ixgbe: let the xdpdrv work with more than 64 cpus

Originally, ixgbe driver doesn't allow the mounting of xdpdrv if the
server is equipped with more than 64 cpus online. So it turns out that
the loading of xdpdrv causes the "NOMEM" failure.

Actually, we can adjust the algorithm and then make it work through
mapping the current cpu to some xdp ring with the protect of @tx_lock.

Here are some numbers before/after applying this patch with xdp-example
loaded on the eth0X:

As client (tx path):
                     Before    After
TCP_STREAM send-64   734.14    714.20
TCP_STREAM send-128  1401.91   1395.05
TCP_STREAM send-512  5311.67   5292.84
TCP_STREAM send-1k   9277.40   9356.22 (not stable)
TCP_RR     send-1    22559.75  21844.22
TCP_RR     send-128  23169.54  22725.13
TCP_RR     send-512  21670.91  21412.56

As server (rx path):
                     Before    After
TCP_STREAM send-64   1416.49   1383.12
TCP_STREAM send-128  3141.49   3055.50
TCP_STREAM send-512  9488.73   9487.44
TCP_STREAM send-1k   9491.17   9356.22 (not stable)
TCP_RR     send-1    23617.74  23601.60
...

Notice: the TCP_RR mode is unstable as the official document explains.

I tested many times with different parameters combined through netperf.
Though the result is not that accurate, I cannot see much influence on
this patch. The static key is places on the hot path, but it actually
shouldn't cause a huge regression theoretically.

Co-developed-by: Shujin Li <lishujin@kuaishou.com>
Signed-off-by: Shujin Li <lishujin@kuaishou.com>
Signed-off-by: Jason Xing <xingwanli@kuaishou.com>
Tested-by: Sandeep Penigalapati <sandeep.penigalapati@intel.com>
Signed-off-by: Tony Nguyen <anthony.l.nguyen@intel.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 9 insertions, 7 deletions

diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c
index b1d22e4d5ec9..db2bc58dfcfd 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_xsk.c
@@ -100,6 +100,7 @@ static int ixgbe_run_xdp_zc(struct ixgbe_adapter *adapter,
 {
 	int err, result = IXGBE_XDP_PASS;
 	struct bpf_prog *xdp_prog;
+	struct ixgbe_ring *ring;
 	struct xdp_frame *xdpf;
 	u32 act;
 
@@ -120,7 +121,12 @@ static int ixgbe_run_xdp_zc(struct ixgbe_adapter *adapter,
 		xdpf = xdp_convert_buff_to_frame(xdp);
 		if (unlikely(!xdpf))
 			goto out_failure;
-		result = ixgbe_xmit_xdp_ring(adapter, xdpf);
+		ring = ixgbe_determine_xdp_ring(adapter);
+		if (static_branch_unlikely(&ixgbe_xdp_locking_key))
+			spin_lock(&ring->tx_lock);
+		result = ixgbe_xmit_xdp_ring(ring, xdpf);
+		if (static_branch_unlikely(&ixgbe_xdp_locking_key))
+			spin_unlock(&ring->tx_lock);
 		if (result == IXGBE_XDP_CONSUMED)
 			goto out_failure;
 		break;
@@ -334,13 +340,9 @@ int ixgbe_clean_rx_irq_zc(struct ixgbe_q_vector *q_vector,
 		xdp_do_flush_map();
 
 	if (xdp_xmit & IXGBE_XDP_TX) {
-		struct ixgbe_ring *ring = adapter->xdp_ring[smp_processor_id()];
+		struct ixgbe_ring *ring = ixgbe_determine_xdp_ring(adapter);
 
-		/* Force memory writes to complete before letting h/w
-		 * know there are new descriptors to fetch.
-		 */
-		wmb();
-		writel(ring->next_to_use, ring->tail);
+		ixgbe_xdp_ring_update_tail_locked(ring);
 	}
 
 	u64_stats_update_begin(&rx_ring->syncp);