[PATCH net-next 1/4] u64_stats: Introduce u64_stats_copy()

The following (anti-)pattern was observed in the code tree:

        do {
                start = u64_stats_fetch_begin(&pstats->syncp);
                memcpy(&temp, &pstats->stats, sizeof(temp));
        } while (u64_stats_fetch_retry(&pstats->syncp, start));

On 64bit arches, struct u64_stats_sync is empty and provides no help
against load/store tearing, especially for memcpy(), for which arches may
provide their highly-optimized implements.

In theory the affected code should convert to u64_stats_t, or use
READ_ONCE()/WRITE_ONCE() properly.

However since there are needs to copy chunks of statistics, instead of
writing loops at random places, we provide a safe memcpy() variant for
u64_stats.

Signed-off-by: David Yang <[email protected]>
---
 include/linux/u64_stats_sync.h | 15 +++++++++++++++
 1 file changed, 15 insertions(+)

diff --git a/include/linux/u64_stats_sync.h b/include/linux/u64_stats_sync.h
index 457879938fc1..849ff6e159c6 100644
--- a/include/linux/u64_stats_sync.h
+++ b/include/linux/u64_stats_sync.h
@@ -79,6 +79,14 @@ static inline u64 u64_stats_read(const u64_stats_t *p)
 	return local64_read(&p->v);
 }
 
+static inline void *u64_stats_copy(void *dst, const void *src, size_t len)
+{
+	BUILD_BUG_ON(len % sizeof(u64_stats_t));
+	for (size_t i = 0; i < len / sizeof(u64_stats_t); i++)
+		((u64 *)dst)[i] = local64_read(&((local64_t *)src)[i]);
+	return dst;
+}
+
 static inline void u64_stats_set(u64_stats_t *p, u64 val)
 {
 	local64_set(&p->v, val);
@@ -110,6 +118,7 @@ static inline bool __u64_stats_fetch_retry(const struct u64_stats_sync *syncp,
 }
 
 #else /* 64 bit */
+#include <linux/string.h>
 
 typedef struct {
 	u64		v;
@@ -120,6 +129,12 @@ static inline u64 u64_stats_read(const u64_stats_t *p)
 	return p->v;
 }
 
+static inline void *u64_stats_copy(void *dst, const void *src, size_t len)
+{
+	BUILD_BUG_ON(len % sizeof(u64_stats_t));
+	return memcpy(dst, src, len);
+}
+
 static inline void u64_stats_set(u64_stats_t *p, u64 val)
 {
 	p->v = val;
-- 
2.51.0