Merge branch 'mlxsw-Add-support-for-buffer-drops-mirroring'

Petr Machata says:

====================
mlxsw: Add support for buffer drops mirroring

This set offloads the recently introduced qevent infrastructure in TC and
allows mlxsw to support mirroring of packets that were dropped due to
buffer related reasons (e.g., early drops) during forwarding.

Up until now mlxsw only supported mirroring that was either triggered by
per-port triggers (i.e., via matchall) or by the policy engine (i.e.,
via flower). Packets that are dropped due to buffer related reasons are
mirrored using a third type of trigger, a global trigger.

Global triggers are bound once to a mirroring (SPAN) agent and enabled
on a per-{port, TC} basis. This allows users, for example, to request
that only packets that were early dropped on a specific netdev to be
mirrored.

Patch set overview:

Patch #1 extends flow_block_offload and indirect offload structure to pass
a scheduler instead of a netdevice. That is necessary, because binding type
and netdevice are not a unique identifier of the block anymore.

Patches #2-#3 add the required registers to support above mentioned
functionality.

Patches #4-#6 gradually add support for global mirroring triggers.

Patch #7 adds support for enablement of global mirroring triggers.

Patches #8-#11 are cleanups in the flow offload code and shuffle some
code around to make the qevent offload easier.

Patch #12 implements offload of RED early_drop qevent.

Patch #13 extends the RED selftest for offloaded datapath to cover
early_drop qevent.

v2:
- Patch #1:
    - In struct flow_block_indr, track both sch and dev.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/net/ethernet/broadcom/bnxt/bnxt_tc.c

@@ -1888,7 +1888,7 @@ static void bnxt_tc_setup_indr_rel(void *cb_priv)
 	kfree(priv);
 }
 
-static int bnxt_tc_setup_indr_block(struct net_device *netdev, struct bnxt *bp,
+static int bnxt_tc_setup_indr_block(struct net_device *netdev, struct Qdisc *sch, struct bnxt *bp,
 				    struct flow_block_offload *f, void *data,
 				    void (*cleanup)(struct flow_block_cb *block_cb))
 {
@@ -1911,7 +1911,7 @@ static int bnxt_tc_setup_indr_block(struct net_device *netdev, struct bnxt *bp,
 		block_cb = flow_indr_block_cb_alloc(bnxt_tc_setup_indr_block_cb,
 						    cb_priv, cb_priv,
 						    bnxt_tc_setup_indr_rel, f,
-						    netdev, data, bp, cleanup);
+						    netdev, sch, data, bp, cleanup);
 		if (IS_ERR(block_cb)) {
 			list_del(&cb_priv->list);
 			kfree(cb_priv);
@@ -1946,7 +1946,7 @@ static bool bnxt_is_netdev_indr_offload(struct net_device *netdev)
 	return netif_is_vxlan(netdev);
 }
 
-static int bnxt_tc_setup_indr_cb(struct net_device *netdev, void *cb_priv,
+static int bnxt_tc_setup_indr_cb(struct net_device *netdev, struct Qdisc *sch, void *cb_priv,
 				 enum tc_setup_type type, void *type_data,
 				 void *data,
 				 void (*cleanup)(struct flow_block_cb *block_cb))
@@ -1956,8 +1956,7 @@ static int bnxt_tc_setup_indr_cb(struct net_device *netdev, void *cb_priv,
 
 	switch (type) {
 	case TC_SETUP_BLOCK:
-		return bnxt_tc_setup_indr_block(netdev, cb_priv, type_data, data,
-						cleanup);
+		return bnxt_tc_setup_indr_block(netdev, sch, cb_priv, type_data, data, cleanup);
 	default:
 		break;
 	}

drivers/net/ethernet/mellanox/mlx5/core/en/rep/tc.c

@@ -404,7 +404,7 @@ static void mlx5e_rep_indr_block_unbind(void *cb_priv)
 static LIST_HEAD(mlx5e_block_cb_list);
 
 static int
-mlx5e_rep_indr_setup_block(struct net_device *netdev,
+mlx5e_rep_indr_setup_block(struct net_device *netdev, struct Qdisc *sch,
 			   struct mlx5e_rep_priv *rpriv,
 			   struct flow_block_offload *f,
 			   flow_setup_cb_t *setup_cb,
@@ -442,7 +442,7 @@ mlx5e_rep_indr_setup_block(struct net_device *netdev,
 
 		block_cb = flow_indr_block_cb_alloc(setup_cb, indr_priv, indr_priv,
 						    mlx5e_rep_indr_block_unbind,
-						    f, netdev, data, rpriv,
+						    f, netdev, sch, data, rpriv,
 						    cleanup);
 		if (IS_ERR(block_cb)) {
 			list_del(&indr_priv->list);
@@ -472,18 +472,18 @@ mlx5e_rep_indr_setup_block(struct net_device *netdev,
 }
 
 static
-int mlx5e_rep_indr_setup_cb(struct net_device *netdev, void *cb_priv,
+int mlx5e_rep_indr_setup_cb(struct net_device *netdev, struct Qdisc *sch, void *cb_priv,
 			    enum tc_setup_type type, void *type_data,
 			    void *data,
 			    void (*cleanup)(struct flow_block_cb *block_cb))
 {
 	switch (type) {
 	case TC_SETUP_BLOCK:
-		return mlx5e_rep_indr_setup_block(netdev, cb_priv, type_data,
+		return mlx5e_rep_indr_setup_block(netdev, sch, cb_priv, type_data,
 						  mlx5e_rep_indr_setup_tc_cb,
 						  data, cleanup);
 	case TC_SETUP_FT:
-		return mlx5e_rep_indr_setup_block(netdev, cb_priv, type_data,
+		return mlx5e_rep_indr_setup_block(netdev, sch, cb_priv, type_data,
 						  mlx5e_rep_indr_setup_ft_cb,
 						  data, cleanup);
 	default:

drivers/net/ethernet/mellanox/mlxsw/reg.h

@@ -9502,6 +9502,106 @@ MLXSW_ITEM32(reg, mogcr, ptp_iftc, 0x00, 1, 1);
  */
 MLXSW_ITEM32(reg, mogcr, ptp_eftc, 0x00, 0, 1);
 
+/* MPAGR - Monitoring Port Analyzer Global Register
+ * ------------------------------------------------
+ * This register is used for global port analyzer configurations.
+ * Note: This register is not supported by current FW versions for Spectrum-1.
+ */
+#define MLXSW_REG_MPAGR_ID 0x9089
+#define MLXSW_REG_MPAGR_LEN 0x0C
+
+MLXSW_REG_DEFINE(mpagr, MLXSW_REG_MPAGR_ID, MLXSW_REG_MPAGR_LEN);
+
+enum mlxsw_reg_mpagr_trigger {
+	MLXSW_REG_MPAGR_TRIGGER_EGRESS,
+	MLXSW_REG_MPAGR_TRIGGER_INGRESS,
+	MLXSW_REG_MPAGR_TRIGGER_INGRESS_WRED,
+	MLXSW_REG_MPAGR_TRIGGER_INGRESS_SHARED_BUFFER,
+	MLXSW_REG_MPAGR_TRIGGER_INGRESS_ING_CONG,
+	MLXSW_REG_MPAGR_TRIGGER_INGRESS_EGR_CONG,
+	MLXSW_REG_MPAGR_TRIGGER_EGRESS_ECN,
+	MLXSW_REG_MPAGR_TRIGGER_EGRESS_HIGH_LATENCY,
+};
+
+/* reg_mpagr_trigger
+ * Mirror trigger.
+ * Access: Index
+ */
+MLXSW_ITEM32(reg, mpagr, trigger, 0x00, 0, 4);
+
+/* reg_mpagr_pa_id
+ * Port analyzer ID.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, mpagr, pa_id, 0x04, 0, 4);
+
+/* reg_mpagr_probability_rate
+ * Sampling rate.
+ * Valid values are: 1 to 3.5*10^9
+ * Value of 1 means "sample all". Default is 1.
+ * Access: RW
+ */
+MLXSW_ITEM32(reg, mpagr, probability_rate, 0x08, 0, 32);
+
+static inline void mlxsw_reg_mpagr_pack(char *payload,
+					enum mlxsw_reg_mpagr_trigger trigger,
+					u8 pa_id, u32 probability_rate)
+{
+	MLXSW_REG_ZERO(mpagr, payload);
+	mlxsw_reg_mpagr_trigger_set(payload, trigger);
+	mlxsw_reg_mpagr_pa_id_set(payload, pa_id);
+	mlxsw_reg_mpagr_probability_rate_set(payload, probability_rate);
+}
+
+/* MOMTE - Monitoring Mirror Trigger Enable Register
+ * -------------------------------------------------
+ * This register is used to configure the mirror enable for different mirror
+ * reasons.
+ */
+#define MLXSW_REG_MOMTE_ID 0x908D
+#define MLXSW_REG_MOMTE_LEN 0x10
+
+MLXSW_REG_DEFINE(momte, MLXSW_REG_MOMTE_ID, MLXSW_REG_MOMTE_LEN);
+
+/* reg_momte_local_port
+ * Local port number.
+ * Access: Index
+ */
+MLXSW_ITEM32(reg, momte, local_port, 0x00, 16, 8);
+
+enum mlxsw_reg_momte_type {
+	MLXSW_REG_MOMTE_TYPE_WRED = 0x20,
+	MLXSW_REG_MOMTE_TYPE_SHARED_BUFFER_TCLASS = 0x31,
+	MLXSW_REG_MOMTE_TYPE_SHARED_BUFFER_TCLASS_DESCRIPTORS = 0x32,
+	MLXSW_REG_MOMTE_TYPE_SHARED_BUFFER_EGRESS_PORT = 0x33,
+	MLXSW_REG_MOMTE_TYPE_ING_CONG = 0x40,
+	MLXSW_REG_MOMTE_TYPE_EGR_CONG = 0x50,
+	MLXSW_REG_MOMTE_TYPE_ECN = 0x60,
+	MLXSW_REG_MOMTE_TYPE_HIGH_LATENCY = 0x70,
+};
+
+/* reg_momte_type
+ * Type of mirroring.
+ * Access: Index
+ */
+MLXSW_ITEM32(reg, momte, type, 0x04, 0, 8);
+
+/* reg_momte_tclass_en
+ * TClass/PG mirror enable. Each bit represents corresponding tclass.
+ * 0: disable (default)
+ * 1: enable
+ * Access: RW
+ */
+MLXSW_ITEM_BIT_ARRAY(reg, momte, tclass_en, 0x08, 0x08, 1);
+
+static inline void mlxsw_reg_momte_pack(char *payload, u8 local_port,
+					enum mlxsw_reg_momte_type type)
+{
+	MLXSW_REG_ZERO(momte, payload);
+	mlxsw_reg_momte_local_port_set(payload, local_port);
+	mlxsw_reg_momte_type_set(payload, type);
+}
+
 /* MTPPPC - Time Precision Packet Port Configuration
  * -------------------------------------------------
  * This register serves for configuration of which PTP messages should be
@@ -10853,6 +10953,8 @@ static const struct mlxsw_reg_info *mlxsw_reg_infos[] = {
 	MLXSW_REG(mgpc),
 	MLXSW_REG(mprs),
 	MLXSW_REG(mogcr),
+	MLXSW_REG(mpagr),
+	MLXSW_REG(momte),
 	MLXSW_REG(mtpppc),
 	MLXSW_REG(mtpptr),
 	MLXSW_REG(mtptpt),

drivers/net/ethernet/mellanox/mlxsw/spectrum.c

@@ -175,10 +175,6 @@ struct mlxsw_sp_mlxfw_dev {
 	struct mlxsw_sp *mlxsw_sp;
 };
 
-struct mlxsw_sp_span_ops {
-	u32 (*buffsize_get)(int mtu, u32 speed);
-};
-
 static int mlxsw_sp_component_query(struct mlxfw_dev *mlxfw_dev,
 				    u16 component_index, u32 *p_max_size,
 				    u8 *p_align_bits, u16 *p_max_write_size)
@@ -1333,6 +1329,21 @@ static int mlxsw_sp_port_kill_vid(struct net_device *dev,
 	return 0;
 }
 
+static int mlxsw_sp_setup_tc_block(struct mlxsw_sp_port *mlxsw_sp_port,
+				   struct flow_block_offload *f)
+{
+	switch (f->binder_type) {
+	case FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS:
+		return mlxsw_sp_setup_tc_block_clsact(mlxsw_sp_port, f, true);
+	case FLOW_BLOCK_BINDER_TYPE_CLSACT_EGRESS:
+		return mlxsw_sp_setup_tc_block_clsact(mlxsw_sp_port, f, false);
+	case FLOW_BLOCK_BINDER_TYPE_RED_EARLY_DROP:
+		return mlxsw_sp_setup_tc_block_qevent_early_drop(mlxsw_sp_port, f);
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
 static int mlxsw_sp_setup_tc(struct net_device *dev, enum tc_setup_type type,
 			     void *type_data)
 {
@@ -2812,52 +2823,6 @@ static const struct mlxsw_sp_ptp_ops mlxsw_sp2_ptp_ops = {
 	.get_stats	= mlxsw_sp2_get_stats,
 };
 
-static u32 mlxsw_sp1_span_buffsize_get(int mtu, u32 speed)
-{
-	return mtu * 5 / 2;
-}
-
-static const struct mlxsw_sp_span_ops mlxsw_sp1_span_ops = {
-	.buffsize_get = mlxsw_sp1_span_buffsize_get,
-};
-
-#define MLXSW_SP2_SPAN_EG_MIRROR_BUFFER_FACTOR 38
-#define MLXSW_SP3_SPAN_EG_MIRROR_BUFFER_FACTOR 50
-
-static u32 __mlxsw_sp_span_buffsize_get(int mtu, u32 speed, u32 buffer_factor)
-{
-	return 3 * mtu + buffer_factor * speed / 1000;
-}
-
-static u32 mlxsw_sp2_span_buffsize_get(int mtu, u32 speed)
-{
-	int factor = MLXSW_SP2_SPAN_EG_MIRROR_BUFFER_FACTOR;
-
-	return __mlxsw_sp_span_buffsize_get(mtu, speed, factor);
-}
-
-static const struct mlxsw_sp_span_ops mlxsw_sp2_span_ops = {
-	.buffsize_get = mlxsw_sp2_span_buffsize_get,
-};
-
-static u32 mlxsw_sp3_span_buffsize_get(int mtu, u32 speed)
-{
-	int factor = MLXSW_SP3_SPAN_EG_MIRROR_BUFFER_FACTOR;
-
-	return __mlxsw_sp_span_buffsize_get(mtu, speed, factor);
-}
-
-static const struct mlxsw_sp_span_ops mlxsw_sp3_span_ops = {
-	.buffsize_get = mlxsw_sp3_span_buffsize_get,
-};
-
-u32 mlxsw_sp_span_buffsize_get(struct mlxsw_sp *mlxsw_sp, int mtu, u32 speed)
-{
-	u32 buffsize = mlxsw_sp->span_ops->buffsize_get(speed, mtu);
-
-	return mlxsw_sp_bytes_cells(mlxsw_sp, buffsize) + 1;
-}
-
 static int mlxsw_sp_netdevice_event(struct notifier_block *unused,
 				    unsigned long event, void *ptr);
 

drivers/net/ethernet/mellanox/mlxsw/spectrum.h

@@ -539,7 +539,6 @@ int mlxsw_sp_flow_counter_alloc(struct mlxsw_sp *mlxsw_sp,
 				unsigned int *p_counter_index);
 void mlxsw_sp_flow_counter_free(struct mlxsw_sp *mlxsw_sp,
 				unsigned int counter_index);
-u32 mlxsw_sp_span_buffsize_get(struct mlxsw_sp *mlxsw_sp, int mtu, u32 speed);
 bool mlxsw_sp_port_dev_check(const struct net_device *dev);
 struct mlxsw_sp *mlxsw_sp_lower_get(struct net_device *dev);
 struct mlxsw_sp_port *mlxsw_sp_port_dev_lower_find(struct net_device *dev);
@@ -711,7 +710,6 @@ struct mlxsw_sp_flow_block {
 
 struct mlxsw_sp_flow_block_binding {
 	struct list_head list;
-	struct net_device *dev;
 	struct mlxsw_sp_port *mlxsw_sp_port;
 	bool ingress;
 };
@@ -769,8 +767,9 @@ mlxsw_sp_flow_block_is_mixed_bound(const struct mlxsw_sp_flow_block *block)
 struct mlxsw_sp_flow_block *mlxsw_sp_flow_block_create(struct mlxsw_sp *mlxsw_sp,
 						       struct net *net);
 void mlxsw_sp_flow_block_destroy(struct mlxsw_sp_flow_block *block);
-int mlxsw_sp_setup_tc_block(struct mlxsw_sp_port *mlxsw_sp_port,
-			    struct flow_block_offload *f);
+int mlxsw_sp_setup_tc_block_clsact(struct mlxsw_sp_port *mlxsw_sp_port,
+				   struct flow_block_offload *f,
+				   bool ingress);
 
 /* spectrum_acl.c */
 struct mlxsw_sp_acl_ruleset;
@@ -962,6 +961,30 @@ extern const struct mlxsw_afk_ops mlxsw_sp1_afk_ops;
 extern const struct mlxsw_afk_ops mlxsw_sp2_afk_ops;
 
 /* spectrum_matchall.c */
+enum mlxsw_sp_mall_action_type {
+	MLXSW_SP_MALL_ACTION_TYPE_MIRROR,
+	MLXSW_SP_MALL_ACTION_TYPE_SAMPLE,
+	MLXSW_SP_MALL_ACTION_TYPE_TRAP,
+};
+
+struct mlxsw_sp_mall_mirror_entry {
+	const struct net_device *to_dev;
+	int span_id;
+};
+
+struct mlxsw_sp_mall_entry {
+	struct list_head list;
+	unsigned long cookie;
+	unsigned int priority;
+	enum mlxsw_sp_mall_action_type type;
+	bool ingress;
+	union {
+		struct mlxsw_sp_mall_mirror_entry mirror;
+		struct mlxsw_sp_port_sample sample;
+	};
+	struct rcu_head rcu;
+};
+
 int mlxsw_sp_mall_replace(struct mlxsw_sp *mlxsw_sp,
 			  struct mlxsw_sp_flow_block *block,
 			  struct tc_cls_matchall_offload *f);
@@ -1008,6 +1031,8 @@ int mlxsw_sp_setup_tc_tbf(struct mlxsw_sp_port *mlxsw_sp_port,
 			  struct tc_tbf_qopt_offload *p);
 int mlxsw_sp_setup_tc_fifo(struct mlxsw_sp_port *mlxsw_sp_port,
 			   struct tc_fifo_qopt_offload *p);
+int mlxsw_sp_setup_tc_block_qevent_early_drop(struct mlxsw_sp_port *mlxsw_sp_port,
+					      struct flow_block_offload *f);
 
 /* spectrum_fid.c */
 bool mlxsw_sp_fid_is_dummy(struct mlxsw_sp *mlxsw_sp, u16 fid_index);

drivers/net/ethernet/mellanox/mlxsw/spectrum_flow.c

@@ -219,8 +219,7 @@ static int mlxsw_sp_setup_tc_block_bind(struct mlxsw_sp_port *mlxsw_sp_port,
 					       mlxsw_sp_tc_block_release);
 		if (IS_ERR(block_cb)) {
 			mlxsw_sp_flow_block_destroy(flow_block);
-			err = PTR_ERR(block_cb);
-			goto err_cb_register;
+			return PTR_ERR(block_cb);
 		}
 		register_block = true;
 	} else {
@@ -247,7 +246,6 @@ static int mlxsw_sp_setup_tc_block_bind(struct mlxsw_sp_port *mlxsw_sp_port,
 err_block_bind:
 	if (!flow_block_cb_decref(block_cb))
 		flow_block_cb_free(block_cb);
-err_cb_register:
 	return err;
 }
 
@@ -279,18 +277,10 @@ static void mlxsw_sp_setup_tc_block_unbind(struct mlxsw_sp_port *mlxsw_sp_port,
 	}
 }
 
-int mlxsw_sp_setup_tc_block(struct mlxsw_sp_port *mlxsw_sp_port,
-			    struct flow_block_offload *f)
+int mlxsw_sp_setup_tc_block_clsact(struct mlxsw_sp_port *mlxsw_sp_port,
+				   struct flow_block_offload *f,
+				   bool ingress)
 {
-	bool ingress;
-
-	if (f->binder_type == FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS)
-		ingress = true;
-	else if (f->binder_type == FLOW_BLOCK_BINDER_TYPE_CLSACT_EGRESS)
-		ingress = false;
-	else
-		return -EOPNOTSUPP;
-
 	f->driver_block_list = &mlxsw_sp_block_cb_list;
 
 	switch (f->command) {

drivers/net/ethernet/mellanox/mlxsw/spectrum_matchall.c

@@ -10,29 +10,6 @@
 #include "spectrum_span.h"
 #include "reg.h"
 
-enum mlxsw_sp_mall_action_type {
-	MLXSW_SP_MALL_ACTION_TYPE_MIRROR,
-	MLXSW_SP_MALL_ACTION_TYPE_SAMPLE,
-};
-
-struct mlxsw_sp_mall_mirror_entry {
-	const struct net_device *to_dev;
-	int span_id;
-};
-
-struct mlxsw_sp_mall_entry {
-	struct list_head list;
-	unsigned long cookie;
-	unsigned int priority;
-	enum mlxsw_sp_mall_action_type type;
-	bool ingress;
-	union {
-		struct mlxsw_sp_mall_mirror_entry mirror;
-		struct mlxsw_sp_port_sample sample;
-	};
-	struct rcu_head rcu;
-};
-
 static struct mlxsw_sp_mall_entry *
 mlxsw_sp_mall_entry_find(struct mlxsw_sp_flow_block *block, unsigned long cookie)
 {

drivers/net/ethernet/mellanox/mlxsw/spectrum_span.h

@@ -26,6 +26,9 @@ struct mlxsw_sp_span_parms {
 enum mlxsw_sp_span_trigger {
 	MLXSW_SP_SPAN_TRIGGER_INGRESS,
 	MLXSW_SP_SPAN_TRIGGER_EGRESS,
+	MLXSW_SP_SPAN_TRIGGER_TAIL_DROP,
+	MLXSW_SP_SPAN_TRIGGER_EARLY_DROP,
+	MLXSW_SP_SPAN_TRIGGER_ECN,
 };
 
 struct mlxsw_sp_span_trigger_parms {
@@ -34,6 +37,11 @@ struct mlxsw_sp_span_trigger_parms {
 
 struct mlxsw_sp_span_entry_ops;
 
+struct mlxsw_sp_span_ops {
+	int (*init)(struct mlxsw_sp *mlxsw_sp);
+	u32 (*buffsize_get)(int mtu, u32 speed);
+};
+
 struct mlxsw_sp_span_entry {
 	const struct net_device *to_dev;
 	const struct mlxsw_sp_span_entry_ops *ops;
@@ -81,5 +89,13 @@ mlxsw_sp_span_agent_unbind(struct mlxsw_sp *mlxsw_sp,
 			   enum mlxsw_sp_span_trigger trigger,
 			   struct mlxsw_sp_port *mlxsw_sp_port,
 			   const struct mlxsw_sp_span_trigger_parms *parms);
+int mlxsw_sp_span_trigger_enable(struct mlxsw_sp_port *mlxsw_sp_port,
+				 enum mlxsw_sp_span_trigger trigger, u8 tc);
+void mlxsw_sp_span_trigger_disable(struct mlxsw_sp_port *mlxsw_sp_port,
+				   enum mlxsw_sp_span_trigger trigger, u8 tc);
+
+extern const struct mlxsw_sp_span_ops mlxsw_sp1_span_ops;
+extern const struct mlxsw_sp_span_ops mlxsw_sp2_span_ops;
+extern const struct mlxsw_sp_span_ops mlxsw_sp3_span_ops;
 
 #endif

drivers/net/ethernet/netronome/nfp/flower/main.h

@@ -458,7 +458,7 @@ void nfp_flower_qos_cleanup(struct nfp_app *app);
 int nfp_flower_setup_qos_offload(struct nfp_app *app, struct net_device *netdev,
 				 struct tc_cls_matchall_offload *flow);
 void nfp_flower_stats_rlim_reply(struct nfp_app *app, struct sk_buff *skb);
-int nfp_flower_indr_setup_tc_cb(struct net_device *netdev, void *cb_priv,
+int nfp_flower_indr_setup_tc_cb(struct net_device *netdev, struct Qdisc *sch, void *cb_priv,
 				enum tc_setup_type type, void *type_data,
 				void *data,
 				void (*cleanup)(struct flow_block_cb *block_cb));

drivers/net/ethernet/netronome/nfp/flower/offload.c

@@ -1646,7 +1646,7 @@ void nfp_flower_setup_indr_tc_release(void *cb_priv)
 }
 
 static int
-nfp_flower_setup_indr_tc_block(struct net_device *netdev, struct nfp_app *app,
+nfp_flower_setup_indr_tc_block(struct net_device *netdev, struct Qdisc *sch, struct nfp_app *app,
 			       struct flow_block_offload *f, void *data,
 			       void (*cleanup)(struct flow_block_cb *block_cb))
 {
@@ -1680,7 +1680,7 @@ nfp_flower_setup_indr_tc_block(struct net_device *netdev, struct nfp_app *app,
 		block_cb = flow_indr_block_cb_alloc(nfp_flower_setup_indr_block_cb,
 						    cb_priv, cb_priv,
 						    nfp_flower_setup_indr_tc_release,
-						    f, netdev, data, app, cleanup);
+						    f, netdev, sch, data, app, cleanup);
 		if (IS_ERR(block_cb)) {
 			list_del(&cb_priv->list);
 			kfree(cb_priv);
@@ -1711,7 +1711,7 @@ nfp_flower_setup_indr_tc_block(struct net_device *netdev, struct nfp_app *app,
 }
 
 int
-nfp_flower_indr_setup_tc_cb(struct net_device *netdev, void *cb_priv,
+nfp_flower_indr_setup_tc_cb(struct net_device *netdev, struct Qdisc *sch, void *cb_priv,
 			    enum tc_setup_type type, void *type_data,
 			    void *data,
 			    void (*cleanup)(struct flow_block_cb *block_cb))
@@ -1721,7 +1721,7 @@ nfp_flower_indr_setup_tc_cb(struct net_device *netdev, void *cb_priv,
 
 	switch (type) {
 	case TC_SETUP_BLOCK:
-		return nfp_flower_setup_indr_tc_block(netdev, cb_priv,
+		return nfp_flower_setup_indr_tc_block(netdev, sch, cb_priv,
 						      type_data, data, cleanup);
 	default:
 		return -EOPNOTSUPP;

include/net/flow_offload.h

@@ -444,6 +444,7 @@ struct flow_block_offload {
 	struct list_head cb_list;
 	struct list_head *driver_block_list;
 	struct netlink_ext_ack *extack;
+	struct Qdisc *sch;
 };
 
 enum tc_setup_type;
@@ -455,6 +456,7 @@ struct flow_block_cb;
 struct flow_block_indr {
 	struct list_head		list;
 	struct net_device		*dev;
+	struct Qdisc			*sch;
 	enum flow_block_binder_type	binder_type;
 	void				*data;
 	void				*cb_priv;
@@ -479,7 +481,8 @@ struct flow_block_cb *flow_indr_block_cb_alloc(flow_setup_cb_t *cb,
 					       void *cb_ident, void *cb_priv,
 					       void (*release)(void *cb_priv),
 					       struct flow_block_offload *bo,
-					       struct net_device *dev, void *data,
+					       struct net_device *dev,
+					       struct Qdisc *sch, void *data,
 					       void *indr_cb_priv,
 					       void (*cleanup)(struct flow_block_cb *block_cb));
 void flow_block_cb_free(struct flow_block_cb *block_cb);
@@ -553,7 +556,7 @@ static inline void flow_block_init(struct flow_block *flow_block)
 	INIT_LIST_HEAD(&flow_block->cb_list);
 }
 
-typedef int flow_indr_block_bind_cb_t(struct net_device *dev, void *cb_priv,
+typedef int flow_indr_block_bind_cb_t(struct net_device *dev, struct Qdisc *sch, void *cb_priv,
 				      enum tc_setup_type type, void *type_data,
 				      void *data,
 				      void (*cleanup)(struct flow_block_cb *block_cb));
@@ -561,7 +564,7 @@ typedef int flow_indr_block_bind_cb_t(struct net_device *dev, void *cb_priv,
 int flow_indr_dev_register(flow_indr_block_bind_cb_t *cb, void *cb_priv);
 void flow_indr_dev_unregister(flow_indr_block_bind_cb_t *cb, void *cb_priv,
 			      void (*release)(void *cb_priv));
-int flow_indr_dev_setup_offload(struct net_device *dev,
+int flow_indr_dev_setup_offload(struct net_device *dev, struct Qdisc *sch,
 				enum tc_setup_type type, void *data,
 				struct flow_block_offload *bo,
 				void (*cleanup)(struct flow_block_cb *block_cb));

net/core/flow_offload.c

@@ -429,7 +429,7 @@ EXPORT_SYMBOL(flow_indr_dev_unregister);
 
 static void flow_block_indr_init(struct flow_block_cb *flow_block,
 				 struct flow_block_offload *bo,
-				 struct net_device *dev, void *data,
+				 struct net_device *dev, struct Qdisc *sch, void *data,
 				 void *cb_priv,
 				 void (*cleanup)(struct flow_block_cb *block_cb))
 {
@@ -437,6 +437,7 @@ static void flow_block_indr_init(struct flow_block_cb *flow_block,
 	flow_block->indr.data = data;
 	flow_block->indr.cb_priv = cb_priv;
 	flow_block->indr.dev = dev;
+	flow_block->indr.sch = sch;
 	flow_block->indr.cleanup = cleanup;
 }
 
@@ -444,7 +445,8 @@ struct flow_block_cb *flow_indr_block_cb_alloc(flow_setup_cb_t *cb,
 					       void *cb_ident, void *cb_priv,
 					       void (*release)(void *cb_priv),
 					       struct flow_block_offload *bo,
-					       struct net_device *dev, void *data,
+					       struct net_device *dev,
+					       struct Qdisc *sch, void *data,
 					       void *indr_cb_priv,
 					       void (*cleanup)(struct flow_block_cb *block_cb))
 {
@@ -454,7 +456,7 @@ struct flow_block_cb *flow_indr_block_cb_alloc(flow_setup_cb_t *cb,
 	if (IS_ERR(block_cb))
 		goto out;
 
-	flow_block_indr_init(block_cb, bo, dev, data, indr_cb_priv, cleanup);
+	flow_block_indr_init(block_cb, bo, dev, sch, data, indr_cb_priv, cleanup);
 	list_add(&block_cb->indr.list, &flow_block_indr_list);
 
 out:
@@ -462,7 +464,7 @@ struct flow_block_cb *flow_indr_block_cb_alloc(flow_setup_cb_t *cb,
 }
 EXPORT_SYMBOL(flow_indr_block_cb_alloc);
 
-int flow_indr_dev_setup_offload(struct net_device *dev,
+int flow_indr_dev_setup_offload(struct net_device *dev, struct Qdisc *sch,
 				enum tc_setup_type type, void *data,
 				struct flow_block_offload *bo,
 				void (*cleanup)(struct flow_block_cb *block_cb))
@@ -471,7 +473,7 @@ int flow_indr_dev_setup_offload(struct net_device *dev,
 
 	mutex_lock(&flow_indr_block_lock);
 	list_for_each_entry(this, &flow_block_indr_dev_list, list)
-		this->cb(dev, this->cb_priv, type, bo, data, cleanup);
+		this->cb(dev, sch, this->cb_priv, type, bo, data, cleanup);
 
 	mutex_unlock(&flow_indr_block_lock);
 

net/netfilter/nf_flow_table_offload.c

@@ -964,7 +964,7 @@ static int nf_flow_table_indr_offload_cmd(struct flow_block_offload *bo,
 	nf_flow_table_block_offload_init(bo, dev_net(dev), cmd, flowtable,
 					 extack);
 
-	return flow_indr_dev_setup_offload(dev, TC_SETUP_FT, flowtable, bo,
+	return flow_indr_dev_setup_offload(dev, NULL, TC_SETUP_FT, flowtable, bo,
 					   nf_flow_table_indr_cleanup);
 }
 

net/netfilter/nf_tables_offload.c

@@ -312,7 +312,7 @@ static int nft_indr_block_offload_cmd(struct nft_base_chain *basechain,
 
 	nft_flow_block_offload_init(&bo, dev_net(dev), cmd, basechain, &extack);
 
-	err = flow_indr_dev_setup_offload(dev, TC_SETUP_BLOCK, basechain, &bo,
+	err = flow_indr_dev_setup_offload(dev, NULL, TC_SETUP_BLOCK, basechain, &bo,
 					  nft_indr_block_cleanup);
 	if (err < 0)
 		return err;

net/sched/cls_api.c

@@ -622,7 +622,7 @@ static int tcf_block_setup(struct tcf_block *block,
 			   struct flow_block_offload *bo);
 
 static void tcf_block_offload_init(struct flow_block_offload *bo,
-				   struct net_device *dev,
+				   struct net_device *dev, struct Qdisc *sch,
 				   enum flow_block_command command,
 				   enum flow_block_binder_type binder_type,
 				   struct flow_block *flow_block,
@@ -634,6 +634,7 @@ static void tcf_block_offload_init(struct flow_block_offload *bo,
 	bo->block = flow_block;
 	bo->block_shared = shared;
 	bo->extack = extack;
+	bo->sch = sch;
 	INIT_LIST_HEAD(&bo->cb_list);
 }
 
@@ -644,10 +645,11 @@ static void tc_block_indr_cleanup(struct flow_block_cb *block_cb)
 {
 	struct tcf_block *block = block_cb->indr.data;
 	struct net_device *dev = block_cb->indr.dev;
+	struct Qdisc *sch = block_cb->indr.sch;
 	struct netlink_ext_ack extack = {};
 	struct flow_block_offload bo;
 
-	tcf_block_offload_init(&bo, dev, FLOW_BLOCK_UNBIND,
+	tcf_block_offload_init(&bo, dev, sch, FLOW_BLOCK_UNBIND,
 			       block_cb->indr.binder_type,
 			       &block->flow_block, tcf_block_shared(block),
 			       &extack);
@@ -666,14 +668,14 @@ static bool tcf_block_offload_in_use(struct tcf_block *block)
 }
 
 static int tcf_block_offload_cmd(struct tcf_block *block,
-				 struct net_device *dev,
+				 struct net_device *dev, struct Qdisc *sch,
 				 struct tcf_block_ext_info *ei,
 				 enum flow_block_command command,
 				 struct netlink_ext_ack *extack)
 {
 	struct flow_block_offload bo = {};
 
-	tcf_block_offload_init(&bo, dev, command, ei->binder_type,
+	tcf_block_offload_init(&bo, dev, sch, command, ei->binder_type,
 			       &block->flow_block, tcf_block_shared(block),
 			       extack);
 
@@ -690,7 +692,7 @@ static int tcf_block_offload_cmd(struct tcf_block *block,
 		return tcf_block_setup(block, &bo);
 	}
 
-	flow_indr_dev_setup_offload(dev, TC_SETUP_BLOCK, block, &bo,
+	flow_indr_dev_setup_offload(dev, sch, TC_SETUP_BLOCK, block, &bo,
 				    tc_block_indr_cleanup);
 	tcf_block_setup(block, &bo);
 
@@ -717,7 +719,7 @@ static int tcf_block_offload_bind(struct tcf_block *block, struct Qdisc *q,
 		goto err_unlock;
 	}
 
-	err = tcf_block_offload_cmd(block, dev, ei, FLOW_BLOCK_BIND, extack);
+	err = tcf_block_offload_cmd(block, dev, q, ei, FLOW_BLOCK_BIND, extack);
 	if (err == -EOPNOTSUPP)
 		goto no_offload_dev_inc;
 	if (err)
@@ -744,7 +746,7 @@ static void tcf_block_offload_unbind(struct tcf_block *block, struct Qdisc *q,
 	int err;
 
 	down_write(&block->cb_lock);
-	err = tcf_block_offload_cmd(block, dev, ei, FLOW_BLOCK_UNBIND, NULL);
+	err = tcf_block_offload_cmd(block, dev, q, ei, FLOW_BLOCK_UNBIND, NULL);
 	if (err == -EOPNOTSUPP)
 		goto no_offload_dev_dec;
 	up_write(&block->cb_lock);

tools/testing/selftests/drivers/net/mlxsw/sch_red_core.sh

@@ -121,6 +121,7 @@ h1_destroy()
 h2_create()
 {
 	host_create $h2 2
+	tc qdisc add dev $h2 clsact
 
 	# Some of the tests in this suite use multicast traffic. As this traffic
 	# enters BR2_10 resp. BR2_11, it is flooded to all other ports. Thus
@@ -141,6 +142,7 @@ h2_create()
 h2_destroy()
 {
 	ethtool -s $h2 autoneg on
+	tc qdisc del dev $h2 clsact
 	host_destroy $h2
 }
 
@@ -336,6 +338,17 @@ get_qdisc_npackets()
 		qdisc_stats_get $swp3 $(get_qdisc_handle $vlan) .packets
 }
 
+send_packets()
+{
+	local vlan=$1; shift
+	local proto=$1; shift
+	local pkts=$1; shift
+
+	$MZ $h2.$vlan -p 8000 -a own -b $h3_mac \
+	    -A $(ipaddr 2 $vlan) -B $(ipaddr 3 $vlan) \
+	    -t $proto -q -c $pkts "$@"
+}
+
 # This sends traffic in an attempt to build a backlog of $size. Returns 0 on
 # success. After 10 failed attempts it bails out and returns 1. It dumps the
 # backlog size to stdout.
@@ -364,9 +377,7 @@ build_backlog()
 			return 1
 		fi
 
-		$MZ $h2.$vlan -p 8000 -a own -b $h3_mac \
-		    -A $(ipaddr 2 $vlan) -B $(ipaddr 3 $vlan) \
-		    -t $proto -q -c $pkts "$@"
+		send_packets $vlan $proto $pkts "$@"
 	done
 }
 
@@ -531,3 +542,92 @@ do_mc_backlog_test()
 
 	log_test "TC $((vlan - 10)): Qdisc reports MC backlog"
 }
+
+do_drop_test()
+{
+	local vlan=$1; shift
+	local limit=$1; shift
+	local trigger=$1; shift
+	local subtest=$1; shift
+	local fetch_counter=$1; shift
+	local backlog
+	local base
+	local now
+	local pct
+
+	RET=0
+
+	start_traffic $h1.$vlan $(ipaddr 1 $vlan) $(ipaddr 3 $vlan) $h3_mac
+
+	# Create a bit of a backlog and observe no mirroring due to drops.
+	qevent_rule_install_$subtest
+	base=$($fetch_counter)
+
+	build_backlog $vlan $((2 * limit / 3)) udp >/dev/null
+
+	busywait 1100 until_counter_is ">= $((base + 1))" $fetch_counter >/dev/null
+	check_fail $? "Spurious packets observed without buffer pressure"
+
+	qevent_rule_uninstall_$subtest
+
+	# Push to the queue until it's at the limit. The configured limit is
+	# rounded by the qdisc and then by the driver, so this is the best we
+	# can do to get to the real limit of the system. Do this with the rules
+	# uninstalled so that the inevitable drops don't get counted.
+	build_backlog $vlan $((3 * limit / 2)) udp >/dev/null
+
+	qevent_rule_install_$subtest
+	base=$($fetch_counter)
+
+	send_packets $vlan udp 11
+
+	now=$(busywait 1100 until_counter_is ">= $((base + 10))" $fetch_counter)
+	check_err $? "Dropped packets not observed: 11 expected, $((now - base)) seen"
+
+	# When no extra traffic is injected, there should be no mirroring.
+	busywait 1100 until_counter_is ">= $((base + 20))" $fetch_counter >/dev/null
+	check_fail $? "Spurious packets observed"
+
+	# When the rule is uninstalled, there should be no mirroring.
+	qevent_rule_uninstall_$subtest
+	send_packets $vlan udp 11
+	busywait 1100 until_counter_is ">= $((base + 20))" $fetch_counter >/dev/null
+	check_fail $? "Spurious packets observed after uninstall"
+
+	log_test "TC $((vlan - 10)): ${trigger}ped packets $subtest'd"
+
+	stop_traffic
+	sleep 1
+}
+
+qevent_rule_install_mirror()
+{
+	tc filter add block 10 pref 1234 handle 102 matchall skip_sw \
+	   action mirred egress mirror dev $swp2 hw_stats disabled
+}
+
+qevent_rule_uninstall_mirror()
+{
+	tc filter del block 10 pref 1234 handle 102 matchall
+}
+
+qevent_counter_fetch_mirror()
+{
+	tc_rule_handle_stats_get "dev $h2 ingress" 101
+}
+
+do_drop_mirror_test()
+{
+	local vlan=$1; shift
+	local limit=$1; shift
+	local qevent_name=$1; shift
+
+	tc filter add dev $h2 ingress pref 1 handle 101 prot ip \
+	   flower skip_sw ip_proto udp \
+	   action drop
+
+	do_drop_test "$vlan" "$limit" "$qevent_name" mirror \
+		     qevent_counter_fetch_mirror
+
+	tc filter del dev $h2 ingress pref 1 handle 101 flower
+}

tools/testing/selftests/drivers/net/mlxsw/sch_red_ets.sh

@@ -7,6 +7,7 @@ ALL_TESTS="
 	ecn_nodrop_test
 	red_test
 	mc_backlog_test
+	red_mirror_test
 "
 : ${QDISC:=ets}
 source sch_red_core.sh
@@ -83,6 +84,16 @@ mc_backlog_test()
 	uninstall_qdisc
 }
 
+red_mirror_test()
+{
+	install_qdisc qevent early_drop block 10
+
+	do_drop_mirror_test 10 $BACKLOG1 early_drop
+	do_drop_mirror_test 11 $BACKLOG2 early_drop
+
+	uninstall_qdisc
+}
+
 trap cleanup EXIT
 
 setup_prepare

tools/testing/selftests/drivers/net/mlxsw/sch_red_root.sh

@@ -7,6 +7,7 @@ ALL_TESTS="
 	ecn_nodrop_test
 	red_test
 	mc_backlog_test
+	red_mirror_test
 "
 source sch_red_core.sh
 
@@ -57,6 +58,13 @@ mc_backlog_test()
 	uninstall_qdisc
 }
 
+red_mirror_test()
+{
+	install_qdisc qevent early_drop block 10
+	do_drop_mirror_test 10 $BACKLOG
+	uninstall_qdisc
+}
+
 trap cleanup EXIT
 
 setup_prepare