bpf, libbpf: use correct barriers in perf ring buffer walk

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 <daniel@iogearbox.net>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: "Paul E. McKenney" <paulmck@linux.vnet.ibm.com>
Cc: Will Deacon <will.deacon@arm.com>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>

1 files changed, 4 insertions, 6 deletions

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index bd71efcc53be..0c21355f04a7 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -27,6 +27,7 @@
 #include <linux/list.h>
 #include <linux/limits.h>
 #include <linux/perf_event.h>
+#include <linux/ring_buffer.h>
 #include <sys/stat.h>
 #include <sys/types.h>
 #include <sys/vfs.h>
@@ -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;
 }