summaryrefslogtreecommitdiffstats
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/Makefile3
-rw-r--r--kernel/exit.c14
-rw-r--r--kernel/freezer.c9
-rw-r--r--kernel/perf_event.c82
-rw-r--r--kernel/power/Makefile5
-rw-r--r--kernel/power/hibernate.c7
-rw-r--r--kernel/power/process.c8
-rw-r--r--kernel/power/suspend.c2
-rw-r--r--kernel/printk.c14
-rw-r--r--kernel/trace/Makefile2
-rw-r--r--kernel/trace/trace.c6
11 files changed, 93 insertions, 59 deletions
diff --git a/kernel/Makefile b/kernel/Makefile
index 0b5ff083fa2..5669f71dfdd 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -100,6 +100,7 @@ obj-$(CONFIG_FUNCTION_TRACER) += trace/
obj-$(CONFIG_TRACING) += trace/
obj-$(CONFIG_X86_DS) += trace/
obj-$(CONFIG_RING_BUFFER) += trace/
+obj-$(CONFIG_TRACEPOINTS) += trace/
obj-$(CONFIG_SMP) += sched_cpupri.o
obj-$(CONFIG_IRQ_WORK) += irq_work.o
obj-$(CONFIG_PERF_EVENTS) += perf_event.o
@@ -121,7 +122,7 @@ $(obj)/configs.o: $(obj)/config_data.h
# config_data.h contains the same information as ikconfig.h but gzipped.
# Info from config_data can be extracted from /proc/config*
targets += config_data.gz
-$(obj)/config_data.gz: .config FORCE
+$(obj)/config_data.gz: $(KCONFIG_CONFIG) FORCE
$(call if_changed,gzip)
quiet_cmd_ikconfiggz = IKCFG $@
diff --git a/kernel/exit.c b/kernel/exit.c
index 89c74861a3d..f9a45ebcc7b 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -994,6 +994,15 @@ NORET_TYPE void do_exit(long code)
exit_fs(tsk);
check_stack_usage();
exit_thread();
+
+ /*
+ * Flush inherited counters to the parent - before the parent
+ * gets woken up by child-exit notifications.
+ *
+ * because of cgroup mode, must be called before cgroup_exit()
+ */
+ perf_event_exit_task(tsk);
+
cgroup_exit(tsk, 1);
if (group_dead)
@@ -1007,11 +1016,6 @@ NORET_TYPE void do_exit(long code)
* FIXME: do that only when needed, using sched_exit tracepoint
*/
flush_ptrace_hw_breakpoint(tsk);
- /*
- * Flush inherited counters to the parent - before the parent
- * gets woken up by child-exit notifications.
- */
- perf_event_exit_task(tsk);
exit_notify(tsk, group_dead);
#ifdef CONFIG_NUMA
diff --git a/kernel/freezer.c b/kernel/freezer.c
index bd1d42b17cb..66ecd2ead21 100644
--- a/kernel/freezer.c
+++ b/kernel/freezer.c
@@ -104,8 +104,13 @@ bool freeze_task(struct task_struct *p, bool sig_only)
}
if (should_send_signal(p)) {
- if (!signal_pending(p))
- fake_signal_wake_up(p);
+ fake_signal_wake_up(p);
+ /*
+ * fake_signal_wake_up() goes through p's scheduler
+ * lock and guarantees that TASK_STOPPED/TRACED ->
+ * TASK_RUNNING transition can't race with task state
+ * testing in try_to_freeze_tasks().
+ */
} else if (sig_only) {
return false;
} else {
diff --git a/kernel/perf_event.c b/kernel/perf_event.c
index 11847bf1e8c..b782b7a79f0 100644
--- a/kernel/perf_event.c
+++ b/kernel/perf_event.c
@@ -38,6 +38,12 @@
#include <asm/irq_regs.h>
+enum event_type_t {
+ EVENT_FLEXIBLE = 0x1,
+ EVENT_PINNED = 0x2,
+ EVENT_ALL = EVENT_FLEXIBLE | EVENT_PINNED,
+};
+
atomic_t perf_task_events __read_mostly;
static atomic_t nr_mmap_events __read_mostly;
static atomic_t nr_comm_events __read_mostly;
@@ -65,6 +71,12 @@ int sysctl_perf_event_sample_rate __read_mostly = 100000;
static atomic64_t perf_event_id;
+static void cpu_ctx_sched_out(struct perf_cpu_context *cpuctx,
+ enum event_type_t event_type);
+
+static void cpu_ctx_sched_in(struct perf_cpu_context *cpuctx,
+ enum event_type_t event_type);
+
void __weak perf_event_print_debug(void) { }
extern __weak const char *perf_pmu_name(void)
@@ -72,6 +84,11 @@ extern __weak const char *perf_pmu_name(void)
return "pmu";
}
+static inline u64 perf_clock(void)
+{
+ return local_clock();
+}
+
void perf_pmu_disable(struct pmu *pmu)
{
int *count = this_cpu_ptr(pmu->pmu_disable_count);
@@ -240,11 +257,6 @@ static void perf_unpin_context(struct perf_event_context *ctx)
put_ctx(ctx);
}
-static inline u64 perf_clock(void)
-{
- return local_clock();
-}
-
/*
* Update the record of the current time in a context.
*/
@@ -256,6 +268,12 @@ static void update_context_time(struct perf_event_context *ctx)
ctx->timestamp = now;
}
+static u64 perf_event_time(struct perf_event *event)
+{
+ struct perf_event_context *ctx = event->ctx;
+ return ctx ? ctx->time : 0;
+}
+
/*
* Update the total_time_enabled and total_time_running fields for a event.
*/
@@ -269,7 +287,7 @@ static void update_event_times(struct perf_event *event)
return;
if (ctx->is_active)
- run_end = ctx->time;
+ run_end = perf_event_time(event);
else
run_end = event->tstamp_stopped;
@@ -278,7 +296,7 @@ static void update_event_times(struct perf_event *event)
if (event->state == PERF_EVENT_STATE_INACTIVE)
run_end = event->tstamp_stopped;
else
- run_end = ctx->time;
+ run_end = perf_event_time(event);
event->total_time_running = run_end - event->tstamp_running;
}
@@ -534,6 +552,7 @@ event_sched_out(struct perf_event *event,
struct perf_cpu_context *cpuctx,
struct perf_event_context *ctx)
{
+ u64 tstamp = perf_event_time(event);
u64 delta;
/*
* An event which could not be activated because of
@@ -545,7 +564,7 @@ event_sched_out(struct perf_event *event,
&& !event_filter_match(event)) {
delta = ctx->time - event->tstamp_stopped;
event->tstamp_running += delta;
- event->tstamp_stopped = ctx->time;
+ event->tstamp_stopped = tstamp;
}
if (event->state != PERF_EVENT_STATE_ACTIVE)
@@ -556,7 +575,7 @@ event_sched_out(struct perf_event *event,
event->pending_disable = 0;
event->state = PERF_EVENT_STATE_OFF;
}
- event->tstamp_stopped = ctx->time;
+ event->tstamp_stopped = tstamp;
event->pmu->del(event, 0);
event->oncpu = -1;
@@ -768,6 +787,8 @@ event_sched_in(struct perf_event *event,
struct perf_cpu_context *cpuctx,
struct perf_event_context *ctx)
{
+ u64 tstamp = perf_event_time(event);
+
if (event->state <= PERF_EVENT_STATE_OFF)
return 0;
@@ -784,9 +805,9 @@ event_sched_in(struct perf_event *event,
return -EAGAIN;
}
- event->tstamp_running += ctx->time - event->tstamp_stopped;
+ event->tstamp_running += tstamp - event->tstamp_stopped;
- event->shadow_ctx_time = ctx->time - ctx->timestamp;
+ event->shadow_ctx_time = tstamp - ctx->timestamp;
if (!is_software_event(event))
cpuctx->active_oncpu++;
@@ -898,11 +919,13 @@ static int group_can_go_on(struct perf_event *event,
static void add_event_to_ctx(struct perf_event *event,
struct perf_event_context *ctx)
{
+ u64 tstamp = perf_event_time(event);
+
list_add_event(event, ctx);
perf_group_attach(event);
- event->tstamp_enabled = ctx->time;
- event->tstamp_running = ctx->time;
- event->tstamp_stopped = ctx->time;
+ event->tstamp_enabled = tstamp;
+ event->tstamp_running = tstamp;
+ event->tstamp_stopped = tstamp;
}
/*
@@ -937,7 +960,7 @@ static void __perf_install_in_context(void *info)
add_event_to_ctx(event, ctx);
- if (event->cpu != -1 && event->cpu != smp_processor_id())
+ if (!event_filter_match(event))
goto unlock;
/*
@@ -1042,14 +1065,13 @@ static void __perf_event_mark_enabled(struct perf_event *event,
struct perf_event_context *ctx)
{
struct perf_event *sub;
+ u64 tstamp = perf_event_time(event);
event->state = PERF_EVENT_STATE_INACTIVE;
- event->tstamp_enabled = ctx->time - event->total_time_enabled;
+ event->tstamp_enabled = tstamp - event->total_time_enabled;
list_for_each_entry(sub, &event->sibling_list, group_entry) {
- if (sub->state >= PERF_EVENT_STATE_INACTIVE) {
- sub->tstamp_enabled =
- ctx->time - sub->total_time_enabled;
- }
+ if (sub->state >= PERF_EVENT_STATE_INACTIVE)
+ sub->tstamp_enabled = tstamp - sub->total_time_enabled;
}
}
@@ -1082,7 +1104,7 @@ static void __perf_event_enable(void *info)
goto unlock;
__perf_event_mark_enabled(event, ctx);
- if (event->cpu != -1 && event->cpu != smp_processor_id())
+ if (!event_filter_match(event))
goto unlock;
/*
@@ -1193,12 +1215,6 @@ static int perf_event_refresh(struct perf_event *event, int refresh)
return 0;
}
-enum event_type_t {
- EVENT_FLEXIBLE = 0x1,
- EVENT_PINNED = 0x2,
- EVENT_ALL = EVENT_FLEXIBLE | EVENT_PINNED,
-};
-
static void ctx_sched_out(struct perf_event_context *ctx,
struct perf_cpu_context *cpuctx,
enum event_type_t event_type)
@@ -1435,7 +1451,7 @@ ctx_pinned_sched_in(struct perf_event_context *ctx,
list_for_each_entry(event, &ctx->pinned_groups, group_entry) {
if (event->state <= PERF_EVENT_STATE_OFF)
continue;
- if (event->cpu != -1 && event->cpu != smp_processor_id())
+ if (!event_filter_match(event))
continue;
if (group_can_go_on(event, cpuctx, 1))
@@ -1467,7 +1483,7 @@ ctx_flexible_sched_in(struct perf_event_context *ctx,
* Listen to the 'cpu' scheduling filter constraint
* of events:
*/
- if (event->cpu != -1 && event->cpu != smp_processor_id())
+ if (!event_filter_match(event))
continue;
if (group_can_go_on(event, cpuctx, can_add_hw)) {
@@ -1694,7 +1710,7 @@ static void perf_ctx_adjust_freq(struct perf_event_context *ctx, u64 period)
if (event->state != PERF_EVENT_STATE_ACTIVE)
continue;
- if (event->cpu != -1 && event->cpu != smp_processor_id())
+ if (!event_filter_match(event))
continue;
hwc = &event->hw;
@@ -3893,7 +3909,7 @@ static int perf_event_task_match(struct perf_event *event)
if (event->state < PERF_EVENT_STATE_INACTIVE)
return 0;
- if (event->cpu != -1 && event->cpu != smp_processor_id())
+ if (!event_filter_match(event))
return 0;
if (event->attr.comm || event->attr.mmap ||
@@ -4030,7 +4046,7 @@ static int perf_event_comm_match(struct perf_event *event)
if (event->state < PERF_EVENT_STATE_INACTIVE)
return 0;
- if (event->cpu != -1 && event->cpu != smp_processor_id())
+ if (!event_filter_match(event))
return 0;
if (event->attr.comm)
@@ -4178,7 +4194,7 @@ static int perf_event_mmap_match(struct perf_event *event,
if (event->state < PERF_EVENT_STATE_INACTIVE)
return 0;
- if (event->cpu != -1 && event->cpu != smp_processor_id())
+ if (!event_filter_match(event))
return 0;
if ((!executable && event->attr.mmap_data) ||
diff --git a/kernel/power/Makefile b/kernel/power/Makefile
index f9063c6b185..b75597235d8 100644
--- a/kernel/power/Makefile
+++ b/kernel/power/Makefile
@@ -1,7 +1,4 @@
-
-ifeq ($(CONFIG_PM_DEBUG),y)
-EXTRA_CFLAGS += -DDEBUG
-endif
+ccflags-$(CONFIG_PM_DEBUG) := -DDEBUG
obj-$(CONFIG_PM) += main.o
obj-$(CONFIG_PM_SLEEP) += console.o
diff --git a/kernel/power/hibernate.c b/kernel/power/hibernate.c
index 048d0b51483..870f72bc72a 100644
--- a/kernel/power/hibernate.c
+++ b/kernel/power/hibernate.c
@@ -62,7 +62,7 @@ void hibernation_set_ops(struct platform_hibernation_ops *ops)
{
if (ops && !(ops->begin && ops->end && ops->pre_snapshot
&& ops->prepare && ops->finish && ops->enter && ops->pre_restore
- && ops->restore_cleanup)) {
+ && ops->restore_cleanup && ops->leave)) {
WARN_ON(1);
return;
}
@@ -278,7 +278,7 @@ static int create_image(int platform_mode)
goto Enable_irqs;
}
- if (hibernation_test(TEST_CORE) || !pm_check_wakeup_events())
+ if (hibernation_test(TEST_CORE) || pm_wakeup_pending())
goto Power_up;
in_suspend = 1;
@@ -516,7 +516,7 @@ int hibernation_platform_enter(void)
local_irq_disable();
sysdev_suspend(PMSG_HIBERNATE);
- if (!pm_check_wakeup_events()) {
+ if (pm_wakeup_pending()) {
error = -EAGAIN;
goto Power_up;
}
@@ -647,6 +647,7 @@ int hibernate(void)
swsusp_free();
if (!error)
power_down();
+ in_suspend = 0;
pm_restore_gfp_mask();
} else {
pr_debug("PM: Image restored successfully.\n");
diff --git a/kernel/power/process.c b/kernel/power/process.c
index e50b4c1b2a0..d6d2a10320e 100644
--- a/kernel/power/process.c
+++ b/kernel/power/process.c
@@ -64,6 +64,12 @@ static int try_to_freeze_tasks(bool sig_only)
* perturb a task in TASK_STOPPED or TASK_TRACED.
* It is "frozen enough". If the task does wake
* up, it will immediately call try_to_freeze.
+ *
+ * Because freeze_task() goes through p's
+ * scheduler lock after setting TIF_FREEZE, it's
+ * guaranteed that either we see TASK_RUNNING or
+ * try_to_stop() after schedule() in ptrace/signal
+ * stop sees TIF_FREEZE.
*/
if (!task_is_stopped_or_traced(p) &&
!freezer_should_skip(p))
@@ -79,7 +85,7 @@ static int try_to_freeze_tasks(bool sig_only)
if (!todo || time_after(jiffies, end_time))
break;
- if (!pm_check_wakeup_events()) {
+ if (pm_wakeup_pending()) {
wakeup = true;
break;
}
diff --git a/kernel/power/suspend.c b/kernel/power/suspend.c
index 031d5e3a619..8850df68794 100644
--- a/kernel/power/suspend.c
+++ b/kernel/power/suspend.c
@@ -164,7 +164,7 @@ static int suspend_enter(suspend_state_t state)
error = sysdev_suspend(PMSG_SUSPEND);
if (!error) {
- if (!suspend_test(TEST_CORE) && pm_check_wakeup_events()) {
+ if (!(suspend_test(TEST_CORE) || pm_wakeup_pending())) {
error = suspend_ops->enter(state);
events_check_enabled = false;
}
diff --git a/kernel/printk.c b/kernel/printk.c
index 4642a5c439e..f64b8997fc7 100644
--- a/kernel/printk.c
+++ b/kernel/printk.c
@@ -273,12 +273,12 @@ int do_syslog(int type, char __user *buf, int len, bool from_file)
* at open time.
*/
if (type == SYSLOG_ACTION_OPEN || !from_file) {
- if (dmesg_restrict && !capable(CAP_SYS_ADMIN))
- return -EPERM;
+ if (dmesg_restrict && !capable(CAP_SYSLOG))
+ goto warn; /* switch to return -EPERM after 2.6.39 */
if ((type != SYSLOG_ACTION_READ_ALL &&
type != SYSLOG_ACTION_SIZE_BUFFER) &&
- !capable(CAP_SYS_ADMIN))
- return -EPERM;
+ !capable(CAP_SYSLOG))
+ goto warn; /* switch to return -EPERM after 2.6.39 */
}
error = security_syslog(type);
@@ -422,6 +422,12 @@ int do_syslog(int type, char __user *buf, int len, bool from_file)
}
out:
return error;
+warn:
+ /* remove after 2.6.39 */
+ if (capable(CAP_SYS_ADMIN))
+ WARN_ONCE(1, "Attempt to access syslog with CAP_SYS_ADMIN "
+ "but no CAP_SYSLOG (deprecated and denied).\n");
+ return -EPERM;
}
SYSCALL_DEFINE3(syslog, int, type, char __user *, buf, int, len)
diff --git a/kernel/trace/Makefile b/kernel/trace/Makefile
index 53f338190b2..761c510a06c 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/trace.c b/kernel/trace/trace.c
index f8cf959bad4..dc53ecb8058 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -1313,12 +1313,10 @@ ftrace_trace_userstack(struct ring_buffer *buffer, unsigned long flags, int pc)
__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;
@@ -1333,8 +1331,8 @@ ftrace_trace_userstack(struct ring_buffer *buffer, unsigned long flags, int pc)
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();
}
generated by cgit v1.2.3-70-g09d2 (git 2.46.0) at 2025-03-20 15:53:50 +0000