perf, trace: Optimize tracepoints by using per-tracepoint-per-cpu hlist to track events

Avoid the swevent hash-table by using per-tracepoint
hlists.

Also, avoid conditionals on the fast path by ordering
with probe unregister so that we should never get on
the callback path without the data being there.

Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
Cc: Paul Mackerras <paulus@samba.org>
Cc: Mike Galbraith <efault@gmx.de>
Cc: Steven Rostedt <rostedt@goodmis.org>
LKML-Reference: <20100521090710.473188012@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

1 files changed, 6 insertions, 3 deletions

diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
index 20c96de0aea0..4681f60dac00 100644
--- a/kernel/trace/trace_kprobe.c
+++ b/kernel/trace/trace_kprobe.c
@@ -1341,6 +1341,7 @@ static __kprobes void kprobe_perf_func(struct kprobe *kp,
         struct trace_probe *tp = container_of(kp, struct trace_probe, rp.kp);
         struct ftrace_event_call *call = &tp->call;
         struct kprobe_trace_entry_head *entry;
+        struct hlist_head *head;
         u8 *data;
         int size, __size, i;
         int rctx;
@@ -1361,7 +1362,8 @@ static __kprobes void kprobe_perf_func(struct kprobe *kp,
         for (i = 0; i < tp->nr_args; i++)
                 call_fetch(&tp->args[i].fetch, regs, data + tp->args[i].offset);
 
-        perf_trace_buf_submit(entry, size, rctx, entry->ip, 1, regs, call->perf_data);
+        head = per_cpu_ptr(call->perf_events, smp_processor_id());
+        perf_trace_buf_submit(entry, size, rctx, entry->ip, 1, regs, head);
 }
 
 /* Kretprobe profile handler */
@@ -1371,6 +1373,7 @@ static __kprobes void kretprobe_perf_func(struct kretprobe_instance *ri,
         struct trace_probe *tp = container_of(ri->rp, struct trace_probe, rp);
         struct ftrace_event_call *call = &tp->call;
         struct kretprobe_trace_entry_head *entry;
+        struct hlist_head *head;
         u8 *data;
         int size, __size, i;
         int rctx;
@@ -1392,8 +1395,8 @@ static __kprobes void kretprobe_perf_func(struct kretprobe_instance *ri,
         for (i = 0; i < tp->nr_args; i++)
                 call_fetch(&tp->args[i].fetch, regs, data + tp->args[i].offset);
 
-        perf_trace_buf_submit(entry, size, rctx, entry->ret_ip, 1,
-                              regs, call->perf_data);
+        head = per_cpu_ptr(call->perf_events, smp_processor_id());
+        perf_trace_buf_submit(entry, size, rctx, entry->ret_ip, 1, regs, head);
 }
 
 static int probe_perf_enable(struct ftrace_event_call *call)