igc: Add Tx hardware timestamp request for AF_XDP zero-copy packet

This patch adds support to per-packet Tx hardware timestamp request to
AF_XDP zero-copy packet via XDP Tx metadata framework. Please note that
user needs to enable Tx HW timestamp capability via igc_ioctl() with
SIOCSHWTSTAMP cmd before sending xsk Tx hardware timestamp request.

Same as implementation in RX timestamp XDP hints kfunc metadata, Timer 0
(adjustable clock) is used in xsk Tx hardware timestamp. i225/i226 have
four sets of timestamping registers. *skb and *xsk_tx_buffer pointers
are used to indicate whether the timestamping register is already occupied.

Furthermore, a boolean variable named xsk_pending_ts is used to hold the
transmit completion until the tx hardware timestamp is ready. This is
because, for i225/i226, the timestamp notification event comes some time
after the transmit completion event. The driver will retrigger hardware irq
to clean the packet after retrieve the tx hardware timestamp.

Besides, xsk_meta is added into struct igc_tx_timestamp_request as a hook
to the metadata location of the transmit packet. When the Tx timestamp
interrupt is fired, the interrupt handler will copy the value of Tx hwts
into metadata location via xsk_tx_metadata_complete().

This patch is tested with tools/testing/selftests/bpf/xdp_hw_metadata
on Intel ADL-S platform. Below are the test steps and results.

Test Step 1: Run xdp_hw_metadata app
 ./xdp_hw_metadata <iface> > /dev/shm/result.log

Test Step 2: Enable Tx hardware timestamp
 hwstamp_ctl -i <iface> -t 1 -r 1

Test Step 3: Run ptp4l and phc2sys for time synchronization

Test Step 4: Generate UDP packets with 1ms interval for 10s
 trafgen --dev <iface> '{eth(da=<addr>), udp(dp=9091)}' -t 1ms -n 10000

Test Step 5: Rerun Step 1-3 with 10s iperf3 as background traffic

Test Step 6: Rerun Step 1-4 with 10s iperf3 as background traffic

Based on iperf3 results below, the impact of holding tx completion to
throughput is not observable.

Result of last UDP packet (no. 10000) in Step 4:
poll: 1 (0) skip=99 fail=0 redir=10000
xsk_ring_cons__peek: 1
0x5640a37972d0: rx_desc[9999]->addr=f2110 addr=f2110 comp_addr=f2110 EoP
rx_hash: 0x2049BE1D with RSS type:0x1
HW RX-time:   1679819246792971268 (sec:1679819246.7930) delta to User RX-time sec:0.0000 (14.990 usec)
XDP RX-time:   1679819246792981987 (sec:1679819246.7930) delta to User RX-time sec:0.0000 (4.271 usec)
No rx_vlan_tci or rx_vlan_proto, err=-95
0x5640a37972d0: ping-pong with csum=ab19 (want 315b) csum_start=34 csum_offset=6
0x5640a37972d0: complete tx idx=9999 addr=f010
HW TX-complete-time:   1679819246793036971 (sec:1679819246.7930) delta to User TX-complete-time sec:0.0001 (77.656 usec)
XDP RX-time:   1679819246792981987 (sec:1679819246.7930) delta to User TX-complete-time sec:0.0001 (132.640 usec)
HW RX-time:   1679819246792971268 (sec:1679819246.7930) delta to HW TX-complete-time sec:0.0001 (65.703 usec)
0x5640a37972d0: complete rx idx=10127 addr=f2110

Result of iperf3 without tx hwts request in step 5:
[ ID] Interval           Transfer     Bitrate         Retr
[  5]   0.00-10.00  sec  2.74 GBytes  2.36 Gbits/sec    0             sender
[  5]   0.00-10.05  sec  2.74 GBytes  2.34 Gbits/sec                  receiver

Result of iperf3 running parallel with trafgen command in step 6:
[ ID] Interval           Transfer     Bitrate         Retr
[  5]   0.00-10.00  sec  2.74 GBytes  2.36 Gbits/sec    0             sender
[  5]   0.00-10.04  sec  2.74 GBytes  2.34 Gbits/sec                  receiver

Co-developed-by: Lai Peter Jun Ann <jun.ann.lai@intel.com>
Signed-off-by: Lai Peter Jun Ann <jun.ann.lai@intel.com>
Signed-off-by: Song Yoong Siang <yoong.siang.song@intel.com>
Acked-by: John Fastabend <john.fastabend@gmail.com>
Acked-by: Vinicius Costa Gomes <vinicius.gomes@intel.com>
Tested-by: Naama Meir <naamax.meir@linux.intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Link: https://lore.kernel.org/r/20240424210256.3440903-1-anthony.l.nguyen@intel.com
Signed-off-by: Paolo Abeni <pabeni@redhat.com>

1 files changed, 107 insertions, 6 deletions

diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
index b529fb59f9d5..34c257a51ed1 100644
--- a/drivers/net/ethernet/intel/igc/igc_main.c
+++ b/drivers/net/ethernet/intel/igc/igc_main.c
@@ -2873,6 +2873,89 @@ static void igc_update_tx_stats(struct igc_q_vector *q_vector,
 	q_vector->tx.total_packets += packets;
 }
 
+static void igc_xsk_request_timestamp(void *_priv)
+{
+	struct igc_metadata_request *meta_req = _priv;
+	struct igc_ring *tx_ring = meta_req->tx_ring;
+	struct igc_tx_timestamp_request *tstamp;
+	u32 tx_flags = IGC_TX_FLAGS_TSTAMP;
+	struct igc_adapter *adapter;
+	unsigned long lock_flags;
+	bool found = false;
+	int i;
+
+	if (test_bit(IGC_RING_FLAG_TX_HWTSTAMP, &tx_ring->flags)) {
+		adapter = netdev_priv(tx_ring->netdev);
+
+		spin_lock_irqsave(&adapter->ptp_tx_lock, lock_flags);
+
+		/* Search for available tstamp regs */
+		for (i = 0; i < IGC_MAX_TX_TSTAMP_REGS; i++) {
+			tstamp = &adapter->tx_tstamp[i];
+
+			/* tstamp->skb and tstamp->xsk_tx_buffer are in union.
+			 * When tstamp->skb is equal to NULL,
+			 * tstamp->xsk_tx_buffer is equal to NULL as well.
+			 * This condition means that the particular tstamp reg
+			 * is not occupied by other packet.
+			 */
+			if (!tstamp->skb) {
+				found = true;
+				break;
+			}
+		}
+
+		/* Return if no available tstamp regs */
+		if (!found) {
+			adapter->tx_hwtstamp_skipped++;
+			spin_unlock_irqrestore(&adapter->ptp_tx_lock,
+					       lock_flags);
+			return;
+		}
+
+		tstamp->start = jiffies;
+		tstamp->xsk_queue_index = tx_ring->queue_index;
+		tstamp->xsk_tx_buffer = meta_req->tx_buffer;
+		tstamp->buffer_type = IGC_TX_BUFFER_TYPE_XSK;
+
+		/* Hold the transmit completion until timestamp is ready */
+		meta_req->tx_buffer->xsk_pending_ts = true;
+
+		/* Keep the pointer to tx_timestamp, which is located in XDP
+		 * metadata area. It is the location to store the value of
+		 * tx hardware timestamp.
+		 */
+		xsk_tx_metadata_to_compl(meta_req->meta, &tstamp->xsk_meta);
+
+		/* Set timestamp bit based on the _TSTAMP(_X) bit. */
+		tx_flags |= tstamp->flags;
+		meta_req->cmd_type |= IGC_SET_FLAG(tx_flags,
+						   IGC_TX_FLAGS_TSTAMP,
+						   (IGC_ADVTXD_MAC_TSTAMP));
+		meta_req->cmd_type |= IGC_SET_FLAG(tx_flags,
+						   IGC_TX_FLAGS_TSTAMP_1,
+						   (IGC_ADVTXD_TSTAMP_REG_1));
+		meta_req->cmd_type |= IGC_SET_FLAG(tx_flags,
+						   IGC_TX_FLAGS_TSTAMP_2,
+						   (IGC_ADVTXD_TSTAMP_REG_2));
+		meta_req->cmd_type |= IGC_SET_FLAG(tx_flags,
+						   IGC_TX_FLAGS_TSTAMP_3,
+						   (IGC_ADVTXD_TSTAMP_REG_3));
+
+		spin_unlock_irqrestore(&adapter->ptp_tx_lock, lock_flags);
+	}
+}
+
+static u64 igc_xsk_fill_timestamp(void *_priv)
+{
+	return *(u64 *)_priv;
+}
+
+const struct xsk_tx_metadata_ops igc_xsk_tx_metadata_ops = {
+	.tmo_request_timestamp		= igc_xsk_request_timestamp,
+	.tmo_fill_timestamp		= igc_xsk_fill_timestamp,
+};
+
 static void igc_xdp_xmit_zc(struct igc_ring *ring)
 {
 	struct xsk_buff_pool *pool = ring->xsk_pool;
@@ -2894,24 +2977,34 @@ static void igc_xdp_xmit_zc(struct igc_ring *ring)
 	budget = igc_desc_unused(ring);
 
 	while (xsk_tx_peek_desc(pool, &xdp_desc) && budget--) {
-		u32 cmd_type, olinfo_status;
+		struct igc_metadata_request meta_req;
+		struct xsk_tx_metadata *meta = NULL;
 		struct igc_tx_buffer *bi;
+		u32 olinfo_status;
 		dma_addr_t dma;
 
-		cmd_type = IGC_ADVTXD_DTYP_DATA | IGC_ADVTXD_DCMD_DEXT |
-			   IGC_ADVTXD_DCMD_IFCS | IGC_TXD_DCMD |
-			   xdp_desc.len;
+		meta_req.cmd_type = IGC_ADVTXD_DTYP_DATA |
+				    IGC_ADVTXD_DCMD_DEXT |
+				    IGC_ADVTXD_DCMD_IFCS |
+				    IGC_TXD_DCMD | xdp_desc.len;
 		olinfo_status = xdp_desc.len << IGC_ADVTXD_PAYLEN_SHIFT;
 
 		dma = xsk_buff_raw_get_dma(pool, xdp_desc.addr);
+		meta = xsk_buff_get_metadata(pool, xdp_desc.addr);
 		xsk_buff_raw_dma_sync_for_device(pool, dma, xdp_desc.len);
+		bi = &ring->tx_buffer_info[ntu];
+
+		meta_req.tx_ring = ring;
+		meta_req.tx_buffer = bi;
+		meta_req.meta = meta;
+		xsk_tx_metadata_request(meta, &igc_xsk_tx_metadata_ops,
+					&meta_req);
 
 		tx_desc = IGC_TX_DESC(ring, ntu);
-		tx_desc->read.cmd_type_len = cpu_to_le32(cmd_type);
+		tx_desc->read.cmd_type_len = cpu_to_le32(meta_req.cmd_type);
 		tx_desc->read.olinfo_status = cpu_to_le32(olinfo_status);
 		tx_desc->read.buffer_addr = cpu_to_le64(dma);
 
-		bi = &ring->tx_buffer_info[ntu];
 		bi->type = IGC_TX_BUFFER_TYPE_XSK;
 		bi->protocol = 0;
 		bi->bytecount = xdp_desc.len;
@@ -2974,6 +3067,13 @@ static bool igc_clean_tx_irq(struct igc_q_vector *q_vector, int napi_budget)
 		if (!(eop_desc->wb.status & cpu_to_le32(IGC_TXD_STAT_DD)))
 			break;
 
+		/* Hold the completions while there's a pending tx hardware
+		 * timestamp request from XDP Tx metadata.
+		 */
+		if (tx_buffer->type == IGC_TX_BUFFER_TYPE_XSK &&
+		    tx_buffer->xsk_pending_ts)
+			break;
+
 		/* clear next_to_watch to prevent false hangs */
 		tx_buffer->next_to_watch = NULL;
 
@@ -6802,6 +6902,7 @@ static int igc_probe(struct pci_dev *pdev,
 
 	netdev->netdev_ops = &igc_netdev_ops;
 	netdev->xdp_metadata_ops = &igc_xdp_metadata_ops;
+	netdev->xsk_tx_metadata_ops = &igc_xsk_tx_metadata_ops;
 	igc_ethtool_set_ops(netdev);
 	netdev->watchdog_timeo = 5 * HZ;