perf: split perf_trace_buf_prepare into alloc and update parts

split allows to move expensive update of 'struct trace_entry' to later phase.
Repurpose unused 1st argument of perf_tp_event() to indicate event type.

While splitting use temp variable 'rctx' instead of '*rctx' to avoid
unnecessary loads done by the compiler due to -fno-strict-aliasing

Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 20 insertions, 19 deletions

diff --git a/kernel/trace/trace_event_perf.c b/kernel/trace/trace_event_perf.c
index 7a68afca8249..5a927075977f 100644
--- a/kernel/trace/trace_event_perf.c
+++ b/kernel/trace/trace_event_perf.c
@@ -260,42 +260,43 @@ void perf_trace_del(struct perf_event *p_event, int flags)
         tp_event->class->reg(tp_event, TRACE_REG_PERF_DEL, p_event);
 }
 
-void *perf_trace_buf_prepare(int size, unsigned short type,
-                             struct pt_regs **regs, int *rctxp)
+void *perf_trace_buf_alloc(int size, struct pt_regs **regs, int *rctxp)
 {
-        struct trace_entry *entry;
-        unsigned long flags;
         char *raw_data;
-        int pc;
+        int rctx;
 
         BUILD_BUG_ON(PERF_MAX_TRACE_SIZE % sizeof(unsigned long));
 
         if (WARN_ONCE(size > PERF_MAX_TRACE_SIZE,
-                        "perf buffer not large enough"))
+                      "perf buffer not large enough"))
                 return NULL;
 
-        pc = preempt_count();
-
-        *rctxp = perf_swevent_get_recursion_context();
-        if (*rctxp < 0)
+        *rctxp = rctx = perf_swevent_get_recursion_context();
+        if (rctx < 0)
                 return NULL;
 
         if (regs)
-                *regs = this_cpu_ptr(&__perf_regs[*rctxp]);
-        raw_data = this_cpu_ptr(perf_trace_buf[*rctxp]);
+                *regs = this_cpu_ptr(&__perf_regs[rctx]);
+        raw_data = this_cpu_ptr(perf_trace_buf[rctx]);
 
         /* zero the dead bytes from align to not leak stack to user */
         memset(&raw_data[size - sizeof(u64)], 0, sizeof(u64));
+        return raw_data;
+}
+EXPORT_SYMBOL_GPL(perf_trace_buf_alloc);
+NOKPROBE_SYMBOL(perf_trace_buf_alloc);
+
+void perf_trace_buf_update(void *record, u16 type)
+{
+        struct trace_entry *entry = record;
+        int pc = preempt_count();
+        unsigned long flags;
 
-        entry = (struct trace_entry *)raw_data;
         local_save_flags(flags);
         tracing_generic_entry_update(entry, flags, pc);
         entry->type = type;
-
-        return raw_data;
 }
-EXPORT_SYMBOL_GPL(perf_trace_buf_prepare);
-NOKPROBE_SYMBOL(perf_trace_buf_prepare);
+NOKPROBE_SYMBOL(perf_trace_buf_update);
 
 #ifdef CONFIG_FUNCTION_TRACER
 static void
@@ -319,13 +320,13 @@ perf_ftrace_function_call(unsigned long ip, unsigned long parent_ip,
         memset(&regs, 0, sizeof(regs));
         perf_fetch_caller_regs(&regs);
 
-        entry = perf_trace_buf_prepare(ENTRY_SIZE, TRACE_FN, NULL, &rctx);
+        entry = perf_trace_buf_alloc(ENTRY_SIZE, NULL, &rctx);
         if (!entry)
                 return;
 
         entry->ip = ip;
         entry->parent_ip = parent_ip;
-        perf_trace_buf_submit(entry, ENTRY_SIZE, rctx, 0,
+        perf_trace_buf_submit(entry, ENTRY_SIZE, rctx, TRACE_FN,
                               1, &regs, head, NULL);
 
 #undef ENTRY_SIZE