[PATCH net-next 3/3] net: add READ_ONCE()/WRITE_ONCE() annotations for dev->prio_tc_map

[Eric Dumazet <edumazet@google.com>]

Concurrent fast-path readers access dev->prio_tc_map (e.g. via
skb_tx_hash(), netdev_get_prio_tc_map(), and qdiscs) while writers
update entries in dev->prio_tc_map or reset/clear the map via
netdev_reset_tc() and netdev_unbind_sb_channel().

Furthermore, memset() in netdev_reset_tc() and
netdev_unbind_sb_channel() provides no guarantee of performing
atomic word/byte stores.

Add READ_ONCE() and WRITE_ONCE() annotations to netdev_get_prio_tc_map()
and netdev_set_prio_tc_map(), replace memset() in dev.c with explicit
WRITE_ONCE() loops, and update direct array accesses in qdiscs to use
netdev_get_prio_tc_map().

Signed-off-by: Eric Dumazet <edumazet@google.com>
---
 include/linux/netdevice.h  | 4 ++--
 net/core/dev.c             | 6 ++++--
 net/sched/sch_mqprio_lib.c | 3 ++-
 net/sched/sch_taprio.c     | 2 +-
 4 files changed, 9 insertions(+), 6 deletions(-)

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index db0002bd68f90fa4dd087edabc11549bc8ee0f66..de307c01d33eb8835bdbe32118c2fc086e53a51c 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -2671,7 +2671,7 @@ static inline bool netif_elide_gro(const struct net_device *dev)
 static inline
 int netdev_get_prio_tc_map(const struct net_device *dev, u32 prio)
 {
-	return dev->prio_tc_map[prio & TC_BITMASK];
+	return READ_ONCE(dev->prio_tc_map[prio & TC_BITMASK]);
 }
 
 static inline
@@ -2680,7 +2680,7 @@ int netdev_set_prio_tc_map(struct net_device *dev, u8 prio, u8 tc)
 	if (tc >= READ_ONCE(dev->num_tc))
 		return -EINVAL;
 
-	dev->prio_tc_map[prio & TC_BITMASK] = tc & TC_BITMASK;
+	WRITE_ONCE(dev->prio_tc_map[prio & TC_BITMASK], tc & TC_BITMASK);
 	return 0;
 }
 
diff --git a/net/core/dev.c b/net/core/dev.c
index 8ffae11d272e979bab5b64f4d912d3d97f738d48..d52285ac01a54fdafa63703f1af134e19d028ffd 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -3124,7 +3124,8 @@ void netdev_reset_tc(struct net_device *dev)
 	WRITE_ONCE(dev->num_tc, 0);
 	for (i = 0; i < TC_MAX_QUEUE; i++)
 		WRITE_ONCE(dev->tc_to_txq[i].combined, 0);
-	memset(dev->prio_tc_map, 0, sizeof(dev->prio_tc_map));
+	for (i = 0; i <= TC_BITMASK; i++)
+		WRITE_ONCE(dev->prio_tc_map[i], 0);
 }
 EXPORT_SYMBOL(netdev_reset_tc);
 
@@ -3172,7 +3173,8 @@ void netdev_unbind_sb_channel(struct net_device *dev,
 #endif
 	for (i = 0; i < TC_MAX_QUEUE; i++)
 		WRITE_ONCE(sb_dev->tc_to_txq[i].combined, 0);
-	memset(sb_dev->prio_tc_map, 0, sizeof(sb_dev->prio_tc_map));
+	for (i = 0; i <= TC_BITMASK; i++)
+		WRITE_ONCE(sb_dev->prio_tc_map[i], 0);
 
 	while (txq-- != &dev->_tx[0]) {
 		if (txq->sb_dev == sb_dev)
diff --git a/net/sched/sch_mqprio_lib.c b/net/sched/sch_mqprio_lib.c
index b60e130c70781479eed0ea5a02d01197f03f4895..888935e34d4381f85aaf4c97cf9c4bacb93e13f1 100644
--- a/net/sched/sch_mqprio_lib.c
+++ b/net/sched/sch_mqprio_lib.c
@@ -105,7 +105,8 @@ void mqprio_qopt_reconstruct(struct net_device *dev, struct tc_mqprio_qopt *qopt
 	int tc, num_tc = netdev_get_num_tc(dev);
 
 	qopt->num_tc = num_tc;
-	memcpy(qopt->prio_tc_map, dev->prio_tc_map, sizeof(qopt->prio_tc_map));
+	for (tc = 0; tc <= TC_BITMASK; tc++)
+		qopt->prio_tc_map[tc] = netdev_get_prio_tc_map(dev, tc);
 
 	for (tc = 0; tc < num_tc; tc++) {
 		struct netdev_tc_txq res;
diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c
index 18fcb4e78456a2f74fa5d3465175d100a39575b4..39ac5b97aa3af83fe63ab5ff9173c39700f6bbb0 100644
--- a/net/sched/sch_taprio.c
+++ b/net/sched/sch_taprio.c
@@ -1813,7 +1813,7 @@ static int taprio_mqprio_cmp(const struct net_device *dev,
 	}
 
 	for (i = 0; i <= TC_BITMASK; i++)
-		if (dev->prio_tc_map[i] != mqprio->prio_tc_map[i])
+		if (netdev_get_prio_tc_map(dev, i) != mqprio->prio_tc_map[i])
 			return -1;
 
 	return 0;
-- 
2.55.0.679.g6767b8d81c-goog