RDMA/efa: Expose RDMA read related attributes

Query the device attributes for RDMA operations, including maximum
transfer size and maximum number of SGEs per RDMA WR, and report them
back to the userspace library.

Link: https://lore.kernel.org/r/20191121141509.59297-4-galpress@amazon.comSigned-off-by: NDaniel Kranzdorf <dkkranzd@amazon.com>
Reviewed-by: NYossi Leybovich <sleybo@amazon.com>
Signed-off-by: NGal Pressman <galpress@amazon.com>
Signed-off-by: NJason Gunthorpe <jgg@mellanox.com>

drivers/infiniband/hw/efa/efa_admin_cmds_defs.h

@@ -562,6 +562,16 @@ struct efa_admin_feature_device_attr_desc {
 
 	/* Indicates how many bits are used virtual address access */
 	u8 virt_addr_width;
+
+	/*
+	 * 0 : rdma_read - If set, RDMA Read is supported on
+	 *    TX queues
+	 * 31:1 : reserved - MBZ
+	 */
+	u32 device_caps;
+
+	/* Max RDMA transfer size in bytes */
+	u32 max_rdma_size;
 };
 
 struct efa_admin_feature_queue_attr_desc {
@@ -608,6 +618,9 @@ struct efa_admin_feature_queue_attr_desc {
 
 	/* The maximum size of LLQ in bytes */
 	u32 max_llq_size;
+
+	/* Maximum number of SGEs for a single RDMA read WQE */
+	u16 max_wr_rdma_sges;
 };
 
 struct efa_admin_feature_aenq_desc {
@@ -622,6 +635,7 @@ struct efa_admin_feature_network_attr_desc {
 	/* Raw address data in network byte order */
 	u8 addr[16];
 
+	/* max packet payload size in bytes */
 	u32 mtu;
 };
 
@@ -797,4 +811,7 @@ struct efa_admin_mmio_req_read_less_resp {
 /* get_set_feature_common_desc */
 #define EFA_ADMIN_GET_SET_FEATURE_COMMON_DESC_SELECT_MASK   GENMASK(1, 0)
 
+/* feature_device_attr_desc */
+#define EFA_ADMIN_FEATURE_DEVICE_ATTR_DESC_RDMA_READ_MASK   BIT(0)
+
 #endif /* _EFA_ADMIN_CMDS_H_ */

drivers/infiniband/hw/efa/efa_com_cmd.c

@@ -444,6 +444,8 @@ int efa_com_get_device_attr(struct efa_com_dev *edev,
 	result->phys_addr_width = resp.u.device_attr.phys_addr_width;
 	result->virt_addr_width = resp.u.device_attr.virt_addr_width;
 	result->db_bar = resp.u.device_attr.db_bar;
+	result->max_rdma_size = resp.u.device_attr.max_rdma_size;
+	result->device_caps = resp.u.device_attr.device_caps;
 
 	if (result->admin_api_version < 1) {
 		ibdev_err_ratelimited(
@@ -477,6 +479,7 @@ int efa_com_get_device_attr(struct efa_com_dev *edev,
 	result->max_ah = resp.u.queue_attr.max_ah;
 	result->max_llq_size = resp.u.queue_attr.max_llq_size;
 	result->sub_cqs_per_cq = resp.u.queue_attr.sub_cqs_per_cq;
+	result->max_wr_rdma_sge = resp.u.queue_attr.max_wr_rdma_sges;
 
 	err = efa_com_get_feature(edev, &resp, EFA_ADMIN_NETWORK_ATTR);
 	if (err) {

drivers/infiniband/hw/efa/efa_com_cmd.h

@@ -121,9 +121,12 @@ struct efa_com_get_device_attr_result {
 	u32 max_pd;
 	u32 max_ah;
 	u32 max_llq_size;
+	u32 max_rdma_size;
+	u32 device_caps;
 	u16 sub_cqs_per_cq;
 	u16 max_sq_sge;
 	u16 max_rq_sge;
+	u16 max_wr_rdma_sge;
 	u8 db_bar;
 };
 

drivers/infiniband/hw/efa/efa_verbs.c

@@ -70,9 +70,6 @@ static const char *const efa_stats_names[] = {
 #define EFA_CHUNK_USED_SIZE \
 	((EFA_PTRS_PER_CHUNK * EFA_CHUNK_PAYLOAD_PTR_SIZE) + EFA_CHUNK_PTR_SIZE)
 
-#define EFA_SUPPORTED_ACCESS_FLAGS \
-	(IB_ACCESS_LOCAL_WRITE | IB_ACCESS_REMOTE_READ)
-
 struct pbl_chunk {
 	dma_addr_t dma_addr;
 	u64 *buf;
@@ -142,6 +139,11 @@ to_emmap(struct rdma_user_mmap_entry *rdma_entry)
 	return container_of(rdma_entry, struct efa_user_mmap_entry, rdma_entry);
 }
 
+static inline bool is_rdma_read_cap(struct efa_dev *dev)
+{
+	return dev->dev_attr.device_caps & EFA_ADMIN_FEATURE_DEVICE_ATTR_DESC_RDMA_READ_MASK;
+}
+
 #define field_avail(x, fld, sz) (offsetof(typeof(x), fld) + \
 				 FIELD_SIZEOF(typeof(x), fld) <= (sz))
 
@@ -201,12 +203,17 @@ int efa_query_device(struct ib_device *ibdev,
 				 dev_attr->max_rq_depth);
 	props->max_send_sge = dev_attr->max_sq_sge;
 	props->max_recv_sge = dev_attr->max_rq_sge;
+	props->max_sge_rd = dev_attr->max_wr_rdma_sge;
 
 	if (udata && udata->outlen) {
 		resp.max_sq_sge = dev_attr->max_sq_sge;
 		resp.max_rq_sge = dev_attr->max_rq_sge;
 		resp.max_sq_wr = dev_attr->max_sq_depth;
 		resp.max_rq_wr = dev_attr->max_rq_depth;
+		resp.max_rdma_size = dev_attr->max_rdma_size;
+
+		if (is_rdma_read_cap(dev))
+			resp.device_caps |= EFA_QUERY_DEVICE_CAPS_RDMA_READ;
 
 		err = ib_copy_to_udata(udata, &resp,
 				       min(sizeof(resp), udata->outlen));
@@ -1345,6 +1352,7 @@ struct ib_mr *efa_reg_mr(struct ib_pd *ibpd, u64 start, u64 length,
 	struct efa_com_reg_mr_params params = {};
 	struct efa_com_reg_mr_result result = {};
 	struct pbl_context pbl;
+	int supp_access_flags;
 	unsigned int pg_sz;
 	struct efa_mr *mr;
 	int inline_size;
@@ -1358,10 +1366,14 @@ struct ib_mr *efa_reg_mr(struct ib_pd *ibpd, u64 start, u64 length,
 		goto err_out;
 	}
 
-	if (access_flags & ~EFA_SUPPORTED_ACCESS_FLAGS) {
+	supp_access_flags =
+		IB_ACCESS_LOCAL_WRITE |
+		(is_rdma_read_cap(dev) ? IB_ACCESS_REMOTE_READ : 0);
+
+	if (access_flags & ~supp_access_flags) {
 		ibdev_dbg(&dev->ibdev,
 			  "Unsupported access flags[%#x], supported[%#x]\n",
-			  access_flags, EFA_SUPPORTED_ACCESS_FLAGS);
+			  access_flags, supp_access_flags);
 		err = -EOPNOTSUPP;
 		goto err_out;
 	}

include/uapi/rdma/efa-abi.h

@@ -90,12 +90,18 @@ struct efa_ibv_create_ah_resp {
 	__u8 reserved_30[2];
 };
 
+enum {
+	EFA_QUERY_DEVICE_CAPS_RDMA_READ = 1 << 0,
+};
+
 struct efa_ibv_ex_query_device_resp {
 	__u32 comp_mask;
 	__u32 max_sq_wr;
 	__u32 max_rq_wr;
 	__u16 max_sq_sge;
 	__u16 max_rq_sge;
+	__u32 max_rdma_size;
+	__u32 device_caps;
 };
 
 #endif /* EFA_ABI_USER_H */