Expose CQ moderation to user space

index ee2739ae4305..deccefb71a6b 100644
@@ -306,5 +306,6 @@ IB_UVERBS_DECLARE_EX_CMD(destroy_wq);
 IB_UVERBS_DECLARE_EX_CMD(create_rwq_ind_table);
 IB_UVERBS_DECLARE_EX_CMD(destroy_rwq_ind_table);
 IB_UVERBS_DECLARE_EX_CMD(modify_qp);
+IB_UVERBS_DECLARE_EX_CMD(modify_cq);
 
 #endif /* UVERBS_H */

index ab29a0327831..c7819e5540f1 100644
@@ -3856,3 +3856,39 @@ int ib_uverbs_ex_query_device(struct ib_uverbs_file *file,
 	err = ib_copy_to_udata(ucore, &resp, resp.response_length);
 	return err;
 }
+
+int ib_uverbs_ex_modify_cq(struct ib_uverbs_file *file,
+			   struct ib_device *ib_dev,
+			   struct ib_udata *ucore,
+			   struct ib_udata *uhw)
+{
+	struct ib_uverbs_ex_modify_cq cmd = {};
+	struct ib_cq *cq;
+	int ret;
+
+	/* sanity checks */
+	if (ucore->inlen > sizeof(cmd) &&
+	    !ib_is_udata_cleared(ucore, sizeof(cmd),
+				 ucore->inlen - sizeof(cmd)))
+		return -EOPNOTSUPP;
+
+	ret = ib_copy_from_udata(&cmd, ucore, min(sizeof(cmd), ucore->inlen));
+	if (ret)
+		return ret;
+
+	if (cmd.attr_mask != IB_CQ_MODERATE)
+		return -EINVAL;
+
+	if (!cmd.comp_mask)
+		return -EINVAL;
+
+	cq = uobj_get_obj_read(cq, cmd.cq_handle, file->ucontext);
+	if (!cq)
+		return -EINVAL;
+
+	ret = ib_modify_cq(cq, cmd.cq_count, cmd.cq_period);
+
+	uobj_put_obj_read(cq);
+
+	return ret;
+}

index b5febfd84ee5..381fd9c096ae 100644
@@ -128,6 +128,7 @@ static int (*uverbs_ex_cmd_table[])(struct ib_uverbs_file *file,
 	[IB_USER_VERBS_EX_CMD_CREATE_RWQ_IND_TBL] = ib_uverbs_ex_create_rwq_ind_table,
 	[IB_USER_VERBS_EX_CMD_DESTROY_RWQ_IND_TBL] = ib_uverbs_ex_destroy_rwq_ind_table,
 	[IB_USER_VERBS_EX_CMD_MODIFY_QP]        = ib_uverbs_ex_modify_qp,
+	[IB_USER_VERBS_EX_CMD_MODIFY_CQ]        = ib_uverbs_ex_modify_cq,
 };
 
 static void ib_uverbs_add_one(struct ib_device *device);

index 4c0a539cd2a2..ec80fec2d113 100644
@@ -311,6 +311,10 @@ struct ib_cq_init_attr {
 	u32		flags;
 };
 
+enum ib_cq_attr_mask {
+	IB_CQ_MODERATE = 1 << 0,
+};
+
 struct ib_device_attr {
 	u64			fw_ver;
 	__be64			sys_image_guid;

index d4e0b53bfc75..854aaafc60d0 100644
@@ -100,7 +100,8 @@ enum {
 	IB_USER_VERBS_EX_CMD_MODIFY_WQ,
 	IB_USER_VERBS_EX_CMD_DESTROY_WQ,
 	IB_USER_VERBS_EX_CMD_CREATE_RWQ_IND_TBL,
-	IB_USER_VERBS_EX_CMD_DESTROY_RWQ_IND_TBL
+	IB_USER_VERBS_EX_CMD_DESTROY_RWQ_IND_TBL,
+	IB_USER_VERBS_EX_CMD_MODIFY_CQ
 };
 
 /*

@@ -1150,6 +1151,14 @@ struct ib_uverbs_ex_destroy_rwq_ind_table  {
 	__u32 ind_tbl_handle;
 };
 
+struct ib_uverbs_ex_modify_cq {
+	__u32 cq_handle;
+	__u32 attr_mask;
+	__u16 cq_count;
+	__u16 cq_period;
+	__u32 comp_mask;
+};
+
 #define IB_DEVICE_NAME_MAX 64
 
 #endif /* IB_USER_VERBS_H */

index c636842c5be0..58845e67dad1 100644
@@ -2733,6 +2733,9 @@ static void *mlx4_ib_add(struct mlx4_dev *dev)
 	ibdev->ib_dev.get_dev_fw_str    = get_fw_ver_str;
 	ibdev->ib_dev.disassociate_ucontext = mlx4_ib_disassociate_ucontext;
 
+	ibdev->ib_dev.uverbs_ex_cmd_mask |=
+		(1ull << IB_USER_VERBS_EX_CMD_MODIFY_CQ);
+
 	if ((dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_RSS) &&
 	    ((mlx4_ib_port_link_layer(&ibdev->ib_dev, 1) ==
 	    IB_LINK_LAYER_ETHERNET) ||

index 1fa19820355a..9a55064ed69a 100644
@@ -47,6 +47,7 @@
 #include <linux/mlx4/device.h>
 #include <linux/mlx4/doorbell.h>
 #include <linux/mlx4/qp.h>
+#include <linux/mlx4/cq.h>
 
 #define MLX4_IB_DRV_NAME	"mlx4_ib"
 

index 09cebe528488..508e8cc5ee86 100644
@@ -136,6 +136,9 @@ enum {
 	MLX4_CQE_BAD_FCS                 = 1 << 4,
 };
 
+#define MLX4_MAX_CQ_PERIOD (BIT(16) - 1)
+#define MLX4_MAX_CQ_COUNT (BIT(16) - 1)
+
 static inline void mlx4_cq_arm(struct mlx4_cq *cq, u32 cmd,
 			       void __iomem *uar_page,
 			       spinlock_t *doorbell_lock)

index 01b218a3c277..18705cbcdc8c 100644
@@ -1149,6 +1149,9 @@ int mlx5_ib_modify_cq(struct ib_cq *cq, u16 cq_count, u16 cq_period)
 	if (!MLX5_CAP_GEN(dev->mdev, cq_moderation))
 		return -ENOSYS;
 
+	if (cq_period > MLX5_MAX_CQ_PERIOD)
+		return -EINVAL;
+
 	err = mlx5_core_modify_cq_moderation(dev->mdev, &mcq->mcq,
 					     cq_period, cq_count);
 	if (err)

index c44dd0896f80..da4c577d653c 100644
@@ -4020,7 +4020,8 @@ static void *mlx5_ib_add(struct mlx5_core_dev *mdev)
 		(1ull << IB_USER_VERBS_EX_CMD_QUERY_DEVICE)	|
 		(1ull << IB_USER_VERBS_EX_CMD_CREATE_CQ)	|
 		(1ull << IB_USER_VERBS_EX_CMD_CREATE_QP)	|
-		(1ull << IB_USER_VERBS_EX_CMD_MODIFY_QP);
+		(1ull << IB_USER_VERBS_EX_CMD_MODIFY_QP)	|
+		(1ull << IB_USER_VERBS_EX_CMD_MODIFY_CQ);
 
 	dev->ib_dev.query_device	= mlx5_ib_query_device;
 	dev->ib_dev.query_port		= mlx5_ib_query_port;

index cc718e245b1e..6be357b219ec 100644
@@ -128,6 +128,9 @@ enum {
 	CQE_SIZE_128_PAD = 2,
 };
 
+#define MLX5_MAX_CQ_PERIOD (BIT(__mlx5_bit_sz(cqc, cq_period)) - 1)
+#define MLX5_MAX_CQ_COUNT (BIT(__mlx5_bit_sz(cqc, cq_max_count)) - 1)
+
 static inline int cqe_sz_to_mlx_sz(u8 size, int padding_128_en)
 {
 	return padding_128_en ? CQE_SIZE_128_PAD :

index c7819e5540f1..ce969cc84494 100644
@@ -3852,6 +3852,15 @@ int ib_uverbs_ex_query_device(struct ib_uverbs_file *file,
 	resp.tm_caps.max_sge		= attr.tm_caps.max_sge;
 	resp.tm_caps.flags		= attr.tm_caps.flags;
 	resp.response_length += sizeof(resp.tm_caps);
+
+	if (ucore->outlen < resp.response_length + sizeof(resp.cq_moderation_caps))
+		goto end;
+
+	resp.cq_moderation_caps.max_cq_moderation_count  =
+		attr.cq_caps.max_cq_moderation_count;
+	resp.cq_moderation_caps.max_cq_moderation_period =
+		attr.cq_caps.max_cq_moderation_period;
+	resp.response_length += sizeof(resp.cq_moderation_caps);
 end:
 	err = ib_copy_to_udata(ucore, &resp, resp.response_length);
 	return err;

index ec80fec2d113..e1d027acddbd 100644
@@ -315,6 +315,11 @@ enum ib_cq_attr_mask {
 	IB_CQ_MODERATE = 1 << 0,
 };
 
+struct ib_cq_caps {
+	u16     max_cq_moderation_count;
+	u16     max_cq_moderation_period;
+};
+
 struct ib_device_attr {
 	u64			fw_ver;
 	__be64			sys_image_guid;

@@ -365,6 +370,7 @@ struct ib_device_attr {
 	u32			max_wq_type_rq;
 	u32			raw_packet_caps; /* Use ib_raw_packet_caps enum */
 	struct ib_tm_caps	tm_caps;
+	struct ib_cq_caps       cq_caps;
 };
 
 enum ib_mtu {

index 854aaafc60d0..7745a0eea57c 100644
@@ -125,6 +125,12 @@ struct ib_uverbs_comp_event_desc {
 	__u64 cq_handle;
 };
 
+struct ib_uverbs_cq_caps {
+	__u16     max_cq_moderation_count;
+	__u16     max_cq_moderation_period;
+	__u32     reserved;
+};
+
 /*
  * All commands from userspace should start with a __u32 command field
  * followed by __u16 in_words and out_words fields (which give the

@@ -263,6 +269,7 @@ struct ib_uverbs_ex_query_device_resp {
 	__u32  max_wq_type_rq;
 	__u32 raw_packet_caps;
 	struct ib_uverbs_tm_caps tm_caps;
+	struct ib_uverbs_cq_caps cq_moderation_caps;
 };
 
 struct ib_uverbs_query_port {

index 58845e67dad1..c6420e26f2d8 100644
@@ -563,6 +563,9 @@ static int mlx4_ib_query_device(struct ib_device *ibdev,
 		props->max_wq_type_rq = props->max_qp;
 	}
 
+	props->cq_caps.max_cq_moderation_count = MLX4_MAX_CQ_COUNT;
+	props->cq_caps.max_cq_moderation_period = MLX4_MAX_CQ_PERIOD;
+
 	if (!mlx4_is_slave(dev->dev))
 		err = mlx4_get_internal_clock_params(dev->dev, &clock_params);
 

index da4c577d653c..61ce3ca503b8 100644
@@ -790,6 +790,13 @@ static int mlx5_ib_query_device(struct ib_device *ibdev,
 		props->tm_caps.max_sge = MLX5_TM_MAX_SGE;
 	}
 
+	if (MLX5_CAP_GEN(dev->mdev, cq_moderation)) {
+		props->cq_caps.max_cq_moderation_count =
+						MLX5_MAX_CQ_COUNT;
+		props->cq_caps.max_cq_moderation_period =
+						MLX5_MAX_CQ_PERIOD;
+	}
+
 	if (field_avail(typeof(resp), cqe_comp_caps, uhw->outlen)) {
 		resp.cqe_comp_caps.max_num =
 			MLX5_CAP_GEN(dev->mdev, cqe_compression) ?