igb: Add support for ETF offload

Implement HW offload support for SO_TXTIME through igb's Launchtime
feature. This is done by extending igb_setup_tc() so it supports
TC_SETUP_QDISC_ETF and configuring i210 so time based transmit
arbitration is enabled.

The FQTSS transmission mode added before is extended so strict
priority (SP) queues wait for stream reservation (SR) ones.
igb_config_tx_modes() is extended so it can support enabling/disabling
Launchtime following the previous approach used for the credit-based
shaper (CBS).

As the previous flow, FQTSS transmission mode is enabled automatically
by the driver once Launchtime (or CBS, as before) is enabled.
Similarly, it's automatically disabled when the feature is disabled
for the last queue that had it setup on.

The driver just consumes the transmit times from the skbuffs directly,
so no special handling is done in case an 'invalid' time is provided.
We assume this has been handled by the ETF qdisc already.

Signed-off-by: Jesus Sanchez-Palencia <jesus.sanchez-palencia@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/net/ethernet/intel/igb/e1000_defines.h

@@ -1048,6 +1048,22 @@
 #define E1000_TQAVCTRL_XMIT_MODE	BIT(0)
 #define E1000_TQAVCTRL_DATAFETCHARB	BIT(4)
 #define E1000_TQAVCTRL_DATATRANARB	BIT(8)
+#define E1000_TQAVCTRL_DATATRANTIM	BIT(9)
+#define E1000_TQAVCTRL_SP_WAIT_SR	BIT(10)
+/* Fetch Time Delta - bits 31:16
+ *
+ * This field holds the value to be reduced from the launch time for
+ * fetch time decision. The FetchTimeDelta value is defined in 32 ns
+ * granularity.
+ *
+ * This field is 16 bits wide, and so the maximum value is:
+ *
+ * 65535 * 32 = 2097120 ~= 2.1 msec
+ *
+ * XXX: We are configuring the max value here since we couldn't come up
+ * with a reason for not doing so.
+ */
+#define E1000_TQAVCTRL_FETCHTIME_DELTA	(0xFFFF << 16)
 
 /* TX Qav Credit Control fields */
 #define E1000_TQAVCC_IDLESLOPE_MASK	0xFFFF

drivers/net/ethernet/intel/igb/igb.h

@@ -262,6 +262,7 @@ struct igb_ring {
 	u16 count;			/* number of desc. in the ring */
 	u8 queue_index;			/* logical index of the ring*/
 	u8 reg_idx;			/* physical index of the ring */
+	bool launchtime_enable;		/* true if LaunchTime is enabled */
 	bool cbs_enable;		/* indicates if CBS is enabled */
 	s32 idleslope;			/* idleSlope in kbps */
 	s32 sendslope;			/* sendSlope in kbps */

drivers/net/ethernet/intel/igb/igb_main.c

@@ -1666,13 +1666,26 @@ static bool is_any_cbs_enabled(struct igb_adapter *adapter)
 	return false;
 }
 
+static bool is_any_txtime_enabled(struct igb_adapter *adapter)
+{
+	int i;
+
+	for (i = 0; i < adapter->num_tx_queues; i++) {
+		if (adapter->tx_ring[i]->launchtime_enable)
+			return true;
+	}
+
+	return false;
+}
+
 /**
  *  igb_config_tx_modes - Configure "Qav Tx mode" features on igb
  *  @adapter: pointer to adapter struct
  *  @queue: queue number
  *
- *  Configure CBS for a given hardware queue. Parameters are retrieved
- *  from the correct Tx ring, so igb_save_cbs_params() should be used
+ *  Configure CBS and Launchtime for a given hardware queue.
+ *  Parameters are retrieved from the correct Tx ring, so
+ *  igb_save_cbs_params() and igb_save_txtime_params() should be used
  *  for setting those correctly prior to this function being called.
  **/
 static void igb_config_tx_modes(struct igb_adapter *adapter, int queue)
@@ -1686,6 +1699,19 @@ static void igb_config_tx_modes(struct igb_adapter *adapter, int queue)
 	WARN_ON(hw->mac.type != e1000_i210);
 	WARN_ON(queue < 0 || queue > 1);
 
+	/* If any of the Qav features is enabled, configure queues as SR and
+	 * with HIGH PRIO. If none is, then configure them with LOW PRIO and
+	 * as SP.
+	 */
+	if (ring->cbs_enable || ring->launchtime_enable) {
+		set_tx_desc_fetch_prio(hw, queue, TX_QUEUE_PRIO_HIGH);
+		set_queue_mode(hw, queue, QUEUE_MODE_STREAM_RESERVATION);
+	} else {
+		set_tx_desc_fetch_prio(hw, queue, TX_QUEUE_PRIO_LOW);
+		set_queue_mode(hw, queue, QUEUE_MODE_STRICT_PRIORITY);
+	}
+
+	/* If CBS is enabled, set DataTranARB and config its parameters. */
 	if (ring->cbs_enable || queue == 0) {
 		/* i210 does not allow the queue 0 to be in the Strict
 		 * Priority mode while the Qav mode is enabled, so,
@@ -1702,9 +1728,6 @@ static void igb_config_tx_modes(struct igb_adapter *adapter, int queue)
 			ring->hicredit = ETH_FRAME_LEN;
 		}
 
-		set_tx_desc_fetch_prio(hw, queue, TX_QUEUE_PRIO_HIGH);
-		set_queue_mode(hw, queue, QUEUE_MODE_STREAM_RESERVATION);
-
 		/* Always set data transfer arbitration to credit-based
 		 * shaper algorithm on TQAVCTRL if CBS is enabled for any of
 		 * the queues.
@@ -1780,8 +1803,6 @@ static void igb_config_tx_modes(struct igb_adapter *adapter, int queue)
 		wr32(E1000_I210_TQAVHC(queue),
 		     0x80000000 + ring->hicredit * 0x7735);
 	} else {
-		set_tx_desc_fetch_prio(hw, queue, TX_QUEUE_PRIO_LOW);
-		set_queue_mode(hw, queue, QUEUE_MODE_STRICT_PRIORITY);
 
 		/* Set idleSlope to zero. */
 		tqavcc = rd32(E1000_I210_TQAVCC(queue));
@@ -1802,17 +1823,61 @@ static void igb_config_tx_modes(struct igb_adapter *adapter, int queue)
 		}
 	}
 
+	/* If LaunchTime is enabled, set DataTranTIM. */
+	if (ring->launchtime_enable) {
+		/* Always set DataTranTIM on TQAVCTRL if LaunchTime is enabled
+		 * for any of the SR queues, and configure fetchtime delta.
+		 * XXX NOTE:
+		 *     - LaunchTime will be enabled for all SR queues.
+		 *     - A fixed offset can be added relative to the launch
+		 *       time of all packets if configured at reg LAUNCH_OS0.
+		 *       We are keeping it as 0 for now (default value).
+		 */
+		tqavctrl = rd32(E1000_I210_TQAVCTRL);
+		tqavctrl |= E1000_TQAVCTRL_DATATRANTIM |
+		       E1000_TQAVCTRL_FETCHTIME_DELTA;
+		wr32(E1000_I210_TQAVCTRL, tqavctrl);
+	} else {
+		/* If Launchtime is not enabled for any SR queues anymore,
+		 * then clear DataTranTIM on TQAVCTRL and clear fetchtime delta,
+		 * effectively disabling Launchtime.
+		 */
+		if (!is_any_txtime_enabled(adapter)) {
+			tqavctrl = rd32(E1000_I210_TQAVCTRL);
+			tqavctrl &= ~E1000_TQAVCTRL_DATATRANTIM;
+			tqavctrl &= ~E1000_TQAVCTRL_FETCHTIME_DELTA;
+			wr32(E1000_I210_TQAVCTRL, tqavctrl);
+		}
+	}
+
 	/* XXX: In i210 controller the sendSlope and loCredit parameters from
 	 * CBS are not configurable by software so we don't do any 'controller
 	 * configuration' in respect to these parameters.
 	 */
 
-	netdev_dbg(netdev, "CBS %s: queue %d idleslope %d sendslope %d hiCredit %d locredit %d\n",
-		   (ring->cbs_enable) ? "enabled" : "disabled", queue,
+	netdev_dbg(netdev, "Qav Tx mode: cbs %s, launchtime %s, queue %d \
+			    idleslope %d sendslope %d hiCredit %d \
+			    locredit %d\n",
+		   (ring->cbs_enable) ? "enabled" : "disabled",
+		   (ring->launchtime_enable) ? "enabled" : "disabled", queue,
 		   ring->idleslope, ring->sendslope, ring->hicredit,
 		   ring->locredit);
 }
 
+static int igb_save_txtime_params(struct igb_adapter *adapter, int queue,
+				  bool enable)
+{
+	struct igb_ring *ring;
+
+	if (queue < 0 || queue > adapter->num_tx_queues)
+		return -EINVAL;
+
+	ring = adapter->tx_ring[queue];
+	ring->launchtime_enable = enable;
+
+	return 0;
+}
+
 static int igb_save_cbs_params(struct igb_adapter *adapter, int queue,
 			       bool enable, int idleslope, int sendslope,
 			       int hicredit, int locredit)
@@ -1856,10 +1921,11 @@ static void igb_setup_tx_mode(struct igb_adapter *adapter)
 		int i, max_queue;
 
 		/* Configure TQAVCTRL register: set transmit mode to 'Qav',
-		 * set data fetch arbitration to 'round robin'.
+		 * set data fetch arbitration to 'round robin', set SP_WAIT_SR
+		 * so SP queues wait for SR ones.
 		 */
 		val = rd32(E1000_I210_TQAVCTRL);
-		val |= E1000_TQAVCTRL_XMIT_MODE;
+		val |= E1000_TQAVCTRL_XMIT_MODE | E1000_TQAVCTRL_SP_WAIT_SR;
 		val &= ~E1000_TQAVCTRL_DATAFETCHARB;
 		wr32(E1000_I210_TQAVCTRL, val);
 
@@ -2483,7 +2549,7 @@ static void igb_offload_apply(struct igb_adapter *adapter, s32 queue)
 
 	igb_config_tx_modes(adapter, queue);
 
-	if (!is_any_cbs_enabled(adapter))
+	if (!is_any_cbs_enabled(adapter) && !is_any_txtime_enabled(adapter))
 		enable_fqtss(adapter, false);
 }
 
@@ -2756,6 +2822,29 @@ static int igb_setup_tc_block(struct igb_adapter *adapter,
 	}
 }
 
+static int igb_offload_txtime(struct igb_adapter *adapter,
+			      struct tc_etf_qopt_offload *qopt)
+{
+	struct e1000_hw *hw = &adapter->hw;
+	int err;
+
+	/* Launchtime offloading is only supported by i210 controller. */
+	if (hw->mac.type != e1000_i210)
+		return -EOPNOTSUPP;
+
+	/* Launchtime offloading is only supported by queues 0 and 1. */
+	if (qopt->queue < 0 || qopt->queue > 1)
+		return -EINVAL;
+
+	err = igb_save_txtime_params(adapter, qopt->queue, qopt->enable);
+	if (err)
+		return err;
+
+	igb_offload_apply(adapter, qopt->queue);
+
+	return 0;
+}
+
 static int igb_setup_tc(struct net_device *dev, enum tc_setup_type type,
 			void *type_data)
 {
@@ -2766,6 +2855,8 @@ static int igb_setup_tc(struct net_device *dev, enum tc_setup_type type,
 		return igb_offload_cbs(adapter, type_data);
 	case TC_SETUP_BLOCK:
 		return igb_setup_tc_block(adapter, type_data);
+	case TC_SETUP_QDISC_ETF:
+		return igb_offload_txtime(adapter, type_data);
 
 	default:
 		return -EOPNOTSUPP;
@@ -5586,11 +5677,14 @@ set_itr_now:
 	}
 }
 
-static void igb_tx_ctxtdesc(struct igb_ring *tx_ring, u32 vlan_macip_lens,
-			    u32 type_tucmd, u32 mss_l4len_idx)
+static void igb_tx_ctxtdesc(struct igb_ring *tx_ring,
+			    struct igb_tx_buffer *first,
+			    u32 vlan_macip_lens, u32 type_tucmd,
+			    u32 mss_l4len_idx)
 {
 	struct e1000_adv_tx_context_desc *context_desc;
 	u16 i = tx_ring->next_to_use;
+	struct timespec64 ts;
 
 	context_desc = IGB_TX_CTXTDESC(tx_ring, i);
 
@@ -5605,9 +5699,18 @@ static void igb_tx_ctxtdesc(struct igb_ring *tx_ring, u32 vlan_macip_lens,
 		mss_l4len_idx |= tx_ring->reg_idx << 4;
 
 	context_desc->vlan_macip_lens	= cpu_to_le32(vlan_macip_lens);
-	context_desc->seqnum_seed	= 0;
 	context_desc->type_tucmd_mlhl	= cpu_to_le32(type_tucmd);
 	context_desc->mss_l4len_idx	= cpu_to_le32(mss_l4len_idx);
+
+	/* We assume there is always a valid tx time available. Invalid times
+	 * should have been handled by the upper layers.
+	 */
+	if (tx_ring->launchtime_enable) {
+		ts = ns_to_timespec64(first->skb->tstamp);
+		context_desc->seqnum_seed = cpu_to_le32(ts.tv_nsec / 32);
+	} else {
+		context_desc->seqnum_seed = 0;
+	}
 }
 
 static int igb_tso(struct igb_ring *tx_ring,
@@ -5690,7 +5793,8 @@ static int igb_tso(struct igb_ring *tx_ring,
 	vlan_macip_lens |= (ip.hdr - skb->data) << E1000_ADVTXD_MACLEN_SHIFT;
 	vlan_macip_lens |= first->tx_flags & IGB_TX_FLAGS_VLAN_MASK;
 
-	igb_tx_ctxtdesc(tx_ring, vlan_macip_lens, type_tucmd, mss_l4len_idx);
+	igb_tx_ctxtdesc(tx_ring, first, vlan_macip_lens,
+			type_tucmd, mss_l4len_idx);
 
 	return 1;
 }
@@ -5745,7 +5849,7 @@ no_csum:
 	vlan_macip_lens |= skb_network_offset(skb) << E1000_ADVTXD_MACLEN_SHIFT;
 	vlan_macip_lens |= first->tx_flags & IGB_TX_FLAGS_VLAN_MASK;
 
-	igb_tx_ctxtdesc(tx_ring, vlan_macip_lens, type_tucmd, 0);
+	igb_tx_ctxtdesc(tx_ring, first, vlan_macip_lens, type_tucmd, 0);
 }
 
 #define IGB_SET_FLAG(_input, _flag, _result) \