From patchwork Thu Mar 7 09:55:36 2024 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Wen Gu X-Patchwork-Id: 13585285 X-Patchwork-Delegate: kuba@kernel.org Received: from out30-98.freemail.mail.aliyun.com (out30-98.freemail.mail.aliyun.com [115.124.30.98]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 7B42512CDA5; Thu, 7 Mar 2024 09:56:07 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=115.124.30.98 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1709805370; cv=none; b=jdOpZaBRUwM27a47Ob5dfOFhiJF7LhDny/LQ5whCQXR//64CJR3l1bNvKotWuXIwqgkU0w9EqAbwN7HDZGVloB45tcodypn2OcrBPcGIYUtdioKtHHanoI/YHZbYWW4l/TPr+Q4fV6vDEf8DLHO7v0Q6bFrUXXZJVTr9lxqPrGc= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1709805370; c=relaxed/simple; bh=r9ynUyNwuaAraBQrB6g6AiLMJHHVsRdHoISqka/UdYE=; h=From:To:Cc:Subject:Date:Message-Id:In-Reply-To:References: MIME-Version; b=dsOBEE2U7D+0E2FA2iaoID8MxQEwr0PkE31tZwQMO6GFi29wsgcQFtJqfWZiKlUEjAOjXVcQ0uTJcwrvwTdmgKfswXvQkP6RrChVS4uP+g3Vvj+72Xhw7gAUmuHKsCHKoIQ7p7y83kkrsYwbWnPLvUlBbxxhonIjhRVdxCSNXdc= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=linux.alibaba.com; spf=pass smtp.mailfrom=linux.alibaba.com; dkim=pass (1024-bit key) header.d=linux.alibaba.com header.i=@linux.alibaba.com header.b=BrHgl4oH; arc=none smtp.client-ip=115.124.30.98 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=linux.alibaba.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=linux.alibaba.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (1024-bit key) header.d=linux.alibaba.com header.i=@linux.alibaba.com header.b="BrHgl4oH" DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linux.alibaba.com; s=default; t=1709805365; h=From:To:Subject:Date:Message-Id:MIME-Version; bh=57tNxaCG7lrGDX+5Lxm1v4EurawfrxZMeQiUcDOKJSg=; b=BrHgl4oHMaEqt9ZQD7IC4UnWFxAh4ErehCrIaLE5Uz2xD8D6qh1KXJw19c2hSwiz8gZtoBFeA31LPE29PNVXGT1RCR2l4BMvfj0Mr0TyJf8e9PD0hZFn8VkhJ2T4Xu6PWNut9Wwi/o/FbtJfA+btkAgS23Uo+JM4Bx97Yr7hmhk= X-Alimail-AntiSpam: AC=PASS;BC=-1|-1;BR=01201311R781e4;CH=green;DM=||false|;DS=||;FP=0|-1|-1|-1|0|-1|-1|-1;HT=ay29a033018046056;MF=guwen@linux.alibaba.com;NM=1;PH=DS;RN=19;SR=0;TI=SMTPD_---0W2-Ke2X_1709805363; Received: from localhost(mailfrom:guwen@linux.alibaba.com fp:SMTPD_---0W2-Ke2X_1709805363) by smtp.aliyun-inc.com; Thu, 07 Mar 2024 17:56:04 +0800 From: Wen Gu To: wintera@linux.ibm.com, twinkler@linux.ibm.com, hca@linux.ibm.com, gor@linux.ibm.com, agordeev@linux.ibm.com, davem@davemloft.net, edumazet@google.com, kuba@kernel.org, pabeni@redhat.com, wenjia@linux.ibm.com, jaka@linux.ibm.com Cc: borntraeger@linux.ibm.com, svens@linux.ibm.com, alibuda@linux.alibaba.com, tonylu@linux.alibaba.com, guwen@linux.alibaba.com, linux-kernel@vger.kernel.org, linux-s390@vger.kernel.org, netdev@vger.kernel.org Subject: [PATCH net-next v2 11/11] net/smc: implement DMB-merged operations of loopback-ism Date: Thu, 7 Mar 2024 17:55:36 +0800 Message-Id: <20240307095536.29648-12-guwen@linux.alibaba.com> X-Mailer: git-send-email 2.32.0.3.g01195cf9f In-Reply-To: <20240307095536.29648-1-guwen@linux.alibaba.com> References: <20240307095536.29648-1-guwen@linux.alibaba.com> Precedence: bulk X-Mailing-List: netdev@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 X-Patchwork-Delegate: kuba@kernel.org 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 --- net/smc/smc_loopback.c | 136 +++++++++++++++++++++++++++++++++++------ net/smc/smc_loopback.h | 3 + 2 files changed, 119 insertions(+), 20 deletions(-) diff --git a/net/smc/smc_loopback.c b/net/smc/smc_loopback.c index 6828e0ad3e90..7e772f3772de 100644 --- a/net/smc/smc_loopback.c +++ b/net/smc/smc_loopback.c @@ -21,6 +21,7 @@ #if IS_ENABLED(CONFIG_SMC_LO) #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"; @@ -82,6 +83,7 @@ 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 */ @@ -95,6 +97,7 @@ static int smc_lo_register_dmb(struct smcd_dev *smcd, struct smcd_dmb *dmb, } hash_add(ldev->dmb_ht, &dmb_node->list, dmb_node->token); write_unlock(&ldev->dmb_ht_lock); + atomic_inc(&ldev->dmb_cnt); dmb->sba_idx = dmb_node->sba_idx; dmb->dmb_tok = dmb_node->token; @@ -111,13 +114,29 @@ static int smc_lo_register_dmb(struct smcd_dev *smcd, struct smcd_dmb *dmb, 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(&ldev->dmb_ht_lock); + hash_del(&dmb_node->list); + write_unlock(&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(&ldev->dmb_ht_lock); + /* find dmb from hash table */ + read_lock(&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; @@ -125,16 +144,76 @@ static int smc_lo_unregister_dmb(struct smcd_dev *smcd, struct smcd_dmb *dmb) } } if (!dmb_node) { - write_unlock(&ldev->dmb_ht_lock); + read_unlock(&ldev->dmb_ht_lock); return -EINVAL; } - hash_del(&dmb_node->list); - write_unlock(&ldev->dmb_ht_lock); + read_unlock(&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(&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(&ldev->dmb_ht_lock); + return -EINVAL; + } + read_unlock(&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(&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(&ldev->dmb_ht_lock); + return -EINVAL; + } + read_unlock(&ldev->dmb_ht_lock); + + if (refcount_dec_and_test(&dmb_node->refcnt)) + __smc_lo_unregister_dmb(ldev, dmb_node); return 0; } @@ -170,8 +249,22 @@ static int smc_lo_move_data(struct smcd_dev *smcd, u64 dmb_tok, { struct smc_lo_dmb_node *rmb_node = NULL, *tmp_node; struct smc_lo_dev *ldev = smcd->priv; - - read_lock(&ldev->dmb_ht_lock); + 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() is used here just to make lockdep + * happy, because spin_(un)lock_bh(&conn->send_lock) wraps + * smc_lo_move_data() and if we use read_lock() here, lockdep + * will complain about SOFTIRQ-safe -> SOFTIRQ-unsafe lock + * order detected, but in fact ldev->dmb_ht_lock will never + * be held in bh context. + */ + 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; @@ -182,19 +275,14 @@ static int smc_lo_move_data(struct smcd_dev *smcd, u64 dmb_tok, read_unlock(&ldev->dmb_ht_lock); return -EINVAL; } - read_unlock(&ldev->dmb_ht_lock); + read_unlock_bh(&ldev->dmb_ht_lock); memcpy((char *)rmb_node->cpu_addr + offset, data, size); - if (sf) { - struct smc_connection *conn = - smcd->conn[rmb_node->sba_idx]; - - if (conn && !conn->killed) - smcd_cdc_rx_handler(conn); - else - return -EPIPE; - } + conn = smcd->conn[rmb_node->sba_idx]; + if (!conn || conn->killed) + return -EPIPE; + smcd_cdc_rx_handler(conn); return 0; } @@ -226,6 +314,9 @@ 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 = smc_lo_add_vlan_id, .del_vlan_id = smc_lo_del_vlan_id, .set_vlan_required = smc_lo_set_vlan_required, @@ -304,12 +395,17 @@ static int smc_lo_dev_init(struct smc_lo_dev *ldev) smc_lo_generate_id(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 24ab9d747613..9156a6c37e65 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; }; #endif