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, 21 insertions, 2 deletions

diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe.h b/drivers/net/ethernet/intel/ixgbe/ixgbe.h
index a604552fa634..4a69823e6abd 100644
--- a/drivers/net/ethernet/intel/ixgbe/ixgbe.h
+++ b/drivers/net/ethernet/intel/ixgbe/ixgbe.h
@@ -351,6 +351,7 @@ struct ixgbe_ring {
 	};
 	u16 rx_offset;
 	struct xdp_rxq_info xdp_rxq;
+	spinlock_t tx_lock;	/* used in XDP mode */
 	struct xsk_buff_pool *xsk_pool;
 	u16 ring_idx;		/* {rx,tx,xdp}_ring back reference idx */
 	u16 rx_buf_len;
@@ -375,11 +376,13 @@ enum ixgbe_ring_f_enum {
 #define IXGBE_MAX_FCOE_INDICES		8
 #define MAX_RX_QUEUES			(IXGBE_MAX_FDIR_INDICES + 1)
 #define MAX_TX_QUEUES			(IXGBE_MAX_FDIR_INDICES + 1)
-#define MAX_XDP_QUEUES			(IXGBE_MAX_FDIR_INDICES + 1)
+#define IXGBE_MAX_XDP_QS		(IXGBE_MAX_FDIR_INDICES + 1)
 #define IXGBE_MAX_L2A_QUEUES		4
 #define IXGBE_BAD_L2A_QUEUE		3
 #define IXGBE_MAX_MACVLANS		63
 
+DECLARE_STATIC_KEY_FALSE(ixgbe_xdp_locking_key);
+
 struct ixgbe_ring_feature {
 	u16 limit;	/* upper limit on feature indices */
 	u16 indices;	/* current value of indices */
@@ -629,7 +632,7 @@ struct ixgbe_adapter {
 
 	/* XDP */
 	int num_xdp_queues;
-	struct ixgbe_ring *xdp_ring[MAX_XDP_QUEUES];
+	struct ixgbe_ring *xdp_ring[IXGBE_MAX_XDP_QS];
 	unsigned long *af_xdp_zc_qps; /* tracks AF_XDP ZC enabled rings */
 
 	/* TX */
@@ -772,6 +775,22 @@ struct ixgbe_adapter {
 #endif /* CONFIG_IXGBE_IPSEC */
 };
 
+static inline int ixgbe_determine_xdp_q_idx(int cpu)
+{
+	if (static_key_enabled(&ixgbe_xdp_locking_key))
+		return cpu % IXGBE_MAX_XDP_QS;
+	else
+		return cpu;
+}
+
+static inline
+struct ixgbe_ring *ixgbe_determine_xdp_ring(struct ixgbe_adapter *adapter)
+{
+	int index = ixgbe_determine_xdp_q_idx(smp_processor_id());
+
+	return adapter->xdp_ring[index];
+}
+
 static inline u8 ixgbe_max_rss_indices(struct ixgbe_adapter *adapter)
 {
 	switch (adapter->hw.mac.type) {