Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-2.6

[pandora-kernel.git] / kernel / perf_event.c

diff --git a/kernel/perf_event.c b/kernel/perf_event.c
index 3472bb1..8e81a98 100644 (file)
--- a/kernel/perf_event.c
+++ b/kernel/perf_event.c
@@ -145,7 +145,8 @@ static struct srcu_struct pmus_srcu;
  */
 int sysctl_perf_event_paranoid __read_mostly = 1;
 
-int sysctl_perf_event_mlock __read_mostly = 512; /* 'free' kb per user */
+/* Minimum for 512 kiB + 1 user control page */
+int sysctl_perf_event_mlock __read_mostly = 512 + (PAGE_SIZE / 1024); /* 'free' kiB per user */
 
 /*
  * max perf event sample rate
@@ -363,6 +364,7 @@ void perf_cgroup_switch(struct task_struct *task, int mode)
                        }
 
                        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
@@ -941,6 +943,7 @@ static void perf_group_attach(struct perf_event *event)
 static void
 list_del_event(struct perf_event *event, struct perf_event_context *ctx)
 {
+       struct perf_cpu_context *cpuctx;
        /*
         * We can have double detach due to exit/hot-unplug + close.
         */
@@ -949,8 +952,17 @@ list_del_event(struct perf_event *event, struct perf_event_context *ctx)
 
        event->attach_state &= ~PERF_ATTACH_CONTEXT;
 
-       if (is_cgroup_event(event))
+       if (is_cgroup_event(event)) {
                ctx->nr_cgroups--;
+               cpuctx = __get_cpu_context(ctx);
+               /*
+                * if there are no more cgroup events
+                * then cler cgrp to avoid stale pointer
+                * in update_cgrp_time_from_cpuctx()
+                */
+               if (!ctx->nr_cgroups)
+                       cpuctx->cgrp = NULL;
+       }
 
        ctx->nr_events--;
        if (event->attr.inherit_stat)
@@ -2412,6 +2424,14 @@ static void perf_event_enable_on_exec(struct perf_event_context *ctx)
        if (!ctx || !ctx->nr_events)
                goto out;
 
+       /*
+        * We must ctxsw out cgroup events to avoid conflict
+        * when invoking perf_task_event_sched_in() later on
+        * in this function. Otherwise we end up trying to
+        * ctxswin cgroup events which are already scheduled
+        * in.
+        */
+       perf_cgroup_sched_out(current);
        task_ctx_sched_out(ctx, EVENT_ALL);
 
        raw_spin_lock(&ctx->lock);
@@ -2436,6 +2456,9 @@ static void perf_event_enable_on_exec(struct perf_event_context *ctx)
 
        raw_spin_unlock(&ctx->lock);
 
+       /*
+        * Also calls ctxswin for cgroup events, if any:
+        */
        perf_event_context_sched_in(ctx, ctx->task);
 out:
        local_irq_restore(flags);
@@ -6520,6 +6543,11 @@ SYSCALL_DEFINE5(perf_event_open,
                goto err_alloc;
        }
 
+       if (task) {
+               put_task_struct(task);
+               task = NULL;
+       }
+
        /*
         * Look up the group leader (we will attach this event to it):
         */