net/mlx5: CQ Database per EQ

Before this patch the driver had one CQ database protected via one
spinlock, this spinlock is meant to synchronize between CQ
adding/removing and CQ IRQ interrupt handling.

On a system with large number of CPUs and on a work load that requires
lots of interrupts, this global spinlock becomes a very nasty hotspot
and introduces a contention between the active cores, which will
significantly hurt performance and becomes a bottleneck that prevents
seamless cpu scaling.

To solve this we simply move the CQ database and its spinlock to be per
EQ (IRQ), thus per core.

Tested with:
system: 2 sockets, 14 cores per socket, hyperthreading, 2x14x2=56 cores
netperf command: ./super_netperf 200 -P 0 -t TCP_RR  -H <server> -l 30 -- -r 300,300 -o -s 1M,1M -S 1M,1M

WITHOUT THIS PATCH:
Average:     CPU    %usr   %nice    %sys %iowait    %irq   %soft %steal  %guest  %gnice   %idle
Average:     all    4.32    0.00   36.15    0.09    0.00   34.02   0.00    0.00    0.00   25.41

Samples: 2M of event 'cycles:pp', Event count (approx.): 1554616897271
Overhead  Command          Shared Object                 Symbol
+   14.28%  swapper          [kernel.vmlinux]              [k] intel_idle
+   12.25%  swapper          [kernel.vmlinux]              [k] queued_spin_lock_slowpath
+   10.29%  netserver        [kernel.vmlinux]              [k] queued_spin_lock_slowpath
+    1.32%  netserver        [kernel.vmlinux]              [k] mlx5e_xmit

WITH THIS PATCH:
Average:     CPU    %usr   %nice    %sys %iowait    %irq   %soft  %steal  %guest  %gnice   %idle
Average:     all    4.27    0.00   34.31    0.01    0.00   18.71    0.00    0.00    0.00   42.69

Samples: 2M of event 'cycles:pp', Event count (approx.): 1498132937483
Overhead  Command          Shared Object             Symbol
+   23.33%  swapper          [kernel.vmlinux]          [k] intel_idle
+    1.69%  netserver        [kernel.vmlinux]          [k] mlx5e_xmit

Tested-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Saeed Mahameed <saeedm@mellanox.com>
Reviewed-by: Gal Pressman <galp@mellanox.com>

1 files changed, 8 insertions, 2 deletions

diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
index 25106e996a96..328403ebf2f5 100644
--- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c
+++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c
@@ -415,7 +415,7 @@ static irqreturn_t mlx5_eq_int(int irq, void *eq_ptr)
 		switch (eqe->type) {
 		case MLX5_EVENT_TYPE_COMP:
 			cqn = be32_to_cpu(eqe->data.comp.cqn) & 0xffffff;
-			mlx5_cq_completion(dev, cqn);
+			mlx5_cq_completion(eq, cqn);
 			break;
 		case MLX5_EVENT_TYPE_DCT_DRAINED:
 			rsn = be32_to_cpu(eqe->data.dct.dctn) & 0xffffff;
@@ -472,7 +472,7 @@ static irqreturn_t mlx5_eq_int(int irq, void *eq_ptr)
 			cqn = be32_to_cpu(eqe->data.cq_err.cqn) & 0xffffff;
 			mlx5_core_warn(dev, "CQ error on CQN 0x%x, syndrome 0x%x\n",
 				       cqn, eqe->data.cq_err.syndrome);
-			mlx5_cq_event(dev, cqn, eqe->type);
+			mlx5_cq_event(eq, cqn, eqe->type);
 			break;
 
 		case MLX5_EVENT_TYPE_PAGE_REQUEST:
@@ -567,6 +567,7 @@ int mlx5_create_map_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq, u8 vecidx,
 		       int nent, u64 mask, const char *name,
 		       enum mlx5_eq_type type)
 {
+	struct mlx5_cq_table *cq_table = &eq->cq_table;
 	u32 out[MLX5_ST_SZ_DW(create_eq_out)] = {0};
 	struct mlx5_priv *priv = &dev->priv;
 	irq_handler_t handler;
@@ -576,6 +577,11 @@ int mlx5_create_map_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq, u8 vecidx,
 	u32 *in;
 	int err;
 
+	/* Init CQ table */
+	memset(cq_table, 0, sizeof(*cq_table));
+	spin_lock_init(&cq_table->lock);
+	INIT_RADIX_TREE(&cq_table->tree, GFP_ATOMIC);
+
 	eq->type = type;
 	eq->nent = roundup_pow_of_two(nent + MLX5_NUM_SPARE_EQE);
 	eq->cons_index = 0;