IB/mlx5: Add debug control parameters for congestion control

PATCH Applied Leon Romanovsky 2 participants 2 messages May 30, 2017 – Jul 28, 2017 1 message not in the archive

Subsystems (3)

InfiniBand Mellanox mlx5 core Mellanox MLX5 IB driver

lore

Share & tools

lore

Leon Romanovsky

author

2017-05-30 07:05 UTC #0 lore raw

PATCH 1/1 IB/mlx5: Add debug control parameters for congestion control

From: Parav Pandit <parav-VPRAkNaXOzVWk0Htik3J/[email protected]>

This patch adds debug control parameters for congestion control which can be read or written through debugfs. They are for reaction point and notification point nodes.

These control parameters are as below:

 +------------------------------+-----------------------------------------+
 |      Name                    |           Description                   |
 |------------------------------+-----------------------------------------|
 |rp_clamp_tgt_rate             | When set target rate is updated to      |
 |                              | current rate                            |
 |------------------------------+-----------------------------------------|
 |rp_clamp_tgt_rate_ati         | When set update target rate based on    |
 |                              | timer as well                           |
 |------------------------------+-----------------------------------------|
 |rp_time_reset                 | time between rate increase if no        |
 |                              | CNP is received unit in usec            |
 |------------------------------+-----------------------------------------|
 |rp_byte_reset                 | Number of bytes between rate inease if  |
 |                              | no CNP is received                      |
 |------------------------------+-----------------------------------------|
 |rp_threshold                  | Threshold for reaction point rate       |
 |                              | control                                 |
 |------------------------------+-----------------------------------------|
 |rp_ai_rate                    | Rate for target rate, unit in Mbps      |
 |------------------------------+-----------------------------------------|
 |rp_hai_rate                   | Rate for hyper increase state           |
 |                              | unit in Mbps                            |
 |------------------------------+-----------------------------------------|
 |rp_min_dec_fac                | Minimum factor by which the current     |
 |                              | transmit rate can be changed when       |
 |                              | processing a CNP, unit is percerntage   |
 |------------------------------+-----------------------------------------|
 |rp_min_rate                   | Minimum value for rate limit,           |
 |                              | unit in Mbps                            |
 |------------------------------+-----------------------------------------|
 |rp_rate_to_set_on_first_cnp   | Rate that is set when first CNP is      |
 |                              | received, unit is Mbps                  |
 |------------------------------+-----------------------------------------|
 |rp_dce_tcp_g                  | Used to calculate alpha                 |
 |------------------------------+-----------------------------------------|
 |rp_dce_tcp_rtt                | Time between updates of alpha value,    |
 |                              | unit is usec                            |
 |------------------------------+-----------------------------------------|
 |rp_rate_reduce_monitor_period | Minimum time between consecutive rate   |
 |                              | reductions                              |
 |------------------------------+-----------------------------------------|
 |rp_initial_alpha_value        | Initial value of alpha                  |
 |------------------------------+-----------------------------------------|
 |rp_gd                         | When CNP is received, flow rate is      |
 |                              | reduced based on gd, rp_gd is given as  |
 |                              | log2(rp_gd)                             |
 |------------------------------+-----------------------------------------|
 |np_cnp_dscp                   | dscp code point for generated cnp       |
 |------------------------------+-----------------------------------------|
 |np_cnp_prio_mode              | 802.1p priority for generated cnp       |
 |------------------------------+-----------------------------------------|
 |np_cnp_prio                   | cnp priority mode                       |
 +------------------------------+-----------------------------------------+

Signed-off-by Parav Pandit <parav-VPRAkNaXOzVWk0Htik3J/[email protected]>

Reviewed-by Daniel Jurgens <danielj-VPRAkNaXOzVWk0Htik3J/[email protected]>

Reviewed-by Eli Cohen <eli-VPRAkNaXOzVWk0Htik3J/[email protected]>

Signed-off-by Leon Romanovsky <[email protected]>

---
 drivers/infiniband/hw/mlx5/Makefile  |   2 +-
 drivers/infiniband/hw/mlx5/cmd.c     |  20 ++
 drivers/infiniband/hw/mlx5/cmd.h     |   4 +
 drivers/infiniband/hw/mlx5/cong.c    | 421 +++++++++++++++++++++++++++++++++++
 drivers/infiniband/hw/mlx5/main.c    |   9 +-
 drivers/infiniband/hw/mlx5/mlx5_ib.h |  37 +++
 include/linux/mlx5/mlx5_ifc.h        |   3 +-
 7 files changed, 493 insertions(+), 3 deletions(-)
 create mode 100644 drivers/infiniband/hw/mlx5/cong.c

drivers/infiniband/hw/mlx5/Makefile +1 -1

index 90ad2adc752f..bc6299697dda 100644
@@ -1,4 +1,4 @@
 obj-$(CONFIG_MLX5_INFINIBAND)	+= mlx5_ib.o
 
-mlx5_ib-y :=	main.o cq.o doorbell.o qp.o mem.o srq.o mr.o ah.o mad.o gsi.o ib_virt.o cmd.o
+mlx5_ib-y :=	main.o cq.o doorbell.o qp.o mem.o srq.o mr.o ah.o mad.o gsi.o ib_virt.o cmd.o cong.o
 mlx5_ib-$(CONFIG_INFINIBAND_ON_DEMAND_PAGING) += odp.o

drivers/infiniband/hw/mlx5/cmd.c +20 -0

index 18d5e1db93ed..470995fa38d2 100644
@@ -57,3 +57,23 @@ int mlx5_cmd_query_cong_counter(struct mlx5_core_dev *dev,
 	MLX5_SET(query_cong_statistics_in, in, clear, reset);
 	return mlx5_cmd_exec(dev, in, sizeof(in), out, out_size);
 }
+
+int mlx5_cmd_query_cong_params(struct mlx5_core_dev *dev, int cong_point,
+			       void *out, int out_size)
+{
+	u32 in[MLX5_ST_SZ_DW(query_cong_params_in)] = { };
+
+	MLX5_SET(query_cong_params_in, in, opcode,
+		 MLX5_CMD_OP_QUERY_CONG_PARAMS);
+	MLX5_SET(query_cong_params_in, in, cong_protocol, cong_point);
+
+	return mlx5_cmd_exec(dev, in, sizeof(in), out, out_size);
+}
+
+int mlx5_cmd_modify_cong_params(struct mlx5_core_dev *dev,
+				void *in, int in_size)
+{
+	u32 out[MLX5_ST_SZ_DW(modify_cong_params_out)] = { };
+
+	return mlx5_cmd_exec(dev, in, in_size, out, sizeof(out));
+}

drivers/infiniband/hw/mlx5/cmd.h +4 -0

index fa09228193a6..af4c24596274 100644
@@ -39,4 +39,8 @@
 int mlx5_cmd_null_mkey(struct mlx5_core_dev *dev, u32 *null_mkey);
 int mlx5_cmd_query_cong_counter(struct mlx5_core_dev *dev,
 				bool reset, void *out, int out_size);
+int mlx5_cmd_query_cong_params(struct mlx5_core_dev *dev, int cong_point,
+			       void *out, int out_size);
+int mlx5_cmd_modify_cong_params(struct mlx5_core_dev *mdev,
+				void *in, int in_size);
 #endif /* MLX5_IB_CMD_H */

drivers/infiniband/hw/mlx5/cong.c new file +421 -0

421 lines not on this page · raw message

drivers/infiniband/hw/mlx5/main.c +8 -1

index 9f3ba320ce70..fbdbb6d77bf3 100644
@@ -3739,9 +3739,13 @@ static void *mlx5_ib_add(struct mlx5_core_dev *mdev)
 			goto err_odp;
 	}
 
+	err = mlx5_ib_init_cong_debugfs(dev);
+	if (err)
+		goto err_cnt;
+
 	dev->mdev->priv.uar = mlx5_get_uars_page(dev->mdev);
 	if (!dev->mdev->priv.uar)
-		goto err_cnt;
+		goto err_cong;
 
 	err = mlx5_alloc_bfreg(dev->mdev, &dev->bfreg, false, false);
 	if (err)

@@ -3786,6 +3790,8 @@ static void *mlx5_ib_add(struct mlx5_core_dev *mdev)
 	mlx5_put_uars_page(dev->mdev, dev->mdev->priv.uar);
 
 err_cnt:
+	mlx5_ib_cleanup_cong_debugfs(dev);
+err_cong:
 	if (MLX5_CAP_GEN(dev->mdev, max_qp_cnt))
 		mlx5_ib_dealloc_counters(dev);

@@ -3820,6 +3826,7 @@ static void mlx5_ib_remove(struct mlx5_core_dev *mdev, void *context)
 	mlx5_free_bfreg(dev->mdev, &dev->fp_bfreg);
 	mlx5_free_bfreg(dev->mdev, &dev->bfreg);
 	mlx5_put_uars_page(dev->mdev, mdev->priv.uar);
+	mlx5_ib_cleanup_cong_debugfs(dev);
 	if (MLX5_CAP_GEN(dev->mdev, max_qp_cnt))
 		mlx5_ib_dealloc_counters(dev);
 	destroy_umrc_res(dev);

drivers/infiniband/hw/mlx5/mlx5_ib.h +37 -0

index 38c877bc45e5..f7233c42365a 100644
@@ -618,6 +618,39 @@ struct mlx5_roce {
 	atomic_t		next_port;
 };
 
+struct mlx5_ib_dbg_param {
+	int			offset;
+	struct mlx5_ib_dev	*dev;
+	struct dentry		*dentry;
+};
+
+enum mlx5_ib_dbg_cc_types {
+	MLX5_IB_DBG_CC_RP_CLAMP_TGT_RATE,
+	MLX5_IB_DBG_CC_RP_CLAMP_TGT_RATE_ATI,
+	MLX5_IB_DBG_CC_RP_TIME_RESET,
+	MLX5_IB_DBG_CC_RP_BYTE_RESET,
+	MLX5_IB_DBG_CC_RP_THRESHOLD,
+	MLX5_IB_DBG_CC_RP_AI_RATE,
+	MLX5_IB_DBG_CC_RP_HAI_RATE,
+	MLX5_IB_DBG_CC_RP_MIN_DEC_FAC,
+	MLX5_IB_DBG_CC_RP_MIN_RATE,
+	MLX5_IB_DBG_CC_RP_RATE_TO_SET_ON_FIRST_CNP,
+	MLX5_IB_DBG_CC_RP_DCE_TCP_G,
+	MLX5_IB_DBG_CC_RP_DCE_TCP_RTT,
+	MLX5_IB_DBG_CC_RP_RATE_REDUCE_MONITOR_PERIOD,
+	MLX5_IB_DBG_CC_RP_INITIAL_ALPHA_VALUE,
+	MLX5_IB_DBG_CC_RP_GD,
+	MLX5_IB_DBG_CC_NP_CNP_DSCP,
+	MLX5_IB_DBG_CC_NP_CNP_PRIO_MODE,
+	MLX5_IB_DBG_CC_NP_CNP_PRIO,
+	MLX5_IB_DBG_CC_MAX,
+};
+
+struct mlx5_ib_dbg_cc_params {
+	struct dentry			*root;
+	struct mlx5_ib_dbg_param	params[MLX5_IB_DBG_CC_MAX];
+};
+
 struct mlx5_ib_dev {
 	struct ib_device		ib_dev;
 	struct mlx5_core_dev		*mdev;

@@ -654,6 +687,7 @@ struct mlx5_ib_dev {
 	struct mlx5_ib_port	*port;
 	struct mlx5_sq_bfreg     bfreg;
 	struct mlx5_sq_bfreg     fp_bfreg;
+	struct mlx5_ib_dbg_cc_params *dbg_cc_params;
 };
 
 static inline struct mlx5_ib_cq *to_mibcq(struct mlx5_core_cq *mcq)

@@ -903,6 +937,9 @@ __be16 mlx5_get_roce_udp_sport(struct mlx5_ib_dev *dev, u8 port_num,
 int mlx5_get_roce_gid_type(struct mlx5_ib_dev *dev, u8 port_num,
 			   int index, enum ib_gid_type *gid_type);
 
+void mlx5_ib_cleanup_cong_debugfs(struct mlx5_ib_dev *dev);
+int mlx5_ib_init_cong_debugfs(struct mlx5_ib_dev *dev);
+
 /* GSI QP helper functions */
 struct ib_qp *mlx5_ib_gsi_create_qp(struct ib_pd *pd,
 				    struct ib_qp_init_attr *init_attr);

include/linux/mlx5/mlx5_ifc.h +2 -1

index 32de0724b400..f585ab991a8e 100644
@@ -1165,7 +1165,8 @@ struct mlx5_ifc_cong_control_r_roce_ecn_np_bits {
 
 	u8         reserved_at_c0[0x12];
 	u8         cnp_dscp[0x6];
-	u8         reserved_at_d8[0x5];
+	u8         reserved_at_d8[0x4];
+	u8         cnp_prio_mode[0x1];
 	u8         cnp_802p_prio[0x3];
 
 	u8         reserved_at_e0[0x720];

--
2.12.2

--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in the body of a message to [email protected] More majordomo info at http://vger.kernel.org/majordomo-info.html

A message that is not in the archive (sent off-list or not yet received): 20170530070515.6836-1-leon-DgEjT+Ai2ygdnm+yROfE0A@public.gmane.org

Doug Ledford

Applied

2017-07-28 18:16 UTC #2 lore raw

Quoted 8 lines · Leon Romanovsky

From: Parav Pandit <parav-VPRAkNaXOzVWk0Htik3J/[email protected]>
This patch adds debug control parameters for congestion control which can be read or written through debugfs. They are for reaction point and
notification point nodes.
These control parameters are as below:

[ snip ]

Thanks, applied.

Signature · 8 lines

Doug Ledford <[email protected]>
    GPG KeyID: B826A3330E572FDD
    Key fingerprint = AE6B 1BDA 122B 23B4 265B  1274 B826 A333 0E57 2FDD

--
To unsubscribe from this list: send the line "unsubscribe linux-rdma" in
the body of a message to [email protected]
More majordomo info at  http://vger.kernel.org/majordomo-info.html