RDMA/efa: Add rdma write capability to device caps

Add rdma write capability that is propagated from the device to rdma-core.
Enable MR creation with remote write permissions according to this device
capability.

Link: https://lore.kernel.org/r/20230404154313.35194-1-ynachum@amazon.com
Reviewed-by: Firas Jahjah <firasj@amazon.com>
Reviewed-by: Michael Margolin <mrgolin@amazon.com>
Signed-off-by: Yonatan Nachum <ynachum@amazon.com>
Signed-off-by: Jason Gunthorpe <jgg@nvidia.com>

Author: YonatanNachum

drivers/infiniband/hw/efa/efa_admin_cmds_defs.h

@@ -376,7 +376,9 @@ struct efa_admin_reg_mr_cmd {
 	 * 0 : local_write_enable - Local write permissions:
 	 *    must be set for RQ buffers and buffers posted for
 	 *    RDMA Read requests
-	 * 1 : reserved1 - MBZ
+	 * 1 : remote_write_enable - Remote write
+	 *    permissions: must be set to enable RDMA write to
+	 *    the region
 	 * 2 : remote_read_enable - Remote read permissions:
 	 *    must be set to enable RDMA read from the region
 	 * 7:3 : reserved2 - MBZ
@@ -620,7 +622,9 @@ struct efa_admin_feature_device_attr_desc {
 	 *    modify QP command
 	 * 2 : data_polling_128 - If set, 128 bytes data
 	 *    polling is supported
-	 * 31:3 : reserved - MBZ
+	 * 3 : rdma_write - If set, RDMA Write is supported
+	 *    on TX queues
+	 * 31:4 : reserved - MBZ
 	 */
 	u32 device_caps;
 
@@ -674,7 +678,7 @@ 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 */
+	/* Maximum number of SGEs for a single RDMA read/write WQE */
 	u16 max_wr_rdma_sges;
 
 	/*
@@ -979,6 +983,7 @@ struct efa_admin_host_info {
 #define EFA_ADMIN_REG_MR_CMD_PHYS_PAGE_SIZE_SHIFT_MASK      GENMASK(4, 0)
 #define EFA_ADMIN_REG_MR_CMD_MEM_ADDR_PHY_MODE_EN_MASK      BIT(7)
 #define EFA_ADMIN_REG_MR_CMD_LOCAL_WRITE_ENABLE_MASK        BIT(0)
+#define EFA_ADMIN_REG_MR_CMD_REMOTE_WRITE_ENABLE_MASK       BIT(1)
 #define EFA_ADMIN_REG_MR_CMD_REMOTE_READ_ENABLE_MASK        BIT(2)
 
 /* create_cq_cmd */
@@ -994,6 +999,7 @@ struct efa_admin_host_info {
 #define EFA_ADMIN_FEATURE_DEVICE_ATTR_DESC_RDMA_READ_MASK   BIT(0)
 #define EFA_ADMIN_FEATURE_DEVICE_ATTR_DESC_RNR_RETRY_MASK   BIT(1)
 #define EFA_ADMIN_FEATURE_DEVICE_ATTR_DESC_DATA_POLLING_128_MASK BIT(2)
+#define EFA_ADMIN_FEATURE_DEVICE_ATTR_DESC_RDMA_WRITE_MASK  BIT(3)
 
 /* create_eq_cmd */
 #define EFA_ADMIN_CREATE_EQ_CMD_ENTRY_SIZE_WORDS_MASK       GENMASK(4, 0)

drivers/infiniband/hw/efa/efa_io_defs.h

@@ -1,6 +1,6 @@
 /* SPDX-License-Identifier: GPL-2.0 OR BSD-2-Clause */
 /*
- * Copyright 2018-2022 Amazon.com, Inc. or its affiliates. All rights reserved.
+ * Copyright 2018-2023 Amazon.com, Inc. or its affiliates. All rights reserved.
  */
 
 #ifndef _EFA_IO_H_
@@ -23,6 +23,8 @@ enum efa_io_send_op_type {
 	EFA_IO_SEND                                 = 0,
 	/* RDMA read */
 	EFA_IO_RDMA_READ                            = 1,
+	/* RDMA write */
+	EFA_IO_RDMA_WRITE                           = 2,
 };
 
 enum efa_io_comp_status {
@@ -62,8 +64,7 @@ struct efa_io_tx_meta_desc {
 
 	/*
 	 * control flags
-	 * 3:0 : op_type - operation type: send/rdma/fast mem
-	 *    ops/etc
+	 * 3:0 : op_type - enum efa_io_send_op_type
 	 * 4 : has_imm - immediate_data field carries valid
 	 *    data.
 	 * 5 : inline_msg - inline mode - inline message data
@@ -219,28 +220,32 @@ struct efa_io_cdesc_common {
 	 * 2:1 : q_type - enum efa_io_queue_type: send/recv
 	 * 3 : has_imm - indicates that immediate data is
 	 *    present - for RX completions only
-	 * 7:4 : reserved28 - MBZ
+	 * 6:4 : op_type - enum efa_io_send_op_type
+	 * 7 : reserved31 - MBZ
 	 */
 	u8 flags;
 
 	/* local QP number */
 	u16 qp_num;
-
-	/* Transferred length */
-	u16 length;
 };
 
 /* Tx completion descriptor */
 struct efa_io_tx_cdesc {
 	/* Common completion info */
 	struct efa_io_cdesc_common common;
+
+	/* MBZ */
+	u16 reserved16;
 };
 
 /* Rx Completion Descriptor */
 struct efa_io_rx_cdesc {
 	/* Common completion info */
 	struct efa_io_cdesc_common common;
 
+	/* Transferred length bits[15:0] */
+	u16 length;
+
 	/* Remote Address Handle FW index, 0xFFFF indicates invalid ah */
 	u16 ah;
 
@@ -250,16 +255,26 @@ struct efa_io_rx_cdesc {
 	u32 imm;
 };
 
+/* Rx Completion Descriptor RDMA write info */
+struct efa_io_rx_cdesc_rdma_write {
+	/* Transferred length bits[31:16] */
+	u16 length_hi;
+};
+
 /* Extended Rx Completion Descriptor */
 struct efa_io_rx_cdesc_ex {
 	/* Base RX completion info */
-	struct efa_io_rx_cdesc rx_cdesc_base;
+	struct efa_io_rx_cdesc base;
 
-	/*
-	 * Valid only in case of unknown AH (0xFFFF) and CQ set_src_addr is
-	 * enabled.
-	 */
-	u8 src_addr[16];
+	union {
+		struct efa_io_rx_cdesc_rdma_write rdma_write;
+
+		/*
+		 * Valid only in case of unknown AH (0xFFFF) and CQ
+		 * set_src_addr is enabled.
+		 */
+		u8 src_addr[16];
+	} u;
 };
 
 /* tx_meta_desc */
@@ -285,5 +300,6 @@ struct efa_io_rx_cdesc_ex {
 #define EFA_IO_CDESC_COMMON_PHASE_MASK                      BIT(0)
 #define EFA_IO_CDESC_COMMON_Q_TYPE_MASK                     GENMASK(2, 1)
 #define EFA_IO_CDESC_COMMON_HAS_IMM_MASK                    BIT(3)
+#define EFA_IO_CDESC_COMMON_OP_TYPE_MASK                    GENMASK(6, 4)
 
 #endif /* _EFA_IO_H_ */

drivers/infiniband/hw/efa/efa_verbs.c

@@ -253,6 +253,9 @@ int efa_query_device(struct ib_device *ibdev,
 		if (EFA_DEV_CAP(dev, DATA_POLLING_128))
 			resp.device_caps |= EFA_QUERY_DEVICE_CAPS_DATA_POLLING_128;
 
+		if (EFA_DEV_CAP(dev, RDMA_WRITE))
+			resp.device_caps |= EFA_QUERY_DEVICE_CAPS_RDMA_WRITE;
+
 		if (dev->neqs)
 			resp.device_caps |= EFA_QUERY_DEVICE_CAPS_CQ_NOTIFICATIONS;
 
@@ -1572,7 +1575,8 @@ static struct efa_mr *efa_alloc_mr(struct ib_pd *ibpd, int access_flags,
 
 	supp_access_flags =
 		IB_ACCESS_LOCAL_WRITE |
-		(EFA_DEV_CAP(dev, RDMA_READ) ? IB_ACCESS_REMOTE_READ : 0);
+		(EFA_DEV_CAP(dev, RDMA_READ) ? IB_ACCESS_REMOTE_READ : 0) |
+		(EFA_DEV_CAP(dev, RDMA_WRITE) ? IB_ACCESS_REMOTE_WRITE : 0);
 
 	access_flags &= ~IB_ACCESS_OPTIONAL;
 	if (access_flags & ~supp_access_flags) {

include/uapi/rdma/efa-abi.h

@@ -121,6 +121,7 @@ enum {
 	EFA_QUERY_DEVICE_CAPS_CQ_NOTIFICATIONS = 1 << 2,
 	EFA_QUERY_DEVICE_CAPS_CQ_WITH_SGID     = 1 << 3,
 	EFA_QUERY_DEVICE_CAPS_DATA_POLLING_128 = 1 << 4,
+	EFA_QUERY_DEVICE_CAPS_RDMA_WRITE = 1 << 5,
 };
 
 struct efa_ibv_ex_query_device_resp {