123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336337338339340341342343344345346347348349350351352353354355356357358359360361362363364365366367368369370371372373374375376377378379380381382383384385386387388389390391392393394395396397398399400401402403404405406407408409410411412413414415416417418419420421422423424425426427428429430431432433434435436437438439440441442443444445446447448449450451452453454455456457458459460461462463464465466467468469470471472473474475476477478479480481482483484485486487488489490491492493494495496497498499500501502503504505506507508509510511512513514515516517518519520521522523524525526527528529530531532533534535536537538539540541542543544545546547548549550551552553554555556557558559560561562563564565566567568569570571572573574575576577578579// SPDX-License-Identifier: GPL-2.0
/*
 *  Shared Memory Communications over RDMA (SMC-R) and RoCE
 *
 *  IB infrastructure:
 *  Establish SMC-R as an Infiniband Client to be notified about added and
 *  removed IB devices of type RDMA.
 *  Determine device and port characteristics for these IB devices.
 *
 *  Copyright IBM Corp. 2016
 *
 *  Author(s):  Ursula Braun <ubraun@linux.vnet.ibm.com>
 */

#include <linux/random.h>
#include <linux/workqueue.h>
#include <linux/scatterlist.h>
#include <rdma/ib_verbs.h>
#include <rdma/ib_cache.h>

#include "smc_pnet.h"
#include "smc_ib.h"
#include "smc_core.h"
#include "smc_wr.h"
#include "smc.h"

#define SMC_MAX_CQE 32766	/* max. # of completion queue elements */

#define SMC_QP_MIN_RNR_TIMER		5
#define SMC_QP_TIMEOUT			15 /* 4096 * 2 ** timeout usec */
#define SMC_QP_RETRY_CNT			7 /* 7: infinite */
#define SMC_QP_RNR_RETRY			7 /* 7: infinite */

struct smc_ib_devices smc_ib_devices = {	/* smc-registered ib devices */
	.lock = __SPIN_LOCK_UNLOCKED(smc_ib_devices.lock),
	.list = LIST_HEAD_INIT(smc_ib_devices.list),
};

#define SMC_LOCAL_SYSTEMID_RESET	"%%%%%%%"

u8 local_systemid[SMC_SYSTEMID_LEN] = SMC_LOCAL_SYSTEMID_RESET;	/* unique system
								 * identifier
								 */

static int smc_ib_modify_qp_init(struct smc_link *lnk)
{
	struct ib_qp_attr qp_attr;

	memset(&qp_attr, 0, sizeof(qp_attr));
	qp_attr.qp_state = IB_QPS_INIT;
	qp_attr.pkey_index = 0;
	qp_attr.port_num = lnk->ibport;
	qp_attr.qp_access_flags = IB_ACCESS_LOCAL_WRITE
				| IB_ACCESS_REMOTE_WRITE;
	return ib_modify_qp(lnk->roce_qp, &qp_attr,
			    IB_QP_STATE | IB_QP_PKEY_INDEX |
			    IB_QP_ACCESS_FLAGS | IB_QP_PORT);
}

static int smc_ib_modify_qp_rtr(struct smc_link *lnk)
{
	enum ib_qp_attr_mask qp_attr_mask =
		IB_QP_STATE | IB_QP_AV | IB_QP_PATH_MTU | IB_QP_DEST_QPN |
		IB_QP_RQ_PSN | IB_QP_MAX_DEST_RD_ATOMIC | IB_QP_MIN_RNR_TIMER;
	struct ib_qp_attr qp_attr;

	memset(&qp_attr, 0, sizeof(qp_attr));
	qp_attr.qp_state = IB_QPS_RTR;
	qp_attr.path_mtu = min(lnk->path_mtu, lnk->peer_mtu);
	qp_attr.ah_attr.type = RDMA_AH_ATTR_TYPE_ROCE;
	rdma_ah_set_port_num(&qp_attr.ah_attr, lnk->ibport);
	rdma_ah_set_grh(&qp_attr.ah_attr, NULL, 0, lnk->sgid_index, 1, 0);
	rdma_ah_set_dgid_raw(&qp_attr.ah_attr, lnk->peer_gid);
	memcpy(&qp_attr.ah_attr.roce.dmac, lnk->peer_mac,
	       sizeof(lnk->peer_mac));
	qp_attr.dest_qp_num = lnk->peer_qpn;
	qp_attr.rq_psn = lnk->peer_psn; /* starting receive packet seq # */
	qp_attr.max_dest_rd_atomic = 1; /* max # of resources for incoming
					 * requests
					 */
	qp_attr.min_rnr_timer = SMC_QP_MIN_RNR_TIMER;

	return ib_modify_qp(lnk->roce_qp, &qp_attr, qp_attr_mask);
}

int smc_ib_modify_qp_rts(struct smc_link *lnk)
{
	struct ib_qp_attr qp_attr;

	memset(&qp_attr, 0, sizeof(qp_attr));
	qp_attr.qp_state = IB_QPS_RTS;
	qp_attr.timeout = SMC_QP_TIMEOUT;	/* local ack timeout */
	qp_attr.retry_cnt = SMC_QP_RETRY_CNT;	/* retry count */
	qp_attr.rnr_retry = SMC_QP_RNR_RETRY;	/* RNR retries, 7=infinite */
	qp_attr.sq_psn = lnk->psn_initial;	/* starting send packet seq # */
	qp_attr.max_rd_atomic = 1;	/* # of outstanding RDMA reads and
					 * atomic ops allowed
					 */
	return ib_modify_qp(lnk->roce_qp, &qp_attr,
			    IB_QP_STATE | IB_QP_TIMEOUT | IB_QP_RETRY_CNT |
			    IB_QP_SQ_PSN | IB_QP_RNR_RETRY |
			    IB_QP_MAX_QP_RD_ATOMIC);
}

int smc_ib_modify_qp_reset(struct smc_link *lnk)
{
	struct ib_qp_attr qp_attr;

	memset(&qp_attr, 0, sizeof(qp_attr));
	qp_attr.qp_state = IB_QPS_RESET;
	return ib_modify_qp(lnk->roce_qp, &qp_attr, IB_QP_STATE);
}

int smc_ib_ready_link(struct smc_link *lnk)
{
	struct smc_link_group *lgr = smc_get_lgr(lnk);
	int rc = 0;

	rc = smc_ib_modify_qp_init(lnk);
	if (rc)
		goto out;

	rc = smc_ib_modify_qp_rtr(lnk);
	if (rc)
		goto out;
	smc_wr_remember_qp_attr(lnk);
	rc = ib_req_notify_cq(lnk->smcibdev->roce_cq_recv,
			      IB_CQ_SOLICITED_MASK);
	if (rc)
		goto out;
	rc = smc_wr_rx_post_init(lnk);
	if (rc)
		goto out;
	smc_wr_remember_qp_attr(lnk);

	if (lgr->role == SMC_SERV) {
		rc = smc_ib_modify_qp_rts(lnk);
		if (rc)
			goto out;
		smc_wr_remember_qp_attr(lnk);
	}
out:
	return rc;
}

static int smc_ib_fill_mac(struct smc_ib_device *smcibdev, u8 ibport)
{
	const struct ib_gid_attr *attr;
	int rc = 0;

	attr = rdma_get_gid_attr(smcibdev->ibdev, ibport, 0);
	if (IS_ERR(attr))
		return -ENODEV;

	if (attr->ndev)
		memcpy(smcibdev->mac[ibport - 1], attr->ndev->dev_addr,
		       ETH_ALEN);
	else
		rc = -ENODEV;

	rdma_put_gid_attr(attr);
	return rc;
}

/* Create an identifier unique for this instance of SMC-R.
 * The MAC-address of the first active registered IB device
 * plus a random 2-byte number is used to create this identifier.
 * This name is delivered to the peer during connection initialization.
 */
static inline void smc_ib_define_local_systemid(struct smc_ib_device *smcibdev,
						u8 ibport)
{
	memcpy(&local_systemid[2], &smcibdev->mac[ibport - 1],
	       sizeof(smcibdev->mac[ibport - 1]));
	get_random_bytes(&local_systemid[0], 2);
}

bool smc_ib_port_active(struct smc_ib_device *smcibdev, u8 ibport)
{
	return smcibdev->pattr[ibport - 1].state == IB_PORT_ACTIVE;
}

/* determine the gid for an ib-device port and vlan id */
int smc_ib_determine_gid(struct smc_ib_device *smcibdev, u8 ibport,
			 unsigned short vlan_id, u8 gid[], u8 *sgid_index)
{
	const struct ib_gid_attr *attr;
	int i;

	for (i = 0; i < smcibdev->pattr[ibport - 1].gid_tbl_len; i++) {
		attr = rdma_get_gid_attr(smcibdev->ibdev, ibport, i);
		if (IS_ERR(attr))
			continue;

		if (attr->ndev &&
		    ((!vlan_id && !is_vlan_dev(attr->ndev)) ||
		     (vlan_id && is_vlan_dev(attr->ndev) &&
		      vlan_dev_vlan_id(attr->ndev) == vlan_id)) &&
		    attr->gid_type == IB_GID_TYPE_ROCE) {
			if (gid)
				memcpy(gid, &attr->gid, SMC_GID_SIZE);
			if (sgid_index)
				*sgid_index = attr->index;
			rdma_put_gid_attr(attr);
			return 0;
		}
		rdma_put_gid_attr(attr);
	}
	return -ENODEV;
}

static int smc_ib_remember_port_attr(struct smc_ib_device *smcibdev, u8 ibport)
{
	int rc;

	memset(&smcibdev->pattr[ibport - 1], 0,
	       sizeof(smcibdev->pattr[ibport - 1]));
	rc = ib_query_port(smcibdev->ibdev, ibport,
			   &smcibdev->pattr[ibport - 1]);
	if (rc)
		goto out;
	/* the SMC protocol requires specification of the RoCE MAC address */
	rc = smc_ib_fill_mac(smcibdev, ibport);
	if (rc)
		goto out;
	if (!strncmp(local_systemid, SMC_LOCAL_SYSTEMID_RESET,
		     sizeof(local_systemid)) &&
	    smc_ib_port_active(smcibdev, ibport))
		/* create unique system identifier */
		smc_ib_define_local_systemid(smcibdev, ibport);
out:
	return rc;
}

/* process context wrapper for might_sleep smc_ib_remember_port_attr */
static void smc_ib_port_event_work(struct work_struct *work)
{
	struct smc_ib_device *smcibdev = container_of(
		work, struct smc_ib_device, port_event_work);
	u8 port_idx;

	for_each_set_bit(port_idx, &smcibdev->port_event_mask, SMC_MAX_PORTS) {
		smc_ib_remember_port_attr(smcibdev, port_idx + 1);
		clear_bit(port_idx, &smcibdev->port_event_mask);
		if (!smc_ib_port_active(smcibdev, port_idx + 1))
			smc_port_terminate(smcibdev, port_idx + 1);
	}
}

/* can be called in IRQ context */
static void smc_ib_global_event_handler(struct ib_event_handler *handler,
					struct ib_event *ibevent)
{
	struct smc_ib_device *smcibdev;
	u8 port_idx;

	smcibdev = container_of(handler, struct smc_ib_device, event_handler);

	switch (ibevent->event) {
	case IB_EVENT_PORT_ERR:
	case IB_EVENT_DEVICE_FATAL:
	case IB_EVENT_PORT_ACTIVE:
		port_idx = ibevent->element.port_num - 1;
		set_bit(port_idx, &smcibdev->port_event_mask);
		schedule_work(&smcibdev->port_event_work);
		break;
	default:
		break;
	}
}

void smc_ib_dealloc_protection_domain(struct smc_link *lnk)
{
	if (lnk->roce_pd)
		ib_dealloc_pd(lnk->roce_pd);
	lnk->roce_pd = NULL;
}

int smc_ib_create_protection_domain(struct smc_link *lnk)
{
	int rc;

	lnk->roce_pd = ib_alloc_pd(lnk->smcibdev->ibdev, 0);
	rc = PTR_ERR_OR_ZERO(lnk->roce_pd);
	if (IS_ERR(lnk->roce_pd))
		lnk->roce_pd = NULL;
	return rc;
}

static void smc_ib_qp_event_handler(struct ib_event *ibevent, void *priv)
{
	struct smc_ib_device *smcibdev =
		(struct smc_ib_device *)ibevent->device;
	u8 port_idx;

	switch (ibevent->event) {
	case IB_EVENT_DEVICE_FATAL:
	case IB_EVENT_GID_CHANGE:
	case IB_EVENT_PORT_ERR:
	case IB_EVENT_QP_ACCESS_ERR:
		port_idx = ibevent->element.port_num - 1;
		set_bit(port_idx, &smcibdev->port_event_mask);
		schedule_work(&smcibdev->port_event_work);
		break;
	default:
		break;
	}
}

void smc_ib_destroy_queue_pair(struct smc_link *lnk)
{
	if (lnk->roce_qp)
		ib_destroy_qp(lnk->roce_qp);
	lnk->roce_qp = NULL;
}

/* create a queue pair within the protection domain for a link */
int smc_ib_create_queue_pair(struct smc_link *lnk)
{
	struct ib_qp_init_attr qp_attr = {
		.event_handler = smc_ib_qp_event_handler,
		.qp_context = lnk,
		.send_cq = lnk->smcibdev->roce_cq_send,
		.recv_cq = lnk->smcibdev->roce_cq_recv,
		.srq = NULL,
		.cap = {
				/* include unsolicited rdma_writes as well,
				 * there are max. 2 RDMA_WRITE per 1 WR_SEND
				 */
			.max_send_wr = SMC_WR_BUF_CNT * 3,
			.max_recv_wr = SMC_WR_BUF_CNT * 3,
			.max_send_sge = SMC_IB_MAX_SEND_SGE,
			.max_recv_sge = 1,
		},
		.sq_sig_type = IB_SIGNAL_REQ_WR,
		.qp_type = IB_QPT_RC,
	};
	int rc;

	lnk->roce_qp = ib_create_qp(lnk->roce_pd, &qp_attr);
	rc = PTR_ERR_OR_ZERO(lnk->roce_qp);
	if (IS_ERR(lnk->roce_qp))
		lnk->roce_qp = NULL;
	else
		smc_wr_remember_qp_attr(lnk);
	return rc;
}

void smc_ib_put_memory_region(struct ib_mr *mr)
{
	ib_dereg_mr(mr);
}

static int smc_ib_map_mr_sg(struct smc_buf_desc *buf_slot)
{
	unsigned int offset = 0;
	int sg_num;

	/* map the largest prefix of a dma mapped SG list */
	sg_num = ib_map_mr_sg(buf_slot->mr_rx[SMC_SINGLE_LINK],
			      buf_slot->sgt[SMC_SINGLE_LINK].sgl,
			      buf_slot->sgt[SMC_SINGLE_LINK].orig_nents,
			      &offset, PAGE_SIZE);

	return sg_num;
}

/* Allocate a memory region and map the dma mapped SG list of buf_slot */
int smc_ib_get_memory_region(struct ib_pd *pd, int access_flags,
			     struct smc_buf_desc *buf_slot)
{
	if (buf_slot->mr_rx[SMC_SINGLE_LINK])
		return 0; /* already done */

	buf_slot->mr_rx[SMC_SINGLE_LINK] =
		ib_alloc_mr(pd, IB_MR_TYPE_MEM_REG, 1 << buf_slot->order);
	if (IS_ERR(buf_slot->mr_rx[SMC_SINGLE_LINK])) {
		int rc;

		rc = PTR_ERR(buf_slot->mr_rx[SMC_SINGLE_LINK]);
		buf_slot->mr_rx[SMC_SINGLE_LINK] = NULL;
		return rc;
	}

	if (smc_ib_map_mr_sg(buf_slot) != 1)
		return -EINVAL;

	return 0;
}

/* synchronize buffer usage for cpu access */
void smc_ib_sync_sg_for_cpu(struct smc_ib_device *smcibdev,
			    struct smc_buf_desc *buf_slot,
			    enum dma_data_direction data_direction)
{
	struct scatterlist *sg;
	unsigned int i;

	/* for now there is just one DMA address */
	for_each_sg(buf_slot->sgt[SMC_SINGLE_LINK].sgl, sg,
		    buf_slot->sgt[SMC_SINGLE_LINK].nents, i) {
		if (!sg_dma_len(sg))
			break;
		ib_dma_sync_single_for_cpu(smcibdev->ibdev,
					   sg_dma_address(sg),
					   sg_dma_len(sg),
					   data_direction);
	}
}

/* synchronize buffer usage for device access */
void smc_ib_sync_sg_for_device(struct smc_ib_device *smcibdev,
			       struct smc_buf_desc *buf_slot,
			       enum dma_data_direction data_direction)
{
	struct scatterlist *sg;
	unsigned int i;

	/* for now there is just one DMA address */
	for_each_sg(buf_slot->sgt[SMC_SINGLE_LINK].sgl, sg,
		    buf_slot->sgt[SMC_SINGLE_LINK].nents, i) {
		if (!sg_dma_len(sg))
			break;
		ib_dma_sync_single_for_device(smcibdev->ibdev,
					      sg_dma_address(sg),
					      sg_dma_len(sg),
					      data_direction);
	}
}

/* Map a new TX or RX buffer SG-table to DMA */
int smc_ib_buf_map_sg(struct smc_ib_device *smcibdev,
		      struct smc_buf_desc *buf_slot,
		      enum dma_data_direction data_direction)
{
	int mapped_nents;

	mapped_nents = ib_dma_map_sg(smcibdev->ibdev,
				     buf_slot->sgt[SMC_SINGLE_LINK].sgl,
				     buf_slot->sgt[SMC_SINGLE_LINK].orig_nents,
				     data_direction);
	if (!mapped_nents)
		return -ENOMEM;

	return mapped_nents;
}

void smc_ib_buf_unmap_sg(struct smc_ib_device *smcibdev,
			 struct smc_buf_desc *buf_slot,
			 enum dma_data_direction data_direction)
{
	if (!buf_slot->sgt[SMC_SINGLE_LINK].sgl->dma_address)
		return; /* already unmapped */

	ib_dma_unmap_sg(smcibdev->ibdev,
			buf_slot->sgt[SMC_SINGLE_LINK].sgl,
			buf_slot->sgt[SMC_SINGLE_LINK].orig_nents,
			data_direction);
	buf_slot->sgt[SMC_SINGLE_LINK].sgl->dma_address = 0;
}

long smc_ib_setup_per_ibdev(struct smc_ib_device *smcibdev)
{
	struct ib_cq_init_attr cqattr =	{
		.cqe = SMC_MAX_CQE, .comp_vector = 0 };
	int cqe_size_order, smc_order;
	long rc;

	/* the calculated number of cq entries fits to mlx5 cq allocation */
	cqe_size_order = cache_line_size() == 128 ? 7 : 6;
	smc_order = MAX_ORDER - cqe_size_order - 1;
	if (SMC_MAX_CQE + 2 > (0x00000001 << smc_order) * PAGE_SIZE)
		cqattr.cqe = (0x00000001 << smc_order) * PAGE_SIZE - 2;
	smcibdev->roce_cq_send = ib_create_cq(smcibdev->ibdev,
					      smc_wr_tx_cq_handler, NULL,
					      smcibdev, &cqattr);
	rc = PTR_ERR_OR_ZERO(smcibdev->roce_cq_send);
	if (IS_ERR(smcibdev->roce_cq_send)) {
		smcibdev->roce_cq_send = NULL;
		return rc;
	}
	smcibdev->roce_cq_recv = ib_create_cq(smcibdev->ibdev,
					      smc_wr_rx_cq_handler, NULL,
					      smcibdev, &cqattr);
	rc = PTR_ERR_OR_ZERO(smcibdev->roce_cq_recv);
	if (IS_ERR(smcibdev->roce_cq_recv)) {
		smcibdev->roce_cq_recv = NULL;
		goto err;
	}
	smc_wr_add_dev(smcibdev);
	smcibdev->initialized = 1;
	return rc;

err:
	ib_destroy_cq(smcibdev->roce_cq_send);
	return rc;
}

static void smc_ib_cleanup_per_ibdev(struct smc_ib_device *smcibdev)
{
	if (!smcibdev->initialized)
		return;
	smcibdev->initialized = 0;
	smc_wr_remove_dev(smcibdev);
	ib_destroy_cq(smcibdev->roce_cq_recv);
	ib_destroy_cq(smcibdev->roce_cq_send);
}

static struct ib_client smc_ib_client;

/* callback function for ib_register_client() */
static void smc_ib_add_dev(struct ib_device *ibdev)
{
	struct smc_ib_device *smcibdev;
	u8 port_cnt;
	int i;

	if (ibdev->node_type != RDMA_NODE_IB_CA)
		return;

	smcibdev = kzalloc(sizeof(*smcibdev), GFP_KERNEL);
	if (!smcibdev)
		return;

	smcibdev->ibdev = ibdev;
	INIT_WORK(&smcibdev->port_event_work, smc_ib_port_event_work);

	spin_lock(&smc_ib_devices.lock);
	list_add_tail(&smcibdev->list, &smc_ib_devices.list);
	spin_unlock(&smc_ib_devices.lock);
	ib_set_client_data(ibdev, &smc_ib_client, smcibdev);
	INIT_IB_EVENT_HANDLER(&smcibdev->event_handler, smcibdev->ibdev,
			      smc_ib_global_event_handler);
	ib_register_event_handler(&smcibdev->event_handler);

	/* trigger reading of the port attributes */
	port_cnt = smcibdev->ibdev->phys_port_cnt;
	for (i = 0;
	     i < min_t(size_t, port_cnt, SMC_MAX_PORTS);
	     i++) {
		set_bit(i, &smcibdev->port_event_mask);
		/* determine pnetids of the port */
		smc_pnetid_by_dev_port(ibdev->dev.parent, i,
				       smcibdev->pnetid[i]);
	}
	schedule_work(&smcibdev->port_event_work);
}

/* callback function for ib_register_client() */
static void smc_ib_remove_dev(struct ib_device *ibdev, void *client_data)
{
	struct smc_ib_device *smcibdev;

	smcibdev = ib_get_client_data(ibdev, &smc_ib_client);
	ib_set_client_data(ibdev, &smc_ib_client, NULL);
	spin_lock(&smc_ib_devices.lock);
	list_del_init(&smcibdev->list); /* remove from smc_ib_devices */
	spin_unlock(&smc_ib_devices.lock);
	smc_pnet_remove_by_ibdev(smcibdev);
	smc_ib_cleanup_per_ibdev(smcibdev);
	ib_unregister_event_handler(&smcibdev->event_handler);
	kfree(smcibdev);
}

static struct ib_client smc_ib_client = {
	.name	= "smc_ib",
	.add	= smc_ib_add_dev,
	.remove = smc_ib_remove_dev,
};

int __init smc_ib_register_client(void)
{
	return ib_register_client(&smc_ib_client);
}

void smc_ib_unregister_client(void)
{
	ib_unregister_client(&smc_ib_client);
}