[PATCH bpf-next 3/3] bpf, libbpf: use proper barriers in perf ring buffer walk

[Daniel Borkmann]

Add bpf_perf_read_head() and bpf_perf_write_tail() helpers to make it
more clear in what context barriers are used here, and use smp_rmb()
as well as smp_mb() barriers. Given libbpf is not restricted to x86-64
only, the compiler barrier needs to be replaced with smp_rmb(). Also
the __sync_synchronize() emits mfence whereas faster lock + add can
be used on x86-64 via smp_mb().

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 <dan...@iogearbox.net>
---
 tools/lib/bpf/libbpf.c | 25 +++++++++++++++++++------
 1 file changed, 19 insertions(+), 6 deletions(-)

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index bd71efc..e8ae8db 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -20,6 +20,7 @@
 #include <fcntl.h>
 #include <errno.h>
 #include <asm/unistd.h>
+#include <asm/barrier.h>
 #include <linux/err.h>
 #include <linux/kernel.h>
 #include <linux/bpf.h>
@@ -2413,18 +2414,32 @@ int bpf_prog_load_xattr(const struct bpf_prog_load_attr 
*attr,
        return 0;
 }
 
+static __u64 bpf_perf_read_head(struct perf_event_mmap_page *header)
+{
+       __u64 data_head = READ_ONCE(header->data_head);
+
+       smp_rmb();
+       return data_head;
+}
+
+static void bpf_perf_write_tail(struct perf_event_mmap_page *header,
+                               __u64 data_tail)
+{
+       smp_mb();
+       header->data_tail = data_tail;
+}
+
 enum bpf_perf_event_ret
 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 = bpf_perf_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 +2482,6 @@ bpf_perf_event_read_simple(void *mem, unsigned long size,
                data_tail += ehdr->size;
        }
 
-       __sync_synchronize(); /* smp_mb() */
-       header->data_tail = data_tail;
-
+       bpf_perf_write_tail(header, data_tail);
        return ret;
 }
-- 
2.9.5