_metadata *find_syscall_meta(unsigned long syscall)
* with "SyS" instead of "sys", leading to an unwanted
* mismatch.
*/
- if (start->name && !strcmp(start->name + 3, str + 3))
- return start;
+ if ((*start)->name && !strcmp((*start)->name + 3, str + 3))
+ return *start;
}
return NULL;
}
generated by cgit v1.2.3 (git 2.0.4) at 2025-05-10 04:56:54 +0000