Commit d99dc602 authored by Gary Leshner's avatar Gary Leshner Committed by Jason Gunthorpe
Browse files

IB/hfi1: Add functions to transmit datagram ipoib packets 

This patch implements the mechanism to accelerate the transmit side of
a multiple transmit queue RDMA netdev by submitting the packets to
the SDMA engine directly instead of sending through the verbs layer.

This patch also changes the UD/SEND_ONLY op to output the entropy value
in byte 0 of deth[1]. UD/SEND_ONLY_WITH_IMMEDIATE uses the previous
behavior with no entropy value being output.

The code in the ipoib rdma netdev which submits tx requests upon
successful submission will call trace_sdma_output_ibhdr to output
the ibhdr to the trace buffer.

Link: https://lore.kernel.org/r/20200511160548.173205.45616.stgit@awfm-01.aw.intel.com


Reviewed-by: default avatarMike Marciniszyn <mike.marciniszyn@intel.com>
Reviewed-by: default avatarDennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: default avatarGary Leshner <Gary.S.Leshner@intel.com>
Signed-off-by: default avatarKaike Wan <kaike.wan@intel.com>
Signed-off-by: default avatarDennis Dalessandro <dennis.dalessandro@intel.com>
Signed-off-by: default avatarJason Gunthorpe <jgg@mellanox.com>
parent fe810b50

drivers/infiniband/hw/hfi1/Makefile

+1 −0
Original line number Diff line number Diff line
@@ -22,6 +22,7 @@ hfi1-y := \ 
	init.o \

	intr.o \

	iowait.o \

	ipoib_tx.o \

	mad.o \

	mmu_rb.o \

	msix.o \

drivers/infiniband/hw/hfi1/ipoib.h

0 → 100644
+145 −0
Original line number Diff line number Diff line 
/* SPDX-License-Identifier: (GPL-2.0 OR BSD-3-Clause) */

/*

 * Copyright(c) 2020 Intel Corporation.

 *

 */



/*

 * This file contains HFI1 support for IPOIB functionality

 */



#ifndef HFI1_IPOIB_H

#define HFI1_IPOIB_H



#include <linux/types.h>

#include <linux/stddef.h>

#include <linux/atomic.h>

#include <linux/netdevice.h>

#include <linux/slab.h>

#include <linux/skbuff.h>

#include <linux/list.h>

#include <linux/if_infiniband.h>



#include "hfi.h"

#include "iowait.h"



#include <rdma/ib_verbs.h>



#define HFI1_IPOIB_ENTROPY_SHIFT   24



#define HFI1_IPOIB_TXREQ_NAME_LEN   32



#define HFI1_IPOIB_ENCAP_LEN 4



struct hfi1_ipoib_dev_priv;



union hfi1_ipoib_flow {

	u16 as_int;

	struct {

		u8 tx_queue;

		u8 sc5;

	} __attribute__((__packed__));

};



/**

 * struct hfi1_ipoib_circ_buf - List of items to be processed

 * @items: ring of items

 * @head: ring head

 * @tail: ring tail

 * @max_items: max items + 1 that the ring can contain

 * @producer_lock: producer sync lock

 * @consumer_lock: consumer sync lock

 */

struct hfi1_ipoib_circ_buf {

	void **items;

	unsigned long head;

	unsigned long tail;

	unsigned long max_items;

	spinlock_t producer_lock; /* head sync lock */

	spinlock_t consumer_lock; /* tail sync lock */

};



/**

 * struct hfi1_ipoib_txq - IPOIB per Tx queue information

 * @priv: private pointer

 * @sde: sdma engine

 * @tx_list: tx request list

 * @sent_txreqs: count of txreqs posted to sdma

 * @flow: tracks when list needs to be flushed for a flow change

 * @q_idx: ipoib Tx queue index

 * @pkts_sent: indicator packets have been sent from this queue

 * @wait: iowait structure

 * @complete_txreqs: count of txreqs completed by sdma

 * @napi: pointer to tx napi interface

 * @tx_ring: ring of ipoib txreqs to be reaped by napi callback

 */

struct hfi1_ipoib_txq {

	struct hfi1_ipoib_dev_priv *priv;

	struct sdma_engine *sde;

	struct list_head tx_list;

	u64 sent_txreqs;

	union hfi1_ipoib_flow flow;

	u8 q_idx;

	bool pkts_sent;

	struct iowait wait;



	atomic64_t ____cacheline_aligned_in_smp complete_txreqs;

	struct napi_struct *napi;

	struct hfi1_ipoib_circ_buf tx_ring;

};



struct hfi1_ipoib_dev_priv {

	struct hfi1_devdata *dd;

	struct net_device   *netdev;

	struct ib_device    *device;

	struct hfi1_ipoib_txq *txqs;

	struct kmem_cache *txreq_cache;

	struct napi_struct *tx_napis;

	u16 pkey;

	u16 pkey_index;

	u32 qkey;

	u8 port_num;



	const struct net_device_ops *netdev_ops;

	struct rvt_qp *qp;

	struct pcpu_sw_netstats __percpu *netstats;

};



/* hfi1 ipoib rdma netdev's private data structure */

struct hfi1_ipoib_rdma_netdev {

	struct rdma_netdev rn;  /* keep this first */

	/* followed by device private data */

	struct hfi1_ipoib_dev_priv dev_priv;

};



static inline struct hfi1_ipoib_dev_priv *

hfi1_ipoib_priv(const struct net_device *dev)

{

	return &((struct hfi1_ipoib_rdma_netdev *)netdev_priv(dev))->dev_priv;

}



static inline void

hfi1_ipoib_update_tx_netstats(struct hfi1_ipoib_dev_priv *priv,

			      u64 packets,

			      u64 bytes)

{

	struct pcpu_sw_netstats *netstats = this_cpu_ptr(priv->netstats);



	u64_stats_update_begin(&netstats->syncp);

	netstats->tx_packets += packets;

	netstats->tx_bytes += bytes;

	u64_stats_update_end(&netstats->syncp);

}



int hfi1_ipoib_send_dma(struct net_device *dev,

			struct sk_buff *skb,

			struct ib_ah *address,

			u32 dqpn);



int hfi1_ipoib_txreq_init(struct hfi1_ipoib_dev_priv *priv);

void hfi1_ipoib_txreq_deinit(struct hfi1_ipoib_dev_priv *priv);



void hfi1_ipoib_napi_tx_enable(struct net_device *dev);

void hfi1_ipoib_napi_tx_disable(struct net_device *dev);



#endif /* _IPOIB_H */

drivers/infiniband/hw/hfi1/ipoib_tx.c

0 → 100644
+828 −0

File added.

Preview size limit exceeded, changes collapsed.

drivers/infiniband/hw/hfi1/trace.c

+9 −1
Original line number Diff line number Diff line 
/*

 * Copyright(c) 2015 - 2018 Intel Corporation.

 * Copyright(c) 2015 - 2020 Intel Corporation.

 *

 * This file is provided under a dual BSD/GPLv2 license.  When using or

 * redistributing this file, you may do so under either license.
@@ -47,6 +47,7 @@ 
#define CREATE_TRACE_POINTS

#include "trace.h"

#include "exp_rcv.h"

#include "ipoib.h"



static u8 __get_ib_hdr_len(struct ib_header *hdr)

{
@@ -126,6 +127,7 @@ const char *hfi1_trace_get_packet_l2_str(u8 l2) 
#define RETH_PRN "reth vaddr:0x%.16llx rkey:0x%.8x dlen:0x%.8x"

#define AETH_PRN "aeth syn:0x%.2x %s msn:0x%.8x"

#define DETH_PRN "deth qkey:0x%.8x sqpn:0x%.6x"

#define DETH_ENTROPY_PRN "deth qkey:0x%.8x sqpn:0x%.6x entropy:0x%.2x"

#define IETH_PRN "ieth rkey:0x%.8x"

#define ATOMICACKETH_PRN "origdata:%llx"

#define ATOMICETH_PRN "vaddr:0x%llx rkey:0x%.8x sdata:%llx cdata:%llx"
@@ -444,6 +446,12 @@ const char *parse_everbs_hdrs( 
		break;

	/* deth */

	case OP(UD, SEND_ONLY):

		trace_seq_printf(p, DETH_ENTROPY_PRN,

				 be32_to_cpu(eh->ud.deth[0]),

				 be32_to_cpu(eh->ud.deth[1]) & RVT_QPN_MASK,

				 be32_to_cpu(eh->ud.deth[1]) >>

					     HFI1_IPOIB_ENTROPY_SHIFT);

		break;

	case OP(UD, SEND_ONLY_WITH_IMMEDIATE):

		trace_seq_printf(p, DETH_PRN,

				 be32_to_cpu(eh->ud.deth[0]),

include/rdma/ib_verbs.h

+1 −0
Original line number Diff line number Diff line
@@ -2205,6 +2205,7 @@ struct rdma_netdev { 
	void              *clnt_priv;

	struct ib_device  *hca;

	u8                 port_num;

	int                mtu;



	/*

	 * cleanup function must be specified.

CRA Git | Maintained and supported by SUSTech CRA and CCSE