From: Sasha Levin <sashal@kernel.org>
To: linux-kernel@vger.kernel.org, stable@vger.kernel.org
Cc: Eric Dumazet <edumazet@google.com>,
"David S . Miller" <davem@davemloft.net>,
Sasha Levin <sashal@kernel.org>,
kuba@kernel.org, pabeni@redhat.com, imagedong@tencent.com,
bigeasy@linutronix.de, kuniyu@amazon.com, petrm@nvidia.com,
netdev@vger.kernel.org
Subject: [PATCH AUTOSEL 5.10 25/39] net: add atomic_long_t to net_device_stats fields
Date: Sun, 18 Dec 2022 11:15:45 -0500 [thread overview]
Message-ID: <20221218161559.932604-25-sashal@kernel.org> (raw)
In-Reply-To: <20221218161559.932604-1-sashal@kernel.org>
From: Eric Dumazet <edumazet@google.com>
[ Upstream commit 6c1c5097781f563b70a81683ea6fdac21637573b ]
Long standing KCSAN issues are caused by data-race around
some dev->stats changes.
Most performance critical paths already use per-cpu
variables, or per-queue ones.
It is reasonable (and more correct) to use atomic operations
for the slow paths.
This patch adds an union for each field of net_device_stats,
so that we can convert paths that are not yet protected
by a spinlock or a mutex.
netdev_stats_to_stats64() no longer has an #if BITS_PER_LONG==64
Note that the memcpy() we were using on 64bit arches
had no provision to avoid load-tearing,
while atomic_long_read() is providing the needed protection
at no cost.
Signed-off-by: Eric Dumazet <edumazet@google.com>
Signed-off-by: David S. Miller <davem@davemloft.net>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
include/linux/netdevice.h | 58 +++++++++++++++++++++++----------------
include/net/dst.h | 5 ++--
net/core/dev.c | 14 ++--------
3 files changed, 40 insertions(+), 37 deletions(-)
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index ef75567efd27..b478a16ef284 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -166,31 +166,38 @@ static inline bool dev_xmit_complete(int rc)
* (unsigned long) so they can be read and written atomically.
*/
+#define NET_DEV_STAT(FIELD) \
+ union { \
+ unsigned long FIELD; \
+ atomic_long_t __##FIELD; \
+ }
+
struct net_device_stats {
- unsigned long rx_packets;
- unsigned long tx_packets;
- unsigned long rx_bytes;
- unsigned long tx_bytes;
- unsigned long rx_errors;
- unsigned long tx_errors;
- unsigned long rx_dropped;
- unsigned long tx_dropped;
- unsigned long multicast;
- unsigned long collisions;
- unsigned long rx_length_errors;
- unsigned long rx_over_errors;
- unsigned long rx_crc_errors;
- unsigned long rx_frame_errors;
- unsigned long rx_fifo_errors;
- unsigned long rx_missed_errors;
- unsigned long tx_aborted_errors;
- unsigned long tx_carrier_errors;
- unsigned long tx_fifo_errors;
- unsigned long tx_heartbeat_errors;
- unsigned long tx_window_errors;
- unsigned long rx_compressed;
- unsigned long tx_compressed;
+ NET_DEV_STAT(rx_packets);
+ NET_DEV_STAT(tx_packets);
+ NET_DEV_STAT(rx_bytes);
+ NET_DEV_STAT(tx_bytes);
+ NET_DEV_STAT(rx_errors);
+ NET_DEV_STAT(tx_errors);
+ NET_DEV_STAT(rx_dropped);
+ NET_DEV_STAT(tx_dropped);
+ NET_DEV_STAT(multicast);
+ NET_DEV_STAT(collisions);
+ NET_DEV_STAT(rx_length_errors);
+ NET_DEV_STAT(rx_over_errors);
+ NET_DEV_STAT(rx_crc_errors);
+ NET_DEV_STAT(rx_frame_errors);
+ NET_DEV_STAT(rx_fifo_errors);
+ NET_DEV_STAT(rx_missed_errors);
+ NET_DEV_STAT(tx_aborted_errors);
+ NET_DEV_STAT(tx_carrier_errors);
+ NET_DEV_STAT(tx_fifo_errors);
+ NET_DEV_STAT(tx_heartbeat_errors);
+ NET_DEV_STAT(tx_window_errors);
+ NET_DEV_STAT(rx_compressed);
+ NET_DEV_STAT(tx_compressed);
};
+#undef NET_DEV_STAT
#include <linux/cache.h>
@@ -5256,4 +5263,9 @@ do { \
extern struct net_device *blackhole_netdev;
+/* Note: Avoid these macros in fast path, prefer per-cpu or per-queue counters. */
+#define DEV_STATS_INC(DEV, FIELD) atomic_long_inc(&(DEV)->stats.__##FIELD)
+#define DEV_STATS_ADD(DEV, FIELD, VAL) \
+ atomic_long_add((VAL), &(DEV)->stats.__##FIELD)
+
#endif /* _LINUX_NETDEVICE_H */
diff --git a/include/net/dst.h b/include/net/dst.h
index acd15c544cf3..ae2cf57d796b 100644
--- a/include/net/dst.h
+++ b/include/net/dst.h
@@ -356,9 +356,8 @@ static inline void __skb_tunnel_rx(struct sk_buff *skb, struct net_device *dev,
static inline void skb_tunnel_rx(struct sk_buff *skb, struct net_device *dev,
struct net *net)
{
- /* TODO : stats should be SMP safe */
- dev->stats.rx_packets++;
- dev->stats.rx_bytes += skb->len;
+ DEV_STATS_INC(dev, rx_packets);
+ DEV_STATS_ADD(dev, rx_bytes, skb->len);
__skb_tunnel_rx(skb, dev, net);
}
diff --git a/net/core/dev.c b/net/core/dev.c
index 34b5aab42b91..5afe56e8e763 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -10320,24 +10320,16 @@ void netdev_run_todo(void)
void netdev_stats_to_stats64(struct rtnl_link_stats64 *stats64,
const struct net_device_stats *netdev_stats)
{
-#if BITS_PER_LONG == 64
- BUILD_BUG_ON(sizeof(*stats64) < sizeof(*netdev_stats));
- memcpy(stats64, netdev_stats, sizeof(*netdev_stats));
- /* zero out counters that only exist in rtnl_link_stats64 */
- memset((char *)stats64 + sizeof(*netdev_stats), 0,
- sizeof(*stats64) - sizeof(*netdev_stats));
-#else
- size_t i, n = sizeof(*netdev_stats) / sizeof(unsigned long);
- const unsigned long *src = (const unsigned long *)netdev_stats;
+ size_t i, n = sizeof(*netdev_stats) / sizeof(atomic_long_t);
+ const atomic_long_t *src = (atomic_long_t *)netdev_stats;
u64 *dst = (u64 *)stats64;
BUILD_BUG_ON(n > sizeof(*stats64) / sizeof(u64));
for (i = 0; i < n; i++)
- dst[i] = src[i];
+ dst[i] = atomic_long_read(&src[i]);
/* zero out counters that only exist in rtnl_link_stats64 */
memset((char *)stats64 + n * sizeof(u64), 0,
sizeof(*stats64) - n * sizeof(u64));
-#endif
}
EXPORT_SYMBOL(netdev_stats_to_stats64);
--
2.35.1
next prev parent reply other threads:[~2022-12-18 16:49 UTC|newest]
Thread overview: 16+ messages / expand[flat|nested] mbox.gz Atom feed top
[not found] <20221218161559.932604-1-sashal@kernel.org>
2022-12-18 16:15 ` [PATCH AUTOSEL 5.10 02/39] brcmfmac: return error when getting invalid max_flowrings from dongle Sasha Levin
2022-12-18 16:15 ` [PATCH AUTOSEL 5.10 03/39] wifi: ath9k: verify the expected usb_endpoints are present Sasha Levin
2022-12-18 16:15 ` [PATCH AUTOSEL 5.10 04/39] wifi: ar5523: Fix use-after-free on ar5523_cmd() timed out Sasha Levin
2022-12-18 16:15 ` [PATCH AUTOSEL 5.10 08/39] qed (gcc13): use u16 for fid to be big enough Sasha Levin
2022-12-18 16:15 ` [PATCH AUTOSEL 5.10 09/39] bpf: make sure skb->len != 0 when redirecting to a tunneling device Sasha Levin
2022-12-18 16:15 ` [PATCH AUTOSEL 5.10 10/39] net: ethernet: ti: Fix return type of netcp_ndo_start_xmit() Sasha Levin
2022-12-18 16:15 ` [PATCH AUTOSEL 5.10 11/39] hamradio: baycom_epp: Fix return type of baycom_send_packet() Sasha Levin
2022-12-18 16:15 ` [PATCH AUTOSEL 5.10 12/39] wifi: brcmfmac: Fix potential shift-out-of-bounds in brcmf_fw_alloc_request() Sasha Levin
2022-12-18 16:15 ` [PATCH AUTOSEL 5.10 13/39] igb: Do not free q_vector unless new one was allocated Sasha Levin
2022-12-18 16:15 ` [PATCH AUTOSEL 5.10 16/39] s390/ctcm: Fix return type of ctc{mp,}m_tx() Sasha Levin
2022-12-18 16:15 ` [PATCH AUTOSEL 5.10 17/39] s390/netiucv: Fix return type of netiucv_tx() Sasha Levin
2022-12-18 16:15 ` [PATCH AUTOSEL 5.10 18/39] s390/lcs: Fix return type of lcs_start_xmit() Sasha Levin
2022-12-18 16:15 ` Sasha Levin [this message]
2022-12-18 16:15 ` [PATCH AUTOSEL 5.10 26/39] mrp: introduce active flags to prevent UAF when applicant uninit Sasha Levin
2022-12-18 16:15 ` [PATCH AUTOSEL 5.10 27/39] ppp: associate skb with a device at tx Sasha Levin
2022-12-18 16:15 ` [PATCH AUTOSEL 5.10 29/39] ethtool: avoiding integer overflow in ethtool_phys_id() Sasha Levin
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=20221218161559.932604-25-sashal@kernel.org \
--to=sashal@kernel.org \
--cc=bigeasy@linutronix.de \
--cc=davem@davemloft.net \
--cc=edumazet@google.com \
--cc=imagedong@tencent.com \
--cc=kuba@kernel.org \
--cc=kuniyu@amazon.com \
--cc=linux-kernel@vger.kernel.org \
--cc=netdev@vger.kernel.org \
--cc=pabeni@redhat.com \
--cc=petrm@nvidia.com \
--cc=stable@vger.kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).