summaryrefslogtreecommitdiff
path: root/kernel
diff options
context:
space:
mode:
Diffstat (limited to 'kernel')
-rw-r--r--kernel/Kconfig.preempt12
-rw-r--r--kernel/Makefile4
-rw-r--r--kernel/bpf/btf.c2
-rw-r--r--kernel/entry/common.c16
-rw-r--r--kernel/events/core.c212
-rw-r--r--kernel/irq_work.c2
-rw-r--r--kernel/kprobes.c124
-rw-r--r--kernel/sched/core.c16
-rw-r--r--kernel/sched/idle.c1
-rw-r--r--kernel/sched/sched.h6
-rw-r--r--kernel/signal.c40
-rw-r--r--kernel/static_call.c541
-rw-r--r--kernel/static_call_inline.c543
-rw-r--r--kernel/trace/Kconfig1
-rw-r--r--kernel/trace/bpf_trace.c4
-rw-r--r--kernel/trace/fgraph.c17
-rw-r--r--kernel/trace/fprobe.c8
-rw-r--r--kernel/trace/rethook.c2
-rw-r--r--kernel/trace/trace_events_user.c86
-rw-r--r--kernel/trace/trace_kprobe.c4
-rw-r--r--kernel/watch_queue.c1
21 files changed, 746 insertions, 896 deletions
diff --git a/kernel/Kconfig.preempt b/kernel/Kconfig.preempt
index 8c6de5a9ecc4..c2f1fd95a821 100644
--- a/kernel/Kconfig.preempt
+++ b/kernel/Kconfig.preempt
@@ -133,14 +133,4 @@ config SCHED_CORE
which is the likely usage by Linux distributions, there should
be no measurable impact on performance.
-config ARCH_WANTS_RT_DELAYED_SIGNALS
- bool
- help
- This option is selected by architectures where raising signals
- can happen in atomic contexts on PREEMPT_RT enabled kernels. This
- option delays raising the signal until the return to user space
- loop where it is also delivered. X86 requires this to deliver
- signals from trap handlers which run on IST stacks.
-
-config RT_DELAYED_SIGNALS
- def_bool PREEMPT_RT && ARCH_WANTS_RT_DELAYED_SIGNALS
+
diff --git a/kernel/Makefile b/kernel/Makefile
index 56f4ee97f328..847a82bfe0e3 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -108,12 +108,14 @@ obj-$(CONFIG_TRACING) += trace/
obj-$(CONFIG_TRACE_CLOCK) += trace/
obj-$(CONFIG_RING_BUFFER) += trace/
obj-$(CONFIG_TRACEPOINTS) += trace/
+obj-$(CONFIG_RETHOOK) += trace/
obj-$(CONFIG_IRQ_WORK) += irq_work.o
obj-$(CONFIG_CPU_PM) += cpu_pm.o
obj-$(CONFIG_BPF) += bpf/
obj-$(CONFIG_KCSAN) += kcsan/
obj-$(CONFIG_SHADOW_CALL_STACK) += scs.o
-obj-$(CONFIG_HAVE_STATIC_CALL_INLINE) += static_call.o
+obj-$(CONFIG_HAVE_STATIC_CALL) += static_call.o
+obj-$(CONFIG_HAVE_STATIC_CALL_INLINE) += static_call_inline.o
obj-$(CONFIG_CFI_CLANG) += cfi.o
obj-$(CONFIG_PERF_EVENTS) += events/
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index 24788ce564a0..0918a39279f6 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -5507,7 +5507,7 @@ int btf_distill_func_proto(struct bpf_verifier_log *log,
}
args = (const struct btf_param *)(func + 1);
nargs = btf_type_vlen(func);
- if (nargs >= MAX_BPF_FUNC_ARGS) {
+ if (nargs > MAX_BPF_FUNC_ARGS) {
bpf_log(log,
"The function %s has %d arguments. Too many.\n",
tname, nargs);
diff --git a/kernel/entry/common.c b/kernel/entry/common.c
index ef8d94a98b7e..93c3b86e781c 100644
--- a/kernel/entry/common.c
+++ b/kernel/entry/common.c
@@ -142,18 +142,6 @@ void noinstr exit_to_user_mode(void)
/* Workaround to allow gradual conversion of architecture code */
void __weak arch_do_signal_or_restart(struct pt_regs *regs) { }
-#ifdef CONFIG_RT_DELAYED_SIGNALS
-static inline void raise_delayed_signal(void)
-{
- if (unlikely(current->forced_info.si_signo)) {
- force_sig_info(&current->forced_info);
- current->forced_info.si_signo = 0;
- }
-}
-#else
-static inline void raise_delayed_signal(void) { }
-#endif
-
static unsigned long exit_to_user_mode_loop(struct pt_regs *regs,
unsigned long ti_work)
{
@@ -168,8 +156,6 @@ static unsigned long exit_to_user_mode_loop(struct pt_regs *regs,
if (ti_work & _TIF_NEED_RESCHED)
schedule();
- raise_delayed_signal();
-
if (ti_work & _TIF_UPROBE)
uprobe_notify_resume(regs);
@@ -406,7 +392,7 @@ DEFINE_STATIC_CALL(irqentry_exit_cond_resched, raw_irqentry_exit_cond_resched);
DEFINE_STATIC_KEY_TRUE(sk_dynamic_irqentry_exit_cond_resched);
void dynamic_irqentry_exit_cond_resched(void)
{
- if (!static_key_unlikely(&sk_dynamic_irqentry_exit_cond_resched))
+ if (!static_branch_unlikely(&sk_dynamic_irqentry_exit_cond_resched))
return;
raw_irqentry_exit_cond_resched();
}
diff --git a/kernel/events/core.c b/kernel/events/core.c
index cfde994ce61c..23bb19716ad3 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -574,8 +574,7 @@ 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,
- struct task_struct *task);
+ enum event_type_t event_type);
static void update_context_time(struct perf_event_context *ctx);
static u64 perf_event_time(struct perf_event *event);
@@ -781,7 +780,6 @@ static inline void update_cgrp_time_from_cpuctx(struct perf_cpu_context *cpuctx,
static inline void update_cgrp_time_from_event(struct perf_event *event)
{
struct perf_cgroup_info *info;
- struct perf_cgroup *cgrp;
/*
* ensure we access cgroup data only when needed and
@@ -790,21 +788,19 @@ static inline void update_cgrp_time_from_event(struct perf_event *event)
if (!is_cgroup_event(event))
return;
- cgrp = perf_cgroup_from_task(current, event->ctx);
+ info = this_cpu_ptr(event->cgrp->info);
/*
* Do not update time when cgroup is not active
*/
- if (cgroup_is_descendant(cgrp->css.cgroup, event->cgrp->css.cgroup)) {
- info = this_cpu_ptr(event->cgrp->info);
+ if (info->active)
__update_cgrp_time(info, perf_clock(), true);
- }
}
static inline void
-perf_cgroup_set_timestamp(struct task_struct *task,
- struct perf_event_context *ctx)
+perf_cgroup_set_timestamp(struct perf_cpu_context *cpuctx)
{
- struct perf_cgroup *cgrp;
+ struct perf_event_context *ctx = &cpuctx->ctx;
+ struct perf_cgroup *cgrp = cpuctx->cgrp;
struct perf_cgroup_info *info;
struct cgroup_subsys_state *css;
@@ -813,10 +809,10 @@ perf_cgroup_set_timestamp(struct task_struct *task,
* ensure we do not access cgroup data
* unless we have the cgroup pinned (css_get)
*/
- if (!task || !ctx->nr_cgroups)
+ if (!cgrp)
return;
- cgrp = perf_cgroup_from_task(task, ctx);
+ WARN_ON_ONCE(!ctx->nr_cgroups);
for (css = &cgrp->css; css; css = css->parent) {
cgrp = container_of(css, struct perf_cgroup, css);
@@ -828,17 +824,12 @@ perf_cgroup_set_timestamp(struct task_struct *task,
static DEFINE_PER_CPU(struct list_head, cgrp_cpuctx_list);
-#define PERF_CGROUP_SWOUT 0x1 /* cgroup switch out every event */
-#define PERF_CGROUP_SWIN 0x2 /* cgroup switch in events based on task */
-
/*
* reschedule events based on the cgroup constraint of task.
- *
- * mode SWOUT : schedule out everything
- * mode SWIN : schedule in based on cgroup for next
*/
-static void perf_cgroup_switch(struct task_struct *task, int mode)
+static void perf_cgroup_switch(struct task_struct *task)
{
+ struct perf_cgroup *cgrp;
struct perf_cpu_context *cpuctx, *tmp;
struct list_head *list;
unsigned long flags;
@@ -849,35 +840,31 @@ static void perf_cgroup_switch(struct task_struct *task, int mode)
*/
local_irq_save(flags);
+ cgrp = perf_cgroup_from_task(task, NULL);
+
list = this_cpu_ptr(&cgrp_cpuctx_list);
list_for_each_entry_safe(cpuctx, tmp, list, cgrp_cpuctx_entry) {
WARN_ON_ONCE(cpuctx->ctx.nr_cgroups == 0);
+ if (READ_ONCE(cpuctx->cgrp) == cgrp)
+ continue;
perf_ctx_lock(cpuctx, cpuctx->task_ctx);
perf_pmu_disable(cpuctx->ctx.pmu);
- if (mode & PERF_CGROUP_SWOUT) {
- cpu_ctx_sched_out(cpuctx, EVENT_ALL);
- /*
- * must not be done before ctxswout due
- * to event_filter_match() in event_sched_out()
- */
- cpuctx->cgrp = NULL;
- }
+ cpu_ctx_sched_out(cpuctx, EVENT_ALL);
+ /*
+ * must not be done before ctxswout due
+ * to update_cgrp_time_from_cpuctx() in
+ * ctx_sched_out()
+ */
+ cpuctx->cgrp = cgrp;
+ /*
+ * set cgrp before ctxsw in to allow
+ * perf_cgroup_set_timestamp() in ctx_sched_in()
+ * to not have to pass task around
+ */
+ cpu_ctx_sched_in(cpuctx, EVENT_ALL);
- if (mode & PERF_CGROUP_SWIN) {
- WARN_ON_ONCE(cpuctx->cgrp);
- /*
- * set cgrp before ctxsw in to allow
- * event_filter_match() to not have to pass
- * task around
- * we pass the cpuctx->ctx to perf_cgroup_from_task()
- * because cgorup events are only per-cpu
- */
- cpuctx->cgrp = perf_cgroup_from_task(task,
- &cpuctx->ctx);
- cpu_ctx_sched_in(cpuctx, EVENT_ALL, task);
- }
perf_pmu_enable(cpuctx->ctx.pmu);
perf_ctx_unlock(cpuctx, cpuctx->task_ctx);
}
@@ -885,58 +872,6 @@ static void perf_cgroup_switch(struct task_struct *task, int mode)
local_irq_restore(flags);
}
-static inline void perf_cgroup_sched_out(struct task_struct *task,
- struct task_struct *next)
-{
- struct perf_cgroup *cgrp1;
- struct perf_cgroup *cgrp2 = NULL;
-
- rcu_read_lock();
- /*
- * we come here when we know perf_cgroup_events > 0
- * we do not need to pass the ctx here because we know
- * we are holding the rcu lock
- */
- cgrp1 = perf_cgroup_from_task(task, NULL);
- cgrp2 = perf_cgroup_from_task(next, NULL);
-
- /*
- * only schedule out current cgroup events if we know
- * that we are switching to a different cgroup. Otherwise,
- * do no touch the cgroup events.
- */
- if (cgrp1 != cgrp2)
- perf_cgroup_switch(task, PERF_CGROUP_SWOUT);
-
- rcu_read_unlock();
-}
-
-static inline void perf_cgroup_sched_in(struct task_struct *prev,
- struct task_struct *task)
-{
- struct perf_cgroup *cgrp1;
- struct perf_cgroup *cgrp2 = NULL;
-
- rcu_read_lock();
- /*
- * we come here when we know perf_cgroup_events > 0
- * we do not need to pass the ctx here because we know
- * we are holding the rcu lock
- */
- cgrp1 = perf_cgroup_from_task(task, NULL);
- cgrp2 = perf_cgroup_from_task(prev, NULL);
-
- /*
- * only need to schedule in cgroup events if we are changing
- * cgroup during ctxsw. Cgroup events were not scheduled
- * out of ctxsw out if that was not the case.
- */
- if (cgrp1 != cgrp2)
- perf_cgroup_switch(task, PERF_CGROUP_SWIN);
-
- rcu_read_unlock();
-}
-
static int perf_cgroup_ensure_storage(struct perf_event *event,
struct cgroup_subsys_state *css)
{
@@ -1032,22 +967,10 @@ perf_cgroup_event_enable(struct perf_event *event, struct perf_event_context *ct
*/
cpuctx = container_of(ctx, struct perf_cpu_context, ctx);
- /*
- * Since setting cpuctx->cgrp is conditional on the current @cgrp
- * matching the event's cgroup, we must do this for every new event,
- * because if the first would mismatch, the second would not try again
- * and we would leave cpuctx->cgrp unset.
- */
- if (ctx->is_active && !cpuctx->cgrp) {
- struct perf_cgroup *cgrp = perf_cgroup_from_task(current, ctx);
-
- if (cgroup_is_descendant(cgrp->css.cgroup, event->cgrp->css.cgroup))
- cpuctx->cgrp = cgrp;
- }
-
if (ctx->nr_cgroups++)
return;
+ cpuctx->cgrp = perf_cgroup_from_task(current, ctx);
list_add(&cpuctx->cgrp_cpuctx_entry,
per_cpu_ptr(&cgrp_cpuctx_list, event->cpu));
}
@@ -1069,9 +992,7 @@ perf_cgroup_event_disable(struct perf_event *event, struct perf_event_context *c
if (--ctx->nr_cgroups)
return;
- if (ctx->is_active && cpuctx->cgrp)
- cpuctx->cgrp = NULL;
-
+ cpuctx->cgrp = NULL;
list_del(&cpuctx->cgrp_cpuctx_entry);
}
@@ -1100,16 +1021,6 @@ static inline void update_cgrp_time_from_cpuctx(struct perf_cpu_context *cpuctx,
{
}
-static inline void perf_cgroup_sched_out(struct task_struct *task,
- struct task_struct *next)
-{
-}
-
-static inline void perf_cgroup_sched_in(struct task_struct *prev,
- struct task_struct *task)
-{
-}
-
static inline int perf_cgroup_connect(pid_t pid, struct perf_event *event,
struct perf_event_attr *attr,
struct perf_event *group_leader)
@@ -1118,13 +1029,7 @@ static inline int perf_cgroup_connect(pid_t pid, struct perf_event *event,
}
static inline void
-perf_cgroup_set_timestamp(struct task_struct *task,
- struct perf_event_context *ctx)
-{
-}
-
-static inline void
-perf_cgroup_switch(struct task_struct *task, struct task_struct *next)
+perf_cgroup_set_timestamp(struct perf_cpu_context *cpuctx)
{
}
@@ -1147,6 +1052,10 @@ static inline void
perf_cgroup_event_disable(struct perf_event *event, struct perf_event_context *ctx)
{
}
+
+static void perf_cgroup_switch(struct task_struct *task)
+{
+}
#endif
/*
@@ -2713,8 +2622,7 @@ static void ctx_sched_out(struct perf_event_context *ctx,
static void
ctx_sched_in(struct perf_event_context *ctx,
struct perf_cpu_context *cpuctx,
- enum event_type_t event_type,
- struct task_struct *task);
+ enum event_type_t event_type);
static void task_ctx_sched_out(struct perf_cpu_context *cpuctx,
struct perf_event_context *ctx,
@@ -2730,15 +2638,14 @@ static void task_ctx_sched_out(struct perf_cpu_context *cpuctx,
}
static void perf_event_sched_in(struct perf_cpu_context *cpuctx,
- struct perf_event_context *ctx,
- struct task_struct *task)
+ struct perf_event_context *ctx)
{
- cpu_ctx_sched_in(cpuctx, EVENT_PINNED, task);
+ cpu_ctx_sched_in(cpuctx, EVENT_PINNED);
if (ctx)
- ctx_sched_in(ctx, cpuctx, EVENT_PINNED, task);
- cpu_ctx_sched_in(cpuctx, EVENT_FLEXIBLE, task);
+ ctx_sched_in(ctx, cpuctx, EVENT_PINNED);
+ cpu_ctx_sched_in(cpuctx, EVENT_FLEXIBLE);
if (ctx)
- ctx_sched_in(ctx, cpuctx, EVENT_FLEXIBLE, task);
+ ctx_sched_in(ctx, cpuctx, EVENT_FLEXIBLE);
}
/*
@@ -2788,7 +2695,7 @@ static void ctx_resched(struct perf_cpu_context *cpuctx,
else if (ctx_event_type & EVENT_PINNED)
cpu_ctx_sched_out(cpuctx, EVENT_FLEXIBLE);
- perf_event_sched_in(cpuctx, task_ctx, current);
+ perf_event_sched_in(cpuctx, task_ctx);
perf_pmu_enable(cpuctx->ctx.pmu);
}
@@ -3011,7 +2918,7 @@ static void __perf_event_enable(struct perf_event *event,
return;
if (!event_filter_match(event)) {
- ctx_sched_in(ctx, cpuctx, EVENT_TIME, current);
+ ctx_sched_in(ctx, cpuctx, EVENT_TIME);
return;
}
@@ -3020,7 +2927,7 @@ static void __perf_event_enable(struct perf_event *event,
* then don't put it on unless the group is on.
*/
if (leader != event && leader->state != PERF_EVENT_STATE_ACTIVE) {
- ctx_sched_in(ctx, cpuctx, EVENT_TIME, current);
+ ctx_sched_in(ctx, cpuctx, EVENT_TIME);
return;
}
@@ -3668,7 +3575,7 @@ void __perf_event_task_sched_out(struct task_struct *task,
* cgroup event are system-wide mode only
*/
if (atomic_read(this_cpu_ptr(&perf_cgroup_events)))
- perf_cgroup_sched_out(task, next);
+ perf_cgroup_switch(next);
}
/*
@@ -3865,8 +3772,7 @@ ctx_flexible_sched_in(struct perf_event_context *ctx,
static void
ctx_sched_in(struct perf_event_context *ctx,
struct perf_cpu_context *cpuctx,
- enum event_type_t event_type,
- struct task_struct *task)
+ enum event_type_t event_type)
{
int is_active = ctx->is_active;
@@ -3878,7 +3784,7 @@ ctx_sched_in(struct perf_event_context *ctx,
if (is_active ^ EVENT_TIME) {
/* start ctx time */
__update_context_time(ctx, false);
- perf_cgroup_set_timestamp(task, ctx);
+ perf_cgroup_set_timestamp(cpuctx);
/*
* CPU-release for the below ->is_active store,
* see __load_acquire() in perf_event_time_now()
@@ -3909,12 +3815,11 @@ ctx_sched_in(struct perf_event_context *ctx,
}
static void cpu_ctx_sched_in(struct perf_cpu_context *cpuctx,
- enum event_type_t event_type,
- struct task_struct *task)
+ enum event_type_t event_type)
{
struct perf_event_context *ctx = &cpuctx->ctx;
- ctx_sched_in(ctx, cpuctx, event_type, task);
+ ctx_sched_in(ctx, cpuctx, event_type);
}
static void perf_event_context_sched_in(struct perf_event_context *ctx,
@@ -3956,7 +3861,7 @@ static void perf_event_context_sched_in(struct perf_event_context *ctx,
*/
if (!RB_EMPTY_ROOT(&ctx->pinned_groups.tree))
cpu_ctx_sched_out(cpuctx, EVENT_FLEXIBLE);
- perf_event_sched_in(cpuctx, ctx, task);
+ perf_event_sched_in(cpuctx, ctx);
if (cpuctx->sched_cb_usage && pmu->sched_task)
pmu->sched_task(cpuctx->task_ctx, true);
@@ -3984,16 +3889,6 @@ void __perf_event_task_sched_in(struct task_struct *prev,
struct perf_event_context *ctx;
int ctxn;
- /*
- * If cgroup events exist on this CPU, then we need to check if we have
- * to switch in PMU state; cgroup event are system-wide mode only.
- *
- * Since cgroup events are CPU events, we must schedule these in before
- * we schedule in the task events.
- */
- if (atomic_read(this_cpu_ptr(&perf_cgroup_events)))
- perf_cgroup_sched_in(prev, task);
-
for_each_task_context_nr(ctxn) {
ctx = task->perf_event_ctxp[ctxn];
if (likely(!ctx))
@@ -4267,7 +4162,7 @@ static bool perf_rotate_context(struct perf_cpu_context *cpuctx)
if (cpu_event)
rotate_ctx(&cpuctx->ctx, cpu_event);
- perf_event_sched_in(cpuctx, task_ctx, current);
+ perf_event_sched_in(cpuctx, task_ctx);
perf_pmu_enable(cpuctx->ctx.pmu);
perf_ctx_unlock(cpuctx, cpuctx->task_ctx);
@@ -4339,7 +4234,7 @@ static void perf_event_enable_on_exec(int ctxn)
clone_ctx = unclone_ctx(ctx);
ctx_resched(cpuctx, ctx, event_type);
} else {
- ctx_sched_in(ctx, cpuctx, EVENT_TIME, current);
+ ctx_sched_in(ctx, cpuctx, EVENT_TIME);
}
perf_ctx_unlock(cpuctx, ctx);
@@ -11635,6 +11530,9 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu,
event->state = PERF_EVENT_STATE_INACTIVE;
+ if (parent_event)
+ event->event_caps = parent_event->event_caps;
+
if (event->attr.sigtrap)
atomic_set(&event->event_limit, 1);
@@ -13562,7 +13460,7 @@ static int __perf_cgroup_move(void *info)
{
struct task_struct *task = info;
rcu_read_lock();
- perf_cgroup_switch(task, PERF_CGROUP_SWOUT | PERF_CGROUP_SWIN);
+ perf_cgroup_switch(task);
rcu_read_unlock();
return 0;
}
diff --git a/kernel/irq_work.c b/kernel/irq_work.c
index f7df715ec28e..7afa40fe5cc4 100644
--- a/kernel/irq_work.c
+++ b/kernel/irq_work.c
@@ -137,7 +137,7 @@ bool irq_work_queue_on(struct irq_work *work, int cpu)
if (!irq_work_claim(work))
return false;
- kasan_record_aux_stack(work);
+ kasan_record_aux_stack_noalloc(work);
preempt_disable();
if (cpu != smp_processor_id()) {
diff --git a/kernel/kprobes.c b/kernel/kprobes.c
index 185badc780b7..dbe57df2e199 100644
--- a/kernel/kprobes.c
+++ b/kernel/kprobes.c
@@ -1237,6 +1237,27 @@ void kprobes_inc_nmissed_count(struct kprobe *p)
}
NOKPROBE_SYMBOL(kprobes_inc_nmissed_count);
+static struct kprobe kprobe_busy = {
+ .addr = (void *) get_kprobe,
+};
+
+void kprobe_busy_begin(void)
+{
+ struct kprobe_ctlblk *kcb;
+
+ preempt_disable();
+ __this_cpu_write(current_kprobe, &kprobe_busy);
+ kcb = get_kprobe_ctlblk();
+ kcb->kprobe_status = KPROBE_HIT_ACTIVE;
+}
+
+void kprobe_busy_end(void)
+{
+ __this_cpu_write(current_kprobe, NULL);
+ preempt_enable();
+}
+
+#if !defined(CONFIG_KRETPROBE_ON_RETHOOK)
static void free_rp_inst_rcu(struct rcu_head *head)
{
struct kretprobe_instance *ri = container_of(head, struct kretprobe_instance, rcu);
@@ -1258,26 +1279,6 @@ static void recycle_rp_inst(struct kretprobe_instance *ri)
}
NOKPROBE_SYMBOL(recycle_rp_inst);
-static struct kprobe kprobe_busy = {
- .addr = (void *) get_kprobe,
-};
-
-void kprobe_busy_begin(void)
-{
- struct kprobe_ctlblk *kcb;
-
- preempt_disable();
- __this_cpu_write(current_kprobe, &kprobe_busy);
- kcb = get_kprobe_ctlblk();
- kcb->kprobe_status = KPROBE_HIT_ACTIVE;
-}
-
-void kprobe_busy_end(void)
-{
- __this_cpu_write(current_kprobe, NULL);
- preempt_enable();
-}
-
/*
* This function is called from delayed_put_task_struct() when a task is
* dead and cleaned up to recycle any kretprobe instances associated with
@@ -1327,6 +1328,7 @@ static inline void free_rp_inst(struct kretprobe *rp)
rp->rph = NULL;
}
}
+#endif /* !CONFIG_KRETPROBE_ON_RETHOOK */
/* Add the new probe to 'ap->list'. */
static int add_new_kprobe(struct kprobe *ap, struct kprobe *p)
@@ -1925,6 +1927,7 @@ static struct notifier_block kprobe_exceptions_nb = {
#ifdef CONFIG_KRETPROBES
+#if !defined(CONFIG_KRETPROBE_ON_RETHOOK)
/* This assumes the 'tsk' is the current task or the is not running. */
static kprobe_opcode_t *__kretprobe_find_ret_addr(struct task_struct *tsk,
struct llist_node **cur)
@@ -2087,6 +2090,57 @@ static int pre_handler_kretprobe(struct kprobe *p, struct pt_regs *regs)
return 0;
}
NOKPROBE_SYMBOL(pre_handler_kretprobe);
+#else /* CONFIG_KRETPROBE_ON_RETHOOK */
+/*
+ * This kprobe pre_handler is registered with every kretprobe. When probe
+ * hits it will set up the return probe.
+ */
+static int pre_handler_kretprobe(struct kprobe *p, struct pt_regs *regs)
+{
+ struct kretprobe *rp = container_of(p, struct kretprobe, kp);
+ struct kretprobe_instance *ri;
+ struct rethook_node *rhn;
+
+ rhn = rethook_try_get(rp->rh);
+ if (!rhn) {
+ rp->nmissed++;
+ return 0;
+ }
+
+ ri = container_of(rhn, struct kretprobe_instance, node);
+
+ if (rp->entry_handler && rp->entry_handler(ri, regs))
+ rethook_recycle(rhn);
+ else
+ rethook_hook(rhn, regs, kprobe_ftrace(p));
+
+ return 0;
+}
+NOKPROBE_SYMBOL(pre_handler_kretprobe);
+
+static void kretprobe_rethook_handler(struct rethook_node *rh, void *data,
+ struct pt_regs *regs)
+{
+ struct kretprobe *rp = (struct kretprobe *)data;
+ struct kretprobe_instance *ri;
+ struct kprobe_ctlblk *kcb;
+
+ /* The data must NOT be null. This means rethook data structure is broken. */
+ if (WARN_ON_ONCE(!data))
+ return;
+
+ __this_cpu_write(current_kprobe, &rp->kp);
+ kcb = get_kprobe_ctlblk();
+ kcb->kprobe_status = KPROBE_HIT_ACTIVE;
+
+ ri = container_of(rh, struct kretprobe_instance, node);
+ rp->handler(ri, regs);
+
+ __this_cpu_write(current_kprobe, NULL);
+}
+NOKPROBE_SYMBOL(kretprobe_rethook_handler);
+
+#endif /* !CONFIG_KRETPROBE_ON_RETHOOK */
/**
* kprobe_on_func_entry() -- check whether given address is function entry
@@ -2155,6 +2209,29 @@ int register_kretprobe(struct kretprobe *rp)
rp->maxactive = num_possible_cpus();
#endif
}
+#ifdef CONFIG_KRETPROBE_ON_RETHOOK
+ rp->rh = rethook_alloc((void *)rp, kretprobe_rethook_handler);
+ if (!rp->rh)
+ return -ENOMEM;
+
+ for (i = 0; i < rp->maxactive; i++) {
+ inst = kzalloc(sizeof(struct kretprobe_instance) +
+ rp->data_size, GFP_KERNEL);
+ if (inst == NULL) {
+ rethook_free(rp->rh);
+ rp->rh = NULL;
+ return -ENOMEM;
+ }
+ rethook_add_node(rp->rh, &inst->node);
+ }
+ rp->nmissed = 0;
+ /* Establish function entry probe point */
+ ret = register_kprobe(&rp->kp);
+ if (ret != 0) {
+ rethook_free(rp->rh);
+ rp->rh = NULL;
+ }
+#else /* !CONFIG_KRETPROBE_ON_RETHOOK */
rp->freelist.head = NULL;
rp->rph = kzalloc(sizeof(struct kretprobe_holder), GFP_KERNEL);
if (!rp->rph)
@@ -2179,6 +2256,7 @@ int register_kretprobe(struct kretprobe *rp)
ret = register_kprobe(&rp->kp);
if (ret != 0)
free_rp_inst(rp);
+#endif
return ret;
}
EXPORT_SYMBOL_GPL(register_kretprobe);
@@ -2217,7 +2295,11 @@ void unregister_kretprobes(struct kretprobe **rps, int num)
for (i = 0; i < num; i++) {
if (__unregister_kprobe_top(&rps[i]->kp) < 0)
rps[i]->kp.addr = NULL;
+#ifdef CONFIG_KRETPROBE_ON_RETHOOK
+ rethook_free(rps[i]->rh);
+#else
rps[i]->rph->rp = NULL;
+#endif
}
mutex_unlock(&kprobe_mutex);
@@ -2225,7 +2307,9 @@ void unregister_kretprobes(struct kretprobe **rps, int num)
for (i = 0; i < num; i++) {
if (rps[i]->kp.addr) {
__unregister_kprobe_bottom(&rps[i]->kp);
+#ifndef CONFIG_KRETPROBE_ON_RETHOOK
free_rp_inst(rps[i]);
+#endif
}
}
}
diff --git a/kernel/sched/core.c b/kernel/sched/core.c
index d575b4914925..51efaabac3e4 100644
--- a/kernel/sched/core.c
+++ b/kernel/sched/core.c
@@ -5752,6 +5752,8 @@ static inline struct task_struct *pick_task(struct rq *rq)
extern void task_vruntime_update(struct rq *rq, struct task_struct *p, bool in_fi);
+static void queue_core_balance(struct rq *rq);
+
static struct task_struct *
pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
{
@@ -5801,7 +5803,7 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
}
rq->core_pick = NULL;
- return next;
+ goto out;
}
put_prev_task_balance(rq, prev, rf);
@@ -5851,7 +5853,7 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
*/
WARN_ON_ONCE(fi_before);
task_vruntime_update(rq, next, false);
- goto done;
+ goto out_set_next;
}
}
@@ -5970,8 +5972,12 @@ pick_next_task(struct rq *rq, struct task_struct *prev, struct rq_flags *rf)
resched_curr(rq_i);
}
-done:
+out_set_next:
set_next_task(rq, next);
+out:
+ if (rq->core->core_forceidle_count && next == rq->idle)
+ queue_core_balance(rq);
+
return next;
}
@@ -6000,7 +6006,7 @@ static bool try_steal_cookie(int this, int that)
if (p == src->core_pick || p == src->curr)
goto next;
- if (!cpumask_test_cpu(this, &p->cpus_mask))
+ if (!is_cpu_allowed(p, this))
goto next;
if (p->core_occupation > dst->idle->core_occupation)
@@ -6066,7 +6072,7 @@ static void sched_core_balance(struct rq *rq)
static DEFINE_PER_CPU(struct callback_head, core_balance_head);
-void queue_core_balance(struct rq *rq)
+static void queue_core_balance(struct rq *rq)
{
if (!sched_core_enabled(rq))
return;
diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c
index 8f8b5020e76a..ecb0d7052877 100644
--- a/kernel/sched/idle.c
+++ b/kernel/sched/idle.c
@@ -434,7 +434,6 @@ static void set_next_task_idle(struct rq *rq, struct task_struct *next, bool fir
{
update_idle_core(rq);
schedstat_inc(rq->sched_goidle);
- queue_core_balance(rq);
}
#ifdef CONFIG_SMP
diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
index 58263f90c559..8dccb34eb190 100644
--- a/kernel/sched/sched.h
+++ b/kernel/sched/sched.h
@@ -1232,8 +1232,6 @@ static inline bool sched_group_cookie_match(struct rq *rq,
return false;
}
-extern void queue_core_balance(struct rq *rq);
-
static inline bool sched_core_enqueued(struct task_struct *p)
{
return !RB_EMPTY_NODE(&p->core_node);
@@ -1267,10 +1265,6 @@ static inline raw_spinlock_t *__rq_lockp(struct rq *rq)
return &rq->__lock;
}
-static inline void queue_core_balance(struct rq *rq)
-{
-}
-
static inline bool sched_cpu_cookie_match(struct rq *rq, struct task_struct *p)
{
return true;
diff --git a/kernel/signal.c b/kernel/signal.c
index 368a34c25bbf..30cd1ca43bcd 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -1308,43 +1308,6 @@ enum sig_handler {
};
/*
- * On some archictectures, PREEMPT_RT has to delay sending a signal from a
- * trap since it cannot enable preemption, and the signal code's
- * spin_locks turn into mutexes. Instead, it must set TIF_NOTIFY_RESUME
- * which will send the signal on exit of the trap.
- */
-#ifdef CONFIG_RT_DELAYED_SIGNALS
-static inline bool force_sig_delayed(struct kernel_siginfo *info,
- struct task_struct *t)
-{
- if (!in_atomic())
- return false;
-
- if (WARN_ON_ONCE(t->forced_info.si_signo))
- return true;
-
- if (is_si_special(info)) {
- WARN_ON_ONCE(info != SEND_SIG_PRIV);
- t->forced_info.si_signo = info->si_signo;
- t->forced_info.si_errno = 0;
- t->forced_info.si_code = SI_KERNEL;
- t->forced_info.si_pid = 0;
- t->forced_info.si_uid = 0;
- } else {
- t->forced_info = *info;
- }
- set_tsk_thread_flag(t, TIF_NOTIFY_RESUME);
- return true;
-}
-#else
-static inline bool force_sig_delayed(struct kernel_siginfo *info,
- struct task_struct *t)
-{
- return false;
-}
-#endif
-
-/*
* Force a signal that the process can't ignore: if necessary
* we unblock the signal and change any SIG_IGN to SIG_DFL.
*
@@ -1364,9 +1327,6 @@ force_sig_info_to_task(struct kernel_siginfo *info, struct task_struct *t,
struct k_sigaction *action;
int sig = info->si_signo;
- if (force_sig_delayed(info, t))
- return 0;
-
spin_lock_irqsave(&t->sighand->siglock, flags);
action = &t->sighand->action[sig-1];
ignored = action->sa.sa_handler == SIG_IGN;
diff --git a/kernel/static_call.c b/kernel/static_call.c
index f2b8baea35d2..e9c3e69f3837 100644
--- a/kernel/static_call.c
+++ b/kernel/static_call.c
@@ -1,549 +1,8 @@
// SPDX-License-Identifier: GPL-2.0
-#include <linux/init.h>
#include <linux/static_call.h>
-#include <linux/bug.h>
-#include <linux/smp.h>
-#include <linux/sort.h>
-#include <linux/slab.h>
-#include <linux/module.h>
-#include <linux/cpu.h>
-#include <linux/processor.h>
-#include <asm/sections.h>
-
-extern struct static_call_site __start_static_call_sites[],
- __stop_static_call_sites[];
-extern struct static_call_tramp_key __start_static_call_tramp_key[],
- __stop_static_call_tramp_key[];
-
-static bool static_call_initialized;
-
-/* mutex to protect key modules/sites */
-static DEFINE_MUTEX(static_call_mutex);
-
-static void static_call_lock(void)
-{
- mutex_lock(&static_call_mutex);
-}
-
-static void static_call_unlock(void)
-{
- mutex_unlock(&static_call_mutex);
-}
-
-static inline void *static_call_addr(struct static_call_site *site)
-{
- return (void *)((long)site->addr + (long)&site->addr);
-}
-
-static inline unsigned long __static_call_key(const struct static_call_site *site)
-{
- return (long)site->key + (long)&site->key;
-}
-
-static inline struct static_call_key *static_call_key(const struct static_call_site *site)
-{
- return (void *)(__static_call_key(site) & ~STATIC_CALL_SITE_FLAGS);
-}
-
-/* These assume the key is word-aligned. */
-static inline bool static_call_is_init(struct static_call_site *site)
-{
- return __static_call_key(site) & STATIC_CALL_SITE_INIT;
-}
-
-static inline bool static_call_is_tail(struct static_call_site *site)
-{
- return __static_call_key(site) & STATIC_CALL_SITE_TAIL;
-}
-
-static inline void static_call_set_init(struct static_call_site *site)
-{
- site->key = (__static_call_key(site) | STATIC_CALL_SITE_INIT) -
- (long)&site->key;
-}
-
-static int static_call_site_cmp(const void *_a, const void *_b)
-{
- const struct static_call_site *a = _a;
- const struct static_call_site *b = _b;
- const struct static_call_key *key_a = static_call_key(a);
- const struct static_call_key *key_b = static_call_key(b);
-
- if (key_a < key_b)
- return -1;
-
- if (key_a > key_b)
- return 1;
-
- return 0;
-}
-
-static void static_call_site_swap(void *_a, void *_b, int size)
-{
- long delta = (unsigned long)_a - (unsigned long)_b;
- struct static_call_site *a = _a;
- struct static_call_site *b = _b;
- struct static_call_site tmp = *a;
-
- a->addr = b->addr - delta;
- a->key = b->key - delta;
-
- b->addr = tmp.addr + delta;
- b->key = tmp.key + delta;
-}
-
-static inline void static_call_sort_entries(struct static_call_site *start,
- struct static_call_site *stop)
-{
- sort(start, stop - start, sizeof(struct static_call_site),
- static_call_site_cmp, static_call_site_swap);
-}
-
-static inline bool static_call_key_has_mods(struct static_call_key *key)
-{
- return !(key->type & 1);
-}
-
-static inline struct static_call_mod *static_call_key_next(struct static_call_key *key)
-{
- if (!static_call_key_has_mods(key))
- return NULL;
-
- return key->mods;
-}
-
-static inline struct static_call_site *static_call_key_sites(struct static_call_key *key)
-{
- if (static_call_key_has_mods(key))
- return NULL;
-
- return (struct static_call_site *)(key->type & ~1);
-}
-
-void __static_call_update(struct static_call_key *key, void *tramp, void *func)
-{
- struct static_call_site *site, *stop;
- struct static_call_mod *site_mod, first;
-
- cpus_read_lock();
- static_call_lock();
-
- if (key->func == func)
- goto done;
-
- key->func = func;
-
- arch_static_call_transform(NULL, tramp, func, false);
-
- /*
- * If uninitialized, we'll not update the callsites, but they still
- * point to the trampoline and we just patched that.
- */
- if (WARN_ON_ONCE(!static_call_initialized))
- goto done;
-
- first = (struct static_call_mod){
- .next = static_call_key_next(key),
- .mod = NULL,
- .sites = static_call_key_sites(key),
- };
-
- for (site_mod = &first; site_mod; site_mod = site_mod->next) {
- bool init = system_state < SYSTEM_RUNNING;
- struct module *mod = site_mod->mod;
-
- if (!site_mod->sites) {
- /*
- * This can happen if the static call key is defined in
- * a module which doesn't use it.
- *
- * It also happens in the has_mods case, where the
- * 'first' entry has no sites associated with it.
- */
- continue;
- }
-
- stop = __stop_static_call_sites;
-
- if (mod) {
-#ifdef CONFIG_MODULES
- stop = mod->static_call_sites +
- mod->num_static_call_sites;
- init = mod->state == MODULE_STATE_COMING;
-#endif
- }
-
- for (site = site_mod->sites;
- site < stop && static_call_key(site) == key; site++) {
- void *site_addr = static_call_addr(site);
-
- if (!init && static_call_is_init(site))
- continue;
-
- if (!kernel_text_address((unsigned long)site_addr)) {
- /*
- * This skips patching built-in __exit, which
- * is part of init_section_contains() but is
- * not part of kernel_text_address().
- *
- * Skipping built-in __exit is fine since it
- * will never be executed.
- */
- WARN_ONCE(!static_call_is_init(site),
- "can't patch static call site at %pS",
- site_addr);
- continue;
- }
-
- arch_static_call_transform(site_addr, NULL, func,
- static_call_is_tail(site));
- }
- }
-
-done:
- static_call_unlock();
- cpus_read_unlock();
-}
-EXPORT_SYMBOL_GPL(__static_call_update);
-
-static int __static_call_init(struct module *mod,
- struct static_call_site *start,
- struct static_call_site *stop)
-{
- struct static_call_site *site;
- struct static_call_key *key, *prev_key = NULL;
- struct static_call_mod *site_mod;
-
- if (start == stop)
- return 0;
-
- static_call_sort_entries(start, stop);
-
- for (site = start; site < stop; site++) {
- void *site_addr = static_call_addr(site);
-
- if ((mod && within_module_init((unsigned long)site_addr, mod)) ||
- (!mod && init_section_contains(site_addr, 1)))
- static_call_set_init(site);
-
- key = static_call_key(site);
- if (key != prev_key) {
- prev_key = key;
-
- /*
- * For vmlinux (!mod) avoid the allocation by storing
- * the sites pointer in the key itself. Also see
- * __static_call_update()'s @first.
- *
- * This allows architectures (eg. x86) to call
- * static_call_init() before memory allocation works.
- */
- if (!mod) {
- key->sites = site;
- key->type |= 1;
- goto do_transform;
- }
-
- site_mod = kzalloc(sizeof(*site_mod), GFP_KERNEL);
- if (!site_mod)
- return -ENOMEM;
-
- /*
- * When the key has a direct sites pointer, extract
- * that into an explicit struct static_call_mod, so we
- * can have a list of modules.
- */
- if (static_call_key_sites(key)) {
- site_mod->mod = NULL;
- site_mod->next = NULL;
- site_mod->sites = static_call_key_sites(key);
-
- key->mods = site_mod;
-
- site_mod = kzalloc(sizeof(*site_mod), GFP_KERNEL);
- if (!site_mod)
- return -ENOMEM;
- }
-
- site_mod->mod = mod;
- site_mod->sites = site;
- site_mod->next = static_call_key_next(key);
- key->mods = site_mod;
- }
-
-do_transform:
- arch_static_call_transform(site_addr, NULL, key->func,
- static_call_is_tail(site));
- }
-
- return 0;
-}
-
-static int addr_conflict(struct static_call_site *site, void *start, void *end)
-{
- unsigned long addr = (unsigned long)static_call_addr(site);
-
- if (addr <= (unsigned long)end &&
- addr + CALL_INSN_SIZE > (unsigned long)start)
- return 1;
-
- return 0;
-}
-
-static int __static_call_text_reserved(struct static_call_site *iter_start,
- struct static_call_site *iter_stop,
- void *start, void *end, bool init)
-{
- struct static_call_site *iter = iter_start;
-
- while (iter < iter_stop) {
- if (init || !static_call_is_init(iter)) {
- if (addr_conflict(iter, start, end))
- return 1;
- }
- iter++;
- }
-
- return 0;
-}
-
-#ifdef CONFIG_MODULES
-
-static int __static_call_mod_text_reserved(void *start, void *end)
-{
- struct module *mod;
- int ret;
-
- preempt_disable();
- mod = __module_text_address((unsigned long)start);
- WARN_ON_ONCE(__module_text_address((unsigned long)end) != mod);
- if (!try_module_get(mod))
- mod = NULL;
- preempt_enable();
-
- if (!mod)
- return 0;
-
- ret = __static_call_text_reserved(mod->static_call_sites,
- mod->static_call_sites + mod->num_static_call_sites,
- start, end, mod->state == MODULE_STATE_COMING);
-
- module_put(mod);
-
- return ret;
-}
-
-static unsigned long tramp_key_lookup(unsigned long addr)
-{
- struct static_call_tramp_key *start = __start_static_call_tramp_key;
- struct static_call_tramp_key *stop = __stop_static_call_tramp_key;
- struct static_call_tramp_key *tramp_key;
-
- for (tramp_key = start; tramp_key != stop; tramp_key++) {
- unsigned long tramp;
-
- tramp = (long)tramp_key->tramp + (long)&tramp_key->tramp;
- if (tramp == addr)
- return (long)tramp_key->key + (long)&tramp_key->key;
- }
-
- return 0;
-}
-
-static int static_call_add_module(struct module *mod)
-{
- struct static_call_site *start = mod->static_call_sites;
- struct static_call_site *stop = start + mod->num_static_call_sites;
- struct static_call_site *site;
-
- for (site = start; site != stop; site++) {
- unsigned long s_key = __static_call_key(site);
- unsigned long addr = s_key & ~STATIC_CALL_SITE_FLAGS;
- unsigned long key;
-
- /*
- * Is the key is exported, 'addr' points to the key, which
- * means modules are allowed to call static_call_update() on
- * it.
- *
- * Otherwise, the key isn't exported, and 'addr' points to the
- * trampoline so we need to lookup the key.
- *
- * We go through this dance to prevent crazy modules from
- * abusing sensitive static calls.
- */
- if (!kernel_text_address(addr))
- continue;
-
- key = tramp_key_lookup(addr);
- if (!key) {
- pr_warn("Failed to fixup __raw_static_call() usage at: %ps\n",
- static_call_addr(site));
- return -EINVAL;
- }
-
- key |= s_key & STATIC_CALL_SITE_FLAGS;
- site->key = key - (long)&site->key;
- }
-
- return __static_call_init(mod, start, stop);
-}
-
-static void static_call_del_module(struct module *mod)
-{
- struct static_call_site *start = mod->static_call_sites;
- struct static_call_site *stop = mod->static_call_sites +
- mod->num_static_call_sites;
- struct static_call_key *key, *prev_key = NULL;
- struct static_call_mod *site_mod, **prev;
- struct static_call_site *site;
-
- for (site = start; site < stop; site++) {
- key = static_call_key(site);
- if (key == prev_key)
- continue;
-
- prev_key = key;
-
- for (prev = &key->mods, site_mod = key->mods;
- site_mod && site_mod->mod != mod;
- prev = &site_mod->next, site_mod = site_mod->next)
- ;
-
- if (!site_mod)
- continue;
-
- *prev = site_mod->next;
- kfree(site_mod);
- }
-}
-
-static int static_call_module_notify(struct notifier_block *nb,
- unsigned long val, void *data)
-{
- struct module *mod = data;
- int ret = 0;
-
- cpus_read_lock();
- static_call_lock();
-
- switch (val) {
- case MODULE_STATE_COMING:
- ret = static_call_add_module(mod);
- if (ret) {
- WARN(1, "Failed to allocate memory for static calls");
- static_call_del_module(mod);
- }
- break;
- case MODULE_STATE_GOING:
- static_call_del_module(mod);
- break;
- }
-
- static_call_unlock();
- cpus_read_unlock();
-
- return notifier_from_errno(ret);
-}
-
-static struct notifier_block static_call_module_nb = {
- .notifier_call = static_call_module_notify,
-};
-
-#else
-
-static inline int __static_call_mod_text_reserved(void *start, void *end)
-{
- return 0;
-}
-
-#endif /* CONFIG_MODULES */
-
-int static_call_text_reserved(void *start, void *end)
-{
- bool init = system_state < SYSTEM_RUNNING;
- int ret = __static_call_text_reserved(__start_static_call_sites,
- __stop_static_call_sites, start, end, init);
-
- if (ret)
- return ret;
-
- return __static_call_mod_text_reserved(start, end);
-}
-
-int __init static_call_init(void)
-{
- int ret;
-
- if (static_call_initialized)
- return 0;
-
- cpus_read_lock();
- static_call_lock();
- ret = __static_call_init(NULL, __start_static_call_sites,
- __stop_static_call_sites);
- static_call_unlock();
- cpus_read_unlock();
-
- if (ret) {
- pr_err("Failed to allocate memory for static_call!\n");
- BUG();
- }
-
- static_call_initialized = true;
-
-#ifdef CONFIG_MODULES
- register_module_notifier(&static_call_module_nb);
-#endif
- return 0;
-}
-early_initcall(static_call_init);
long __static_call_return0(void)
{
return 0;
}
EXPORT_SYMBOL_GPL(__static_call_return0);
-
-#ifdef CONFIG_STATIC_CALL_SELFTEST
-
-static int func_a(int x)
-{
- return x+1;
-}
-
-static int func_b(int x)
-{
- return x+2;
-}
-
-DEFINE_STATIC_CALL(sc_selftest, func_a);
-
-static struct static_call_data {
- int (*func)(int);
- int val;
- int expect;
-} static_call_data [] __initdata = {
- { NULL, 2, 3 },
- { func_b, 2, 4 },
- { func_a, 2, 3 }
-};
-
-static int __init test_static_call_init(void)
-{
- int i;
-
- for (i = 0; i < ARRAY_SIZE(static_call_data); i++ ) {
- struct static_call_data *scd = &static_call_data[i];
-
- if (scd->func)
- static_call_update(sc_selftest, scd->func);
-
- WARN_ON(static_call(sc_selftest)(scd->val) != scd->expect);
- }
-
- return 0;
-}
-early_initcall(test_static_call_init);
-
-#endif /* CONFIG_STATIC_CALL_SELFTEST */
diff --git a/kernel/static_call_inline.c b/kernel/static_call_inline.c
new file mode 100644
index 000000000000..dc5665b62814
--- /dev/null
+++ b/kernel/static_call_inline.c
@@ -0,0 +1,543 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/init.h>
+#include <linux/static_call.h>
+#include <linux/bug.h>
+#include <linux/smp.h>
+#include <linux/sort.h>
+#include <linux/slab.h>
+#include <linux/module.h>
+#include <linux/cpu.h>
+#include <linux/processor.h>
+#include <asm/sections.h>
+
+extern struct static_call_site __start_static_call_sites[],
+ __stop_static_call_sites[];
+extern struct static_call_tramp_key __start_static_call_tramp_key[],
+ __stop_static_call_tramp_key[];
+
+static bool static_call_initialized;
+
+/* mutex to protect key modules/sites */
+static DEFINE_MUTEX(static_call_mutex);
+
+static void static_call_lock(void)
+{
+ mutex_lock(&static_call_mutex);
+}
+
+static void static_call_unlock(void)
+{
+ mutex_unlock(&static_call_mutex);
+}
+
+static inline void *static_call_addr(struct static_call_site *site)
+{
+ return (void *)((long)site->addr + (long)&site->addr);
+}
+
+static inline unsigned long __static_call_key(const struct static_call_site *site)
+{
+ return (long)site->key + (long)&site->key;
+}
+
+static inline struct static_call_key *static_call_key(const struct static_call_site *site)
+{
+ return (void *)(__static_call_key(site) & ~STATIC_CALL_SITE_FLAGS);
+}
+
+/* These assume the key is word-aligned. */
+static inline bool static_call_is_init(struct static_call_site *site)
+{
+ return __static_call_key(site) & STATIC_CALL_SITE_INIT;
+}
+
+static inline bool static_call_is_tail(struct static_call_site *site)
+{
+ return __static_call_key(site) & STATIC_CALL_SITE_TAIL;
+}
+
+static inline void static_call_set_init(struct static_call_site *site)
+{
+ site->key = (__static_call_key(site) | STATIC_CALL_SITE_INIT) -
+ (long)&site->key;
+}
+
+static int static_call_site_cmp(const void *_a, const void *_b)
+{
+ const struct static_call_site *a = _a;
+ const struct static_call_site *b = _b;
+ const struct static_call_key *key_a = static_call_key(a);
+ const struct static_call_key *key_b = static_call_key(b);
+
+ if (key_a < key_b)
+ return -1;
+
+ if (key_a > key_b)
+ return 1;
+
+ return 0;
+}
+
+static void static_call_site_swap(void *_a, void *_b, int size)
+{
+ long delta = (unsigned long)_a - (unsigned long)_b;
+ struct static_call_site *a = _a;
+ struct static_call_site *b = _b;
+ struct static_call_site tmp = *a;
+
+ a->addr = b->addr - delta;
+ a->key = b->key - delta;
+
+ b->addr = tmp.addr + delta;
+ b->key = tmp.key + delta;
+}
+
+static inline void static_call_sort_entries(struct static_call_site *start,
+ struct static_call_site *stop)
+{
+ sort(start, stop - start, sizeof(struct static_call_site),
+ static_call_site_cmp, static_call_site_swap);
+}
+
+static inline bool static_call_key_has_mods(struct static_call_key *key)
+{
+ return !(key->type & 1);
+}
+
+static inline struct static_call_mod *static_call_key_next(struct static_call_key *key)
+{
+ if (!static_call_key_has_mods(key))
+ return NULL;
+
+ return key->mods;
+}
+
+static inline struct static_call_site *static_call_key_sites(struct static_call_key *key)
+{
+ if (static_call_key_has_mods(key))
+ return NULL;
+
+ return (struct static_call_site *)(key->type & ~1);
+}
+
+void __static_call_update(struct static_call_key *key, void *tramp, void *func)
+{
+ struct static_call_site *site, *stop;
+ struct static_call_mod *site_mod, first;
+
+ cpus_read_lock();
+ static_call_lock();
+
+ if (key->func == func)
+ goto done;
+
+ key->func = func;
+
+ arch_static_call_transform(NULL, tramp, func, false);
+
+ /*
+ * If uninitialized, we'll not update the callsites, but they still
+ * point to the trampoline and we just patched that.
+ */
+ if (WARN_ON_ONCE(!static_call_initialized))
+ goto done;
+
+ first = (struct static_call_mod){
+ .next = static_call_key_next(key),
+ .mod = NULL,
+ .sites = static_call_key_sites(key),
+ };
+
+ for (site_mod = &first; site_mod; site_mod = site_mod->next) {
+ bool init = system_state < SYSTEM_RUNNING;
+ struct module *mod = site_mod->mod;
+
+ if (!site_mod->sites) {
+ /*
+ * This can happen if the static call key is defined in
+ * a module which doesn't use it.
+ *
+ * It also happens in the has_mods case, where the
+ * 'first' entry has no sites associated with it.
+ */
+ continue;
+ }
+
+ stop = __stop_static_call_sites;
+
+ if (mod) {
+#ifdef CONFIG_MODULES
+ stop = mod->static_call_sites +
+ mod->num_static_call_sites;
+ init = mod->state == MODULE_STATE_COMING;
+#endif
+ }
+
+ for (site = site_mod->sites;
+ site < stop && static_call_key(site) == key; site++) {
+ void *site_addr = static_call_addr(site);
+
+ if (!init && static_call_is_init(site))
+ continue;
+
+ if (!kernel_text_address((unsigned long)site_addr)) {
+ /*
+ * This skips patching built-in __exit, which
+ * is part of init_section_contains() but is
+ * not part of kernel_text_address().
+ *
+ * Skipping built-in __exit is fine since it
+ * will never be executed.
+ */
+ WARN_ONCE(!static_call_is_init(site),
+ "can't patch static call site at %pS",
+ site_addr);
+ continue;
+ }
+
+ arch_static_call_transform(site_addr, NULL, func,
+ static_call_is_tail(site));
+ }
+ }
+
+done:
+ static_call_unlock();
+ cpus_read_unlock();
+}
+EXPORT_SYMBOL_GPL(__static_call_update);
+
+static int __static_call_init(struct module *mod,
+ struct static_call_site *start,
+ struct static_call_site *stop)
+{
+ struct static_call_site *site;
+ struct static_call_key *key, *prev_key = NULL;
+ struct static_call_mod *site_mod;
+
+ if (start == stop)
+ return 0;
+
+ static_call_sort_entries(start, stop);
+
+ for (site = start; site < stop; site++) {
+ void *site_addr = static_call_addr(site);
+
+ if ((mod && within_module_init((unsigned long)site_addr, mod)) ||
+ (!mod && init_section_contains(site_addr, 1)))
+ static_call_set_init(site);
+
+ key = static_call_key(site);
+ if (key != prev_key) {
+ prev_key = key;
+
+ /*
+ * For vmlinux (!mod) avoid the allocation by storing
+ * the sites pointer in the key itself. Also see
+ * __static_call_update()'s @first.
+ *
+ * This allows architectures (eg. x86) to call
+ * static_call_init() before memory allocation works.
+ */
+ if (!mod) {
+ key->sites = site;
+ key->type |= 1;
+ goto do_transform;
+ }
+
+ site_mod = kzalloc(sizeof(*site_mod), GFP_KERNEL);
+ if (!site_mod)
+ return -ENOMEM;
+
+ /*
+ * When the key has a direct sites pointer, extract
+ * that into an explicit struct static_call_mod, so we
+ * can have a list of modules.
+ */
+ if (static_call_key_sites(key)) {
+ site_mod->mod = NULL;
+ site_mod->next = NULL;
+ site_mod->sites = static_call_key_sites(key);
+
+ key->mods = site_mod;
+
+ site_mod = kzalloc(sizeof(*site_mod), GFP_KERNEL);
+ if (!site_mod)
+ return -ENOMEM;
+ }
+
+ site_mod->mod = mod;
+ site_mod->sites = site;
+ site_mod->next = static_call_key_next(key);
+ key->mods = site_mod;
+ }
+
+do_transform:
+ arch_static_call_transform(site_addr, NULL, key->func,
+ static_call_is_tail(site));
+ }
+
+ return 0;
+}
+
+static int addr_conflict(struct static_call_site *site, void *start, void *end)
+{
+ unsigned long addr = (unsigned long)static_call_addr(site);
+
+ if (addr <= (unsigned long)end &&
+ addr + CALL_INSN_SIZE > (unsigned long)start)
+ return 1;
+
+ return 0;
+}
+
+static int __static_call_text_reserved(struct static_call_site *iter_start,
+ struct static_call_site *iter_stop,
+ void *start, void *end, bool init)
+{
+ struct static_call_site *iter = iter_start;
+
+ while (iter < iter_stop) {
+ if (init || !static_call_is_init(iter)) {
+ if (addr_conflict(iter, start, end))
+ return 1;
+ }
+ iter++;
+ }
+
+ return 0;
+}
+
+#ifdef CONFIG_MODULES
+
+static int __static_call_mod_text_reserved(void *start, void *end)
+{
+ struct module *mod;
+ int ret;
+
+ preempt_disable();
+ mod = __module_text_address((unsigned long)start);
+ WARN_ON_ONCE(__module_text_address((unsigned long)end) != mod);
+ if (!try_module_get(mod))
+ mod = NULL;
+ preempt_enable();
+
+ if (!mod)
+ return 0;
+
+ ret = __static_call_text_reserved(mod->static_call_sites,
+ mod->static_call_sites + mod->num_static_call_sites,
+ start, end, mod->state == MODULE_STATE_COMING);
+
+ module_put(mod);
+
+ return ret;
+}
+
+static unsigned long tramp_key_lookup(unsigned long addr)
+{
+ struct static_call_tramp_key *start = __start_static_call_tramp_key;
+ struct static_call_tramp_key *stop = __stop_static_call_tramp_key;
+ struct static_call_tramp_key *tramp_key;
+
+ for (tramp_key = start; tramp_key != stop; tramp_key++) {
+ unsigned long tramp;
+
+ tramp = (long)tramp_key->tramp + (long)&tramp_key->tramp;
+ if (tramp == addr)
+ return (long)tramp_key->key + (long)&tramp_key->key;
+ }
+
+ return 0;
+}
+
+static int static_call_add_module(struct module *mod)
+{
+ struct static_call_site *start = mod->static_call_sites;
+ struct static_call_site *stop = start + mod->num_static_call_sites;
+ struct static_call_site *site;
+
+ for (site = start; site != stop; site++) {
+ unsigned long s_key = __static_call_key(site);
+ unsigned long addr = s_key & ~STATIC_CALL_SITE_FLAGS;
+ unsigned long key;
+
+ /*
+ * Is the key is exported, 'addr' points to the key, which
+ * means modules are allowed to call static_call_update() on
+ * it.
+ *
+ * Otherwise, the key isn't exported, and 'addr' points to the
+ * trampoline so we need to lookup the key.
+ *
+ * We go through this dance to prevent crazy modules from
+ * abusing sensitive static calls.
+ */
+ if (!kernel_text_address(addr))
+ continue;
+
+ key = tramp_key_lookup(addr);
+ if (!key) {
+ pr_warn("Failed to fixup __raw_static_call() usage at: %ps\n",
+ static_call_addr(site));
+ return -EINVAL;
+ }
+
+ key |= s_key & STATIC_CALL_SITE_FLAGS;
+ site->key = key - (long)&site->key;
+ }
+
+ return __static_call_init(mod, start, stop);
+}
+
+static void static_call_del_module(struct module *mod)
+{
+ struct static_call_site *start = mod->static_call_sites;
+ struct static_call_site *stop = mod->static_call_sites +
+ mod->num_static_call_sites;
+ struct static_call_key *key, *prev_key = NULL;
+ struct static_call_mod *site_mod, **prev;
+ struct static_call_site *site;
+
+ for (site = start; site < stop; site++) {
+ key = static_call_key(site);
+ if (key == prev_key)
+ continue;
+
+ prev_key = key;
+
+ for (prev = &key->mods, site_mod = key->mods;
+ site_mod && site_mod->mod != mod;
+ prev = &site_mod->next, site_mod = site_mod->next)
+ ;
+
+ if (!site_mod)
+ continue;
+
+ *prev = site_mod->next;
+ kfree(site_mod);
+ }
+}
+
+static int static_call_module_notify(struct notifier_block *nb,
+ unsigned long val, void *data)
+{
+ struct module *mod = data;
+ int ret = 0;
+
+ cpus_read_lock();
+ static_call_lock();
+
+ switch (val) {
+ case MODULE_STATE_COMING:
+ ret = static_call_add_module(mod);
+ if (ret) {
+ WARN(1, "Failed to allocate memory for static calls");
+ static_call_del_module(mod);
+ }
+ break;
+ case MODULE_STATE_GOING:
+ static_call_del_module(mod);
+ break;
+ }
+
+ static_call_unlock();
+ cpus_read_unlock();
+
+ return notifier_from_errno(ret);
+}
+
+static struct notifier_block static_call_module_nb = {
+ .notifier_call = static_call_module_notify,
+};
+
+#else
+
+static inline int __static_call_mod_text_reserved(void *start, void *end)
+{
+ return 0;
+}
+
+#endif /* CONFIG_MODULES */
+
+int static_call_text_reserved(void *start, void *end)
+{
+ bool init = system_state < SYSTEM_RUNNING;
+ int ret = __static_call_text_reserved(__start_static_call_sites,
+ __stop_static_call_sites, start, end, init);
+
+ if (ret)
+ return ret;
+
+ return __static_call_mod_text_reserved(start, end);
+}
+
+int __init static_call_init(void)
+{
+ int ret;
+
+ if (static_call_initialized)
+ return 0;
+
+ cpus_read_lock();
+ static_call_lock();
+ ret = __static_call_init(NULL, __start_static_call_sites,
+ __stop_static_call_sites);
+ static_call_unlock();
+ cpus_read_unlock();
+
+ if (ret) {
+ pr_err("Failed to allocate memory for static_call!\n");
+ BUG();
+ }
+
+ static_call_initialized = true;
+
+#ifdef CONFIG_MODULES
+ register_module_notifier(&static_call_module_nb);
+#endif
+ return 0;
+}
+early_initcall(static_call_init);
+
+#ifdef CONFIG_STATIC_CALL_SELFTEST
+
+static int func_a(int x)
+{
+ return x+1;
+}
+
+static int func_b(int x)
+{
+ return x+2;
+}
+
+DEFINE_STATIC_CALL(sc_selftest, func_a);
+
+static struct static_call_data {
+ int (*func)(int);
+ int val;
+ int expect;
+} static_call_data [] __initdata = {
+ { NULL, 2, 3 },
+ { func_b, 2, 4 },
+ { func_a, 2, 3 }
+};
+
+static int __init test_static_call_init(void)
+{
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(static_call_data); i++ ) {
+ struct static_call_data *scd = &static_call_data[i];
+
+ if (scd->func)
+ static_call_update(sc_selftest, scd->func);
+
+ WARN_ON(static_call(sc_selftest)(scd->val) != scd->expect);
+ }
+
+ return 0;
+}
+early_initcall(test_static_call_init);
+
+#endif /* CONFIG_STATIC_CALL_SELFTEST */
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index 9bb54c0b3b2d..2c43e327a619 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -767,6 +767,7 @@ config USER_EVENTS
bool "User trace events"
select TRACING
select DYNAMIC_EVENTS
+ depends on BROKEN || COMPILE_TEST # API needs to be straighten out
help
User trace events are user-defined trace events that
can be used like an existing kernel trace event. User trace
diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index 7fa2ebc07f60..d8553f46caa2 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -2349,11 +2349,11 @@ kprobe_multi_link_handler(struct fprobe *fp, unsigned long entry_ip,
}
static int
-kprobe_multi_resolve_syms(const void *usyms, u32 cnt,
+kprobe_multi_resolve_syms(const void __user *usyms, u32 cnt,
unsigned long *addrs)
{
unsigned long addr, size;
- const char **syms;
+ const char __user **syms;
int err = -ENOMEM;
unsigned int i;
char *func;
diff --git a/kernel/trace/fgraph.c b/kernel/trace/fgraph.c
index 19028e072cdb..8f4fb328133a 100644
--- a/kernel/trace/fgraph.c
+++ b/kernel/trace/fgraph.c
@@ -7,6 +7,7 @@
*
* Highly modified by Steven Rostedt (VMware).
*/
+#include <linux/jump_label.h>
#include <linux/suspend.h>
#include <linux/ftrace.h>
#include <linux/slab.h>
@@ -23,25 +24,13 @@
#define ASSIGN_OPS_HASH(opsname, val)
#endif
-static bool kill_ftrace_graph;
+DEFINE_STATIC_KEY_FALSE(kill_ftrace_graph);
int ftrace_graph_active;
/* Both enabled by default (can be cleared by function_graph tracer flags */
static bool fgraph_sleep_time = true;
/**
- * ftrace_graph_is_dead - returns true if ftrace_graph_stop() was called
- *
- * ftrace_graph_stop() is called when a severe error is detected in
- * the function graph tracing. This function is called by the critical
- * paths of function graph to keep those paths from doing any more harm.
- */
-bool ftrace_graph_is_dead(void)
-{
- return kill_ftrace_graph;
-}
-
-/**
* ftrace_graph_stop - set to permanently disable function graph tracing
*
* In case of an error int function graph tracing, this is called
@@ -51,7 +40,7 @@ bool ftrace_graph_is_dead(void)
*/
void ftrace_graph_stop(void)
{
- kill_ftrace_graph = true;
+ static_branch_enable(&kill_ftrace_graph);
}
/* Add a function return address to the trace stack on thread info.*/
diff --git a/kernel/trace/fprobe.c b/kernel/trace/fprobe.c
index 8b2dd5b9dcd1..89d9f994ebb0 100644
--- a/kernel/trace/fprobe.c
+++ b/kernel/trace/fprobe.c
@@ -150,15 +150,15 @@ static int fprobe_init_rethook(struct fprobe *fp, int num)
fp->rethook = rethook_alloc((void *)fp, fprobe_exit_handler);
for (i = 0; i < size; i++) {
- struct rethook_node *node;
+ struct fprobe_rethook_node *node;
- node = kzalloc(sizeof(struct fprobe_rethook_node), GFP_KERNEL);
+ node = kzalloc(sizeof(*node), GFP_KERNEL);
if (!node) {
rethook_free(fp->rethook);
fp->rethook = NULL;
return -ENOMEM;
}
- rethook_add_node(fp->rethook, node);
+ rethook_add_node(fp->rethook, &node->node);
}
return 0;
}
@@ -215,7 +215,7 @@ int register_fprobe(struct fprobe *fp, const char *filter, const char *notfilter
* correctly calculate the total number of filtered symbols
* from both filter and notfilter.
*/
- hash = fp->ops.local_hash.filter_hash;
+ hash = rcu_access_pointer(fp->ops.local_hash.filter_hash);
if (WARN_ON_ONCE(!hash))
goto out;
diff --git a/kernel/trace/rethook.c b/kernel/trace/rethook.c
index ab463a4d2b23..b56833700d23 100644
--- a/kernel/trace/rethook.c
+++ b/kernel/trace/rethook.c
@@ -65,7 +65,7 @@ static void rethook_free_rcu(struct rcu_head *head)
*/
void rethook_free(struct rethook *rh)
{
- rcu_assign_pointer(rh->handler, NULL);
+ WRITE_ONCE(rh->handler, NULL);
call_rcu(&rh->rcu, rethook_free_rcu);
}
diff --git a/kernel/trace/trace_events_user.c b/kernel/trace/trace_events_user.c
index 8b3d241a31c2..706e1686b5eb 100644
--- a/kernel/trace/trace_events_user.c
+++ b/kernel/trace/trace_events_user.c
@@ -18,7 +18,12 @@
#include <linux/tracefs.h>
#include <linux/types.h>
#include <linux/uaccess.h>
+/* Reminder to move to uapi when everything works */
+#ifdef CONFIG_COMPILE_TEST
+#include <linux/user_events.h>
+#else
#include <uapi/linux/user_events.h>
+#endif
#include "trace.h"
#include "trace_dynevent.h"
@@ -42,9 +47,6 @@
#define MAX_FIELD_ARRAY_SIZE 1024
#define MAX_FIELD_ARG_NAME 256
-#define MAX_BPF_COPY_SIZE PAGE_SIZE
-#define MAX_STACK_BPF_DATA 512
-
static char *register_page_data;
static DEFINE_MUTEX(reg_mutex);
@@ -405,19 +407,6 @@ parse:
type[0] != 'u', FILTER_OTHER);
}
-static void user_event_parse_flags(struct user_event *user, char *flags)
-{
- char *flag;
-
- if (flags == NULL)
- return;
-
- while ((flag = strsep(&flags, ",")) != NULL) {
- if (strcmp(flag, "BPF_ITER") == 0)
- user->flags |= FLAG_BPF_ITER;
- }
-}
-
static int user_event_parse_fields(struct user_event *user, char *args)
{
char *field;
@@ -713,64 +702,14 @@ discard:
}
#ifdef CONFIG_PERF_EVENTS
-static void user_event_bpf(struct user_event *user, struct iov_iter *i)
-{
- struct user_bpf_context context;
- struct user_bpf_iter bpf_i;
- char fast_data[MAX_STACK_BPF_DATA];
- void *temp = NULL;
-
- if ((user->flags & FLAG_BPF_ITER) && iter_is_iovec(i)) {
- /* Raw iterator */
- context.data_type = USER_BPF_DATA_ITER;
- context.data_len = i->count;
- context.iter = &bpf_i;
-
- bpf_i.iov_offset = i->iov_offset;
- bpf_i.iov = i->iov;
- bpf_i.nr_segs = i->nr_segs;
- } else if (i->nr_segs == 1 && iter_is_iovec(i)) {
- /* Single buffer from user */
- context.data_type = USER_BPF_DATA_USER;
- context.data_len = i->count;
- context.udata = i->iov->iov_base + i->iov_offset;
- } else {
- /* Multi buffer from user */
- struct iov_iter copy = *i;
- size_t copy_size = min_t(size_t, i->count, MAX_BPF_COPY_SIZE);
-
- context.data_type = USER_BPF_DATA_KERNEL;
- context.kdata = fast_data;
-
- if (unlikely(copy_size > sizeof(fast_data))) {
- temp = kmalloc(copy_size, GFP_NOWAIT);
-
- if (temp)
- context.kdata = temp;
- else
- copy_size = sizeof(fast_data);
- }
-
- context.data_len = copy_nofault(context.kdata,
- copy_size, &copy);
- }
-
- trace_call_bpf(&user->call, &context);
-
- kfree(temp);
-}
-
/*
- * Writes the user supplied payload out to perf ring buffer or eBPF program.
+ * Writes the user supplied payload out to perf ring buffer.
*/
static void user_event_perf(struct user_event *user, struct iov_iter *i,
void *tpdata, bool *faulted)
{
struct hlist_head *perf_head;
- if (bpf_prog_array_valid(&user->call))
- user_event_bpf(user, i);
-
perf_head = this_cpu_ptr(user->call.perf_events);
if (perf_head && !hlist_empty(perf_head)) {
@@ -1136,8 +1075,6 @@ static int user_event_parse(char *name, char *args, char *flags,
user->tracepoint.name = name;
- user_event_parse_flags(user, flags);
-
ret = user_event_parse_fields(user, args);
if (ret)
@@ -1165,11 +1102,11 @@ static int user_event_parse(char *name, char *args, char *flags,
#endif
mutex_lock(&event_mutex);
+
ret = user_event_trace_register(user);
- mutex_unlock(&event_mutex);
if (ret)
- goto put_user;
+ goto put_user_lock;
user->index = index;
@@ -1181,8 +1118,12 @@ static int user_event_parse(char *name, char *args, char *flags,
set_bit(user->index, page_bitmap);
hash_add(register_table, &user->node, key);
+ mutex_unlock(&event_mutex);
+
*newuser = user;
return 0;
+put_user_lock:
+ mutex_unlock(&event_mutex);
put_user:
user_event_destroy_fields(user);
user_event_destroy_validators(user);
@@ -1575,9 +1516,6 @@ static int user_seq_show(struct seq_file *m, void *p)
busy++;
}
- if (flags & FLAG_BPF_ITER)
- seq_puts(m, " FLAG:BPF_ITER");
-
seq_puts(m, "\n");
active++;
}
diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index b62fd785b599..47cebef78532 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -1433,7 +1433,7 @@ __kretprobe_trace_func(struct trace_kprobe *tk, struct kretprobe_instance *ri,
fbuffer.regs = regs;
entry = fbuffer.entry = ring_buffer_event_data(fbuffer.event);
entry->func = (unsigned long)tk->rp.kp.addr;
- entry->ret_ip = (unsigned long)ri->ret_addr;
+ entry->ret_ip = get_kretprobe_retaddr(ri);
store_trace_args(&entry[1], &tk->tp, regs, sizeof(*entry), dsize);
trace_event_buffer_commit(&fbuffer);
@@ -1628,7 +1628,7 @@ kretprobe_perf_func(struct trace_kprobe *tk, struct kretprobe_instance *ri,
return;
entry->func = (unsigned long)tk->rp.kp.addr;
- entry->ret_ip = (unsigned long)ri->ret_addr;
+ entry->ret_ip = get_kretprobe_retaddr(ri);
store_trace_args(&entry[1], &tk->tp, regs, sizeof(*entry), dsize);
perf_trace_buf_submit(entry, size, rctx, call->event.type, 1, regs,
head, NULL);
diff --git a/kernel/watch_queue.c b/kernel/watch_queue.c
index 3990e4df3d7b..230038d4f908 100644
--- a/kernel/watch_queue.c
+++ b/kernel/watch_queue.c
@@ -370,6 +370,7 @@ static void __put_watch_queue(struct kref *kref)
for (i = 0; i < wqueue->nr_pages; i++)
__free_page(wqueue->notes[i]);
+ kfree(wqueue->notes);
bitmap_free(wqueue->notes_bitmap);
wfilter = rcu_access_pointer(wqueue->filter);
generated by cgit (git 2.34.1) at 2024-06-23 18:34:46 +0000