summaryrefslogtreecommitdiffstats
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/events/core.c246
-rw-r--r--kernel/events/hw_breakpoint.c13
-rw-r--r--kernel/irq/chip.c2
-rw-r--r--kernel/jump_label.c135
-rw-r--r--kernel/printk.c5
-rw-r--r--kernel/sched/core.c18
-rw-r--r--kernel/sched/fair.c8
-rw-r--r--kernel/sched/sched.h14
-rw-r--r--kernel/signal.c28
-rw-r--r--kernel/softirq.c6
-rw-r--r--kernel/trace/ftrace.c134
-rw-r--r--kernel/trace/trace.c6
-rw-r--r--kernel/trace/trace.h38
-rw-r--r--kernel/trace/trace_entries.h54
-rw-r--r--kernel/trace/trace_event_perf.c208
-rw-r--r--kernel/trace/trace_events.c12
-rw-r--r--kernel/trace/trace_events_filter.c175
-rw-r--r--kernel/trace/trace_export.c64
-rw-r--r--kernel/trace/trace_kprobe.c8
-rw-r--r--kernel/trace/trace_output.c12
-rw-r--r--kernel/trace/trace_syscalls.c22
-rw-r--r--kernel/tracepoint.c20
-rw-r--r--kernel/watchdog.c24
23 files changed, 993 insertions, 259 deletions
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 1b5c081..c61234b 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -118,6 +118,13 @@ static int cpu_function_call(int cpu, int (*func) (void *info), void *info)
PERF_FLAG_FD_OUTPUT |\
PERF_FLAG_PID_CGROUP)
+/*
+ * branch priv levels that need permission checks
+ */
+#define PERF_SAMPLE_BRANCH_PERM_PLM \
+ (PERF_SAMPLE_BRANCH_KERNEL |\
+ PERF_SAMPLE_BRANCH_HV)
+
enum event_type_t {
EVENT_FLEXIBLE = 0x1,
EVENT_PINNED = 0x2,
@@ -128,8 +135,9 @@ enum event_type_t {
* perf_sched_events : >0 events exist
* perf_cgroup_events: >0 per-cpu cgroup events exist on this cpu
*/
-struct jump_label_key_deferred perf_sched_events __read_mostly;
+struct static_key_deferred perf_sched_events __read_mostly;
static DEFINE_PER_CPU(atomic_t, perf_cgroup_events);
+static DEFINE_PER_CPU(atomic_t, perf_branch_stack_events);
static atomic_t nr_mmap_events __read_mostly;
static atomic_t nr_comm_events __read_mostly;
@@ -881,6 +889,9 @@ list_add_event(struct perf_event *event, struct perf_event_context *ctx)
if (is_cgroup_event(event))
ctx->nr_cgroups++;
+ if (has_branch_stack(event))
+ ctx->nr_branch_stack++;
+
list_add_rcu(&event->event_entry, &ctx->event_list);
if (!ctx->nr_events)
perf_pmu_rotate_start(ctx->pmu);
@@ -1020,6 +1031,9 @@ list_del_event(struct perf_event *event, struct perf_event_context *ctx)
cpuctx->cgrp = NULL;
}
+ if (has_branch_stack(event))
+ ctx->nr_branch_stack--;
+
ctx->nr_events--;
if (event->attr.inherit_stat)
ctx->nr_stat--;
@@ -2195,6 +2209,66 @@ static void perf_event_context_sched_in(struct perf_event_context *ctx,
}
/*
+ * When sampling the branck stack in system-wide, it may be necessary
+ * to flush the stack on context switch. This happens when the branch
+ * stack does not tag its entries with the pid of the current task.
+ * Otherwise it becomes impossible to associate a branch entry with a
+ * task. This ambiguity is more likely to appear when the branch stack
+ * supports priv level filtering and the user sets it to monitor only
+ * at the user level (which could be a useful measurement in system-wide
+ * mode). In that case, the risk is high of having a branch stack with
+ * branch from multiple tasks. Flushing may mean dropping the existing
+ * entries or stashing them somewhere in the PMU specific code layer.
+ *
+ * This function provides the context switch callback to the lower code
+ * layer. It is invoked ONLY when there is at least one system-wide context
+ * with at least one active event using taken branch sampling.
+ */
+static void perf_branch_stack_sched_in(struct task_struct *prev,
+ struct task_struct *task)
+{
+ struct perf_cpu_context *cpuctx;
+ struct pmu *pmu;
+ unsigned long flags;
+
+ /* no need to flush branch stack if not changing task */
+ if (prev == task)
+ return;
+
+ local_irq_save(flags);
+
+ rcu_read_lock();
+
+ list_for_each_entry_rcu(pmu, &pmus, entry) {
+ cpuctx = this_cpu_ptr(pmu->pmu_cpu_context);
+
+ /*
+ * check if the context has at least one
+ * event using PERF_SAMPLE_BRANCH_STACK
+ */
+ if (cpuctx->ctx.nr_branch_stack > 0
+ && pmu->flush_branch_stack) {
+
+ pmu = cpuctx->ctx.pmu;
+
+ perf_ctx_lock(cpuctx, cpuctx->task_ctx);
+
+ perf_pmu_disable(pmu);
+
+ pmu->flush_branch_stack();
+
+ perf_pmu_enable(pmu);
+
+ perf_ctx_unlock(cpuctx, cpuctx->task_ctx);
+ }
+ }
+
+ rcu_read_unlock();
+
+ local_irq_restore(flags);
+}
+
+/*
* Called from scheduler to add the events of the current task
* with interrupts disabled.
*
@@ -2225,6 +2299,10 @@ void __perf_event_task_sched_in(struct task_struct *prev,
*/
if (atomic_read(&__get_cpu_var(perf_cgroup_events)))
perf_cgroup_sched_in(prev, task);
+
+ /* check for system-wide branch_stack events */
+ if (atomic_read(&__get_cpu_var(perf_branch_stack_events)))
+ perf_branch_stack_sched_in(prev, task);
}
static u64 perf_calculate_period(struct perf_event *event, u64 nsec, u64 count)
@@ -2778,7 +2856,7 @@ static void free_event(struct perf_event *event)
if (!event->parent) {
if (event->attach_state & PERF_ATTACH_TASK)
- jump_label_dec_deferred(&perf_sched_events);
+ static_key_slow_dec_deferred(&perf_sched_events);
if (event->attr.mmap || event->attr.mmap_data)
atomic_dec(&nr_mmap_events);
if (event->attr.comm)
@@ -2789,7 +2867,15 @@ static void free_event(struct perf_event *event)
put_callchain_buffers();
if (is_cgroup_event(event)) {
atomic_dec(&per_cpu(perf_cgroup_events, event->cpu));
- jump_label_dec_deferred(&perf_sched_events);
+ static_key_slow_dec_deferred(&perf_sched_events);
+ }
+
+ if (has_branch_stack(event)) {
+ static_key_slow_dec_deferred(&perf_sched_events);
+ /* is system-wide event */
+ if (!(event->attach_state & PERF_ATTACH_TASK))
+ atomic_dec(&per_cpu(perf_branch_stack_events,
+ event->cpu));
}
}
@@ -3238,10 +3324,6 @@ int perf_event_task_disable(void)
return 0;
}
-#ifndef PERF_EVENT_INDEX_OFFSET
-# define PERF_EVENT_INDEX_OFFSET 0
-#endif
-
static int perf_event_index(struct perf_event *event)
{
if (event->hw.state & PERF_HES_STOPPED)
@@ -3250,21 +3332,26 @@ static int perf_event_index(struct perf_event *event)
if (event->state != PERF_EVENT_STATE_ACTIVE)
return 0;
- return event->hw.idx + 1 - PERF_EVENT_INDEX_OFFSET;
+ return event->pmu->event_idx(event);
}
static void calc_timer_values(struct perf_event *event,
+ u64 *now,
u64 *enabled,
u64 *running)
{
- u64 now, ctx_time;
+ u64 ctx_time;
- now = perf_clock();
- ctx_time = event->shadow_ctx_time + now;
+ *now = perf_clock();
+ ctx_time = event->shadow_ctx_time + *now;
*enabled = ctx_time - event->tstamp_enabled;
*running = ctx_time - event->tstamp_running;
}
+void __weak perf_update_user_clock(struct perf_event_mmap_page *userpg, u64 now)
+{
+}
+
/*
* Callers need to ensure there can be no nesting of this function, otherwise
* the seqlock logic goes bad. We can not serialize this because the arch
@@ -3274,7 +3361,7 @@ void perf_event_update_userpage(struct perf_event *event)
{
struct perf_event_mmap_page *userpg;
struct ring_buffer *rb;
- u64 enabled, running;
+ u64 enabled, running, now;
rcu_read_lock();
/*
@@ -3286,7 +3373,7 @@ void perf_event_update_userpage(struct perf_event *event)
* because of locking issue as we can be called in
* NMI context
*/
- calc_timer_values(event, &enabled, &running);
+ calc_timer_values(event, &now, &enabled, &running);
rb = rcu_dereference(event->rb);
if (!rb)
goto unlock;
@@ -3302,7 +3389,7 @@ void perf_event_update_userpage(struct perf_event *event)
barrier();
userpg->index = perf_event_index(event);
userpg->offset = perf_event_count(event);
- if (event->state == PERF_EVENT_STATE_ACTIVE)
+ if (userpg->index)
userpg->offset -= local64_read(&event->hw.prev_count);
userpg->time_enabled = enabled +
@@ -3311,6 +3398,8 @@ 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);
+
barrier();
++userpg->lock;
preempt_enable();
@@ -3568,6 +3657,8 @@ static int perf_mmap(struct file *file, struct vm_area_struct *vma)
event->mmap_user = get_current_user();
vma->vm_mm->pinned_vm += event->mmap_locked;
+ perf_event_update_userpage(event);
+
unlock:
if (!ret)
atomic_inc(&event->mmap_count);
@@ -3799,7 +3890,7 @@ static void perf_output_read_group(struct perf_output_handle *handle,
static void perf_output_read(struct perf_output_handle *handle,
struct perf_event *event)
{
- u64 enabled = 0, running = 0;
+ u64 enabled = 0, running = 0, now;
u64 read_format = event->attr.read_format;
/*
@@ -3812,7 +3903,7 @@ static void perf_output_read(struct perf_output_handle *handle,
* NMI context
*/
if (read_format & PERF_FORMAT_TOTAL_TIMES)
- calc_timer_values(event, &enabled, &running);
+ calc_timer_values(event, &now, &enabled, &running);
if (event->attr.read_format & PERF_FORMAT_GROUP)
perf_output_read_group(handle, event, enabled, running);
@@ -3902,6 +3993,24 @@ void perf_output_sample(struct perf_output_handle *handle,
}
}
}
+
+ if (sample_type & PERF_SAMPLE_BRANCH_STACK) {
+ if (data->br_stack) {
+ size_t size;
+
+ size = data->br_stack->nr
+ * sizeof(struct perf_branch_entry);
+
+ perf_output_put(handle, data->br_stack->nr);
+ perf_output_copy(handle, data->br_stack->entries, size);
+ } else {
+ /*
+ * we always store at least the value of nr
+ */
+ u64 nr = 0;
+ perf_output_put(handle, nr);
+ }
+ }
}
void perf_prepare_sample(struct perf_event_header *header,
@@ -3944,6 +4053,15 @@ void perf_prepare_sample(struct perf_event_header *header,
WARN_ON_ONCE(size & (sizeof(u64)-1));
header->size += size;
}
+
+ if (sample_type & PERF_SAMPLE_BRANCH_STACK) {
+ int size = sizeof(u64); /* nr */
+ if (data->br_stack) {
+ size += data->br_stack->nr
+ * sizeof(struct perf_branch_entry);
+ }
+ header->size += size;
+ }
}
static void perf_event_output(struct perf_event *event,
@@ -4986,7 +5104,7 @@ fail:
return err;
}
-struct jump_label_key perf_swevent_enabled[PERF_COUNT_SW_MAX];
+struct static_key perf_swevent_enabled[PERF_COUNT_SW_MAX];
static void sw_perf_event_destroy(struct perf_event *event)
{
@@ -4994,7 +5112,7 @@ static void sw_perf_event_destroy(struct perf_event *event)
WARN_ON(event->parent);
- jump_label_dec(&perf_swevent_enabled[event_id]);
+ static_key_slow_dec(&perf_swevent_enabled[event_id]);
swevent_hlist_put(event);
}
@@ -5005,6 +5123,12 @@ static int perf_swevent_init(struct perf_event *event)
if (event->attr.type != PERF_TYPE_SOFTWARE)
return -ENOENT;
+ /*
+ * no branch sampling for software events
+ */
+ if (has_branch_stack(event))
+ return -EOPNOTSUPP;
+
switch (event_id) {
case PERF_COUNT_SW_CPU_CLOCK:
case PERF_COUNT_SW_TASK_CLOCK:
@@ -5024,13 +5148,18 @@ static int perf_swevent_init(struct perf_event *event)
if (err)
return err;
- jump_label_inc(&perf_swevent_enabled[event_id]);
+ static_key_slow_inc(&perf_swevent_enabled[event_id]);
event->destroy = sw_perf_event_destroy;
}
return 0;
}
+static int perf_swevent_event_idx(struct perf_event *event)
+{
+ return 0;
+}
+
static struct pmu perf_swevent = {
.task_ctx_nr = perf_sw_context,
@@ -5040,6 +5169,8 @@ static struct pmu perf_swevent = {
.start = perf_swevent_start,
.stop = perf_swevent_stop,
.read = perf_swevent_read,
+
+ .event_idx = perf_swevent_event_idx,
};
#ifdef CONFIG_EVENT_TRACING
@@ -5108,6 +5239,12 @@ static int perf_tp_event_init(struct perf_event *event)
if (event->attr.type != PERF_TYPE_TRACEPOINT)
return -ENOENT;
+ /*
+ * no branch sampling for tracepoint events
+ */
+ if (has_branch_stack(event))
+ return -EOPNOTSUPP;
+
err = perf_trace_init(event);
if (err)
return err;
@@ -5126,6 +5263,8 @@ static struct pmu perf_tracepoint = {
.start = perf_swevent_start,
.stop = perf_swevent_stop,
.read = perf_swevent_read,
+
+ .event_idx = perf_swevent_event_idx,
};
static inline void perf_tp_register(void)
@@ -5331,6 +5470,12 @@ static int cpu_clock_event_init(struct perf_event *event)
if (event->attr.config != PERF_COUNT_SW_CPU_CLOCK)
return -ENOENT;
+ /*
+ * no branch sampling for software events
+ */
+ if (has_branch_stack(event))
+ return -EOPNOTSUPP;
+
perf_swevent_init_hrtimer(event);
return 0;
@@ -5345,6 +5490,8 @@ static struct pmu perf_cpu_clock = {
.start = cpu_clock_event_start,
.stop = cpu_clock_event_stop,
.read = cpu_clock_event_read,
+
+ .event_idx = perf_swevent_event_idx,
};
/*
@@ -5403,6 +5550,12 @@ static int task_clock_event_init(struct perf_event *event)
if (event->attr.config != PERF_COUNT_SW_TASK_CLOCK)
return -ENOENT;
+ /*
+ * no branch sampling for software events
+ */
+ if (has_branch_stack(event))
+ return -EOPNOTSUPP;
+
perf_swevent_init_hrtimer(event);
return 0;
@@ -5417,6 +5570,8 @@ static struct pmu perf_task_clock = {
.start = task_clock_event_start,
.stop = task_clock_event_stop,
.read = task_clock_event_read,
+
+ .event_idx = perf_swevent_event_idx,
};
static void perf_pmu_nop_void(struct pmu *pmu)
@@ -5444,6 +5599,11 @@ static void perf_pmu_cancel_txn(struct pmu *pmu)
perf_pmu_enable(pmu);
}
+static int perf_event_idx_default(struct perf_event *event)
+{
+ return event->hw.idx + 1;
+}
+
/*
* Ensures all contexts with the same task_ctx_nr have the same
* pmu_cpu_context too.
@@ -5530,6 +5690,7 @@ static int pmu_dev_alloc(struct pmu *pmu)
if (!pmu->dev)
goto out;
+ pmu->dev->groups = pmu->attr_groups;
device_initialize(pmu->dev);
ret = dev_set_name(pmu->dev, "%s", pmu->name);
if (ret)
@@ -5633,6 +5794,9 @@ got_cpu_context:
pmu->pmu_disable = perf_pmu_nop_void;
}
+ if (!pmu->event_idx)
+ pmu->event_idx = perf_event_idx_default;
+
list_add_rcu(&pmu->entry, &pmus);
ret = 0;
unlock:
@@ -5825,7 +5989,7 @@ done:
if (!event->parent) {
if (event->attach_state & PERF_ATTACH_TASK)
- jump_label_inc(&perf_sched_events.key);
+ static_key_slow_inc(&perf_sched_events.key);
if (event->attr.mmap || event->attr.mmap_data)
atomic_inc(&nr_mmap_events);
if (event->attr.comm)
@@ -5839,6 +6003,12 @@ done:
return ERR_PTR(err);
}
}
+ if (has_branch_stack(event)) {
+ static_key_slow_inc(&perf_sched_events.key);
+ if (!(event->attach_state & PERF_ATTACH_TASK))
+ atomic_inc(&per_cpu(perf_branch_stack_events,
+ event->cpu));
+ }
}
return event;
@@ -5908,6 +6078,40 @@ static int perf_copy_attr(struct perf_event_attr __user *uattr,
if (attr->read_format & ~(PERF_FORMAT_MAX-1))
return -EINVAL;
+ if (attr->sample_type & PERF_SAMPLE_BRANCH_STACK) {
+ u64 mask = attr->branch_sample_type;
+
+ /* only using defined bits */
+ if (mask & ~(PERF_SAMPLE_BRANCH_MAX-1))
+ return -EINVAL;
+
+ /* at least one branch bit must be set */
+ if (!(mask & ~PERF_SAMPLE_BRANCH_PLM_ALL))
+ return -EINVAL;
+
+ /* kernel level capture: check permissions */
+ if ((mask & PERF_SAMPLE_BRANCH_PERM_PLM)
+ && perf_paranoid_kernel() && !capable(CAP_SYS_ADMIN))
+ return -EACCES;
+
+ /* propagate priv level, when not set for branch */
+ if (!(mask & PERF_SAMPLE_BRANCH_PLM_ALL)) {
+
+ /* exclude_kernel checked on syscall entry */
+ if (!attr->exclude_kernel)
+ mask |= PERF_SAMPLE_BRANCH_KERNEL;
+
+ if (!attr->exclude_user)
+ mask |= PERF_SAMPLE_BRANCH_USER;
+
+ if (!attr->exclude_hv)
+ mask |= PERF_SAMPLE_BRANCH_HV;
+ /*
+ * adjust user setting (for HW filter setup)
+ */
+ attr->branch_sample_type = mask;
+ }
+ }
out:
return ret;
@@ -6063,7 +6267,7 @@ SYSCALL_DEFINE5(perf_event_open,
* - that may need work on context switch
*/
atomic_inc(&per_cpu(perf_cgroup_events, event->cpu));
- jump_label_inc(&perf_sched_events.key);
+ static_key_slow_inc(&perf_sched_events.key);
}
/*
diff --git a/kernel/events/hw_breakpoint.c b/kernel/events/hw_breakpoint.c
index ee706ce..bb38c4d 100644
--- a/kernel/events/hw_breakpoint.c
+++ b/kernel/events/hw_breakpoint.c
@@ -581,6 +581,12 @@ static int hw_breakpoint_event_init(struct perf_event *bp)
if (bp->attr.type != PERF_TYPE_BREAKPOINT)
return -ENOENT;
+ /*
+ * no branch sampling for breakpoint events
+ */
+ if (has_branch_stack(bp))
+ return -EOPNOTSUPP;
+
err = register_perf_hw_breakpoint(bp);
if (err)
return err;
@@ -613,6 +619,11 @@ static void hw_breakpoint_stop(struct perf_event *bp, int flags)
bp->hw.state = PERF_HES_STOPPED;
}
+static int hw_breakpoint_event_idx(struct perf_event *bp)
+{
+ return 0;
+}
+
static struct pmu perf_breakpoint = {
.task_ctx_nr = perf_sw_context, /* could eventually get its own */
@@ -622,6 +633,8 @@ static struct pmu perf_breakpoint = {
.start = hw_breakpoint_start,
.stop = hw_breakpoint_stop,
.read = hw_breakpoint_pmu_read,
+
+ .event_idx = hw_breakpoint_event_idx,
};
int __init init_hw_breakpoint(void)
diff --git a/kernel/irq/chip.c b/kernel/irq/chip.c
index 25784d6..6080f6b 100644
--- a/kernel/irq/chip.c
+++ b/kernel/irq/chip.c
@@ -16,6 +16,8 @@
#include <linux/interrupt.h>
#include <linux/kernel_stat.h>
+#include <trace/events/irq.h>
+
#include "internals.h"
/**
diff --git a/kernel/jump_label.c b/kernel/jump_label.c
index 01d3b70..4304919 100644
--- a/kernel/jump_label.c
+++ b/kernel/jump_label.c
@@ -12,7 +12,7 @@
#include <linux/slab.h>
#include <linux/sort.h>
#include <linux/err.h>
-#include <linux/jump_label.h>
+#include <linux/static_key.h>
#ifdef HAVE_JUMP_LABEL
@@ -29,11 +29,6 @@ void jump_label_unlock(void)
mutex_unlock(&jump_label_mutex);
}
-bool jump_label_enabled(struct jump_label_key *key)
-{
- return !!atomic_read(&key->enabled);
-}
-
static int jump_label_cmp(const void *a, const void *b)
{
const struct jump_entry *jea = a;
@@ -58,56 +53,66 @@ jump_label_sort_entries(struct jump_entry *start, struct jump_entry *stop)
sort(start, size, sizeof(struct jump_entry), jump_label_cmp, NULL);
}
-static void jump_label_update(struct jump_label_key *key, int enable);
+static void jump_label_update(struct static_key *key, int enable);
-void jump_label_inc(struct jump_label_key *key)
+void static_key_slow_inc(struct static_key *key)
{
if (atomic_inc_not_zero(&key->enabled))
return;
jump_label_lock();
- if (atomic_read(&key->enabled) == 0)
- jump_label_update(key, JUMP_LABEL_ENABLE);
+ if (atomic_read(&key->enabled) == 0) {
+ if (!jump_label_get_branch_default(key))
+ jump_label_update(key, JUMP_LABEL_ENABLE);
+ else
+ jump_label_update(key, JUMP_LABEL_DISABLE);
+ }
atomic_inc(&key->enabled);
jump_label_unlock();
}
-EXPORT_SYMBOL_GPL(jump_label_inc);
+EXPORT_SYMBOL_GPL(static_key_slow_inc);
-static void __jump_label_dec(struct jump_label_key *key,
+static void __static_key_slow_dec(struct static_key *key,
unsigned long rate_limit, struct delayed_work *work)
{
- if (!atomic_dec_and_mutex_lock(&key->enabled, &jump_label_mutex))
+ if (!atomic_dec_and_mutex_lock(&key->enabled, &jump_label_mutex)) {
+ WARN(atomic_read(&key->enabled) < 0,
+ "jump label: negative count!\n");
return;
+ }
if (rate_limit) {
atomic_inc(&key->enabled);
schedule_delayed_work(work, rate_limit);
- } else
- jump_label_update(key, JUMP_LABEL_DISABLE);
-
+ } else {
+ if (!jump_label_get_branch_default(key))
+ jump_label_update(key, JUMP_LABEL_DISABLE);
+ else
+ jump_label_update(key, JUMP_LABEL_ENABLE);
+ }
jump_label_unlock();
}
-EXPORT_SYMBOL_GPL(jump_label_dec);
static void jump_label_update_timeout(struct work_struct *work)
{
- struct jump_label_key_deferred *key =
- container_of(work, struct jump_label_key_deferred, work.work);
- __jump_label_dec(&key->key, 0, NULL);
+ struct static_key_deferred *key =
+ container_of(work, struct static_key_deferred, work.work);
+ __static_key_slow_dec(&key->key, 0, NULL);
}
-void jump_label_dec(struct jump_label_key *key)
+void static_key_slow_dec(struct static_key *key)
{
- __jump_label_dec(key, 0, NULL);
+ __static_key_slow_dec(key, 0, NULL);
}
+EXPORT_SYMBOL_GPL(static_key_slow_dec);
-void jump_label_dec_deferred(struct jump_label_key_deferred *key)
+void static_key_slow_dec_deferred(struct static_key_deferred *key)
{
- __jump_label_dec(&key->key, key->timeout, &key->work);
+ __static_key_slow_dec(&key->key, key->timeout, &key->work);
}
+EXPORT_SYMBOL_GPL(static_key_slow_dec_deferred);
-
-void jump_label_rate_limit(struct jump_label_key_deferred *key,
+void jump_label_rate_limit(struct static_key_deferred *key,
unsigned long rl)
{
key->timeout = rl;
@@ -150,7 +155,7 @@ void __weak __init_or_module arch_jump_label_transform_static(struct jump_entry
arch_jump_label_transform(entry, type);
}
-static void __jump_label_update(struct jump_label_key *key,
+static void __jump_label_update(struct static_key *key,
struct jump_entry *entry,
struct jump_entry *stop, int enable)
{
@@ -167,27 +172,40 @@ static void __jump_label_update(struct jump_label_key *key,
}
}
+static enum jump_label_type jump_label_type(struct static_key *key)
+{
+ bool true_branch = jump_label_get_branch_default(key);
+ bool state = static_key_enabled(key);
+
+ if ((!true_branch && state) || (true_branch && !state))
+ return JUMP_LABEL_ENABLE;
+
+ return JUMP_LABEL_DISABLE;
+}
+
void __init jump_label_init(void)
{
struct jump_entry *iter_start = __start___jump_table;
struct jump_entry *iter_stop = __stop___jump_table;
- struct jump_label_key *key = NULL;
+ struct static_key *key = NULL;
struct jump_entry *iter;
jump_label_lock();
jump_label_sort_entries(iter_start, iter_stop);
for (iter = iter_start; iter < iter_stop; iter++) {
- struct jump_label_key *iterk;
+ struct static_key *iterk;
- iterk = (struct jump_label_key *)(unsigned long)iter->key;
- arch_jump_label_transform_static(iter, jump_label_enabled(iterk) ?
- JUMP_LABEL_ENABLE : JUMP_LABEL_DISABLE);
+ iterk = (struct static_key *)(unsigned long)iter->key;
+ arch_jump_label_transform_static(iter, jump_label_type(iterk));
if (iterk == key)
continue;
key = iterk;
- key->entries = iter;
+ /*
+ * Set key->entries to iter, but preserve JUMP_LABEL_TRUE_BRANCH.
+ */
+ *((unsigned long *)&key->entries) += (unsigned long)iter;
#ifdef CONFIG_MODULES
key->next = NULL;
#endif
@@ -197,8 +215,8 @@ void __init jump_label_init(void)
#ifdef CONFIG_MODULES
-struct jump_label_mod {
- struct jump_label_mod *next;
+struct static_key_mod {
+ struct static_key_mod *next;
struct jump_entry *entries;
struct module *mod;
};
@@ -218,9 +236,9 @@ static int __jump_label_mod_text_reserved(void *start, void *end)
start, end);
}
-static void __jump_label_mod_update(struct jump_label_key *key, int enable)
+static void __jump_label_mod_update(struct static_key *key, int enable)
{
- struct jump_label_mod *mod = key->next;
+ struct static_key_mod *mod = key->next;
while (mod) {
struct module *m = mod->mod;
@@ -251,11 +269,7 @@ void jump_label_apply_nops(struct module *mod)
return;
for (iter = iter_start; iter < iter_stop; iter++) {
- struct jump_label_key *iterk;
-
- iterk = (struct jump_label_key *)(unsigned long)iter->key;
- arch_jump_label_transform_static(iter, jump_label_enabled(iterk) ?
- JUMP_LABEL_ENABLE : JUMP_LABEL_DISABLE);
+ arch_jump_label_transform_static(iter, JUMP_LABEL_DISABLE);
}
}
@@ -264,8 +278,8 @@ static int jump_label_add_module(struct module *mod)
struct jump_entry *iter_start = mod->jump_entries;
struct jump_entry *iter_stop = iter_start + mod->num_jump_entries;
struct jump_entry *iter;
- struct jump_label_key *key = NULL;
- struct jump_label_mod *jlm;
+ struct static_key *key = NULL;
+ struct static_key_mod *jlm;
/* if the module doesn't have jump label entries, just return */
if (iter_start == iter_stop)
@@ -274,28 +288,30 @@ static int jump_label_add_module(struct module *mod)
jump_label_sort_entries(iter_start, iter_stop);
for (iter = iter_start; iter < iter_stop; iter++) {
- if (iter->key == (jump_label_t)(unsigned long)key)
- continue;
+ struct static_key *iterk;
- key = (struct jump_label_key *)(unsigned long)iter->key;
+ iterk = (struct static_key *)(unsigned long)iter->key;
+ if (iterk == key)
+ continue;
+ key = iterk;
if (__module_address(iter->key) == mod) {
- atomic_set(&key->enabled, 0);
- key->entries = iter;
+ /*
+ * Set key->entries to iter, but preserve JUMP_LABEL_TRUE_BRANCH.
+ */
+ *((unsigned long *)&key->entries) += (unsigned long)iter;
key->next = NULL;
continue;
}
-
- jlm = kzalloc(sizeof(struct jump_label_mod), GFP_KERNEL);
+ jlm = kzalloc(sizeof(struct static_key_mod), GFP_KERNEL);
if (!jlm)
return -ENOMEM;
-
jlm->mod = mod;
jlm->entries = iter;
jlm->next = key->next;
key->next = jlm;
- if (jump_label_enabled(key))
+ if (jump_label_type(key) == JUMP_LABEL_ENABLE)
__jump_label_update(key, iter, iter_stop, JUMP_LABEL_ENABLE);
}
@@ -307,14 +323,14 @@ static void jump_label_del_module(struct module *mod)
struct jump_entry *iter_start = mod->jump_entries;
struct jump_entry *iter_stop = iter_start + mod->num_jump_entries;
struct jump_entry *iter;
- struct jump_label_key *key = NULL;
- struct jump_label_mod *jlm, **prev;
+ struct static_key *key = NULL;
+ struct static_key_mod *jlm, **prev;
for (iter = iter_start; iter < iter_stop; iter++) {
if (iter->key == (jump_label_t)(unsigned long)key)
continue;
- key = (struct jump_label_key *)(unsigned long)iter->key;
+ key = (struct static_key *)(unsigned long)iter->key;
if (__module_address(iter->key) == mod)
continue;
@@ -416,12 +432,13 @@ int jump_label_text_reserved(void *start, void *end)
return ret;
}
-static void jump_label_update(struct jump_label_key *key, int enable)
+static void jump_label_update(struct static_key *key, int enable)
{
- struct jump_entry *entry = key->entries, *stop = __stop___jump_table;
+ struct jump_entry *stop = __stop___jump_table;
+ struct jump_entry *entry = jump_label_get_entries(key);
#ifdef CONFIG_MODULES
- struct module *mod = __module_address((jump_label_t)key);
+ struct module *mod = __module_address((unsigned long)key);
__jump_label_mod_update(key, enable);
diff --git a/kernel/printk.c b/kernel/printk.c
index 32690a0..0b3ea2c 100644
--- a/kernel/printk.c
+++ b/kernel/printk.c
@@ -44,6 +44,9 @@
#include <asm/uaccess.h>
+#define CREATE_TRACE_POINTS
+#include <trace/events/printk.h>
+
/*
* Architectures can override it:
*/
@@ -542,6 +545,8 @@ MODULE_PARM_DESC(ignore_loglevel, "ignore loglevel setting, to"
static void _call_console_drivers(unsigned start,
unsigned end, int msg_log_level)
{
+ trace_console(&LOG_BUF(0), start, end, log_buf_len);
+
if ((msg_log_level < console_loglevel || ignore_loglevel) &&
console_drivers && start != end) {
if ((start & LOG_BUF_MASK) > (end & LOG_BUF_MASK)) {
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index b342f57..6c41ba4 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -162,13 +162,13 @@ static int sched_feat_show(struct seq_file *m, void *v)
#ifdef HAVE_JUMP_LABEL
-#define jump_label_key__true jump_label_key_enabled
-#define jump_label_key__false jump_label_key_disabled
+#define jump_label_key__true STATIC_KEY_INIT_TRUE
+#define jump_label_key__false STATIC_KEY_INIT_FALSE
#define SCHED_FEAT(name, enabled) \
jump_label_key__##enabled ,
-struct jump_label_key sched_feat_keys[__SCHED_FEAT_NR] = {
+struct static_key sched_feat_keys[__SCHED_FEAT_NR] = {
#include "features.h"
};
@@ -176,14 +176,14 @@ struct jump_label_key sched_feat_keys[__SCHED_FEAT_NR] = {
static void sched_feat_disable(int i)
{
- if (jump_label_enabled(&sched_feat_keys[i]))
- jump_label_dec(&sched_feat_keys[i]);
+ if (static_key_enabled(&sched_feat_keys[i]))
+ static_key_slow_dec(&sched_feat_keys[i]);
}
static void sched_feat_enable(int i)
{
- if (!jump_label_enabled(&sched_feat_keys[i]))
- jump_label_inc(&sched_feat_keys[i]);
+ if (!static_key_enabled(&sched_feat_keys[i]))
+ static_key_slow_inc(&sched_feat_keys[i]);
}
#else
static void sched_feat_disable(int i) { };
@@ -894,7 +894,7 @@ static void update_rq_clock_task(struct rq *rq, s64 delta)
delta -= irq_delta;
#endif
#ifdef CONFIG_PARAVIRT_TIME_ACCOUNTING
- if (static_branch((&paravirt_steal_rq_enabled))) {
+ if (static_key_false((&paravirt_steal_rq_enabled))) {
u64 st;
steal = paravirt_steal_clock(cpu_of(rq));
@@ -2755,7 +2755,7 @@ void account_idle_time(cputime_t cputime)
static __always_inline bool steal_account_process_tick(void)
{
#ifdef CONFIG_PARAVIRT
- if (static_branch(&paravirt_steal_enabled)) {
+ if (static_key_false(&paravirt_steal_enabled)) {
u64 steal, st = 0;
steal = paravirt_steal_clock(smp_processor_id());
diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
index aca16b8..fd974fa 100644
--- a/kernel/sched/fair.c
+++ b/kernel/sched/fair.c
@@ -1401,20 +1401,20 @@ entity_tick(struct cfs_rq *cfs_rq, struct sched_entity *curr, int queued)
#ifdef CONFIG_CFS_BANDWIDTH
#ifdef HAVE_JUMP_LABEL
-static struct jump_label_key __cfs_bandwidth_used;
+static struct static_key __cfs_bandwidth_used;
static inline bool cfs_bandwidth_used(void)
{
- return static_branch(&__cfs_bandwidth_used);
+ return static_key_false(&__cfs_bandwidth_used);
}
void account_cfs_bandwidth_used(int enabled, int was_enabled)
{
/* only need to count groups transitioning between enabled/!enabled */
if (enabled && !was_enabled)
- jump_label_inc(&__cfs_bandwidth_used);
+ static_key_slow_inc(&__cfs_bandwidth_used);
else if (!enabled && was_enabled)
- jump_label_dec(&__cfs_bandwidth_used);
+ static_key_slow_dec(&__cfs_bandwidth_used);
}
#else /* HAVE_JUMP_LABEL */
static bool cfs_bandwidth_used(void)
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 98c0c26..b4cd6d8 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -611,7 +611,7 @@ static inline void __set_task_cpu(struct task_struct *p, unsigned int cpu)
* Tunables that become constants when CONFIG_SCHED_DEBUG is off:
*/
#ifdef CONFIG_SCHED_DEBUG
-# include <linux/jump_label.h>
+# include <linux/static_key.h>
# define const_debug __read_mostly
#else
# define const_debug const
@@ -630,18 +630,18 @@ enum {
#undef SCHED_FEAT
#if defined(CONFIG_SCHED_DEBUG) && defined(HAVE_JUMP_LABEL)
-static __always_inline bool static_branch__true(struct jump_label_key *key)
+static __always_inline bool static_branch__true(struct static_key *key)
{
- return likely(static_branch(key)); /* Not out of line branch. */
+ return static_key_true(key); /* Not out of line branch. */
}
-static __always_inline bool static_branch__false(struct jump_label_key *key)
+static __always_inline bool static_branch__false(struct static_key *key)
{
- return unlikely(static_branch(key)); /* Out of line branch. */
+ return static_key_false(key); /* Out of line branch. */
}
#define SCHED_FEAT(name, enabled) \
-static __always_inline bool static_branch_##name(struct jump_label_key *key) \
+static __always_inline bool static_branch_##name(struct static_key *key) \
{ \
return static_branch__##enabled(key); \
}
@@ -650,7 +650,7 @@ static __always_inline bool static_branch_##name(struct jump_label_key *key) \
#undef SCHED_FEAT
-extern struct jump_label_key sched_feat_keys[__SCHED_FEAT_NR];
+extern struct static_key sched_feat_keys[__SCHED_FEAT_NR];
#define sched_feat(x) (static_branch_##x(&sched_feat_keys[__SCHED_FEAT_##x]))
#else /* !(SCHED_DEBUG && HAVE_JUMP_LABEL) */
#define sched_feat(x) (sysctl_sched_features & (1UL << __SCHED_FEAT_##x))
diff --git a/kernel/signal.c b/kernel/signal.c
index c73c428..8511e39 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -1054,13 +1054,13 @@ static int __send_signal(int sig, struct siginfo *info, struct task_struct *t,
struct sigpending *pending;
struct sigqueue *q;
int override_rlimit;
-
- trace_signal_generate(sig, info, t);
+ int ret = 0, result;
assert_spin_locked(&t->sighand->siglock);
+ result = TRACE_SIGNAL_IGNORED;
if (!prepare_signal(sig, t, from_ancestor_ns))
- return 0;
+ goto ret;
pending = group ? &t->signal->shared_pending : &t->pending;
/*
@@ -1068,8 +1068,11 @@ static int __send_signal(int sig, struct siginfo *info, struct task_struct *t,
* exactly one non-rt signal, so that we can get more
* detailed information about the cause of the signal.
*/
+ result = TRACE_SIGNAL_ALREADY_PENDING;
if (legacy_queue(pending, sig))
- return 0;
+ goto ret;
+
+ result = TRACE_SIGNAL_DELIVERED;
/*
* fast-pathed signals for kernel-internal things like SIGSTOP
* or SIGKILL.
@@ -1127,14 +1130,15 @@ static int __send_signal(int sig, struct siginfo *info, struct task_struct *t,
* signal was rt and sent by user using something
* other than kill().
*/
- trace_signal_overflow_fail(sig, group, info);
- return -EAGAIN;
+ result = TRACE_SIGNAL_OVERFLOW_FAIL;
+ ret = -EAGAIN;
+ goto ret;
} else {
/*
* This is a silent loss of information. We still
* send the signal, but the *info bits are lost.
*/
- trace_signal_lose_info(sig, group, info);
+ result = TRACE_SIGNAL_LOSE_INFO;
}
}
@@ -1142,7 +1146,9 @@ out_set:
signalfd_notify(t, sig);
sigaddset(&pending->signal, sig);
complete_signal(sig, t, group);
- return 0;
+ret:
+ trace_signal_generate(sig, info, t, group, result);
+ return ret;
}
static int send_signal(int sig, struct siginfo *info, struct task_struct *t,
@@ -1585,7 +1591,7 @@ int send_sigqueue(struct sigqueue *q, struct task_struct *t, int group)
int sig = q->info.si_signo;
struct sigpending *pending;
unsigned long flags;
- int ret;
+ int ret, result;
BUG_ON(!(q->flags & SIGQUEUE_PREALLOC));
@@ -1594,6 +1600,7 @@ int send_sigqueue(struct sigqueue *q, struct task_struct *t, int group)
goto ret;
ret = 1; /* the signal is ignored */
+ result = TRACE_SIGNAL_IGNORED;
if (!prepare_signal(sig, t, 0))
goto out;
@@ -1605,6 +1612,7 @@ int send_sigqueue(struct sigqueue *q, struct task_struct *t, int group)
*/
BUG_ON(q->info.si_code != SI_TIMER);
q->info.si_overrun++;
+ result = TRACE_SIGNAL_ALREADY_PENDING;
goto out;
}
q->info.si_overrun = 0;
@@ -1614,7 +1622,9 @@ int send_sigqueue(struct sigqueue *q, struct task_struct *t, int group)
list_add_tail(&q->list, &pending->list);
sigaddset(&pending->signal, sig);
complete_signal(sig, t, group);
+ result = TRACE_SIGNAL_DELIVERED;
out:
+ trace_signal_generate(sig, &q->info, t, group, result);
unlock_task_sighand(t, &flags);
ret:
return ret;
diff --git a/kernel/softirq.c b/kernel/softirq.c
index c82d95a..8afc6a8 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -375,6 +375,12 @@ void raise_softirq(unsigned int nr)
local_irq_restore(flags);
}
+void __raise_softirq_irqoff(unsigned int nr)
+{
+ trace_softirq_raise(nr);
+ or_softirq_pending(1UL << nr);
+}
+
void open_softirq(int nr, void (*action)(struct softirq_action *))
{
softirq_vec[nr].action = action;
diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 683d559..867bd1d 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -62,6 +62,8 @@
#define FTRACE_HASH_DEFAULT_BITS 10
#define FTRACE_HASH_MAX_BITS 12
+#define FL_GLOBAL_CONTROL_MASK (FTRACE_OPS_FL_GLOBAL | FTRACE_OPS_FL_CONTROL)
+
/* ftrace_enabled is a method to turn ftrace on or off */
int ftrace_enabled __read_mostly;
static int last_ftrace_enabled;
@@ -89,12 +91,14 @@ static struct ftrace_ops ftrace_list_end __read_mostly = {
};
static struct ftrace_ops *ftrace_global_list __read_mostly = &ftrace_list_end;
+static struct ftrace_ops *ftrace_control_list __read_mostly = &ftrace_list_end;
static struct ftrace_ops *ftrace_ops_list __read_mostly = &ftrace_list_end;
ftrace_func_t ftrace_trace_function __read_mostly = ftrace_stub;
static ftrace_func_t __ftrace_trace_function_delay __read_mostly = ftrace_stub;
ftrace_func_t __ftrace_trace_function __read_mostly = ftrace_stub;
ftrace_func_t ftrace_pid_function __read_mostly = ftrace_stub;
static struct ftrace_ops global_ops;
+static struct ftrace_ops control_ops;
static void
ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip);
@@ -168,6 +172,32 @@ static void ftrace_test_stop_func(unsigned long ip, unsigned long parent_ip)
}
#endif
+static void control_ops_disable_all(struct ftrace_ops *ops)
+{
+ int cpu;
+
+ for_each_possible_cpu(cpu)
+ *per_cpu_ptr(ops->disabled, cpu) = 1;
+}
+
+static int control_ops_alloc(struct ftrace_ops *ops)
+{
+ int __percpu *disabled;
+
+ disabled = alloc_percpu(int);
+ if (!disabled)
+ return -ENOMEM;
+
+ ops->disabled = disabled;
+ control_ops_disable_all(ops);
+ return 0;
+}
+
+static void control_ops_free(struct ftrace_ops *ops)
+{
+ free_percpu(ops->disabled);
+}
+
static void update_global_ops(void)
{
ftrace_func_t func;
@@ -259,6 +289,26 @@ static int remove_ftrace_ops(struct ftrace_ops **list, struct ftrace_ops *ops)
return 0;
}
+static void add_ftrace_list_ops(struct ftrace_ops **list,
+ struct ftrace_ops *main_ops,
+ struct ftrace_ops *ops)
+{
+ int first = *list == &ftrace_list_end;
+ add_ftrace_ops(list, ops);
+ if (first)
+ add_ftrace_ops(&ftrace_ops_list, main_ops);
+}
+
+static int remove_ftrace_list_ops(struct ftrace_ops **list,
+ struct ftrace_ops *main_ops,
+ struct ftrace_ops *ops)
+{
+ int ret = remove_ftrace_ops(list, ops);
+ if (!ret && *list == &ftrace_list_end)
+ ret = remove_ftrace_ops(&ftrace_ops_list, main_ops);
+ return ret;
+}
+
static int __register_ftrace_function(struct ftrace_ops *ops)
{
if (ftrace_disabled)
@@ -270,15 +320,20 @@ static int __register_ftrace_function(struct ftrace_ops *ops)
if (WARN_ON(ops->flags & FTRACE_OPS_FL_ENABLED))
return -EBUSY;
+ /* We don't support both control and global flags set. */
+ if ((ops->flags & FL_GLOBAL_CONTROL_MASK) == FL_GLOBAL_CONTROL_MASK)
+ return -EINVAL;
+
if (!core_kernel_data((unsigned long)ops))
ops->flags |= FTRACE_OPS_FL_DYNAMIC;
if (ops->flags & FTRACE_OPS_FL_GLOBAL) {
- int first = ftrace_global_list == &ftrace_list_end;
- add_ftrace_ops(&ftrace_global_list, ops);
+ add_ftrace_list_ops(&ftrace_global_list, &global_ops, ops);
ops->flags |= FTRACE_OPS_FL_ENABLED;
- if (first)
- add_ftrace_ops(&ftrace_ops_list, &global_ops);
+ } else if (ops->flags & FTRACE_OPS_FL_CONTROL) {
+ if (control_ops_alloc(ops))
+ return -ENOMEM;
+ add_ftrace_list_ops(&ftrace_control_list, &control_ops, ops);
} else
add_ftrace_ops(&ftrace_ops_list, ops);
@@ -302,11 +357,23 @@ static int __unregister_ftrace_function(struct ftrace_ops *ops)
return -EINVAL;
if (ops->flags & FTRACE_OPS_FL_GLOBAL) {
- ret = remove_ftrace_ops(&ftrace_global_list, ops);
- if (!ret && ftrace_global_list == &ftrace_list_end)
- ret = remove_ftrace_ops(&ftrace_ops_list, &global_ops);
+ ret = remove_ftrace_list_ops(&ftrace_global_list,
+ &global_ops, ops);
if (!ret)
ops->flags &= ~FTRACE_OPS_FL_ENABLED;
+ } else if (ops->flags & FTRACE_OPS_FL_CONTROL) {
+ ret = remove_ftrace_list_ops(&ftrace_control_list,
+ &control_ops, ops);
+ if (!ret) {
+ /*
+ * The ftrace_ops is now removed from the list,
+ * so there'll be no new users. We must ensure
+ * all current users are done before we free
+ * the control data.
+ */
+ synchronize_sched();
+ control_ops_free(ops);
+ }
} else
ret = remove_ftrace_ops(&ftrace_ops_list, ops);
@@ -1119,6 +1186,12 @@ static void free_ftrace_hash_rcu(struct ftrace_hash *hash)
call_rcu_sched(&hash->rcu, __free_ftrace_hash_rcu);
}
+void ftrace_free_filter(struct ftrace_ops *ops)
+{
+ free_ftrace_hash(ops->filter_hash);
+ free_ftrace_hash(ops->notrace_hash);
+}
+
static struct ftrace_hash *alloc_ftrace_hash(int size_bits)
{
struct ftrace_hash *hash;
@@ -1129,7 +1202,7 @@ static struct ftrace_hash *alloc_ftrace_hash(int size_bits)
return NULL;
size = 1 << size_bits;
- hash->buckets = kzalloc(sizeof(*hash->buckets) * size, GFP_KERNEL);
+ hash->buckets = kcalloc(size, sizeof(*hash->buckets), GFP_KERNEL);
if (!hash->buckets) {
kfree(hash);
@@ -3146,8 +3219,10 @@ ftrace_set_regex(struct ftrace_ops *ops, unsigned char *buf, int len,
mutex_lock(&ftrace_regex_lock);
if (reset)
ftrace_filter_reset(hash);
- if (buf)
- ftrace_match_records(hash, buf, len);
+ if (buf && !ftrace_match_records(hash, buf, len)) {
+ ret = -EINVAL;
+ goto out_regex_unlock;
+ }
mutex_lock(&ftrace_lock);
ret = ftrace_hash_move(ops, enable, orig_hash, hash);
@@ -3157,6 +3232,7 @@ ftrace_set_regex(struct ftrace_ops *ops, unsigned char *buf, int len,
mutex_unlock(&ftrace_lock);
+ out_regex_unlock:
mutex_unlock(&ftrace_regex_lock);
free_ftrace_hash(hash);
@@ -3173,10 +3249,10 @@ ftrace_set_regex(struct ftrace_ops *ops, unsigned char *buf, int len,
* Filters denote which functions should be enabled when tracing is enabled.
* If @buf is NULL and reset is set, all functions will be enabled for tracing.
*/
-void ftrace_set_filter(struct ftrace_ops *ops, unsigned char *buf,
+int ftrace_set_filter(struct ftrace_ops *ops, unsigned char *buf,
int len, int reset)
{
- ftrace_set_regex(ops, buf, len, reset, 1);
+ return ftrace_set_regex(ops, buf, len, reset, 1);
}
EXPORT_SYMBOL_GPL(ftrace_set_filter);
@@ -3191,10 +3267,10 @@ EXPORT_SYMBOL_GPL(ftrace_set_filter);
* is enabled. If @buf is NULL and reset is set, all functions will be enabled
* for tracing.
*/
-void ftrace_set_notrace(struct ftrace_ops *ops, unsigned char *buf,
+int ftrace_set_notrace(struct ftrace_ops *ops, unsigned char *buf,
int len, int reset)
{
- ftrace_set_regex(ops, buf, len, reset, 0);
+ return ftrace_set_regex(ops, buf, len, reset, 0);
}
EXPORT_SYMBOL_GPL(ftrace_set_notrace);
/**
@@ -3871,6 +3947,36 @@ ftrace_ops_test(struct ftrace_ops *ops, unsigned long ip)
#endif /* CONFIG_DYNAMIC_FTRACE */
static void
+ftrace_ops_control_func(unsigned long ip, unsigned long parent_ip)
+{
+ struct ftrace_ops *op;
+
+ if (unlikely(trace_recursion_test(TRACE_CONTROL_BIT)))
+ return;
+
+ /*
+ * Some of the ops may be dynamically allocated,
+ * they must be freed after a synchronize_sched().
+ */
+ preempt_disable_notrace();
+ trace_recursion_set(TRACE_CONTROL_BIT);
+ op = rcu_dereference_raw(ftrace_control_list);
+ while (op != &ftrace_list_end) {
+ if (!ftrace_function_local_disabled(op) &&
+ ftrace_ops_test(op, ip))
+ op->func(ip, parent_ip);
+
+ op = rcu_dereference_raw(op->next);
+ };
+ trace_recursion_clear(TRACE_CONTROL_BIT);
+ preempt_enable_notrace();
+}
+
+static struct ftrace_ops control_ops = {
+ .func = ftrace_ops_control_func,
+};
+
+static void
ftrace_ops_list_func(unsigned long ip, unsigned long parent_ip)
{
struct ftrace_ops *op;
diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
index a3f1bc5..10d5503 100644
--- a/kernel/trace/trace.c
+++ b/kernel/trace/trace.c
@@ -2764,12 +2764,12 @@ static const char readme_msg[] =
"tracing mini-HOWTO:\n\n"
"# mount -t debugfs nodev /sys/kernel/debug\n\n"
"# cat /sys/kernel/debug/tracing/available_tracers\n"
- "wakeup preemptirqsoff preemptoff irqsoff function sched_switch nop\n\n"
+ "wakeup wakeup_rt preemptirqsoff preemptoff irqsoff function nop\n\n"
"# cat /sys/kernel/debug/tracing/current_tracer\n"
"nop\n"
- "# echo sched_switch > /sys/kernel/debug/tracing/current_tracer\n"
+ "# echo wakeup > /sys/kernel/debug/tracing/current_tracer\n"
"# cat /sys/kernel/debug/tracing/current_tracer\n"
- "sched_switch\n"
+ "wakeup\n"
"# cat /sys/kernel/debug/tracing/trace_options\n"
"noprint-parent nosym-offset nosym-addr noverbose\n"
"# echo print-parent > /sys/kernel/debug/tracing/trace_options\n"
diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
index b93ecba..54faec7 100644
--- a/kernel/trace/trace.h
+++ b/kernel/trace/trace.h
@@ -56,17 +56,23 @@ enum trace_type {
#define F_STRUCT(args...) args
#undef FTRACE_ENTRY
-#define FTRACE_ENTRY(name, struct_name, id, tstruct, print) \
- struct struct_name { \
- struct trace_entry ent; \
- tstruct \
+#define FTRACE_ENTRY(name, struct_name, id, tstruct, print, filter) \
+ struct struct_name { \
+ struct trace_entry ent; \
+ tstruct \
}
#undef TP_ARGS
#define TP_ARGS(args...) args
#undef FTRACE_ENTRY_DUP
-#define FTRACE_ENTRY_DUP(name, name_struct, id, tstruct, printk)
+#define FTRACE_ENTRY_DUP(name, name_struct, id, tstruct, printk, filter)
+
+#undef FTRACE_ENTRY_REG
+#define FTRACE_ENTRY_REG(name, struct_name, id, tstruct, print, \
+ filter, regfn) \
+ FTRACE_ENTRY(name, struct_name, id, PARAMS(tstruct), PARAMS(print), \
+ filter)
#include "trace_entries.h"
@@ -288,6 +294,8 @@ struct tracer {
/* for function tracing recursion */
#define TRACE_INTERNAL_BIT (1<<11)
#define TRACE_GLOBAL_BIT (1<<12)
+#define TRACE_CONTROL_BIT (1<<13)
+
/*
* Abuse of the trace_recursion.
* As we need a way to maintain state if we are tracing the function
@@ -589,6 +597,8 @@ static inline int ftrace_trace_task(struct task_struct *task)
static inline int ftrace_is_dead(void) { return 0; }
#endif
+int ftrace_event_is_function(struct ftrace_event_call *call);
+
/*
* struct trace_parser - servers for reading the user input separated by spaces
* @cont: set if the input is not complete - no final space char was found
@@ -766,9 +776,7 @@ struct filter_pred {
u64 val;
struct regex regex;
unsigned short *ops;
-#ifdef CONFIG_FTRACE_STARTUP_TEST
struct ftrace_event_field *field;
-#endif
int offset;
int not;
int op;
@@ -818,12 +826,22 @@ extern const char *__start___trace_bprintk_fmt[];
extern const char *__stop___trace_bprintk_fmt[];
#undef FTRACE_ENTRY
-#define FTRACE_ENTRY(call, struct_name, id, tstruct, print) \
+#define FTRACE_ENTRY(call, struct_name, id, tstruct, print, filter) \
extern struct ftrace_event_call \
__attribute__((__aligned__(4))) event_##call;
#undef FTRACE_ENTRY_DUP
-#define FTRACE_ENTRY_DUP(call, struct_name, id, tstruct, print) \
- FTRACE_ENTRY(call, struct_name, id, PARAMS(tstruct), PARAMS(print))
+#define FTRACE_ENTRY_DUP(call, struct_name, id, tstruct, print, filter) \
+ FTRACE_ENTRY(call, struct_name, id, PARAMS(tstruct), PARAMS(print), \
+ 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 9336590..d91eb05 100644
--- a/kernel/trace/trace_entries.h
+++ b/kernel/trace/trace_entries.h
@@ -55,7 +55,7 @@
/*
* Function trace entry - function address and parent function address:
*/
-FTRACE_ENTRY(function, ftrace_entry,
+FTRACE_ENTRY_REG(function, ftrace_entry,
TRACE_FN,
@@ -64,7 +64,11 @@ FTRACE_ENTRY(function, ftrace_entry,
__field( unsigned long, parent_ip )
),
- F_printk(" %lx <-- %lx", __entry->ip, __entry->parent_ip)
+ F_printk(" %lx <-- %lx", __entry->ip, __entry->parent_ip),
+
+ FILTER_TRACE_FN,
+
+ perf_ftrace_event_register
);
/* Function call entry */
@@ -78,7 +82,9 @@ FTRACE_ENTRY(funcgraph_entry, ftrace_graph_ent_entry,
__field_desc( int, graph_ent, depth )
),
- F_printk("--> %lx (%d)", __entry->func, __entry->depth)
+ F_printk("--> %lx (%d)", __entry->func, __entry->depth),
+
+ FILTER_OTHER
);
/* Function return entry */
@@ -98,7 +104,9 @@ FTRACE_ENTRY(funcgraph_exit, ftrace_graph_ret_entry,
F_printk("<-- %lx (%d) (start: %llx end: %llx) over: %d",
__entry->func, __entry->depth,
__entry->calltime, __entry->rettime,
- __entry->depth)
+ __entry->depth),
+
+ FILTER_OTHER
);
/*
@@ -127,8 +135,9 @@ FTRACE_ENTRY(context_switch, ctx_switch_entry,
F_printk("%u:%u:%u ==> %u:%u:%u [%03u]",
__entry->prev_pid, __entry->prev_prio, __entry->prev_state,
__entry->next_pid, __entry->next_prio, __entry->next_state,
- __entry->next_cpu
- )
+ __entry->next_cpu),
+
+ FILTER_OTHER
);
/*
@@ -146,8 +155,9 @@ FTRACE_ENTRY_DUP(wakeup, ctx_switch_entry,
F_printk("%u:%u:%u ==+ %u:%u:%u [%03u]",
__entry->prev_pid, __entry->prev_prio, __entry->prev_state,
__entry->next_pid, __entry->next_prio, __entry->next_state,
- __entry->next_cpu
- )
+ __entry->next_cpu),
+
+ FILTER_OTHER
);
/*
@@ -169,7 +179,9 @@ FTRACE_ENTRY(kernel_stack, stack_entry,
"\t=> (%08lx)\n\t=> (%08lx)\n\t=> (%08lx)\n\t=> (%08lx)\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])
+ __entry->caller[6], __entry->caller[7]),
+
+ FILTER_OTHER
);
FTRACE_ENTRY(user_stack, userstack_entry,
@@ -185,7 +197,9 @@ FTRACE_ENTRY(user_stack, userstack_entry,
"\t=> (%08lx)\n\t=> (%08lx)\n\t=> (%08lx)\n\t=> (%08lx)\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])
+ __entry->caller[6], __entry->caller[7]),
+
+ FILTER_OTHER
);
/*
@@ -202,7 +216,9 @@ FTRACE_ENTRY(bprint, bprint_entry,
),
F_printk("%08lx fmt:%p",
- __entry->ip, __entry->fmt)
+ __entry->ip, __entry->fmt),
+
+ FILTER_OTHER
);
FTRACE_ENTRY(print, print_entry,
@@ -215,7 +231,9 @@ FTRACE_ENTRY(print, print_entry,
),
F_printk("%08lx %s",
- __entry->ip, __entry->buf)
+ __entry->ip, __entry->buf),
+
+ FILTER_OTHER
);
FTRACE_ENTRY(mmiotrace_rw, trace_mmiotrace_rw,
@@ -234,7 +252,9 @@ FTRACE_ENTRY(mmiotrace_rw, trace_mmiotrace_rw,
F_printk("%lx %lx %lx %d %x %x",
(unsigned long)__entry->phys, __entry->value, __entry->pc,
- __entry->map_id, __entry->opcode, __entry->width)
+ __entry->map_id, __entry->opcode, __entry->width),
+
+ FILTER_OTHER
);
FTRACE_ENTRY(mmiotrace_map, trace_mmiotrace_map,
@@ -252,7 +272,9 @@ FTRACE_ENTRY(mmiotrace_map, trace_mmiotrace_map,
F_printk("%lx %lx %lx %d %x",
(unsigned long)__entry->phys, __entry->virt, __entry->len,
- __entry->map_id, __entry->opcode)
+ __entry->map_id, __entry->opcode),
+
+ FILTER_OTHER
);
@@ -272,6 +294,8 @@ FTRACE_ENTRY(branch, trace_branch,
F_printk("%u:%s:%s (%u)",
__entry->line,
- __entry->func, __entry->file, __entry->correct)
+ __entry->func, __entry->file, __entry->correct),
+
+ FILTER_OTHER
);
diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c
index 19a359d..fee3752 100644
--- a/kernel/trace/trace_event_perf.c
+++ b/kernel/trace/trace_event_perf.c
@@ -24,6 +24,11 @@ static int total_ref_count;
static int perf_trace_event_perm(struct ftrace_event_call *tp_event,
struct perf_event *p_event)
{
+ /* The ftrace function trace is allowed only for root. */
+ if (ftrace_event_is_function(tp_event) &&
+ perf_paranoid_kernel() && !capable(CAP_SYS_ADMIN))
+ return -EPERM;
+
/* No tracing, just counting, so no obvious leak */
if (!(p_event->attr.sample_type & PERF_SAMPLE_RAW))
return 0;
@@ -44,23 +49,17 @@ static int perf_trace_event_perm(struct ftrace_event_call *tp_event,
return 0;
}
-static int perf_trace_event_init(struct ftrace_event_call *tp_event,
- struct perf_event *p_event)
+static int perf_trace_event_reg(struct ftrace_event_call *tp_event,
+ struct perf_event *p_event)
{
struct hlist_head __percpu *list;
- int ret;
+ int ret = -ENOMEM;
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;
@@ -83,7 +82,7 @@ static int perf_trace_event_init(struct ftrace_event_call *tp_event,
}
}
- ret = tp_event->class->reg(tp_event, TRACE_REG_PERF_REGISTER);
+ ret = tp_event->class->reg(tp_event, TRACE_REG_PERF_REGISTER, NULL);
if (ret)
goto fail;
@@ -108,6 +107,69 @@ fail:
return ret;
}
+static void perf_trace_event_unreg(struct perf_event *p_event)
+{
+ struct ftrace_event_call *tp_event = p_event->tp_event;
+ int i;
+
+ if (--tp_event->perf_refcount > 0)
+ goto out;
+
+ tp_event->class->reg(tp_event, TRACE_REG_PERF_UNREGISTER, NULL);
+
+ /*
+ * Ensure our callback won't be called anymore. The buffers
+ * will be freed after that.
+ */
+ tracepoint_synchronize_unregister();
+
+ free_percpu(tp_event->perf_events);
+ tp_event->perf_events = NULL;
+
+ if (!--total_ref_count) {
+ for (i = 0; i < PERF_NR_CONTEXTS; i++) {
+ free_percpu(perf_trace_buf[i]);
+ perf_trace_buf[i] = NULL;
+ }
+ }
+out:
+ module_put(tp_event->mod);
+}
+
+static int perf_trace_event_open(struct perf_event *p_event)
+{
+ struct ftrace_event_call *tp_event = p_event->tp_event;
+ return tp_event->class->reg(tp_event, TRACE_REG_PERF_OPEN, p_event);
+}
+
+static void perf_trace_event_close(struct perf_event *p_event)
+{
+ struct ftrace_event_call *tp_event = p_event->tp_event;
+ tp_event->class->reg(tp_event, TRACE_REG_PERF_CLOSE, p_event);
+}
+
+static int perf_trace_event_init(struct ftrace_event_call *tp_event,
+ struct perf_event *p_event)
+{
+ int ret;
+
+ ret = perf_trace_event_perm(tp_event, p_event);
+ if (ret)
+ return ret;
+
+ ret = perf_trace_event_reg(tp_event, p_event);
+ if (ret)
+ return ret;
+
+ ret = perf_trace_event_open(p_event);
+ if (ret) {
+ perf_trace_event_unreg(p_event);
+ return ret;
+ }
+
+ return 0;
+}
+
int perf_trace_init(struct perf_event *p_event)
{
struct ftrace_event_call *tp_event;
@@ -130,6 +192,14 @@ int perf_trace_init(struct perf_event *p_event)
return ret;
}
+void perf_trace_destroy(struct perf_event *p_event)
+{
+ mutex_lock(&event_mutex);
+ perf_trace_event_close(p_event);
+ perf_trace_event_unreg(p_event);
+ mutex_unlock(&event_mutex);
+}
+
int perf_trace_add(struct perf_event *p_event, int flags)
{
struct ftrace_event_call *tp_event = p_event->tp_event;
@@ -146,43 +216,14 @@ int perf_trace_add(struct perf_event *p_event, int flags)
list = this_cpu_ptr(pcpu_list);
hlist_add_head_rcu(&p_event->hlist_entry, list);
- return 0;
+ return tp_event->class->reg(tp_event, TRACE_REG_PERF_ADD, p_event);
}
void perf_trace_del(struct perf_event *p_event, int flags)
{
- hlist_del_rcu(&p_event->hlist_entry);
-}
-
-void perf_trace_destroy(struct perf_event *p_event)
-{
struct ftrace_event_call *tp_event = p_event->tp_event;
- int i;
-
- mutex_lock(&event_mutex);
- if (--tp_event->perf_refcount > 0)
- goto out;
-
- tp_event->class->reg(tp_event, TRACE_REG_PERF_UNREGISTER);
-
- /*
- * Ensure our callback won't be called anymore. The buffers
- * will be freed after that.
- */
- tracepoint_synchronize_unregister();
-
- free_percpu(tp_event->perf_events);
- tp_event->perf_events = NULL;
-
- if (!--total_ref_count) {
- for (i = 0; i < PERF_NR_CONTEXTS; i++) {
- free_percpu(perf_trace_buf[i]);
- perf_trace_buf[i] = NULL;
- }
- }
-out:
- module_put(tp_event->mod);
- mutex_unlock(&event_mutex);
+ hlist_del_rcu(&p_event->hlist_entry);
+ tp_event->class->reg(tp_event, TRACE_REG_PERF_DEL, p_event);
}
__kprobes void *perf_trace_buf_prepare(int size, unsigned short type,
@@ -214,3 +255,86 @@ __kprobes void *perf_trace_buf_prepare(int size, unsigned short type,
return raw_data;
}
EXPORT_SYMBOL_GPL(perf_trace_buf_prepare);
+
+#ifdef CONFIG_FUNCTION_TRACER
+static void
+perf_ftrace_function_call(unsigned long ip, unsigned long parent_ip)
+{
+ struct ftrace_entry *entry;
+ struct hlist_head *head;
+ struct pt_regs regs;
+ int rctx;
+
+#define ENTRY_SIZE (ALIGN(sizeof(struct ftrace_entry) + sizeof(u32), \
+ sizeof(u64)) - sizeof(u32))
+
+ BUILD_BUG_ON(ENTRY_SIZE > PERF_MAX_TRACE_SIZE);
+
+ perf_fetch_caller_regs(&regs);
+
+ entry = perf_trace_buf_prepare(ENTRY_SIZE, TRACE_FN, NULL, &rctx);
+ if (!entry)
+ return;
+
+ entry->ip = ip;
+ entry->parent_ip = parent_ip;
+
+ head = this_cpu_ptr(event_function.perf_events);
+ perf_trace_buf_submit(entry, ENTRY_SIZE, rctx, 0,
+ 1, &regs, head);
+
+#undef ENTRY_SIZE
+}
+
+static int perf_ftrace_function_register(struct perf_event *event)
+{
+ struct ftrace_ops *ops = &event->ftrace_ops;
+
+ ops->flags |= FTRACE_OPS_FL_CONTROL;
+ ops->func = perf_ftrace_function_call;
+ return register_ftrace_function(ops);
+}
+
+static int perf_ftrace_function_unregister(struct perf_event *event)
+{
+ struct ftrace_ops *ops = &event->ftrace_ops;
+ int ret = unregister_ftrace_function(ops);
+ ftrace_free_filter(ops);
+ return ret;
+}
+
+static void perf_ftrace_function_enable(struct perf_event *event)
+{
+ ftrace_function_local_enable(&event->ftrace_ops);
+}
+
+static void perf_ftrace_function_disable(struct perf_event *event)
+{
+ ftrace_function_local_disable(&event->ftrace_ops);
+}
+
+int perf_ftrace_event_register(struct ftrace_event_call *call,
+ enum trace_reg type, void *data)
+{
+ switch (type) {
+ case TRACE_REG_REGISTER:
+ case TRACE_REG_UNREGISTER:
+ break;
+ case TRACE_REG_PERF_REGISTER:
+ case TRACE_REG_PERF_UNREGISTER:
+ return 0;
+ case TRACE_REG_PERF_OPEN:
+ return perf_ftrace_function_register(data);
+ case TRACE_REG_PERF_CLOSE:
+ return perf_ftrace_function_unregister(data);
+ case TRACE_REG_PERF_ADD:
+ perf_ftrace_function_enable(data);
+ return 0;
+ case TRACE_REG_PERF_DEL:
+ perf_ftrace_function_disable(data);
+ return 0;
+ }
+
+ return -EINVAL;
+}
+#endif /* CONFIG_FUNCTION_TRACER */
diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
index c212a7f..079a93a 100644
--- a/kernel/trace/trace_events.c
+++ b/kernel/trace/trace_events.c
@@ -147,7 +147,8 @@ int trace_event_raw_init(struct ftrace_event_call *call)
}
EXPORT_SYMBOL_GPL(trace_event_raw_init);
-int ftrace_event_reg(struct ftrace_event_call *call, enum trace_reg type)
+int ftrace_event_reg(struct ftrace_event_call *call,
+ enum trace_reg type, void *data)
{
switch (type) {
case TRACE_REG_REGISTER:
@@ -170,6 +171,11 @@ int ftrace_event_reg(struct ftrace_event_call *call, enum trace_reg type)
call->class->perf_probe,
call);
return 0;
+ case TRACE_REG_PERF_OPEN:
+ case TRACE_REG_PERF_CLOSE:
+ case TRACE_REG_PERF_ADD:
+ case TRACE_REG_PERF_DEL:
+ return 0;
#endif
}
return 0;
@@ -209,7 +215,7 @@ static int ftrace_event_enable_disable(struct ftrace_event_call *call,
tracing_stop_cmdline_record();
call->flags &= ~TRACE_EVENT_FL_RECORDED_CMD;
}
- call->class->reg(call, TRACE_REG_UNREGISTER);
+ call->class->reg(call, TRACE_REG_UNREGISTER, NULL);
}
break;
case 1:
@@ -218,7 +224,7 @@ static int ftrace_event_enable_disable(struct ftrace_event_call *call,
tracing_start_cmdline_record();
call->flags |= TRACE_EVENT_FL_RECORDED_CMD;
}
- ret = call->class->reg(call, TRACE_REG_REGISTER);
+ ret = call->class->reg(call, TRACE_REG_REGISTER, NULL);
if (ret) {
tracing_stop_cmdline_record();
pr_info("event trace: Could not enable event "
diff --git a/kernel/trace/trace_events_filter.c b/kernel/trace/trace_events_filter.c
index 24aee71..431dba8 100644
--- a/kernel/trace/trace_events_filter.c
+++ b/kernel/trace/trace_events_filter.c
@@ -81,6 +81,7 @@ enum {
FILT_ERR_TOO_MANY_PREDS,
FILT_ERR_MISSING_FIELD,
FILT_ERR_INVALID_FILTER,
+ FILT_ERR_IP_FIELD_ONLY,
};
static char *err_text[] = {
@@ -96,6 +97,7 @@ static char *err_text[] = {
"Too many terms in predicate expression",
"Missing field name and/or value",
"Meaningless filter expression",
+ "Only 'ip' field is supported for function trace",
};
struct opstack_op {
@@ -685,7 +687,7 @@ find_event_field(struct ftrace_event_call *call, char *name)
static int __alloc_pred_stack(struct pred_stack *stack, int n_preds)
{
- stack->preds = kzalloc(sizeof(*stack->preds)*(n_preds + 1), GFP_KERNEL);
+ stack->preds = kcalloc(n_preds + 1, sizeof(*stack->preds), GFP_KERNEL);
if (!stack->preds)
return -ENOMEM;
stack->index = n_preds;
@@ -826,8 +828,7 @@ static int __alloc_preds(struct event_filter *filter, int n_preds)
if (filter->preds)
__free_preds(filter);
- filter->preds =
- kzalloc(sizeof(*filter->preds) * n_preds, GFP_KERNEL);
+ filter->preds = kcalloc(n_preds, sizeof(*filter->preds), GFP_KERNEL);
if (!filter->preds)
return -ENOMEM;
@@ -900,6 +901,11 @@ int filter_assign_type(const char *type)
return FILTER_OTHER;
}
+static bool is_function_field(struct ftrace_event_field *field)
+{
+ return field->filter_type == FILTER_TRACE_FN;
+}
+
static bool is_string_field(struct ftrace_event_field *field)
{
return field->filter_type == FILTER_DYN_STRING ||
@@ -987,6 +993,11 @@ static int init_pred(struct filter_parse_state *ps,
fn = filter_pred_strloc;
else
fn = filter_pred_pchar;
+ } else if (is_function_field(field)) {
+ if (strcmp(field->name, "ip")) {
+ parse_error(ps, FILT_ERR_IP_FIELD_ONLY, 0);
+ return -EINVAL;
+ }
} else {
if (field->is_signed)
ret = strict_strtoll(pred->regex.pattern, 0, &val);
@@ -1334,10 +1345,7 @@ static struct filter_pred *create_pred(struct filter_parse_state *ps,
strcpy(pred.regex.pattern, operand2);
pred.regex.len = strlen(pred.regex.pattern);
-
-#ifdef CONFIG_FTRACE_STARTUP_TEST
pred.field = field;
-#endif
return init_pred(ps, field, &pred) ? NULL : &pred;
}
@@ -1486,7 +1494,7 @@ static int fold_pred(struct filter_pred *preds, struct filter_pred *root)
children = count_leafs(preds, &preds[root->left]);
children += count_leafs(preds, &preds[root->right]);
- root->ops = kzalloc(sizeof(*root->ops) * children, GFP_KERNEL);
+ root->ops = kcalloc(children, sizeof(*root->ops), GFP_KERNEL);
if (!root->ops)
return -ENOMEM;
@@ -1950,6 +1958,148 @@ void ftrace_profile_free_filter(struct perf_event *event)
__free_filter(filter);
}
+struct function_filter_data {
+ struct ftrace_ops *ops;
+ int first_filter;
+ int first_notrace;
+};
+
+#ifdef CONFIG_FUNCTION_TRACER
+static char **
+ftrace_function_filter_re(char *buf, int len, int *count)
+{
+ char *str, *sep, **re;
+
+ str = kstrndup(buf, len, GFP_KERNEL);
+ if (!str)
+ return NULL;
+
+ /*
+ * The argv_split function takes white space
+ * as a separator, so convert ',' into spaces.
+ */
+ while ((sep = strchr(str, ',')))
+ *sep = ' ';
+
+ re = argv_split(GFP_KERNEL, str, count);
+ kfree(str);
+ return re;
+}
+
+static int ftrace_function_set_regexp(struct ftrace_ops *ops, int filter,
+ int reset, char *re, int len)
+{
+ int ret;
+
+ if (filter)
+ ret = ftrace_set_filter(ops, re, len, reset);
+ else
+ ret = ftrace_set_notrace(ops, re, len, reset);
+
+ return ret;
+}
+
+static int __ftrace_function_set_filter(int filter, char *buf, int len,
+ struct function_filter_data *data)
+{
+ int i, re_cnt, ret;
+ int *reset;
+ char **re;
+
+ reset = filter ? &data->first_filter : &data->first_notrace;
+
+ /*
+ * The 'ip' field could have multiple filters set, separated
+ * either by space or comma. We first cut the filter and apply
+ * all pieces separatelly.
+ */
+ re = ftrace_function_filter_re(buf, len, &re_cnt);
+ if (!re)
+ return -EINVAL;
+
+ for (i = 0; i < re_cnt; i++) {
+ ret = ftrace_function_set_regexp(data->ops, filter, *reset,
+ re[i], strlen(re[i]));
+ if (ret)
+ break;
+
+ if (*reset)
+ *reset = 0;
+ }
+
+ argv_free(re);
+ return ret;
+}
+
+static int ftrace_function_check_pred(struct filter_pred *pred, int leaf)
+{
+ struct ftrace_event_field *field = pred->field;
+
+ if (leaf) {
+ /*
+ * Check the leaf predicate for function trace, verify:
+ * - only '==' and '!=' is used
+ * - the 'ip' field is used
+ */
+ if ((pred->op != OP_EQ) && (pred->op != OP_NE))
+ return -EINVAL;
+
+ if (strcmp(field->name, "ip"))
+ return -EINVAL;
+ } else {
+ /*
+ * Check the non leaf predicate for function trace, verify:
+ * - only '||' is used
+ */
+ if (pred->op != OP_OR)
+ return -EINVAL;
+ }
+
+ return 0;
+}
+
+static int ftrace_function_set_filter_cb(enum move_type move,
+ struct filter_pred *pred,
+ int *err, void *data)
+{
+ /* Checking the node is valid for function trace. */
+ if ((move != MOVE_DOWN) ||
+ (pred->left != FILTER_PRED_INVALID)) {
+ *err = ftrace_function_check_pred(pred, 0);
+ } else {
+ *err = ftrace_function_check_pred(pred, 1);
+ if (*err)
+ return WALK_PRED_ABORT;
+
+ *err = __ftrace_function_set_filter(pred->op == OP_EQ,
+ pred->regex.pattern,
+ pred->regex.len,
+ data);
+ }
+
+ return (*err) ? WALK_PRED_ABORT : WALK_PRED_DEFAULT;
+}
+
+static int ftrace_function_set_filter(struct perf_event *event,
+ struct event_filter *filter)
+{
+ struct function_filter_data data = {
+ .first_filter = 1,
+ .first_notrace = 1,
+ .ops = &event->ftrace_ops,
+ };
+
+ return walk_pred_tree(filter->preds, filter->root,
+ ftrace_function_set_filter_cb, &data);
+}
+#else
+static int ftrace_function_set_filter(struct perf_event *event,
+ struct event_filter *filter)
+{
+ return -ENODEV;
+}
+#endif /* CONFIG_FUNCTION_TRACER */
+
int ftrace_profile_set_filter(struct perf_event *event, int event_id,
char *filter_str)
{
@@ -1970,9 +2120,16 @@ int ftrace_profile_set_filter(struct perf_event *event, int event_id,
goto out_unlock;
err = create_filter(call, filter_str, false, &filter);
- if (!err)
- event->filter = filter;
+ if (err)
+ goto free_filter;
+
+ if (ftrace_event_is_function(call))
+ err = ftrace_function_set_filter(event, filter);
else
+ event->filter = filter;
+
+free_filter:
+ if (err || ftrace_event_is_function(call))
__free_filter(filter);
out_unlock:
diff --git a/kernel/trace/trace_export.c b/kernel/trace/trace_export.c
index bbeec31..7b46c9b 100644
--- a/kernel/trace/trace_export.c
+++ b/kernel/trace/trace_export.c
@@ -18,6 +18,16 @@
#undef TRACE_SYSTEM
#define TRACE_SYSTEM ftrace
+/*
+ * The FTRACE_ENTRY_REG macro allows ftrace entry to define register
+ * function and thus become accesible via perf.
+ */
+#undef FTRACE_ENTRY_REG
+#define FTRACE_ENTRY_REG(name, struct_name, id, tstruct, print, \
+ filter, regfn) \
+ FTRACE_ENTRY(name, struct_name, id, PARAMS(tstruct), PARAMS(print), \
+ filter)
+
/* not needed for this file */
#undef __field_struct
#define __field_struct(type, item)
@@ -44,21 +54,22 @@
#define F_printk(fmt, args...) fmt, args
#undef FTRACE_ENTRY
-#define FTRACE_ENTRY(name, struct_name, id, tstruct, print) \
-struct ____ftrace_##name { \
- tstruct \
-}; \
-static void __always_unused ____ftrace_check_##name(void) \
-{ \
- struct ____ftrace_##name *__entry = NULL; \
- \
- /* force compile-time check on F_printk() */ \
- printk(print); \
+#define FTRACE_ENTRY(name, struct_name, id, tstruct, print, filter) \
+struct ____ftrace_##name { \
+ tstruct \
+}; \
+static void __always_unused ____ftrace_check_##name(void) \
+{ \
+ struct ____ftrace_##name *__entry = NULL; \
+ \
+ /* force compile-time check on F_printk() */ \
+ printk(print); \
}
#undef FTRACE_ENTRY_DUP
-#define FTRACE_ENTRY_DUP(name, struct_name, id, tstruct, print) \
- FTRACE_ENTRY(name, struct_name, id, PARAMS(tstruct), PARAMS(print))
+#define FTRACE_ENTRY_DUP(name, struct_name, id, tstruct, print, filter) \
+ FTRACE_ENTRY(name, struct_name, id, PARAMS(tstruct), PARAMS(print), \
+ filter)
#include "trace_entries.h"
@@ -67,7 +78,7 @@ static void __always_unused ____ftrace_check_##name(void) \
ret = trace_define_field(event_call, #type, #item, \
offsetof(typeof(field), item), \
sizeof(field.item), \
- is_signed_type(type), FILTER_OTHER); \
+ is_signed_type(type), filter_type); \
if (ret) \
return ret;
@@ -77,7 +88,7 @@ static void __always_unused ____ftrace_check_##name(void) \
offsetof(typeof(field), \
container.item), \
sizeof(field.container.item), \
- is_signed_type(type), FILTER_OTHER); \
+ is_signed_type(type), filter_type); \
if (ret) \
return ret;
@@ -91,7 +102,7 @@ static void __always_unused ____ftrace_check_##name(void) \
ret = trace_define_field(event_call, event_storage, #item, \
offsetof(typeof(field), item), \
sizeof(field.item), \
- is_signed_type(type), FILTER_OTHER); \
+ is_signed_type(type), filter_type); \
mutex_unlock(&event_storage_mutex); \
if (ret) \
return ret; \
@@ -104,7 +115,7 @@ static void __always_unused ____ftrace_check_##name(void) \
offsetof(typeof(field), \
container.item), \
sizeof(field.container.item), \
- is_signed_type(type), FILTER_OTHER); \
+ is_signed_type(type), filter_type); \
if (ret) \
return ret;
@@ -112,17 +123,18 @@ static void __always_unused ____ftrace_check_##name(void) \
#define __dynamic_array(type, item) \
ret = trace_define_field(event_call, #type, #item, \
offsetof(typeof(field), item), \
- 0, is_signed_type(type), FILTER_OTHER);\
+ 0, is_signed_type(type), filter_type);\
if (ret) \
return ret;
#undef FTRACE_ENTRY
-#define FTRACE_ENTRY(name, struct_name, id, tstruct, print) \
+#define FTRACE_ENTRY(name, struct_name, id, tstruct, print, filter) \
int \
ftrace_define_fields_##name(struct ftrace_event_call *event_call) \
{ \
struct struct_name field; \
int ret; \
+ int filter_type = filter; \
\
tstruct; \
\
@@ -152,13 +164,15 @@ ftrace_define_fields_##name(struct ftrace_event_call *event_call) \
#undef F_printk
#define F_printk(fmt, args...) #fmt ", " __stringify(args)
-#undef FTRACE_ENTRY
-#define FTRACE_ENTRY(call, struct_name, etype, tstruct, print) \
+#undef FTRACE_ENTRY_REG
+#define FTRACE_ENTRY_REG(call, struct_name, etype, tstruct, print, filter,\
+ regfn) \
\
struct ftrace_event_class event_class_ftrace_##call = { \
.system = __stringify(TRACE_SYSTEM), \
.define_fields = ftrace_define_fields_##call, \
.fields = LIST_HEAD_INIT(event_class_ftrace_##call.fields),\
+ .reg = regfn, \
}; \
\
struct ftrace_event_call __used event_##call = { \
@@ -170,4 +184,14 @@ struct ftrace_event_call __used event_##call = { \
struct ftrace_event_call __used \
__attribute__((section("_ftrace_events"))) *__event_##call = &event_##call;
+#undef FTRACE_ENTRY
+#define FTRACE_ENTRY(call, struct_name, etype, tstruct, print, filter) \
+ FTRACE_ENTRY_REG(call, struct_name, etype, \
+ PARAMS(tstruct), PARAMS(print), filter, NULL)
+
+int ftrace_event_is_function(struct ftrace_event_call *call)
+{
+ return call == &event_function;
+}
+
#include "trace_entries.h"
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index 00d527c..580a05e 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -1892,7 +1892,8 @@ static __kprobes void kretprobe_perf_func(struct kretprobe_instance *ri,
#endif /* CONFIG_PERF_EVENTS */
static __kprobes
-int kprobe_register(struct ftrace_event_call *event, enum trace_reg type)
+int kprobe_register(struct ftrace_event_call *event,
+ enum trace_reg type, void *data)
{
struct trace_probe *tp = (struct trace_probe *)event->data;
@@ -1909,6 +1910,11 @@ int kprobe_register(struct ftrace_event_call *event, enum trace_reg type)
case TRACE_REG_PERF_UNREGISTER:
disable_trace_probe(tp, TP_FLAG_PROFILE);
return 0;
+ case TRACE_REG_PERF_OPEN:
+ case TRACE_REG_PERF_CLOSE:
+ case TRACE_REG_PERF_ADD:
+ case TRACE_REG_PERF_DEL:
+ return 0;
#endif
}
return 0;
diff --git a/kernel/trace/trace_output.c b/kernel/trace/trace_output.c
index 0d6ff35..c5a0187 100644
--- a/kernel/trace/trace_output.c
+++ b/kernel/trace/trace_output.c
@@ -300,7 +300,7 @@ ftrace_print_flags_seq(struct trace_seq *p, const char *delim,
unsigned long mask;
const char *str;
const char *ret = p->buffer + p->len;
- int i;
+ int i, first = 1;
for (i = 0; flag_array[i].name && flags; i++) {
@@ -310,14 +310,16 @@ ftrace_print_flags_seq(struct trace_seq *p, const char *delim,
str = flag_array[i].name;
flags &= ~mask;
- if (p->len && delim)
+ if (!first && delim)
trace_seq_puts(p, delim);
+ else
+ first = 0;
trace_seq_puts(p, str);
}
/* check for left over flags */
if (flags) {
- if (p->len && delim)
+ if (!first && delim)
trace_seq_puts(p, delim);
trace_seq_printf(p, "0x%lx", flags);
}
@@ -344,7 +346,7 @@ ftrace_print_symbols_seq(struct trace_seq *p, unsigned long val,
break;
}
- if (!p->len)
+ if (ret == (const char *)(p->buffer + p->len))
trace_seq_printf(p, "0x%lx", val);
trace_seq_putc(p, 0);
@@ -370,7 +372,7 @@ ftrace_print_symbols_seq_u64(struct trace_seq *p, unsigned long long val,
break;
}
- if (!p->len)
+ if (ret == (const char *)(p->buffer + p->len))
trace_seq_printf(p, "0x%llx", val);
trace_seq_putc(p, 0);
diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c
index cb65454..96fc733 100644
--- a/kernel/trace/trace_syscalls.c
+++ b/kernel/trace/trace_syscalls.c
@@ -17,9 +17,9 @@ static DECLARE_BITMAP(enabled_enter_syscalls, NR_syscalls);
static DECLARE_BITMAP(enabled_exit_syscalls, NR_syscalls);
static int syscall_enter_register(struct ftrace_event_call *event,
- enum trace_reg type);
+ enum trace_reg type, void *data);
static int syscall_exit_register(struct ftrace_event_call *event,
- enum trace_reg type);
+ enum trace_reg type, void *data);
static int syscall_enter_define_fields(struct ftrace_event_call *call);
static int syscall_exit_define_fields(struct ftrace_event_call *call);
@@ -468,8 +468,8 @@ int __init init_ftrace_syscalls(void)
unsigned long addr;
int i;
- syscalls_metadata = kzalloc(sizeof(*syscalls_metadata) *
- NR_syscalls, GFP_KERNEL);
+ syscalls_metadata = kcalloc(NR_syscalls, sizeof(*syscalls_metadata),
+ GFP_KERNEL);
if (!syscalls_metadata) {
WARN_ON(1);
return -ENOMEM;
@@ -649,7 +649,7 @@ void perf_sysexit_disable(struct ftrace_event_call *call)
#endif /* CONFIG_PERF_EVENTS */
static int syscall_enter_register(struct ftrace_event_call *event,
- enum trace_reg type)
+ enum trace_reg type, void *data)
{
switch (type) {
case TRACE_REG_REGISTER:
@@ -664,13 +664,18 @@ static int syscall_enter_register(struct ftrace_event_call *event,
case TRACE_REG_PERF_UNREGISTER:
perf_sysenter_disable(event);
return 0;
+ case TRACE_REG_PERF_OPEN:
+ case TRACE_REG_PERF_CLOSE:
+ case TRACE_REG_PERF_ADD:
+ case TRACE_REG_PERF_DEL:
+ return 0;
#endif
}
return 0;
}
static int syscall_exit_register(struct ftrace_event_call *event,
- enum trace_reg type)
+ enum trace_reg type, void *data)
{
switch (type) {
case TRACE_REG_REGISTER:
@@ -685,6 +690,11 @@ static int syscall_exit_register(struct ftrace_event_call *event,
case TRACE_REG_PERF_UNREGISTER:
perf_sysexit_disable(event);
return 0;
+ case TRACE_REG_PERF_OPEN:
+ case TRACE_REG_PERF_CLOSE:
+ case TRACE_REG_PERF_ADD:
+ case TRACE_REG_PERF_DEL:
+ return 0;
#endif
}
return 0;
diff --git a/kernel/tracepoint.c b/kernel/tracepoint.c
index f1539de..d96ba22 100644
--- a/kernel/tracepoint.c
+++ b/kernel/tracepoint.c
@@ -25,7 +25,7 @@
#include <linux/err.h>
#include <linux/slab.h>
#include <linux/sched.h>
-#include <linux/jump_label.h>
+#include <linux/static_key.h>
extern struct tracepoint * const __start___tracepoints_ptrs[];
extern struct tracepoint * const __stop___tracepoints_ptrs[];
@@ -256,9 +256,9 @@ static void set_tracepoint(struct tracepoint_entry **entry,
{
WARN_ON(strcmp((*entry)->name, elem->name) != 0);
- if (elem->regfunc && !jump_label_enabled(&elem->key) && active)
+ if (elem->regfunc && !static_key_enabled(&elem->key) && active)
elem->regfunc();
- else if (elem->unregfunc && jump_label_enabled(&elem->key) && !active)
+ else if (elem->unregfunc && static_key_enabled(&elem->key) && !active)
elem->unregfunc();
/*
@@ -269,10 +269,10 @@ static void set_tracepoint(struct tracepoint_entry **entry,
* is used.
*/
rcu_assign_pointer(elem->funcs, (*entry)->funcs);
- if (active && !jump_label_enabled(&elem->key))
- jump_label_inc(&elem->key);
- else if (!active && jump_label_enabled(&elem->key))
- jump_label_dec(&elem->key);
+ if (active && !static_key_enabled(&elem->key))
+ static_key_slow_inc(&elem->key);
+ else if (!active && static_key_enabled(&elem->key))
+ static_key_slow_dec(&elem->key);
}
/*
@@ -283,11 +283,11 @@ static void set_tracepoint(struct tracepoint_entry **entry,
*/
static void disable_tracepoint(struct tracepoint *elem)
{
- if (elem->unregfunc && jump_label_enabled(&elem->key))
+ if (elem->unregfunc && static_key_enabled(&elem->key))
elem->unregfunc();
- if (jump_label_enabled(&elem->key))
- jump_label_dec(&elem->key);
+ if (static_key_enabled(&elem->key))
+ static_key_slow_dec(&elem->key);
rcu_assign_pointer(elem->funcs, NULL);
}
diff --git a/kernel/watchdog.c b/kernel/watchdog.c
index d117262..14bc092 100644
--- a/kernel/watchdog.c
+++ b/kernel/watchdog.c
@@ -3,12 +3,9 @@
*
* started by Don Zickus, Copyright (C) 2010 Red Hat, Inc.
*
- * this code detects hard lockups: incidents in where on a CPU
- * the kernel does not respond to anything except NMI.
- *
- * Note: Most of this code is borrowed heavily from softlockup.c,
- * so thanks to Ingo for the initial implementation.
- * Some chunks also taken from arch/x86/kernel/apic/nmi.c, thanks
+ * Note: Most of this code is borrowed heavily from the original softlockup
+ * detector, so thanks to Ingo for the initial implementation.
+ * Some chunks also taken from the old x86-specific nmi watchdog code, thanks
* to those contributors as well.
*/
@@ -117,9 +114,10 @@ static unsigned long get_sample_period(void)
{
/*
* convert watchdog_thresh from seconds to ns
- * the divide by 5 is to give hrtimer 5 chances to
- * increment before the hardlockup detector generates
- * a warning
+ * the divide by 5 is to give hrtimer several chances (two
+ * or three with the current relation between the soft
+ * and hard thresholds) to increment before the
+ * hardlockup detector generates a warning
*/
return get_softlockup_thresh() * (NSEC_PER_SEC / 5);
}
@@ -336,9 +334,11 @@ static int watchdog(void *unused)
set_current_state(TASK_INTERRUPTIBLE);
/*
- * Run briefly once per second to reset the softlockup timestamp.
- * If this gets delayed for more than 60 seconds then the
- * debug-printout triggers in watchdog_timer_fn().
+ * Run briefly (kicked by the hrtimer callback function) once every
+ * get_sample_period() seconds (4 seconds by default) to reset the
+ * softlockup timestamp. If this gets delayed for more than
+ * 2*watchdog_thresh seconds then the debug-printout triggers in
+ * watchdog_timer_fn().
*/
while (!kthread_should_stop()) {
__touch_watchdog();
OpenPOWER on IntegriCloud