mirror of
https://github.com/torvalds/linux
synced 2024-11-05 18:23:50 +00:00
51e3dfa890
If an SMC connection to a certain peer is setup the first time, a new linkgroup is created. In case of setup failures, such a linkgroup is unusable and should disappear. As a first step the linkgroup is removed from the linkgroup list in smc_lgr_forget(). There are 2 problems: smc_listen_decline() might be called before linkgroup creation resulting in a crash due to calling smc_lgr_forget() with parameter NULL. If a setup failure occurs after linkgroup creation, the connection is never unregistered from the linkgroup, preventing linkgroup freeing. This patch introduces an enhanced smc_lgr_cleanup_early() function which * contains a linkgroup check for early smc_listen_decline() invocations * invokes smc_conn_free() to guarantee unregistering of the connection. * schedules fast linkgroup removal of the unusable linkgroup And the unused function smcd_conn_free() is removed from smc_core.h. Fixes:3b2dec2603
("net/smc: restructure client and server code in af_smc") Fixes:2a0674fffb
("net/smc: improve abnormal termination of link groups") Signed-off-by: Ursula Braun <ubraun@linux.ibm.com> Signed-off-by: Karsten Graul <kgraul@linux.ibm.com> Signed-off-by: David S. Miller <davem@davemloft.net>
328 lines
11 KiB
C
328 lines
11 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
/*
|
|
* Shared Memory Communications over RDMA (SMC-R) and RoCE
|
|
*
|
|
* Definitions for SMC Connections, Link Groups and Links
|
|
*
|
|
* Copyright IBM Corp. 2016
|
|
*
|
|
* Author(s): Ursula Braun <ubraun@linux.vnet.ibm.com>
|
|
*/
|
|
|
|
#ifndef _SMC_CORE_H
|
|
#define _SMC_CORE_H
|
|
|
|
#include <linux/atomic.h>
|
|
#include <rdma/ib_verbs.h>
|
|
|
|
#include "smc.h"
|
|
#include "smc_ib.h"
|
|
|
|
#define SMC_RMBS_PER_LGR_MAX 255 /* max. # of RMBs per link group */
|
|
|
|
struct smc_lgr_list { /* list of link group definition */
|
|
struct list_head list;
|
|
spinlock_t lock; /* protects list of link groups */
|
|
u32 num; /* unique link group number */
|
|
};
|
|
|
|
enum smc_lgr_role { /* possible roles of a link group */
|
|
SMC_CLNT, /* client */
|
|
SMC_SERV /* server */
|
|
};
|
|
|
|
enum smc_link_state { /* possible states of a link */
|
|
SMC_LNK_INACTIVE, /* link is inactive */
|
|
SMC_LNK_ACTIVATING, /* link is being activated */
|
|
SMC_LNK_ACTIVE, /* link is active */
|
|
SMC_LNK_DELETING, /* link is being deleted */
|
|
};
|
|
|
|
#define SMC_WR_BUF_SIZE 48 /* size of work request buffer */
|
|
|
|
struct smc_wr_buf {
|
|
u8 raw[SMC_WR_BUF_SIZE];
|
|
};
|
|
|
|
#define SMC_WR_REG_MR_WAIT_TIME (5 * HZ)/* wait time for ib_wr_reg_mr result */
|
|
|
|
enum smc_wr_reg_state {
|
|
POSTED, /* ib_wr_reg_mr request posted */
|
|
CONFIRMED, /* ib_wr_reg_mr response: successful */
|
|
FAILED /* ib_wr_reg_mr response: failure */
|
|
};
|
|
|
|
struct smc_rdma_sge { /* sges for RDMA writes */
|
|
struct ib_sge wr_tx_rdma_sge[SMC_IB_MAX_SEND_SGE];
|
|
};
|
|
|
|
#define SMC_MAX_RDMA_WRITES 2 /* max. # of RDMA writes per
|
|
* message send
|
|
*/
|
|
|
|
struct smc_rdma_sges { /* sges per message send */
|
|
struct smc_rdma_sge tx_rdma_sge[SMC_MAX_RDMA_WRITES];
|
|
};
|
|
|
|
struct smc_rdma_wr { /* work requests per message
|
|
* send
|
|
*/
|
|
struct ib_rdma_wr wr_tx_rdma[SMC_MAX_RDMA_WRITES];
|
|
};
|
|
|
|
struct smc_link {
|
|
struct smc_ib_device *smcibdev; /* ib-device */
|
|
u8 ibport; /* port - values 1 | 2 */
|
|
struct ib_pd *roce_pd; /* IB protection domain,
|
|
* unique for every RoCE QP
|
|
*/
|
|
struct ib_qp *roce_qp; /* IB queue pair */
|
|
struct ib_qp_attr qp_attr; /* IB queue pair attributes */
|
|
|
|
struct smc_wr_buf *wr_tx_bufs; /* WR send payload buffers */
|
|
struct ib_send_wr *wr_tx_ibs; /* WR send meta data */
|
|
struct ib_sge *wr_tx_sges; /* WR send gather meta data */
|
|
struct smc_rdma_sges *wr_tx_rdma_sges;/*RDMA WRITE gather meta data*/
|
|
struct smc_rdma_wr *wr_tx_rdmas; /* WR RDMA WRITE */
|
|
struct smc_wr_tx_pend *wr_tx_pends; /* WR send waiting for CQE */
|
|
/* above four vectors have wr_tx_cnt elements and use the same index */
|
|
dma_addr_t wr_tx_dma_addr; /* DMA address of wr_tx_bufs */
|
|
atomic_long_t wr_tx_id; /* seq # of last sent WR */
|
|
unsigned long *wr_tx_mask; /* bit mask of used indexes */
|
|
u32 wr_tx_cnt; /* number of WR send buffers */
|
|
wait_queue_head_t wr_tx_wait; /* wait for free WR send buf */
|
|
|
|
struct smc_wr_buf *wr_rx_bufs; /* WR recv payload buffers */
|
|
struct ib_recv_wr *wr_rx_ibs; /* WR recv meta data */
|
|
struct ib_sge *wr_rx_sges; /* WR recv scatter meta data */
|
|
/* above three vectors have wr_rx_cnt elements and use the same index */
|
|
dma_addr_t wr_rx_dma_addr; /* DMA address of wr_rx_bufs */
|
|
u64 wr_rx_id; /* seq # of last recv WR */
|
|
u32 wr_rx_cnt; /* number of WR recv buffers */
|
|
unsigned long wr_rx_tstamp; /* jiffies when last buf rx */
|
|
|
|
struct ib_reg_wr wr_reg; /* WR register memory region */
|
|
wait_queue_head_t wr_reg_wait; /* wait for wr_reg result */
|
|
enum smc_wr_reg_state wr_reg_state; /* state of wr_reg request */
|
|
|
|
u8 gid[SMC_GID_SIZE];/* gid matching used vlan id*/
|
|
u8 sgid_index; /* gid index for vlan id */
|
|
u32 peer_qpn; /* QP number of peer */
|
|
enum ib_mtu path_mtu; /* used mtu */
|
|
enum ib_mtu peer_mtu; /* mtu size of peer */
|
|
u32 psn_initial; /* QP tx initial packet seqno */
|
|
u32 peer_psn; /* QP rx initial packet seqno */
|
|
u8 peer_mac[ETH_ALEN]; /* = gid[8:10||13:15] */
|
|
u8 peer_gid[SMC_GID_SIZE]; /* gid of peer*/
|
|
u8 link_id; /* unique # within link group */
|
|
|
|
enum smc_link_state state; /* state of link */
|
|
struct workqueue_struct *llc_wq; /* single thread work queue */
|
|
struct completion llc_confirm; /* wait for rx of conf link */
|
|
struct completion llc_confirm_resp; /* wait 4 rx of cnf lnk rsp */
|
|
int llc_confirm_rc; /* rc from confirm link msg */
|
|
int llc_confirm_resp_rc; /* rc from conf_resp msg */
|
|
struct completion llc_add; /* wait for rx of add link */
|
|
struct completion llc_add_resp; /* wait for rx of add link rsp*/
|
|
struct delayed_work llc_testlink_wrk; /* testlink worker */
|
|
struct completion llc_testlink_resp; /* wait for rx of testlink */
|
|
int llc_testlink_time; /* testlink interval */
|
|
struct completion llc_confirm_rkey; /* wait 4 rx of cnf rkey */
|
|
int llc_confirm_rkey_rc; /* rc from cnf rkey msg */
|
|
struct completion llc_delete_rkey; /* wait 4 rx of del rkey */
|
|
int llc_delete_rkey_rc; /* rc from del rkey msg */
|
|
struct mutex llc_delete_rkey_mutex; /* serialize usage */
|
|
};
|
|
|
|
/* For now we just allow one parallel link per link group. The SMC protocol
|
|
* allows more (up to 8).
|
|
*/
|
|
#define SMC_LINKS_PER_LGR_MAX 1
|
|
#define SMC_SINGLE_LINK 0
|
|
|
|
#define SMC_FIRST_CONTACT 1 /* first contact to a peer */
|
|
#define SMC_REUSE_CONTACT 0 /* follow-on contact to a peer*/
|
|
|
|
/* tx/rx buffer list element for sndbufs list and rmbs list of a lgr */
|
|
struct smc_buf_desc {
|
|
struct list_head list;
|
|
void *cpu_addr; /* virtual address of buffer */
|
|
struct page *pages;
|
|
int len; /* length of buffer */
|
|
u32 used; /* currently used / unused */
|
|
u8 wr_reg : 1; /* mem region registered */
|
|
u8 regerr : 1; /* err during registration */
|
|
union {
|
|
struct { /* SMC-R */
|
|
struct sg_table sgt[SMC_LINKS_PER_LGR_MAX];
|
|
/* virtual buffer */
|
|
struct ib_mr *mr_rx[SMC_LINKS_PER_LGR_MAX];
|
|
/* for rmb only: memory region
|
|
* incl. rkey provided to peer
|
|
*/
|
|
u32 order; /* allocation order */
|
|
};
|
|
struct { /* SMC-D */
|
|
unsigned short sba_idx;
|
|
/* SBA index number */
|
|
u64 token;
|
|
/* DMB token number */
|
|
dma_addr_t dma_addr;
|
|
/* DMA address */
|
|
};
|
|
};
|
|
};
|
|
|
|
struct smc_rtoken { /* address/key of remote RMB */
|
|
u64 dma_addr;
|
|
u32 rkey;
|
|
};
|
|
|
|
#define SMC_LGR_ID_SIZE 4
|
|
#define SMC_BUF_MIN_SIZE 16384 /* minimum size of an RMB */
|
|
#define SMC_RMBE_SIZES 16 /* number of distinct RMBE sizes */
|
|
/* theoretically, the RFC states that largest size would be 512K,
|
|
* i.e. compressed 5 and thus 6 sizes (0..5), despite
|
|
* struct smc_clc_msg_accept_confirm.rmbe_size being a 4 bit value (0..15)
|
|
*/
|
|
|
|
struct smcd_dev;
|
|
|
|
struct smc_link_group {
|
|
struct list_head list;
|
|
struct rb_root conns_all; /* connection tree */
|
|
rwlock_t conns_lock; /* protects conns_all */
|
|
unsigned int conns_num; /* current # of connections */
|
|
unsigned short vlan_id; /* vlan id of link group */
|
|
|
|
struct list_head sndbufs[SMC_RMBE_SIZES];/* tx buffers */
|
|
rwlock_t sndbufs_lock; /* protects tx buffers */
|
|
struct list_head rmbs[SMC_RMBE_SIZES]; /* rx buffers */
|
|
rwlock_t rmbs_lock; /* protects rx buffers */
|
|
|
|
u8 id[SMC_LGR_ID_SIZE]; /* unique lgr id */
|
|
struct delayed_work free_work; /* delayed freeing of an lgr */
|
|
struct work_struct terminate_work; /* abnormal lgr termination */
|
|
u8 sync_err : 1; /* lgr no longer fits to peer */
|
|
u8 terminating : 1;/* lgr is terminating */
|
|
u8 freefast : 1; /* free worker scheduled fast */
|
|
u8 freeing : 1; /* lgr is being freed */
|
|
|
|
bool is_smcd; /* SMC-R or SMC-D */
|
|
union {
|
|
struct { /* SMC-R */
|
|
enum smc_lgr_role role;
|
|
/* client or server */
|
|
struct smc_link lnk[SMC_LINKS_PER_LGR_MAX];
|
|
/* smc link */
|
|
char peer_systemid[SMC_SYSTEMID_LEN];
|
|
/* unique system_id of peer */
|
|
struct smc_rtoken rtokens[SMC_RMBS_PER_LGR_MAX]
|
|
[SMC_LINKS_PER_LGR_MAX];
|
|
/* remote addr/key pairs */
|
|
DECLARE_BITMAP(rtokens_used_mask, SMC_RMBS_PER_LGR_MAX);
|
|
/* used rtoken elements */
|
|
};
|
|
struct { /* SMC-D */
|
|
u64 peer_gid;
|
|
/* Peer GID (remote) */
|
|
struct smcd_dev *smcd;
|
|
/* ISM device for VLAN reg. */
|
|
u8 peer_shutdown : 1;
|
|
/* peer triggered shutdownn */
|
|
};
|
|
};
|
|
};
|
|
|
|
struct smc_clc_msg_local;
|
|
|
|
struct smc_init_info {
|
|
u8 is_smcd;
|
|
unsigned short vlan_id;
|
|
int srv_first_contact;
|
|
int cln_first_contact;
|
|
/* SMC-R */
|
|
struct smc_clc_msg_local *ib_lcl;
|
|
struct smc_ib_device *ib_dev;
|
|
u8 ib_gid[SMC_GID_SIZE];
|
|
u8 ib_port;
|
|
u32 ib_clcqpn;
|
|
/* SMC-D */
|
|
u64 ism_gid;
|
|
struct smcd_dev *ism_dev;
|
|
};
|
|
|
|
/* Find the connection associated with the given alert token in the link group.
|
|
* To use rbtrees we have to implement our own search core.
|
|
* Requires @conns_lock
|
|
* @token alert token to search for
|
|
* @lgr link group to search in
|
|
* Returns connection associated with token if found, NULL otherwise.
|
|
*/
|
|
static inline struct smc_connection *smc_lgr_find_conn(
|
|
u32 token, struct smc_link_group *lgr)
|
|
{
|
|
struct smc_connection *res = NULL;
|
|
struct rb_node *node;
|
|
|
|
node = lgr->conns_all.rb_node;
|
|
while (node) {
|
|
struct smc_connection *cur = rb_entry(node,
|
|
struct smc_connection, alert_node);
|
|
|
|
if (cur->alert_token_local > token) {
|
|
node = node->rb_left;
|
|
} else {
|
|
if (cur->alert_token_local < token) {
|
|
node = node->rb_right;
|
|
} else {
|
|
res = cur;
|
|
break;
|
|
}
|
|
}
|
|
}
|
|
|
|
return res;
|
|
}
|
|
|
|
static inline void smc_lgr_terminate_sched(struct smc_link_group *lgr)
|
|
{
|
|
if (!lgr->terminating && !lgr->freeing)
|
|
schedule_work(&lgr->terminate_work);
|
|
}
|
|
|
|
struct smc_sock;
|
|
struct smc_clc_msg_accept_confirm;
|
|
struct smc_clc_msg_local;
|
|
|
|
void smc_lgr_forget(struct smc_link_group *lgr);
|
|
void smc_lgr_cleanup_early(struct smc_connection *conn);
|
|
void smc_lgr_terminate(struct smc_link_group *lgr, bool soft);
|
|
void smc_port_terminate(struct smc_ib_device *smcibdev, u8 ibport);
|
|
void smc_smcd_terminate(struct smcd_dev *dev, u64 peer_gid,
|
|
unsigned short vlan);
|
|
void smc_smcd_terminate_all(struct smcd_dev *dev);
|
|
void smc_smcr_terminate_all(struct smc_ib_device *smcibdev);
|
|
int smc_buf_create(struct smc_sock *smc, bool is_smcd);
|
|
int smc_uncompress_bufsize(u8 compressed);
|
|
int smc_rmb_rtoken_handling(struct smc_connection *conn,
|
|
struct smc_clc_msg_accept_confirm *clc);
|
|
int smc_rtoken_add(struct smc_link_group *lgr, __be64 nw_vaddr, __be32 nw_rkey);
|
|
int smc_rtoken_delete(struct smc_link_group *lgr, __be32 nw_rkey);
|
|
void smc_sndbuf_sync_sg_for_cpu(struct smc_connection *conn);
|
|
void smc_sndbuf_sync_sg_for_device(struct smc_connection *conn);
|
|
void smc_rmb_sync_sg_for_cpu(struct smc_connection *conn);
|
|
void smc_rmb_sync_sg_for_device(struct smc_connection *conn);
|
|
int smc_vlan_by_tcpsk(struct socket *clcsock, struct smc_init_info *ini);
|
|
|
|
void smc_conn_free(struct smc_connection *conn);
|
|
int smc_conn_create(struct smc_sock *smc, struct smc_init_info *ini);
|
|
void smc_lgr_schedule_free_work_fast(struct smc_link_group *lgr);
|
|
int smc_core_init(void);
|
|
void smc_core_exit(void);
|
|
|
|
static inline struct smc_link_group *smc_get_lgr(struct smc_link *link)
|
|
{
|
|
return container_of(link, struct smc_link_group, lnk[SMC_SINGLE_LINK]);
|
|
}
|
|
#endif
|