RDMA/core: Add Completion Counters support

Add core infrastructure for Completion Counters, a light-weight
alternative to polling CQ for tracking operation completions.

Define the UVERBS_OBJECT_COMP_CNTR ioctl object with create, destroy,
modify and read methods for both success and error counters. Add a QP
attach method on the QP object to associate a completion counter with a
queue pair.

Add ib_comp_cntr struct, ib_comp_cntr_attach_attr, device ops, and
DECLARE_RDMA_OBJ_SIZE for driver object allocation.

Only userspace Completion Counters are supported at this stage.

Reviewed-by: Yonatan Nachum <ynachum@amazon.com>
Signed-off-by: Michael Margolin <mrgolin@amazon.com>
Link: https://patch.msgid.link/20260722083603.30334-2-mrgolin@amazon.com
Signed-off-by: Leon Romanovsky <leon@kernel.org>

1 files changed, 37 insertions, 0 deletions

diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h
index 8d82d303b723..9a952750f068 100644
--- a/include/rdma/ib_verbs.h
+++ b/include/rdma/ib_verbs.h
@@ -1746,6 +1746,34 @@ struct ib_cq {
 	struct rdma_restrack_entry res;
 };
 
+enum ib_qp_attach_comp_cntr_op {
+	IB_QP_ATTACH_COMP_CNTR_OP_SEND = IB_UVERBS_QP_ATTACH_COMP_CNTR_OP_SEND,
+	IB_QP_ATTACH_COMP_CNTR_OP_RECV = IB_UVERBS_QP_ATTACH_COMP_CNTR_OP_RECV,
+	IB_QP_ATTACH_COMP_CNTR_OP_RDMA_READ = IB_UVERBS_QP_ATTACH_COMP_CNTR_OP_RDMA_READ,
+	IB_QP_ATTACH_COMP_CNTR_OP_REMOTE_RDMA_READ = IB_UVERBS_QP_ATTACH_COMP_CNTR_OP_REMOTE_RDMA_READ,
+	IB_QP_ATTACH_COMP_CNTR_OP_RDMA_WRITE = IB_UVERBS_QP_ATTACH_COMP_CNTR_OP_RDMA_WRITE,
+	IB_QP_ATTACH_COMP_CNTR_OP_REMOTE_RDMA_WRITE = IB_UVERBS_QP_ATTACH_COMP_CNTR_OP_REMOTE_RDMA_WRITE,
+};
+
+struct ib_comp_cntr {
+	struct ib_device *device;
+	struct ib_uobject *uobject;
+};
+
+enum ib_comp_cntr_entry {
+	IB_COMP_CNTR_ENTRY_COMP = IB_UVERBS_COMP_CNTR_ENTRY_COMP,
+	IB_COMP_CNTR_ENTRY_ERR = IB_UVERBS_COMP_CNTR_ENTRY_ERR,
+};
+
+enum ib_comp_cntr_modify_op {
+	IB_COMP_CNTR_MODIFY_OP_SET = IB_UVERBS_COMP_CNTR_MODIFY_OP_SET,
+	IB_COMP_CNTR_MODIFY_OP_INC = IB_UVERBS_COMP_CNTR_MODIFY_OP_INC,
+};
+
+struct ib_qp_attach_comp_cntr_attr {
+	u32 op_mask; /* Bitmask of enum ib_qp_attach_comp_cntr_op */
+};
+
 struct ib_srq {
 	struct ib_device       *device;
 	struct ib_pd	       *pd;
@@ -2629,6 +2657,8 @@ struct ib_device_ops {
 			 struct ib_udata *udata);
 	int (*modify_qp)(struct ib_qp *qp, struct ib_qp_attr *qp_attr,
 			 int qp_attr_mask, struct ib_udata *udata);
+	int (*qp_attach_comp_cntr)(struct ib_qp *qp, struct ib_comp_cntr *cc,
+				   struct ib_qp_attach_comp_cntr_attr *attr);
 	int (*query_qp)(struct ib_qp *qp, struct ib_qp_attr *qp_attr,
 			int qp_attr_mask, struct ib_qp_init_attr *qp_init_attr);
 	int (*destroy_qp)(struct ib_qp *qp, struct ib_udata *udata);
@@ -2650,6 +2680,12 @@ struct ib_device_ops {
 	 * post_destroy_cq - Free all kernel resources
 	 */
 	void (*post_destroy_cq)(struct ib_cq *cq);
+	int (*create_comp_cntr)(struct ib_comp_cntr *cc,
+				struct uverbs_attr_bundle *attrs);
+	int (*destroy_comp_cntr)(struct ib_comp_cntr *cc);
+	int (*modify_comp_cntr)(struct ib_comp_cntr *cc, enum ib_comp_cntr_entry entry,
+				enum ib_comp_cntr_modify_op op, u64 value);
+	int (*read_comp_cntr)(struct ib_comp_cntr *cc, enum ib_comp_cntr_entry entry, u64 *value);
 	struct ib_mr *(*get_dma_mr)(struct ib_pd *pd, int mr_access_flags);
 	struct ib_mr *(*reg_user_mr)(struct ib_pd *pd, u64 start, u64 length,
 				     u64 virt_addr, int mr_access_flags,
@@ -2883,6 +2919,7 @@ struct ib_device_ops {
 	DECLARE_RDMA_OBJ_SIZE(ib_ah);
 	DECLARE_RDMA_OBJ_SIZE(ib_counters);
 	DECLARE_RDMA_OBJ_SIZE(ib_cq);
+	DECLARE_RDMA_OBJ_SIZE(ib_comp_cntr);
 	DECLARE_RDMA_OBJ_SIZE(ib_dmah);
 	DECLARE_RDMA_OBJ_SIZE(ib_mw);
 	DECLARE_RDMA_OBJ_SIZE(ib_pd);