1 files changed, 186 insertions, 170 deletions

diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c
index 9cff99558694..48dd8c88903f 100644
--- a/net/sched/sch_cake.c
+++ b/net/sched/sch_cake.c
@@ -361,8 +361,24 @@ static const u8 besteffort[] = {
 static const u8 normal_order[] = {0, 1, 2, 3, 4, 5, 6, 7};
 static const u8 bulk_order[] = {1, 0, 2, 3};
 
+/* There is a big difference in timing between the accurate values placed in the
+ * cache and the approximations given by a single Newton step for small count
+ * values, particularly when stepping from count 1 to 2 or vice versa. Hence,
+ * these values are calculated using eight Newton steps, using the
+ * implementation below. Above 16, a single Newton step gives sufficient
+ * accuracy in either direction, given the precision stored.
+ *
+ * The magnitude of the error when stepping up to count 2 is such as to give the
+ * value that *should* have been produced at count 4.
+ */
+
 #define REC_INV_SQRT_CACHE (16)
-static u32 cobalt_rec_inv_sqrt_cache[REC_INV_SQRT_CACHE] = {0};
+static const u32 inv_sqrt_cache[REC_INV_SQRT_CACHE] = {
+		~0,         ~0, 3037000500, 2479700525,
+	2147483647, 1920767767, 1753413056, 1623345051,
+	1518500250, 1431655765, 1358187914, 1294981364,
+	1239850263, 1191209601, 1147878294, 1108955788
+};
 
 /* http://en.wikipedia.org/wiki/Methods_of_computing_square_roots
  * new_invsqrt = (invsqrt / 2) * (3 - count * invsqrt^2)
@@ -388,47 +404,14 @@ static void cobalt_newton_step(struct cobalt_vars *vars)
 static void cobalt_invsqrt(struct cobalt_vars *vars)
 {
 	if (vars->count < REC_INV_SQRT_CACHE)
-		vars->rec_inv_sqrt = cobalt_rec_inv_sqrt_cache[vars->count];
+		vars->rec_inv_sqrt = inv_sqrt_cache[vars->count];
 	else
 		cobalt_newton_step(vars);
 }
 
-/* There is a big difference in timing between the accurate values placed in
- * the cache and the approximations given by a single Newton step for small
- * count values, particularly when stepping from count 1 to 2 or vice versa.
- * Above 16, a single Newton step gives sufficient accuracy in either
- * direction, given the precision stored.
- *
- * The magnitude of the error when stepping up to count 2 is such as to give
- * the value that *should* have been produced at count 4.
- */
-
-static void cobalt_cache_init(void)
-{
-	struct cobalt_vars v;
-
-	memset(&v, 0, sizeof(v));
-	v.rec_inv_sqrt = ~0U;
-	cobalt_rec_inv_sqrt_cache[0] = v.rec_inv_sqrt;
-
-	for (v.count = 1; v.count < REC_INV_SQRT_CACHE; v.count++) {
-		cobalt_newton_step(&v);
-		cobalt_newton_step(&v);
-		cobalt_newton_step(&v);
-		cobalt_newton_step(&v);
-
-		cobalt_rec_inv_sqrt_cache[v.count] = v.rec_inv_sqrt;
-	}
-}
-
 static void cobalt_vars_init(struct cobalt_vars *vars)
 {
 	memset(vars, 0, sizeof(*vars));
-
-	if (!cobalt_rec_inv_sqrt_cache[0]) {
-		cobalt_cache_init();
-		cobalt_rec_inv_sqrt_cache[0] = ~0;
-	}
 }
 
 /* CoDel control_law is t + interval/sqrt(count)
@@ -501,13 +484,14 @@ static bool cobalt_queue_empty(struct cobalt_vars *vars,
 /* Call this with a freshly dequeued packet for possible congestion marking.
  * Returns true as an instruction to drop the packet, false for delivery.
  */
-static bool cobalt_should_drop(struct cobalt_vars *vars,
-			       struct cobalt_params *p,
-			       ktime_t now,
-			       struct sk_buff *skb,
-			       u32 bulk_flows)
-{
-	bool next_due, over_target, drop = false;
+static enum skb_drop_reason cobalt_should_drop(struct cobalt_vars *vars,
+					       struct cobalt_params *p,
+					       ktime_t now,
+					       struct sk_buff *skb,
+					       u32 bulk_flows)
+{
+	enum skb_drop_reason reason = SKB_NOT_DROPPED_YET;
+	bool next_due, over_target;
 	ktime_t schedule;
 	u64 sojourn;
 
@@ -550,7 +534,8 @@ static bool cobalt_should_drop(struct cobalt_vars *vars,
 
 	if (next_due && vars->dropping) {
 		/* Use ECN mark if possible, otherwise drop */
-		drop = !(vars->ecn_marked = INET_ECN_set_ce(skb));
+		if (!(vars->ecn_marked = INET_ECN_set_ce(skb)))
+			reason = SKB_DROP_REASON_QDISC_CONGESTED;
 
 		vars->count++;
 		if (!vars->count)
@@ -573,16 +558,17 @@ static bool cobalt_should_drop(struct cobalt_vars *vars,
 	}
 
 	/* Simple BLUE implementation.  Lack of ECN is deliberate. */
-	if (vars->p_drop)
-		drop |= (get_random_u32() < vars->p_drop);
+	if (vars->p_drop && reason == SKB_NOT_DROPPED_YET &&
+	    get_random_u32() < vars->p_drop)
+		reason = SKB_DROP_REASON_CAKE_FLOOD;
 
 	/* Overload the drop_next field as an activity timeout */
 	if (!vars->count)
 		vars->drop_next = ktime_add_ns(now, p->interval);
-	else if (ktime_to_ns(schedule) > 0 && !drop)
+	else if (ktime_to_ns(schedule) > 0 && reason == SKB_NOT_DROPPED_YET)
 		vars->drop_next = now;
 
-	return drop;
+	return reason;
 }
 
 static bool cake_update_flowkeys(struct flow_keys *keys,
@@ -644,6 +630,63 @@ static bool cake_ddst(int flow_mode)
 	return (flow_mode & CAKE_FLOW_DUAL_DST) == CAKE_FLOW_DUAL_DST;
 }
 
+static void cake_dec_srchost_bulk_flow_count(struct cake_tin_data *q,
+					     struct cake_flow *flow,
+					     int flow_mode)
+{
+	if (likely(cake_dsrc(flow_mode) &&
+		   q->hosts[flow->srchost].srchost_bulk_flow_count))
+		q->hosts[flow->srchost].srchost_bulk_flow_count--;
+}
+
+static void cake_inc_srchost_bulk_flow_count(struct cake_tin_data *q,
+					     struct cake_flow *flow,
+					     int flow_mode)
+{
+	if (likely(cake_dsrc(flow_mode) &&
+		   q->hosts[flow->srchost].srchost_bulk_flow_count < CAKE_QUEUES))
+		q->hosts[flow->srchost].srchost_bulk_flow_count++;
+}
+
+static void cake_dec_dsthost_bulk_flow_count(struct cake_tin_data *q,
+					     struct cake_flow *flow,
+					     int flow_mode)
+{
+	if (likely(cake_ddst(flow_mode) &&
+		   q->hosts[flow->dsthost].dsthost_bulk_flow_count))
+		q->hosts[flow->dsthost].dsthost_bulk_flow_count--;
+}
+
+static void cake_inc_dsthost_bulk_flow_count(struct cake_tin_data *q,
+					     struct cake_flow *flow,
+					     int flow_mode)
+{
+	if (likely(cake_ddst(flow_mode) &&
+		   q->hosts[flow->dsthost].dsthost_bulk_flow_count < CAKE_QUEUES))
+		q->hosts[flow->dsthost].dsthost_bulk_flow_count++;
+}
+
+static u16 cake_get_flow_quantum(struct cake_tin_data *q,
+				 struct cake_flow *flow,
+				 int flow_mode)
+{
+	u16 host_load = 1;
+
+	if (cake_dsrc(flow_mode))
+		host_load = max(host_load,
+				q->hosts[flow->srchost].srchost_bulk_flow_count);
+
+	if (cake_ddst(flow_mode))
+		host_load = max(host_load,
+				q->hosts[flow->dsthost].dsthost_bulk_flow_count);
+
+	/* The get_random_u16() is a way to apply dithering to avoid
+	 * accumulating roundoff errors
+	 */
+	return (q->flow_quantum * quantum_div[host_load] +
+		get_random_u16()) >> 16;
+}
+
 static u32 cake_hash(struct cake_tin_data *q, const struct sk_buff *skb,
 		     int flow_mode, u16 flow_override, u16 host_override)
 {
@@ -786,12 +829,13 @@ skip_hash:
 		 * queue, accept the collision, update the host tags.
 		 */
 		q->way_collisions++;
-		if (q->flows[outer_hash + k].set == CAKE_SET_BULK) {
-			q->hosts[q->flows[reduced_hash].srchost].srchost_bulk_flow_count--;
-			q->hosts[q->flows[reduced_hash].dsthost].dsthost_bulk_flow_count--;
-		}
 		allocate_src = cake_dsrc(flow_mode);
 		allocate_dst = cake_ddst(flow_mode);
+
+		if (q->flows[outer_hash + k].set == CAKE_SET_BULK) {
+			cake_dec_srchost_bulk_flow_count(q, &q->flows[outer_hash + k], flow_mode);
+			cake_dec_dsthost_bulk_flow_count(q, &q->flows[outer_hash + k], flow_mode);
+		}
 found:
 		/* reserve queue for future packets in same flow */
 		reduced_hash = outer_hash + k;
@@ -815,9 +859,10 @@ found:
 			q->hosts[outer_hash + k].srchost_tag = srchost_hash;
 found_src:
 			srchost_idx = outer_hash + k;
-			if (q->flows[reduced_hash].set == CAKE_SET_BULK)
-				q->hosts[srchost_idx].srchost_bulk_flow_count++;
 			q->flows[reduced_hash].srchost = srchost_idx;
+
+			if (q->flows[reduced_hash].set == CAKE_SET_BULK)
+				cake_inc_srchost_bulk_flow_count(q, &q->flows[reduced_hash], flow_mode);
 		}
 
 		if (allocate_dst) {
@@ -838,9 +883,10 @@ found_src:
 			q->hosts[outer_hash + k].dsthost_tag = dsthost_hash;
 found_dst:
 			dsthost_idx = outer_hash + k;
-			if (q->flows[reduced_hash].set == CAKE_SET_BULK)
-				q->hosts[dsthost_idx].dsthost_bulk_flow_count++;
 			q->flows[reduced_hash].dsthost = dsthost_idx;
+
+			if (q->flows[reduced_hash].set == CAKE_SET_BULK)
+				cake_inc_dsthost_bulk_flow_count(q, &q->flows[reduced_hash], flow_mode);
 		}
 	}
 
@@ -1512,7 +1558,7 @@ static unsigned int cake_drop(struct Qdisc *sch, struct sk_buff **to_free)
 	if (!q->overflow_timeout) {
 		int i;
 		/* Build fresh max-heap */
-		for (i = CAKE_MAX_TINS * CAKE_QUEUES / 2; i >= 0; i--)
+		for (i = CAKE_MAX_TINS * CAKE_QUEUES / 2 - 1; i >= 0; i--)
 			cake_heapify(q, i);
 	}
 	q->overflow_timeout = 65535;
@@ -1539,17 +1585,16 @@ static unsigned int cake_drop(struct Qdisc *sch, struct sk_buff **to_free)
 	b->backlogs[idx]    -= len;
 	b->tin_backlog      -= len;
 	sch->qstats.backlog -= len;
-	qdisc_tree_reduce_backlog(sch, 1, len);
 
 	flow->dropped++;
 	b->tin_dropped++;
-	sch->qstats.drops++;
 
 	if (q->rate_flags & CAKE_FLAG_INGRESS)
 		cake_advance_shaper(q, b, skb, now, true);
 
-	__qdisc_drop(skb, to_free);
+	qdisc_drop_reason(skb, sch, to_free, SKB_DROP_REASON_QDISC_OVERLIMIT);
 	sch->q.qlen--;
+	qdisc_tree_reduce_backlog(sch, 1, len);
 
 	cake_heapify(q, 0);
 
@@ -1853,10 +1898,6 @@ static s32 cake_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 
 	/* flowchain */
 	if (!flow->set || flow->set == CAKE_SET_DECAYING) {
-		struct cake_host *srchost = &b->hosts[flow->srchost];
-		struct cake_host *dsthost = &b->hosts[flow->dsthost];
-		u16 host_load = 1;
-
 		if (!flow->set) {
 			list_add_tail(&flow->flowchain, &b->new_flows);
 		} else {
@@ -1866,18 +1907,8 @@ static s32 cake_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 		flow->set = CAKE_SET_SPARSE;
 		b->sparse_flow_count++;
 
-		if (cake_dsrc(q->flow_mode))
-			host_load = max(host_load, srchost->srchost_bulk_flow_count);
-
-		if (cake_ddst(q->flow_mode))
-			host_load = max(host_load, dsthost->dsthost_bulk_flow_count);
-
-		flow->deficit = (b->flow_quantum *
-				 quantum_div[host_load]) >> 16;
+		flow->deficit = cake_get_flow_quantum(b, flow, q->flow_mode);
 	} else if (flow->set == CAKE_SET_SPARSE_WAIT) {
-		struct cake_host *srchost = &b->hosts[flow->srchost];
-		struct cake_host *dsthost = &b->hosts[flow->dsthost];
-
 		/* this flow was empty, accounted as a sparse flow, but actually
 		 * in the bulk rotation.
 		 */
@@ -1885,12 +1916,8 @@ static s32 cake_enqueue(struct sk_buff *skb, struct Qdisc *sch,
 		b->sparse_flow_count--;
 		b->bulk_flow_count++;
 
-		if (cake_dsrc(q->flow_mode))
-			srchost->srchost_bulk_flow_count++;
-
-		if (cake_ddst(q->flow_mode))
-			dsthost->dsthost_bulk_flow_count++;
-
+		cake_inc_srchost_bulk_flow_count(b, flow, q->flow_mode);
+		cake_inc_dsthost_bulk_flow_count(b, flow, q->flow_mode);
 	}
 
 	if (q->buffer_used > q->buffer_max_used)
@@ -1940,20 +1967,19 @@ static void cake_clear_tin(struct Qdisc *sch, u16 tin)
 	q->cur_tin = tin;
 	for (q->cur_flow = 0; q->cur_flow < CAKE_QUEUES; q->cur_flow++)
 		while (!!(skb = cake_dequeue_one(sch)))
-			kfree_skb(skb);
+			kfree_skb_reason(skb, SKB_DROP_REASON_QUEUE_PURGE);
 }
 
 static struct sk_buff *cake_dequeue(struct Qdisc *sch)
 {
 	struct cake_sched_data *q = qdisc_priv(sch);
 	struct cake_tin_data *b = &q->tins[q->cur_tin];
-	struct cake_host *srchost, *dsthost;
+	enum skb_drop_reason reason;
 	ktime_t now = ktime_get();
 	struct cake_flow *flow;
 	struct list_head *head;
 	bool first_flow = true;
 	struct sk_buff *skb;
-	u16 host_load;
 	u64 delay;
 	u32 len;
 
@@ -2053,11 +2079,6 @@ retry:
 	q->cur_flow = flow - b->flows;
 	first_flow = false;
 
-	/* triple isolation (modified DRR++) */
-	srchost = &b->hosts[flow->srchost];
-	dsthost = &b->hosts[flow->dsthost];
-	host_load = 1;
-
 	/* flow isolation (DRR++) */
 	if (flow->deficit <= 0) {
 		/* Keep all flows with deficits out of the sparse and decaying
@@ -2069,11 +2090,8 @@ retry:
 				b->sparse_flow_count--;
 				b->bulk_flow_count++;
 
-				if (cake_dsrc(q->flow_mode))
-					srchost->srchost_bulk_flow_count++;
-
-				if (cake_ddst(q->flow_mode))
-					dsthost->dsthost_bulk_flow_count++;
+				cake_inc_srchost_bulk_flow_count(b, flow, q->flow_mode);
+				cake_inc_dsthost_bulk_flow_count(b, flow, q->flow_mode);
 
 				flow->set = CAKE_SET_BULK;
 			} else {
@@ -2085,19 +2103,7 @@ retry:
 			}
 		}
 
-		if (cake_dsrc(q->flow_mode))
-			host_load = max(host_load, srchost->srchost_bulk_flow_count);
-
-		if (cake_ddst(q->flow_mode))
-			host_load = max(host_load, dsthost->dsthost_bulk_flow_count);
-
-		WARN_ON(host_load > CAKE_QUEUES);
-
-		/* The get_random_u16() is a way to apply dithering to avoid
-		 * accumulating roundoff errors
-		 */
-		flow->deficit += (b->flow_quantum * quantum_div[host_load] +
-				  get_random_u16()) >> 16;
+		flow->deficit += cake_get_flow_quantum(b, flow, q->flow_mode);
 		list_move_tail(&flow->flowchain, &b->old_flows);
 
 		goto retry;
@@ -2121,11 +2127,8 @@ retry:
 				if (flow->set == CAKE_SET_BULK) {
 					b->bulk_flow_count--;
 
-					if (cake_dsrc(q->flow_mode))
-						srchost->srchost_bulk_flow_count--;
-
-					if (cake_ddst(q->flow_mode))
-						dsthost->dsthost_bulk_flow_count--;
+					cake_dec_srchost_bulk_flow_count(b, flow, q->flow_mode);
+					cake_dec_dsthost_bulk_flow_count(b, flow, q->flow_mode);
 
 					b->decaying_flow_count++;
 				} else if (flow->set == CAKE_SET_SPARSE ||
@@ -2143,12 +2146,8 @@ retry:
 				else if (flow->set == CAKE_SET_BULK) {
 					b->bulk_flow_count--;
 
-					if (cake_dsrc(q->flow_mode))
-						srchost->srchost_bulk_flow_count--;
-
-					if (cake_ddst(q->flow_mode))
-						dsthost->dsthost_bulk_flow_count--;
-
+					cake_dec_srchost_bulk_flow_count(b, flow, q->flow_mode);
+					cake_dec_dsthost_bulk_flow_count(b, flow, q->flow_mode);
 				} else
 					b->decaying_flow_count--;
 
@@ -2157,12 +2156,12 @@ retry:
 			goto begin;
 		}
 
+		reason = cobalt_should_drop(&flow->cvars, &b->cparams, now, skb,
+					    (b->bulk_flow_count *
+					     !!(q->rate_flags &
+						CAKE_FLAG_INGRESS)));
 		/* Last packet in queue may be marked, shouldn't be dropped */
-		if (!cobalt_should_drop(&flow->cvars, &b->cparams, now, skb,
-					(b->bulk_flow_count *
-					 !!(q->rate_flags &
-					    CAKE_FLAG_INGRESS))) ||
-		    !flow->head)
+		if (reason == SKB_NOT_DROPPED_YET || !flow->head)
 			break;
 
 		/* drop this packet, get another one */
@@ -2176,7 +2175,7 @@ retry:
 		b->tin_dropped++;
 		qdisc_tree_reduce_backlog(sch, 1, qdisc_pkt_len(skb));
 		qdisc_qstats_drop(sch);
-		kfree_skb(skb);
+		kfree_skb_reason(skb, reason);
 		if (q->rate_flags & CAKE_FLAG_INGRESS)
 			goto retry;
 	}
@@ -2572,6 +2571,8 @@ static int cake_change(struct Qdisc *sch, struct nlattr *opt,
 {
 	struct cake_sched_data *q = qdisc_priv(sch);
 	struct nlattr *tb[TCA_CAKE_MAX + 1];
+	u16 rate_flags;
+	u8 flow_mode;
 	int err;
 
 	err = nla_parse_nested_deprecated(tb, TCA_CAKE_MAX, opt, cake_policy,
@@ -2579,10 +2580,11 @@ static int cake_change(struct Qdisc *sch, struct nlattr *opt,
 	if (err < 0)
 		return err;
 
+	flow_mode = q->flow_mode;
 	if (tb[TCA_CAKE_NAT]) {
 #if IS_ENABLED(CONFIG_NF_CONNTRACK)
-		q->flow_mode &= ~CAKE_FLOW_NAT_FLAG;
-		q->flow_mode |= CAKE_FLOW_NAT_FLAG *
+		flow_mode &= ~CAKE_FLOW_NAT_FLAG;
+		flow_mode |= CAKE_FLOW_NAT_FLAG *
 			!!nla_get_u32(tb[TCA_CAKE_NAT]);
 #else
 		NL_SET_ERR_MSG_ATTR(extack, tb[TCA_CAKE_NAT],
@@ -2592,29 +2594,34 @@ static int cake_change(struct Qdisc *sch, struct nlattr *opt,
 	}
 
 	if (tb[TCA_CAKE_BASE_RATE64])
-		q->rate_bps = nla_get_u64(tb[TCA_CAKE_BASE_RATE64]);
+		WRITE_ONCE(q->rate_bps,
+			   nla_get_u64(tb[TCA_CAKE_BASE_RATE64]));
 
 	if (tb[TCA_CAKE_DIFFSERV_MODE])
-		q->tin_mode = nla_get_u32(tb[TCA_CAKE_DIFFSERV_MODE]);
+		WRITE_ONCE(q->tin_mode,
+			   nla_get_u32(tb[TCA_CAKE_DIFFSERV_MODE]));
 
+	rate_flags = q->rate_flags;
 	if (tb[TCA_CAKE_WASH]) {
 		if (!!nla_get_u32(tb[TCA_CAKE_WASH]))
-			q->rate_flags |= CAKE_FLAG_WASH;
+			rate_flags |= CAKE_FLAG_WASH;
 		else
-			q->rate_flags &= ~CAKE_FLAG_WASH;
+			rate_flags &= ~CAKE_FLAG_WASH;
 	}
 
 	if (tb[TCA_CAKE_FLOW_MODE])
-		q->flow_mode = ((q->flow_mode & CAKE_FLOW_NAT_FLAG) |
+		flow_mode = ((flow_mode & CAKE_FLOW_NAT_FLAG) |
 				(nla_get_u32(tb[TCA_CAKE_FLOW_MODE]) &
 					CAKE_FLOW_MASK));
 
 	if (tb[TCA_CAKE_ATM])
-		q->atm_mode = nla_get_u32(tb[TCA_CAKE_ATM]);
+		WRITE_ONCE(q->atm_mode,
+			   nla_get_u32(tb[TCA_CAKE_ATM]));
 
 	if (tb[TCA_CAKE_OVERHEAD]) {
-		q->rate_overhead = nla_get_s32(tb[TCA_CAKE_OVERHEAD]);
-		q->rate_flags |= CAKE_FLAG_OVERHEAD;
+		WRITE_ONCE(q->rate_overhead,
+			   nla_get_s32(tb[TCA_CAKE_OVERHEAD]));
+		rate_flags |= CAKE_FLAG_OVERHEAD;
 
 		q->max_netlen = 0;
 		q->max_adjlen = 0;
@@ -2623,7 +2630,7 @@ static int cake_change(struct Qdisc *sch, struct nlattr *opt,
 	}
 
 	if (tb[TCA_CAKE_RAW]) {
-		q->rate_flags &= ~CAKE_FLAG_OVERHEAD;
+		rate_flags &= ~CAKE_FLAG_OVERHEAD;
 
 		q->max_netlen = 0;
 		q->max_adjlen = 0;
@@ -2632,54 +2639,58 @@ static int cake_change(struct Qdisc *sch, struct nlattr *opt,
 	}
 
 	if (tb[TCA_CAKE_MPU])
-		q->rate_mpu = nla_get_u32(tb[TCA_CAKE_MPU]);
+		WRITE_ONCE(q->rate_mpu,
+			   nla_get_u32(tb[TCA_CAKE_MPU]));
 
 	if (tb[TCA_CAKE_RTT]) {
-		q->interval = nla_get_u32(tb[TCA_CAKE_RTT]);
+		u32 interval = nla_get_u32(tb[TCA_CAKE_RTT]);
 
-		if (!q->interval)
-			q->interval = 1;
+		WRITE_ONCE(q->interval, max(interval, 1U));
 	}
 
 	if (tb[TCA_CAKE_TARGET]) {
-		q->target = nla_get_u32(tb[TCA_CAKE_TARGET]);
+		u32 target = nla_get_u32(tb[TCA_CAKE_TARGET]);
 
-		if (!q->target)
-			q->target = 1;
+		WRITE_ONCE(q->target, max(target, 1U));
 	}
 
 	if (tb[TCA_CAKE_AUTORATE]) {
 		if (!!nla_get_u32(tb[TCA_CAKE_AUTORATE]))
-			q->rate_flags |= CAKE_FLAG_AUTORATE_INGRESS;
+			rate_flags |= CAKE_FLAG_AUTORATE_INGRESS;
 		else
-			q->rate_flags &= ~CAKE_FLAG_AUTORATE_INGRESS;
+			rate_flags &= ~CAKE_FLAG_AUTORATE_INGRESS;
 	}
 
 	if (tb[TCA_CAKE_INGRESS]) {
 		if (!!nla_get_u32(tb[TCA_CAKE_INGRESS]))
-			q->rate_flags |= CAKE_FLAG_INGRESS;
+			rate_flags |= CAKE_FLAG_INGRESS;
 		else
-			q->rate_flags &= ~CAKE_FLAG_INGRESS;
+			rate_flags &= ~CAKE_FLAG_INGRESS;
 	}
 
 	if (tb[TCA_CAKE_ACK_FILTER])
-		q->ack_filter = nla_get_u32(tb[TCA_CAKE_ACK_FILTER]);
+		WRITE_ONCE(q->ack_filter,
+			   nla_get_u32(tb[TCA_CAKE_ACK_FILTER]));
 
 	if (tb[TCA_CAKE_MEMORY])
-		q->buffer_config_limit = nla_get_u32(tb[TCA_CAKE_MEMORY]);
+		WRITE_ONCE(q->buffer_config_limit,
+			   nla_get_u32(tb[TCA_CAKE_MEMORY]));
 
 	if (tb[TCA_CAKE_SPLIT_GSO]) {
 		if (!!nla_get_u32(tb[TCA_CAKE_SPLIT_GSO]))
-			q->rate_flags |= CAKE_FLAG_SPLIT_GSO;
+			rate_flags |= CAKE_FLAG_SPLIT_GSO;
 		else
-			q->rate_flags &= ~CAKE_FLAG_SPLIT_GSO;
+			rate_flags &= ~CAKE_FLAG_SPLIT_GSO;
 	}
 
 	if (tb[TCA_CAKE_FWMARK]) {
-		q->fwmark_mask = nla_get_u32(tb[TCA_CAKE_FWMARK]);
-		q->fwmark_shft = q->fwmark_mask ? __ffs(q->fwmark_mask) : 0;
+		WRITE_ONCE(q->fwmark_mask, nla_get_u32(tb[TCA_CAKE_FWMARK]));
+		WRITE_ONCE(q->fwmark_shft,
+			   q->fwmark_mask ? __ffs(q->fwmark_mask) : 0);
 	}
 
+	WRITE_ONCE(q->rate_flags, rate_flags);
+	WRITE_ONCE(q->flow_mode, flow_mode);
 	if (q->tins) {
 		sch_tree_lock(sch);
 		cake_reconfigure(sch);
@@ -2774,68 +2785,72 @@ static int cake_dump(struct Qdisc *sch, struct sk_buff *skb)
 {
 	struct cake_sched_data *q = qdisc_priv(sch);
 	struct nlattr *opts;
+	u16 rate_flags;
+	u8 flow_mode;
 
 	opts = nla_nest_start_noflag(skb, TCA_OPTIONS);
 	if (!opts)
 		goto nla_put_failure;
 
-	if (nla_put_u64_64bit(skb, TCA_CAKE_BASE_RATE64, q->rate_bps,
-			      TCA_CAKE_PAD))
+	if (nla_put_u64_64bit(skb, TCA_CAKE_BASE_RATE64,
+			      READ_ONCE(q->rate_bps), TCA_CAKE_PAD))
 		goto nla_put_failure;
 
-	if (nla_put_u32(skb, TCA_CAKE_FLOW_MODE,
-			q->flow_mode & CAKE_FLOW_MASK))
+	flow_mode = READ_ONCE(q->flow_mode);
+	if (nla_put_u32(skb, TCA_CAKE_FLOW_MODE, flow_mode & CAKE_FLOW_MASK))
 		goto nla_put_failure;
 
-	if (nla_put_u32(skb, TCA_CAKE_RTT, q->interval))
+	if (nla_put_u32(skb, TCA_CAKE_RTT, READ_ONCE(q->interval)))
 		goto nla_put_failure;
 
-	if (nla_put_u32(skb, TCA_CAKE_TARGET, q->target))
+	if (nla_put_u32(skb, TCA_CAKE_TARGET, READ_ONCE(q->target)))
 		goto nla_put_failure;
 
-	if (nla_put_u32(skb, TCA_CAKE_MEMORY, q->buffer_config_limit))
+	if (nla_put_u32(skb, TCA_CAKE_MEMORY,
+			READ_ONCE(q->buffer_config_limit)))
 		goto nla_put_failure;
 
+	rate_flags = READ_ONCE(q->rate_flags);
 	if (nla_put_u32(skb, TCA_CAKE_AUTORATE,
-			!!(q->rate_flags & CAKE_FLAG_AUTORATE_INGRESS)))
+			!!(rate_flags & CAKE_FLAG_AUTORATE_INGRESS)))
 		goto nla_put_failure;
 
 	if (nla_put_u32(skb, TCA_CAKE_INGRESS,
-			!!(q->rate_flags & CAKE_FLAG_INGRESS)))
+			!!(rate_flags & CAKE_FLAG_INGRESS)))
 		goto nla_put_failure;
 
-	if (nla_put_u32(skb, TCA_CAKE_ACK_FILTER, q->ack_filter))
+	if (nla_put_u32(skb, TCA_CAKE_ACK_FILTER, READ_ONCE(q->ack_filter)))
 		goto nla_put_failure;
 
 	if (nla_put_u32(skb, TCA_CAKE_NAT,
-			!!(q->flow_mode & CAKE_FLOW_NAT_FLAG)))
+			!!(flow_mode & CAKE_FLOW_NAT_FLAG)))
 		goto nla_put_failure;
 
-	if (nla_put_u32(skb, TCA_CAKE_DIFFSERV_MODE, q->tin_mode))
+	if (nla_put_u32(skb, TCA_CAKE_DIFFSERV_MODE, READ_ONCE(q->tin_mode)))
 		goto nla_put_failure;
 
 	if (nla_put_u32(skb, TCA_CAKE_WASH,
-			!!(q->rate_flags & CAKE_FLAG_WASH)))
+			!!(rate_flags & CAKE_FLAG_WASH)))
 		goto nla_put_failure;
 
-	if (nla_put_u32(skb, TCA_CAKE_OVERHEAD, q->rate_overhead))
+	if (nla_put_u32(skb, TCA_CAKE_OVERHEAD, READ_ONCE(q->rate_overhead)))
 		goto nla_put_failure;
 
-	if (!(q->rate_flags & CAKE_FLAG_OVERHEAD))
+	if (!(rate_flags & CAKE_FLAG_OVERHEAD))
 		if (nla_put_u32(skb, TCA_CAKE_RAW, 0))
 			goto nla_put_failure;
 
-	if (nla_put_u32(skb, TCA_CAKE_ATM, q->atm_mode))
+	if (nla_put_u32(skb, TCA_CAKE_ATM, READ_ONCE(q->atm_mode)))
 		goto nla_put_failure;
 
-	if (nla_put_u32(skb, TCA_CAKE_MPU, q->rate_mpu))
+	if (nla_put_u32(skb, TCA_CAKE_MPU, READ_ONCE(q->rate_mpu)))
 		goto nla_put_failure;
 
 	if (nla_put_u32(skb, TCA_CAKE_SPLIT_GSO,
-			!!(q->rate_flags & CAKE_FLAG_SPLIT_GSO)))
+			!!(rate_flags & CAKE_FLAG_SPLIT_GSO)))
 		goto nla_put_failure;
 
-	if (nla_put_u32(skb, TCA_CAKE_FWMARK, q->fwmark_mask))
+	if (nla_put_u32(skb, TCA_CAKE_FWMARK, READ_ONCE(q->fwmark_mask)))
 		goto nla_put_failure;
 
 	return nla_nest_end(skb, opts);
@@ -3103,6 +3118,7 @@ static struct Qdisc_ops cake_qdisc_ops __read_mostly = {
 	.dump_stats	=	cake_dump_stats,
 	.owner		=	THIS_MODULE,
 };
+MODULE_ALIAS_NET_SCH("cake");
 
 static int __init cake_module_init(void)
 {