3 files changed, 51 insertions, 16 deletions

diff --git a/kernel/events/core.c b/kernel/events/core.c
index fa0b2d4ad83c..661951ab8ae7 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -231,11 +231,29 @@ int perf_cpu_time_max_percent_handler(struct ctl_table *table, int write,
 #define NR_ACCUMULATED_SAMPLES 128
 static DEFINE_PER_CPU(u64, running_sample_length);
 
-void perf_sample_event_took(u64 sample_len_ns)
+static void perf_duration_warn(struct irq_work *w)
 {
+        u64 allowed_ns = ACCESS_ONCE(perf_sample_allowed_ns);
         u64 avg_local_sample_len;
         u64 local_samples_len;
+
+        local_samples_len = __get_cpu_var(running_sample_length);
+        avg_local_sample_len = local_samples_len/NR_ACCUMULATED_SAMPLES;
+
+        printk_ratelimited(KERN_WARNING
+                        "perf interrupt took too long (%lld > %lld), lowering "
+                        "kernel.perf_event_max_sample_rate to %d\n",
+                        avg_local_sample_len, allowed_ns >> 1,
+                        sysctl_perf_event_sample_rate);
+}
+
+static DEFINE_IRQ_WORK(perf_duration_work, perf_duration_warn);
+
+void perf_sample_event_took(u64 sample_len_ns)
+{
         u64 allowed_ns = ACCESS_ONCE(perf_sample_allowed_ns);
+        u64 avg_local_sample_len;
+        u64 local_samples_len;
 
         if (allowed_ns == 0)
                 return;
@@ -263,13 +281,14 @@ void perf_sample_event_took(u64 sample_len_ns)
         sysctl_perf_event_sample_rate = max_samples_per_tick * HZ;
         perf_sample_period_ns = NSEC_PER_SEC / sysctl_perf_event_sample_rate;
 
-        printk_ratelimited(KERN_WARNING
-                        "perf samples too long (%lld > %lld), lowering "
-                        "kernel.perf_event_max_sample_rate to %d\n",
-                        avg_local_sample_len, allowed_ns,
-                        sysctl_perf_event_sample_rate);
-
         update_perf_cpu_limits();
+
+        if (!irq_work_queue(&perf_duration_work)) {
+                early_printk("perf interrupt took too long (%lld > %lld), lowering "
+                             "kernel.perf_event_max_sample_rate to %d\n",
+                             avg_local_sample_len, allowed_ns >> 1,
+                             sysctl_perf_event_sample_rate);
+        }
 }
 
 static atomic64_t perf_event_id;
@@ -1714,7 +1733,7 @@ group_sched_in(struct perf_event *group_event,
                struct perf_event_context *ctx)
 {
         struct perf_event *event, *partial_group = NULL;
-        struct pmu *pmu = group_event->pmu;
+        struct pmu *pmu = ctx->pmu;
         u64 now = ctx->time;
         bool simulate = false;
 
@@ -2563,8 +2582,6 @@ static void perf_branch_stack_sched_in(struct task_struct *prev,
                 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);
@@ -6294,7 +6311,7 @@ static int perf_event_idx_default(struct perf_event *event)
  * Ensures all contexts with the same task_ctx_nr have the same
  * pmu_cpu_context too.
  */
-static void *find_pmu_context(int ctxn)
+static struct perf_cpu_context __percpu *find_pmu_context(int ctxn)
 {
         struct pmu *pmu;
 
diff --git a/kernel/irq_work.c b/kernel/irq_work.c
index 55fcce6065cf..a82170e2fa78 100644
--- a/kernel/irq_work.c
+++ b/kernel/irq_work.c
@@ -61,11 +61,11 @@ void __weak arch_irq_work_raise(void)
  *
  * Can be re-enqueued while the callback is still in progress.
  */
-void irq_work_queue(struct irq_work *work)
+bool irq_work_queue(struct irq_work *work)
 {
         /* Only queue if not already pending */
         if (!irq_work_claim(work))
-                return;
+                return false;
 
         /* Queue the entry and raise the IPI if needed. */
         preempt_disable();
@@ -83,6 +83,8 @@ void irq_work_queue(struct irq_work *work)
         }
 
         preempt_enable();
+
+        return true;
 }
 EXPORT_SYMBOL_GPL(irq_work_queue);
 
diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c
index e854f420e033..c894614de14d 100644
--- a/kernel/trace/trace_event_perf.c
+++ b/kernel/trace/trace_event_perf.c
@@ -31,9 +31,25 @@ static int perf_trace_event_perm(struct ftrace_event_call *tp_event,
         }
 
         /* The ftrace function trace is allowed only for root. */
-        if (ftrace_event_is_function(tp_event) &&
-            perf_paranoid_tracepoint_raw() && !capable(CAP_SYS_ADMIN))
-                return -EPERM;
+        if (ftrace_event_is_function(tp_event)) {
+                if (perf_paranoid_tracepoint_raw() && !capable(CAP_SYS_ADMIN))
+                        return -EPERM;
+
+                /*
+                 * We don't allow user space callchains for  function trace
+                 * event, due to issues with page faults while tracing page
+                 * fault handler and its overall trickiness nature.
+                 */
+                if (!p_event->attr.exclude_callchain_user)
+                        return -EINVAL;
+
+                /*
+                 * Same reason to disable user stack dump as for user space
+                 * callchains above.
+                 */
+                if (p_event->attr.sample_type & PERF_SAMPLE_STACK_USER)
+                        return -EINVAL;
+        }
 
         /* No tracing, just counting, so no obvious leak */
         if (!(p_event->attr.sample_type & PERF_SAMPLE_RAW))