From 46ac64419ded7bcbe1fb8d0f4df3258384a425c2 Mon Sep 17 00:00:00 2001 From: Wen Gu Date: Sun, 28 Apr 2024 14:07:29 +0800 Subject: net/smc: introduce loopback-ism for SMC intra-OS shortcut This introduces a kind of Emulated-ISM device named loopback-ism for SMCv2.1. The loopback-ism device is currently exclusive for SMC usage, and aims to provide an SMC shortcut for sockets within the same kernel, leading to improved intra-OS traffic performance. Configuration of this feature is managed through the config SMC_LO. Signed-off-by: Wen Gu Reviewed-by: Gerd Bayer Reviewed-by: Wenjia Zhang Reviewed-and-tested-by: Jan Karcher Signed-off-by: Paolo Abeni --- net/smc/smc_loopback.c | 156 +++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 156 insertions(+) create mode 100644 net/smc/smc_loopback.c (limited to 'net/smc/smc_loopback.c') diff --git a/net/smc/smc_loopback.c b/net/smc/smc_loopback.c new file mode 100644 index 000000000000..c364e3e6e3fb --- /dev/null +++ b/net/smc/smc_loopback.c @@ -0,0 +1,156 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Shared Memory Communications Direct over loopback-ism device. + * + * Functions for loopback-ism device. + * + * Copyright (c) 2024, Alibaba Inc. + * + * Author: Wen Gu + * Tony Lu + * + */ + +#include +#include +#include + +#include "smc_ism.h" +#include "smc_loopback.h" + +static const char smc_lo_dev_name[] = "loopback-ism"; +static struct smc_lo_dev *lo_dev; + +static const struct smcd_ops lo_ops = { + .query_remote_gid = NULL, + .register_dmb = NULL, + .unregister_dmb = NULL, + .add_vlan_id = NULL, + .del_vlan_id = NULL, + .set_vlan_required = NULL, + .reset_vlan_required = NULL, + .signal_event = NULL, + .move_data = NULL, + .supports_v2 = NULL, + .get_local_gid = NULL, + .get_chid = NULL, + .get_dev = NULL, +}; + +static struct smcd_dev *smcd_lo_alloc_dev(const struct smcd_ops *ops, + int max_dmbs) +{ + struct smcd_dev *smcd; + + smcd = kzalloc(sizeof(*smcd), GFP_KERNEL); + if (!smcd) + return NULL; + + smcd->conn = kcalloc(max_dmbs, sizeof(struct smc_connection *), + GFP_KERNEL); + if (!smcd->conn) + goto out_smcd; + + smcd->ops = ops; + + spin_lock_init(&smcd->lock); + spin_lock_init(&smcd->lgr_lock); + INIT_LIST_HEAD(&smcd->vlan); + INIT_LIST_HEAD(&smcd->lgr_list); + init_waitqueue_head(&smcd->lgrs_deleted); + return smcd; + +out_smcd: + kfree(smcd); + return NULL; +} + +static int smcd_lo_register_dev(struct smc_lo_dev *ldev) +{ + struct smcd_dev *smcd; + + smcd = smcd_lo_alloc_dev(&lo_ops, SMC_LO_MAX_DMBS); + if (!smcd) + return -ENOMEM; + ldev->smcd = smcd; + smcd->priv = ldev; + + /* TODO: + * register loopback-ism to smcd_dev list. + */ + return 0; +} + +static void smcd_lo_unregister_dev(struct smc_lo_dev *ldev) +{ + struct smcd_dev *smcd = ldev->smcd; + + /* TODO: + * unregister loopback-ism from smcd_dev list. + */ + kfree(smcd->conn); + kfree(smcd); +} + +static int smc_lo_dev_init(struct smc_lo_dev *ldev) +{ + return smcd_lo_register_dev(ldev); +} + +static void smc_lo_dev_exit(struct smc_lo_dev *ldev) +{ + smcd_lo_unregister_dev(ldev); +} + +static void smc_lo_dev_release(struct device *dev) +{ + struct smc_lo_dev *ldev = + container_of(dev, struct smc_lo_dev, dev); + + kfree(ldev); +} + +static int smc_lo_dev_probe(void) +{ + struct smc_lo_dev *ldev; + int ret; + + ldev = kzalloc(sizeof(*ldev), GFP_KERNEL); + if (!ldev) + return -ENOMEM; + + ldev->dev.parent = NULL; + ldev->dev.release = smc_lo_dev_release; + device_initialize(&ldev->dev); + dev_set_name(&ldev->dev, smc_lo_dev_name); + + ret = smc_lo_dev_init(ldev); + if (ret) + goto free_dev; + + lo_dev = ldev; /* global loopback device */ + return 0; + +free_dev: + put_device(&ldev->dev); + return ret; +} + +static void smc_lo_dev_remove(void) +{ + if (!lo_dev) + return; + + smc_lo_dev_exit(lo_dev); + put_device(&lo_dev->dev); /* device_initialize in smc_lo_dev_probe */ +} + +int smc_loopback_init(void) +{ + return smc_lo_dev_probe(); +} + +void smc_loopback_exit(void) +{ + smc_lo_dev_remove(); +} -- cgit v1.2.3-59-g8ed1b From 45783ee85bf337693a99e03cd6142fdcfb06585d Mon Sep 17 00:00:00 2001 From: Wen Gu Date: Sun, 28 Apr 2024 14:07:30 +0800 Subject: net/smc: implement ID-related operations of loopback-ism This implements operations related to IDs for the loopback-ism device. loopback-ism uses an Extended GID that is a 128-bit GID instead of the existing ISM 64-bit GID, and uses the CHID defined with the reserved value 0xFFFF. Signed-off-by: Wen Gu Reviewed-by: Wenjia Zhang Reviewed-and-tested-by: Jan Karcher Signed-off-by: Paolo Abeni --- net/smc/smc_loopback.c | 62 ++++++++++++++++++++++++++++++++++++++++++++++---- net/smc/smc_loopback.h | 3 +++ 2 files changed, 60 insertions(+), 5 deletions(-) (limited to 'net/smc/smc_loopback.c') diff --git a/net/smc/smc_loopback.c b/net/smc/smc_loopback.c index c364e3e6e3fb..0349632a76c4 100644 --- a/net/smc/smc_loopback.c +++ b/net/smc/smc_loopback.c @@ -18,11 +18,62 @@ #include "smc_ism.h" #include "smc_loopback.h" +#define SMC_LO_V2_CAPABLE 0x1 /* loopback-ism acts as ISMv2 */ + static const char smc_lo_dev_name[] = "loopback-ism"; static struct smc_lo_dev *lo_dev; +static void smc_lo_generate_ids(struct smc_lo_dev *ldev) +{ + struct smcd_gid *lgid = &ldev->local_gid; + uuid_t uuid; + + uuid_gen(&uuid); + memcpy(&lgid->gid, &uuid, sizeof(lgid->gid)); + memcpy(&lgid->gid_ext, (u8 *)&uuid + sizeof(lgid->gid), + sizeof(lgid->gid_ext)); + + ldev->chid = SMC_LO_RESERVED_CHID; +} + +static int smc_lo_query_rgid(struct smcd_dev *smcd, struct smcd_gid *rgid, + u32 vid_valid, u32 vid) +{ + struct smc_lo_dev *ldev = smcd->priv; + + /* rgid should be the same as lgid */ + if (!ldev || rgid->gid != ldev->local_gid.gid || + rgid->gid_ext != ldev->local_gid.gid_ext) + return -ENETUNREACH; + return 0; +} + +static int smc_lo_supports_v2(void) +{ + return SMC_LO_V2_CAPABLE; +} + +static void smc_lo_get_local_gid(struct smcd_dev *smcd, + struct smcd_gid *smcd_gid) +{ + struct smc_lo_dev *ldev = smcd->priv; + + smcd_gid->gid = ldev->local_gid.gid; + smcd_gid->gid_ext = ldev->local_gid.gid_ext; +} + +static u16 smc_lo_get_chid(struct smcd_dev *smcd) +{ + return ((struct smc_lo_dev *)smcd->priv)->chid; +} + +static struct device *smc_lo_get_dev(struct smcd_dev *smcd) +{ + return &((struct smc_lo_dev *)smcd->priv)->dev; +} + static const struct smcd_ops lo_ops = { - .query_remote_gid = NULL, + .query_remote_gid = smc_lo_query_rgid, .register_dmb = NULL, .unregister_dmb = NULL, .add_vlan_id = NULL, @@ -31,10 +82,10 @@ static const struct smcd_ops lo_ops = { .reset_vlan_required = NULL, .signal_event = NULL, .move_data = NULL, - .supports_v2 = NULL, - .get_local_gid = NULL, - .get_chid = NULL, - .get_dev = NULL, + .supports_v2 = smc_lo_supports_v2, + .get_local_gid = smc_lo_get_local_gid, + .get_chid = smc_lo_get_chid, + .get_dev = smc_lo_get_dev, }; static struct smcd_dev *smcd_lo_alloc_dev(const struct smcd_ops *ops, @@ -94,6 +145,7 @@ static void smcd_lo_unregister_dev(struct smc_lo_dev *ldev) static int smc_lo_dev_init(struct smc_lo_dev *ldev) { + smc_lo_generate_ids(ldev); return smcd_lo_register_dev(ldev); } diff --git a/net/smc/smc_loopback.h b/net/smc/smc_loopback.h index 7fc4b374bc82..d7df79f7bb64 100644 --- a/net/smc/smc_loopback.h +++ b/net/smc/smc_loopback.h @@ -20,10 +20,13 @@ #if IS_ENABLED(CONFIG_SMC_LO) #define SMC_LO_MAX_DMBS 5000 +#define SMC_LO_RESERVED_CHID 0xFFFF struct smc_lo_dev { struct smcd_dev *smcd; struct device dev; + u16 chid; + struct smcd_gid local_gid; }; int smc_loopback_init(void); -- cgit v1.2.3-59-g8ed1b From f7a22071dbf316c982fb44308874bd7ad9ac2091 Mon Sep 17 00:00:00 2001 From: Wen Gu Date: Sun, 28 Apr 2024 14:07:31 +0800 Subject: net/smc: implement DMB-related operations of loopback-ism This implements DMB (un)registration and data move operations of loopback-ism device. Signed-off-by: Wen Gu Reviewed-by: Wenjia Zhang Reviewed-and-tested-by: Jan Karcher Signed-off-by: Paolo Abeni --- net/smc/smc_loopback.c | 129 +++++++++++++++++++++++++++++++++++++++++++++++-- net/smc/smc_loopback.h | 13 +++++ 2 files changed, 139 insertions(+), 3 deletions(-) (limited to 'net/smc/smc_loopback.c') diff --git a/net/smc/smc_loopback.c b/net/smc/smc_loopback.c index 0349632a76c4..d75852549b00 100644 --- a/net/smc/smc_loopback.c +++ b/net/smc/smc_loopback.c @@ -15,10 +15,12 @@ #include #include +#include "smc_cdc.h" #include "smc_ism.h" #include "smc_loopback.h" #define SMC_LO_V2_CAPABLE 0x1 /* loopback-ism acts as ISMv2 */ +#define SMC_DMA_ADDR_INVALID (~(dma_addr_t)0) static const char smc_lo_dev_name[] = "loopback-ism"; static struct smc_lo_dev *lo_dev; @@ -48,6 +50,125 @@ static int smc_lo_query_rgid(struct smcd_dev *smcd, struct smcd_gid *rgid, return 0; } +static int smc_lo_register_dmb(struct smcd_dev *smcd, struct smcd_dmb *dmb, + void *client_priv) +{ + struct smc_lo_dmb_node *dmb_node, *tmp_node; + struct smc_lo_dev *ldev = smcd->priv; + int sba_idx, rc; + + /* check space for new dmb */ + for_each_clear_bit(sba_idx, ldev->sba_idx_mask, SMC_LO_MAX_DMBS) { + if (!test_and_set_bit(sba_idx, ldev->sba_idx_mask)) + break; + } + if (sba_idx == SMC_LO_MAX_DMBS) + return -ENOSPC; + + dmb_node = kzalloc(sizeof(*dmb_node), GFP_KERNEL); + if (!dmb_node) { + rc = -ENOMEM; + goto err_bit; + } + + dmb_node->sba_idx = sba_idx; + dmb_node->len = dmb->dmb_len; + dmb_node->cpu_addr = kzalloc(dmb_node->len, GFP_KERNEL | + __GFP_NOWARN | __GFP_NORETRY | + __GFP_NOMEMALLOC); + if (!dmb_node->cpu_addr) { + rc = -ENOMEM; + goto err_node; + } + dmb_node->dma_addr = SMC_DMA_ADDR_INVALID; + +again: + /* add new dmb into hash table */ + get_random_bytes(&dmb_node->token, sizeof(dmb_node->token)); + write_lock_bh(&ldev->dmb_ht_lock); + hash_for_each_possible(ldev->dmb_ht, tmp_node, list, dmb_node->token) { + if (tmp_node->token == dmb_node->token) { + write_unlock_bh(&ldev->dmb_ht_lock); + goto again; + } + } + hash_add(ldev->dmb_ht, &dmb_node->list, dmb_node->token); + write_unlock_bh(&ldev->dmb_ht_lock); + + dmb->sba_idx = dmb_node->sba_idx; + dmb->dmb_tok = dmb_node->token; + dmb->cpu_addr = dmb_node->cpu_addr; + dmb->dma_addr = dmb_node->dma_addr; + dmb->dmb_len = dmb_node->len; + + return 0; + +err_node: + kfree(dmb_node); +err_bit: + clear_bit(sba_idx, ldev->sba_idx_mask); + return rc; +} + +static int smc_lo_unregister_dmb(struct smcd_dev *smcd, struct smcd_dmb *dmb) +{ + struct smc_lo_dmb_node *dmb_node = NULL, *tmp_node; + struct smc_lo_dev *ldev = smcd->priv; + + /* remove dmb from hash table */ + write_lock_bh(&ldev->dmb_ht_lock); + hash_for_each_possible(ldev->dmb_ht, tmp_node, list, dmb->dmb_tok) { + if (tmp_node->token == dmb->dmb_tok) { + dmb_node = tmp_node; + break; + } + } + if (!dmb_node) { + write_unlock_bh(&ldev->dmb_ht_lock); + return -EINVAL; + } + hash_del(&dmb_node->list); + write_unlock_bh(&ldev->dmb_ht_lock); + + clear_bit(dmb_node->sba_idx, ldev->sba_idx_mask); + kfree(dmb_node->cpu_addr); + kfree(dmb_node); + + return 0; +} + +static int smc_lo_move_data(struct smcd_dev *smcd, u64 dmb_tok, + unsigned int idx, bool sf, unsigned int offset, + void *data, unsigned int size) +{ + struct smc_lo_dmb_node *rmb_node = NULL, *tmp_node; + struct smc_lo_dev *ldev = smcd->priv; + struct smc_connection *conn; + + read_lock_bh(&ldev->dmb_ht_lock); + hash_for_each_possible(ldev->dmb_ht, tmp_node, list, dmb_tok) { + if (tmp_node->token == dmb_tok) { + rmb_node = tmp_node; + break; + } + } + if (!rmb_node) { + read_unlock_bh(&ldev->dmb_ht_lock); + return -EINVAL; + } + memcpy((char *)rmb_node->cpu_addr + offset, data, size); + read_unlock_bh(&ldev->dmb_ht_lock); + + if (sf) { + conn = smcd->conn[rmb_node->sba_idx]; + if (conn && !conn->killed) + tasklet_schedule(&conn->rx_tsklet); + else + return -EPIPE; + } + return 0; +} + static int smc_lo_supports_v2(void) { return SMC_LO_V2_CAPABLE; @@ -74,14 +195,14 @@ static struct device *smc_lo_get_dev(struct smcd_dev *smcd) static const struct smcd_ops lo_ops = { .query_remote_gid = smc_lo_query_rgid, - .register_dmb = NULL, - .unregister_dmb = NULL, + .register_dmb = smc_lo_register_dmb, + .unregister_dmb = smc_lo_unregister_dmb, .add_vlan_id = NULL, .del_vlan_id = NULL, .set_vlan_required = NULL, .reset_vlan_required = NULL, .signal_event = NULL, - .move_data = NULL, + .move_data = smc_lo_move_data, .supports_v2 = smc_lo_supports_v2, .get_local_gid = smc_lo_get_local_gid, .get_chid = smc_lo_get_chid, @@ -146,6 +267,8 @@ static void smcd_lo_unregister_dev(struct smc_lo_dev *ldev) static int smc_lo_dev_init(struct smc_lo_dev *ldev) { smc_lo_generate_ids(ldev); + rwlock_init(&ldev->dmb_ht_lock); + hash_init(ldev->dmb_ht); return smcd_lo_register_dev(ldev); } diff --git a/net/smc/smc_loopback.h b/net/smc/smc_loopback.h index d7df79f7bb64..b8206338309f 100644 --- a/net/smc/smc_loopback.h +++ b/net/smc/smc_loopback.h @@ -20,13 +20,26 @@ #if IS_ENABLED(CONFIG_SMC_LO) #define SMC_LO_MAX_DMBS 5000 +#define SMC_LO_DMBS_HASH_BITS 12 #define SMC_LO_RESERVED_CHID 0xFFFF +struct smc_lo_dmb_node { + struct hlist_node list; + u64 token; + u32 len; + u32 sba_idx; + void *cpu_addr; + dma_addr_t dma_addr; +}; + struct smc_lo_dev { struct smcd_dev *smcd; struct device dev; u16 chid; struct smcd_gid local_gid; + rwlock_t dmb_ht_lock; + DECLARE_BITMAP(sba_idx_mask, SMC_LO_MAX_DMBS); + DECLARE_HASHTABLE(dmb_ht, SMC_LO_DMBS_HASH_BITS); }; int smc_loopback_init(void); -- cgit v1.2.3-59-g8ed1b From 04791343d858242dc2bd25e05be480ad1591e900 Mon Sep 17 00:00:00 2001 From: Wen Gu Date: Sun, 28 Apr 2024 14:07:34 +0800 Subject: net/smc: register loopback-ism into SMC-D device list After the loopback-ism device is ready, add it to the SMC-D device list as an ISMv2 device, and always keep it at the beginning to ensure it is preferred for providing a shortcut for data transfer within the same kernel. Signed-off-by: Wen Gu Reviewed-by: Wenjia Zhang Reviewed-and-tested-by: Jan Karcher Signed-off-by: Paolo Abeni --- net/smc/smc_ism.c | 30 +++++++++++++++++++++--------- net/smc/smc_ism.h | 1 + net/smc/smc_loopback.c | 20 +++++++++++++------- 3 files changed, 35 insertions(+), 16 deletions(-) (limited to 'net/smc/smc_loopback.c') diff --git a/net/smc/smc_ism.c b/net/smc/smc_ism.c index 188fd28423c2..6bed0a61b746 100644 --- a/net/smc/smc_ism.c +++ b/net/smc/smc_ism.c @@ -91,6 +91,11 @@ bool smc_ism_is_v2_capable(void) return smc_ism_v2_capable; } +void smc_ism_set_v2_capable(void) +{ + smc_ism_v2_capable = true; +} + /* Set a connection using this DMBE. */ void smc_ism_set_conn(struct smc_connection *conn) { @@ -439,7 +444,7 @@ static struct smcd_dev *smcd_alloc_dev(struct device *parent, const char *name, static void smcd_register_dev(struct ism_dev *ism) { const struct smcd_ops *ops = ism_get_smcd_ops(); - struct smcd_dev *smcd; + struct smcd_dev *smcd, *fentry; if (!ops) return; @@ -454,16 +459,23 @@ static void smcd_register_dev(struct ism_dev *ism) if (smc_pnetid_by_dev_port(&ism->pdev->dev, 0, smcd->pnetid)) smc_pnetid_by_table_smcd(smcd); + if (smcd->ops->supports_v2()) + smc_ism_set_v2_capable(); mutex_lock(&smcd_dev_list.mutex); - if (list_empty(&smcd_dev_list.list)) { - if (smcd->ops->supports_v2()) - smc_ism_v2_capable = true; - } - /* sort list: devices without pnetid before devices with pnetid */ - if (smcd->pnetid[0]) + /* sort list: + * - devices without pnetid before devices with pnetid; + * - loopback-ism always at the very beginning; + */ + if (!smcd->pnetid[0]) { + fentry = list_first_entry_or_null(&smcd_dev_list.list, + struct smcd_dev, list); + if (fentry && smc_ism_is_loopback(fentry)) + list_add(&smcd->list, &fentry->list); + else + list_add(&smcd->list, &smcd_dev_list.list); + } else { list_add_tail(&smcd->list, &smcd_dev_list.list); - else - list_add(&smcd->list, &smcd_dev_list.list); + } mutex_unlock(&smcd_dev_list.mutex); pr_warn_ratelimited("smc: adding smcd device %s with pnetid %.16s%s\n", diff --git a/net/smc/smc_ism.h b/net/smc/smc_ism.h index 322973527c61..e6f57e5e1ef9 100644 --- a/net/smc/smc_ism.h +++ b/net/smc/smc_ism.h @@ -52,6 +52,7 @@ int smc_ism_signal_shutdown(struct smc_link_group *lgr); void smc_ism_get_system_eid(u8 **eid); u16 smc_ism_get_chid(struct smcd_dev *dev); bool smc_ism_is_v2_capable(void); +void smc_ism_set_v2_capable(void); int smc_ism_init(void); void smc_ism_exit(void); int smcd_nl_get_device(struct sk_buff *skb, struct netlink_callback *cb); diff --git a/net/smc/smc_loopback.c b/net/smc/smc_loopback.c index d75852549b00..94a57f4ee3f9 100644 --- a/net/smc/smc_loopback.c +++ b/net/smc/smc_loopback.c @@ -246,10 +246,12 @@ static int smcd_lo_register_dev(struct smc_lo_dev *ldev) return -ENOMEM; ldev->smcd = smcd; smcd->priv = ldev; - - /* TODO: - * register loopback-ism to smcd_dev list. - */ + smc_ism_set_v2_capable(); + mutex_lock(&smcd_dev_list.mutex); + list_add(&smcd->list, &smcd_dev_list.list); + mutex_unlock(&smcd_dev_list.mutex); + pr_warn_ratelimited("smc: adding smcd device %s\n", + dev_name(&ldev->dev)); return 0; } @@ -257,9 +259,13 @@ static void smcd_lo_unregister_dev(struct smc_lo_dev *ldev) { struct smcd_dev *smcd = ldev->smcd; - /* TODO: - * unregister loopback-ism from smcd_dev list. - */ + pr_warn_ratelimited("smc: removing smcd device %s\n", + dev_name(&ldev->dev)); + smcd->going_away = 1; + smc_smcd_terminate_all(smcd); + mutex_lock(&smcd_dev_list.mutex); + list_del_init(&smcd->list); + mutex_unlock(&smcd_dev_list.mutex); kfree(smcd->conn); kfree(smcd); } -- cgit v1.2.3-59-g8ed1b From c3a910f2380fe294d14e42af66af3d3eed8fecbf Mon Sep 17 00:00:00 2001 From: Wen Gu Date: Sun, 28 Apr 2024 14:07:38 +0800 Subject: net/smc: implement DMB-merged operations of loopback-ism This implements operations related to merging sndbuf with peer DMB in loopback-ism. The DMB won't be freed until no sndbuf is attached to it. Signed-off-by: Wen Gu Reviewed-by: Wenjia Zhang Reviewed-and-tested-by: Jan Karcher Signed-off-by: Paolo Abeni --- net/smc/smc_loopback.c | 120 ++++++++++++++++++++++++++++++++++++++++++------- net/smc/smc_loopback.h | 3 ++ 2 files changed, 108 insertions(+), 15 deletions(-) (limited to 'net/smc/smc_loopback.c') diff --git a/net/smc/smc_loopback.c b/net/smc/smc_loopback.c index 94a57f4ee3f9..3c5f64ca4115 100644 --- a/net/smc/smc_loopback.c +++ b/net/smc/smc_loopback.c @@ -20,6 +20,7 @@ #include "smc_loopback.h" #define SMC_LO_V2_CAPABLE 0x1 /* loopback-ism acts as ISMv2 */ +#define SMC_LO_SUPPORT_NOCOPY 0x1 #define SMC_DMA_ADDR_INVALID (~(dma_addr_t)0) static const char smc_lo_dev_name[] = "loopback-ism"; @@ -81,6 +82,7 @@ static int smc_lo_register_dmb(struct smcd_dev *smcd, struct smcd_dmb *dmb, goto err_node; } dmb_node->dma_addr = SMC_DMA_ADDR_INVALID; + refcount_set(&dmb_node->refcnt, 1); again: /* add new dmb into hash table */ @@ -94,6 +96,7 @@ again: } hash_add(ldev->dmb_ht, &dmb_node->list, dmb_node->token); write_unlock_bh(&ldev->dmb_ht_lock); + atomic_inc(&ldev->dmb_cnt); dmb->sba_idx = dmb_node->sba_idx; dmb->dmb_tok = dmb_node->token; @@ -110,13 +113,29 @@ err_bit: return rc; } +static void __smc_lo_unregister_dmb(struct smc_lo_dev *ldev, + struct smc_lo_dmb_node *dmb_node) +{ + /* remove dmb from hash table */ + write_lock_bh(&ldev->dmb_ht_lock); + hash_del(&dmb_node->list); + write_unlock_bh(&ldev->dmb_ht_lock); + + clear_bit(dmb_node->sba_idx, ldev->sba_idx_mask); + kvfree(dmb_node->cpu_addr); + kfree(dmb_node); + + if (atomic_dec_and_test(&ldev->dmb_cnt)) + wake_up(&ldev->ldev_release); +} + static int smc_lo_unregister_dmb(struct smcd_dev *smcd, struct smcd_dmb *dmb) { struct smc_lo_dmb_node *dmb_node = NULL, *tmp_node; struct smc_lo_dev *ldev = smcd->priv; - /* remove dmb from hash table */ - write_lock_bh(&ldev->dmb_ht_lock); + /* find dmb from hash table */ + read_lock_bh(&ldev->dmb_ht_lock); hash_for_each_possible(ldev->dmb_ht, tmp_node, list, dmb->dmb_tok) { if (tmp_node->token == dmb->dmb_tok) { dmb_node = tmp_node; @@ -124,16 +143,76 @@ static int smc_lo_unregister_dmb(struct smcd_dev *smcd, struct smcd_dmb *dmb) } } if (!dmb_node) { - write_unlock_bh(&ldev->dmb_ht_lock); + read_unlock_bh(&ldev->dmb_ht_lock); return -EINVAL; } - hash_del(&dmb_node->list); - write_unlock_bh(&ldev->dmb_ht_lock); + read_unlock_bh(&ldev->dmb_ht_lock); - clear_bit(dmb_node->sba_idx, ldev->sba_idx_mask); - kfree(dmb_node->cpu_addr); - kfree(dmb_node); + if (refcount_dec_and_test(&dmb_node->refcnt)) + __smc_lo_unregister_dmb(ldev, dmb_node); + return 0; +} + +static int smc_lo_support_dmb_nocopy(struct smcd_dev *smcd) +{ + return SMC_LO_SUPPORT_NOCOPY; +} + +static int smc_lo_attach_dmb(struct smcd_dev *smcd, struct smcd_dmb *dmb) +{ + struct smc_lo_dmb_node *dmb_node = NULL, *tmp_node; + struct smc_lo_dev *ldev = smcd->priv; + + /* find dmb_node according to dmb->dmb_tok */ + read_lock_bh(&ldev->dmb_ht_lock); + hash_for_each_possible(ldev->dmb_ht, tmp_node, list, dmb->dmb_tok) { + if (tmp_node->token == dmb->dmb_tok) { + dmb_node = tmp_node; + break; + } + } + if (!dmb_node) { + read_unlock_bh(&ldev->dmb_ht_lock); + return -EINVAL; + } + read_unlock_bh(&ldev->dmb_ht_lock); + + if (!refcount_inc_not_zero(&dmb_node->refcnt)) + /* the dmb is being unregistered, but has + * not been removed from the hash table. + */ + return -EINVAL; + /* provide dmb information */ + dmb->sba_idx = dmb_node->sba_idx; + dmb->dmb_tok = dmb_node->token; + dmb->cpu_addr = dmb_node->cpu_addr; + dmb->dma_addr = dmb_node->dma_addr; + dmb->dmb_len = dmb_node->len; + return 0; +} + +static int smc_lo_detach_dmb(struct smcd_dev *smcd, u64 token) +{ + struct smc_lo_dmb_node *dmb_node = NULL, *tmp_node; + struct smc_lo_dev *ldev = smcd->priv; + + /* find dmb_node according to dmb->dmb_tok */ + read_lock_bh(&ldev->dmb_ht_lock); + hash_for_each_possible(ldev->dmb_ht, tmp_node, list, token) { + if (tmp_node->token == token) { + dmb_node = tmp_node; + break; + } + } + if (!dmb_node) { + read_unlock_bh(&ldev->dmb_ht_lock); + return -EINVAL; + } + read_unlock_bh(&ldev->dmb_ht_lock); + + if (refcount_dec_and_test(&dmb_node->refcnt)) + __smc_lo_unregister_dmb(ldev, dmb_node); return 0; } @@ -145,6 +224,12 @@ static int smc_lo_move_data(struct smcd_dev *smcd, u64 dmb_tok, struct smc_lo_dev *ldev = smcd->priv; struct smc_connection *conn; + if (!sf) + /* since sndbuf is merged with peer DMB, there is + * no need to copy data from sndbuf to peer DMB. + */ + return 0; + read_lock_bh(&ldev->dmb_ht_lock); hash_for_each_possible(ldev->dmb_ht, tmp_node, list, dmb_tok) { if (tmp_node->token == dmb_tok) { @@ -159,13 +244,10 @@ static int smc_lo_move_data(struct smcd_dev *smcd, u64 dmb_tok, memcpy((char *)rmb_node->cpu_addr + offset, data, size); read_unlock_bh(&ldev->dmb_ht_lock); - if (sf) { - conn = smcd->conn[rmb_node->sba_idx]; - if (conn && !conn->killed) - tasklet_schedule(&conn->rx_tsklet); - else - return -EPIPE; - } + conn = smcd->conn[rmb_node->sba_idx]; + if (!conn || conn->killed) + return -EPIPE; + tasklet_schedule(&conn->rx_tsklet); return 0; } @@ -197,6 +279,9 @@ static const struct smcd_ops lo_ops = { .query_remote_gid = smc_lo_query_rgid, .register_dmb = smc_lo_register_dmb, .unregister_dmb = smc_lo_unregister_dmb, + .support_dmb_nocopy = smc_lo_support_dmb_nocopy, + .attach_dmb = smc_lo_attach_dmb, + .detach_dmb = smc_lo_detach_dmb, .add_vlan_id = NULL, .del_vlan_id = NULL, .set_vlan_required = NULL, @@ -275,12 +360,17 @@ static int smc_lo_dev_init(struct smc_lo_dev *ldev) smc_lo_generate_ids(ldev); rwlock_init(&ldev->dmb_ht_lock); hash_init(ldev->dmb_ht); + atomic_set(&ldev->dmb_cnt, 0); + init_waitqueue_head(&ldev->ldev_release); + return smcd_lo_register_dev(ldev); } static void smc_lo_dev_exit(struct smc_lo_dev *ldev) { smcd_lo_unregister_dev(ldev); + if (atomic_read(&ldev->dmb_cnt)) + wait_event(ldev->ldev_release, !atomic_read(&ldev->dmb_cnt)); } static void smc_lo_dev_release(struct device *dev) diff --git a/net/smc/smc_loopback.h b/net/smc/smc_loopback.h index b8206338309f..6dd4292dae56 100644 --- a/net/smc/smc_loopback.h +++ b/net/smc/smc_loopback.h @@ -30,6 +30,7 @@ struct smc_lo_dmb_node { u32 sba_idx; void *cpu_addr; dma_addr_t dma_addr; + refcount_t refcnt; }; struct smc_lo_dev { @@ -37,9 +38,11 @@ struct smc_lo_dev { struct device dev; u16 chid; struct smcd_gid local_gid; + atomic_t dmb_cnt; rwlock_t dmb_ht_lock; DECLARE_BITMAP(sba_idx_mask, SMC_LO_MAX_DMBS); DECLARE_HASHTABLE(dmb_ht, SMC_LO_DMBS_HASH_BITS); + wait_queue_head_t ldev_release; }; int smc_loopback_init(void); -- cgit v1.2.3-59-g8ed1b