RDMA/mana_ib: create/destroy AH

Implement create and destroy AH for kernel.

In mana_ib, AV is passed as an sge in WQE.
Allocate DMA memory and write an AV there.

Signed-off-by: Konstantin Taranov <[email protected]>
Link: https://patch.msgid.link/[email protected]
Reviewed-by: Shiraz Saleem <[email protected]>
Reviewed-by: Long Li <[email protected]>
Signed-off-by: Leon Romanovsky <[email protected]>

Author: Konstantin Taranov

drivers/infiniband/hw/mana/Makefile

@@ -1,4 +1,4 @@
 # SPDX-License-Identifier: GPL-2.0-only
 obj-$(CONFIG_MANA_INFINIBAND) += mana_ib.o
 
-mana_ib-y := device.o main.o wq.o qp.o cq.o mr.o
+mana_ib-y := device.o main.o wq.o qp.o cq.o mr.o ah.o

drivers/infiniband/hw/mana/ah.c

@@ -0,0 +1,58 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Copyright (c) 2024, Microsoft Corporation. All rights reserved.
+ */
+
+#include "mana_ib.h"
+
+int mana_ib_create_ah(struct ib_ah *ibah, struct rdma_ah_init_attr *attr,
+		      struct ib_udata *udata)
+{
+	struct mana_ib_dev *mdev = container_of(ibah->device, struct mana_ib_dev, ib_dev);
+	struct mana_ib_ah *ah = container_of(ibah, struct mana_ib_ah, ibah);
+	struct rdma_ah_attr *ah_attr = attr->ah_attr;
+	const struct ib_global_route *grh;
+	enum rdma_network_type ntype;
+
+	if (ah_attr->type != RDMA_AH_ATTR_TYPE_ROCE ||
+	    !(rdma_ah_get_ah_flags(ah_attr) & IB_AH_GRH))
+		return -EINVAL;
+
+	if (udata)
+		return -EINVAL;
+
+	ah->av = dma_pool_zalloc(mdev->av_pool, GFP_ATOMIC, &ah->dma_handle);
+	if (!ah->av)
+		return -ENOMEM;
+
+	grh = rdma_ah_read_grh(ah_attr);
+	ntype = rdma_gid_attr_network_type(grh->sgid_attr);
+
+	copy_in_reverse(ah->av->dest_mac, ah_attr->roce.dmac, ETH_ALEN);
+	ah->av->udp_src_port = rdma_flow_label_to_udp_sport(grh->flow_label);
+	ah->av->hop_limit = grh->hop_limit;
+	ah->av->dscp = (grh->traffic_class >> 2) & 0x3f;
+	ah->av->is_ipv6 = (ntype == RDMA_NETWORK_IPV6);
+
+	if (ah->av->is_ipv6) {
+		copy_in_reverse(ah->av->dest_ip, grh->dgid.raw, 16);
+		copy_in_reverse(ah->av->src_ip, grh->sgid_attr->gid.raw, 16);
+	} else {
+		ah->av->dest_ip[10] = 0xFF;
+		ah->av->dest_ip[11] = 0xFF;
+		copy_in_reverse(&ah->av->dest_ip[12], &grh->dgid.raw[12], 4);
+		copy_in_reverse(&ah->av->src_ip[12], &grh->sgid_attr->gid.raw[12], 4);
+	}
+
+	return 0;
+}
+
+int mana_ib_destroy_ah(struct ib_ah *ibah, u32 flags)
+{
+	struct mana_ib_dev *mdev = container_of(ibah->device, struct mana_ib_dev, ib_dev);
+	struct mana_ib_ah *ah = container_of(ibah, struct mana_ib_ah, ibah);
+
+	dma_pool_free(mdev->av_pool, ah->av, ah->dma_handle);
+
+	return 0;
+}

drivers/infiniband/hw/mana/device.c

@@ -19,6 +19,7 @@ static const struct ib_device_ops mana_ib_dev_ops = {
 	.add_gid = mana_ib_gd_add_gid,
 	.alloc_pd = mana_ib_alloc_pd,
 	.alloc_ucontext = mana_ib_alloc_ucontext,
+	.create_ah = mana_ib_create_ah,
 	.create_cq = mana_ib_create_cq,
 	.create_qp = mana_ib_create_qp,
 	.create_rwq_ind_table = mana_ib_create_rwq_ind_table,
@@ -27,6 +28,7 @@ static const struct ib_device_ops mana_ib_dev_ops = {
 	.dealloc_ucontext = mana_ib_dealloc_ucontext,
 	.del_gid = mana_ib_gd_del_gid,
 	.dereg_mr = mana_ib_dereg_mr,
+	.destroy_ah = mana_ib_destroy_ah,
 	.destroy_cq = mana_ib_destroy_cq,
 	.destroy_qp = mana_ib_destroy_qp,
 	.destroy_rwq_ind_table = mana_ib_destroy_rwq_ind_table,
@@ -44,6 +46,7 @@ static const struct ib_device_ops mana_ib_dev_ops = {
 	.query_port = mana_ib_query_port,
 	.reg_user_mr = mana_ib_reg_user_mr,
 
+	INIT_RDMA_OBJ_SIZE(ib_ah, mana_ib_ah, ibah),
 	INIT_RDMA_OBJ_SIZE(ib_cq, mana_ib_cq, ibcq),
 	INIT_RDMA_OBJ_SIZE(ib_pd, mana_ib_pd, ibpd),
 	INIT_RDMA_OBJ_SIZE(ib_qp, mana_ib_qp, ibqp),
@@ -135,15 +138,22 @@ static int mana_ib_probe(struct auxiliary_device *adev,
 		goto destroy_rnic;
 	}
 
+	dev->av_pool = dma_pool_create("mana_ib_av", mdev->gdma_context->dev,
+				       MANA_AV_BUFFER_SIZE, MANA_AV_BUFFER_SIZE, 0);
+	if (!dev->av_pool)
+		goto destroy_rnic;
+
 	ret = ib_register_device(&dev->ib_dev, "mana_%d",
 				 mdev->gdma_context->dev);
 	if (ret)
-		goto destroy_rnic;
+		goto deallocate_pool;
 
 	dev_set_drvdata(&adev->dev, dev);
 
 	return 0;
 
+deallocate_pool:
+	dma_pool_destroy(dev->av_pool);
 destroy_rnic:
 	xa_destroy(&dev->qp_table_wq);
 	mana_ib_gd_destroy_rnic_adapter(dev);
@@ -161,6 +171,7 @@ static void mana_ib_remove(struct auxiliary_device *adev)
 	struct mana_ib_dev *dev = dev_get_drvdata(&adev->dev);
 
 	ib_unregister_device(&dev->ib_dev);
+	dma_pool_destroy(dev->av_pool);
 	xa_destroy(&dev->qp_table_wq);
 	mana_ib_gd_destroy_rnic_adapter(dev);
 	mana_ib_destroy_eqs(dev);

drivers/infiniband/hw/mana/mana_ib.h

@@ -11,6 +11,7 @@
 #include <rdma/ib_umem.h>
 #include <rdma/mana-abi.h>
 #include <rdma/uverbs_ioctl.h>
+#include <linux/dmapool.h>
 
 #include <net/mana/mana.h>
 
@@ -32,6 +33,11 @@
  */
 #define MANA_CA_ACK_DELAY	16
 
+/*
+ * The buffer used for writing AV
+ */
+#define MANA_AV_BUFFER_SIZE	64
+
 struct mana_ib_adapter_caps {
 	u32 max_sq_id;
 	u32 max_rq_id;
@@ -65,6 +71,7 @@ struct mana_ib_dev {
 	struct gdma_queue **eqs;
 	struct xarray qp_table_wq;
 	struct mana_ib_adapter_caps adapter_caps;
+	struct dma_pool *av_pool;
 };
 
 struct mana_ib_wq {
@@ -88,6 +95,25 @@ struct mana_ib_pd {
 	u32 tx_vp_offset;
 };
 
+struct mana_ib_av {
+	u8 dest_ip[16];
+	u8 dest_mac[ETH_ALEN];
+	u16 udp_src_port;
+	u8 src_ip[16];
+	u32 hop_limit	: 8;
+	u32 reserved1	: 12;
+	u32 dscp	: 6;
+	u32 reserved2	: 5;
+	u32 is_ipv6	: 1;
+	u32 reserved3	: 32;
+};
+
+struct mana_ib_ah {
+	struct ib_ah ibah;
+	struct mana_ib_av *av;
+	dma_addr_t dma_handle;
+};
+
 struct mana_ib_mr {
 	struct ib_mr ibmr;
 	struct ib_umem *umem;
@@ -532,4 +558,8 @@ int mana_ib_gd_destroy_rc_qp(struct mana_ib_dev *mdev, struct mana_ib_qp *qp);
 int mana_ib_gd_create_ud_qp(struct mana_ib_dev *mdev, struct mana_ib_qp *qp,
 			    struct ib_qp_init_attr *attr, u32 doorbell, u32 type);
 int mana_ib_gd_destroy_ud_qp(struct mana_ib_dev *mdev, struct mana_ib_qp *qp);
+
+int mana_ib_create_ah(struct ib_ah *ibah, struct rdma_ah_init_attr *init_attr,
+		      struct ib_udata *udata);
+int mana_ib_destroy_ah(struct ib_ah *ah, u32 flags);
 #endif