perf: Synchronously free aux pages in case of allocation failure

We are currently using asynchronous deallocation in the error path in
AUX mmap code, which is unnecessary and also presents a problem for users
that wish to probe for the biggest possible buffer size they can get:
they'll get -EINVAL on all subsequent attemts to allocate a smaller
buffer before the asynchronous deallocation callback frees up the pages
from the previous unsuccessful attempt.

Currently, gdb does that for allocating AUX buffers for Intel PT traces.
More specifically, overwrite mode of AUX pmus that don't support hardware
sg (some implementations of Intel PT, for instance) is limited to only
one contiguous high order allocation for its buffer and there is no way
of knowing its size without trying.

This patch changes error path freeing to be synchronous as there won't
be any contenders for the AUX pages at that point.

Reported-by: Markus Metzger <markus.t.metzger@intel.com>
Signed-off-by: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Stephane Eranian <eranian@google.com>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: Vince Weaver <vincent.weaver@maine.edu>
Cc: vince@deater.net
Link: http://lkml.kernel.org/r/1453216469-9509-1-git-send-email-alexander.shishkin@linux.intel.com
Signed-off-by: Ingo Molnar <mingo@kernel.org>

diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c
index adfdc0536117c1f10bf8f0dd8014798011e1f855..1faad2cfdb9e4572c91431e4b11941266e23a231 100644 (file)
--- a/kernel/events/ring_buffer.c
+++ b/kernel/events/ring_buffer.c
@@ -459,6 +459,25 @@ static void rb_free_aux_page(struct ring_buffer *rb, int idx)
        __free_page(page);
 }
 
+static void __rb_free_aux(struct ring_buffer *rb)
+{
+       int pg;
+
+       if (rb->aux_priv) {
+               rb->free_aux(rb->aux_priv);
+               rb->free_aux = NULL;
+               rb->aux_priv = NULL;
+       }
+
+       if (rb->aux_nr_pages) {
+               for (pg = 0; pg < rb->aux_nr_pages; pg++)
+                       rb_free_aux_page(rb, pg);
+
+               kfree(rb->aux_pages);
+               rb->aux_nr_pages = 0;
+       }
+}
+
 int rb_alloc_aux(struct ring_buffer *rb, struct perf_event *event,
                 pgoff_t pgoff, int nr_pages, long watermark, int flags)
 {
@@ -547,30 +566,11 @@ out:
        if (!ret)
                rb->aux_pgoff = pgoff;
        else
-               rb_free_aux(rb);
+               __rb_free_aux(rb);
 
        return ret;
 }
 
-static void __rb_free_aux(struct ring_buffer *rb)
-{
-       int pg;
-
-       if (rb->aux_priv) {
-               rb->free_aux(rb->aux_priv);
-               rb->free_aux = NULL;
-               rb->aux_priv = NULL;
-       }
-
-       if (rb->aux_nr_pages) {
-               for (pg = 0; pg < rb->aux_nr_pages; pg++)
-                       rb_free_aux_page(rb, pg);
-
-               kfree(rb->aux_pages);
-               rb->aux_nr_pages = 0;
-       }
-}
-
 void rb_free_aux(struct ring_buffer *rb)
 {
        if (atomic_dec_and_test(&rb->aux_refcount))