From mboxrd@z Thu Jan 1 00:00:00 1970 From: Daniel Borkmann Subject: [PATCH bpf-next v2 2/2] bpf, libbpf: use correct barriers in perf ring buffer walk Date: Fri, 19 Oct 2018 15:51:03 +0200 Message-ID: <20181019135103.3602-3-daniel@iogearbox.net> References: <20181019135103.3602-1-daniel@iogearbox.net> Cc: peterz@infradead.org, paulmck@linux.vnet.ibm.com, will.deacon@arm.com, acme@redhat.com, yhs@fb.com, john.fastabend@gmail.com, netdev@vger.kernel.org, Daniel Borkmann To: alexei.starovoitov@gmail.com Return-path: Received: from www62.your-server.de ([213.133.104.62]:41204 "EHLO www62.your-server.de" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1727014AbeJSV5Y (ORCPT ); Fri, 19 Oct 2018 17:57:24 -0400 In-Reply-To: <20181019135103.3602-1-daniel@iogearbox.net> Sender: netdev-owner@vger.kernel.org List-ID: Given libbpf is a generic library and not restricted to x86-64 only, the compiler barrier in bpf_perf_event_read_simple() after fetching the head needs to be replaced with smp_rmb() at minimum. Also, writing out the tail we should use WRITE_ONCE() to avoid store tearing. Now that we have the logic in place in ring_buffer_read_head() and ring_buffer_write_tail() helper also used by perf tool which would select the correct and best variant for a given architecture (e.g. x86-64 can avoid CPU barriers entirely), make use of these in order to fix bpf_perf_event_read_simple(). Fixes: d0cabbb021be ("tools: bpf: move the event reading loop to libbpf") Fixes: 39111695b1b8 ("samples: bpf: add bpf_perf_event_output example") Signed-off-by: Daniel Borkmann Cc: Peter Zijlstra Cc: "Paul E. McKenney" Cc: Will Deacon Cc: Arnaldo Carvalho de Melo --- tools/lib/bpf/libbpf.c | 10 ++++------ 1 file changed, 4 insertions(+), 6 deletions(-) diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index bd71efc..0c21355 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -27,6 +27,7 @@ #include #include #include +#include #include #include #include @@ -2418,13 +2419,12 @@ bpf_perf_event_read_simple(void *mem, unsigned long size, unsigned long page_size, void **buf, size_t *buf_len, bpf_perf_event_print_t fn, void *priv) { - volatile struct perf_event_mmap_page *header = mem; + struct perf_event_mmap_page *header = mem; + __u64 data_head = ring_buffer_read_head(header); __u64 data_tail = header->data_tail; - __u64 data_head = header->data_head; int ret = LIBBPF_PERF_EVENT_ERROR; void *base, *begin, *end; - asm volatile("" ::: "memory"); /* in real code it should be smp_rmb() */ if (data_head == data_tail) return LIBBPF_PERF_EVENT_CONT; @@ -2467,8 +2467,6 @@ bpf_perf_event_read_simple(void *mem, unsigned long size, data_tail += ehdr->size; } - __sync_synchronize(); /* smp_mb() */ - header->data_tail = data_tail; - + ring_buffer_write_tail(header, data_tail); return ret; } -- 2.9.5