Received-SPF: pass (google.com: domain of linux-kernel+bounces-161278-linux.lists.archive=gmail.com@vger.kernel.org designates 2604:1380:45e3:2400::1 as permitted sender) client-ip=2604:1380:45e3:2400::1;
From: Wen Gu <guwen@linux.alibaba.com>
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 v7 11/11] net/smc: implement DMB-merged operations of loopback-ism
Date: Sun, 28 Apr 2024 14:07:38 +0800
Message-Id: <20240428060738.60843-12-guwen@linux.alibaba.com>
In-Reply-To: <20240428060738.60843-1-guwen@linux.alibaba.com>
References: <20240428060738.60843-1-guwen@linux.alibaba.com>
Precedence: bulk
MIME-Version: 1.0
Content-Transfer-Encoding: 8bit

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 <guwen@linux.alibaba.com>
Reviewed-by: Wenjia Zhang <wenjia@linux.ibm.com>
Reviewed-and-tested-by: Jan Karcher <jaka@linux.ibm.com>
---
 net/smc/smc_loopback.c | 120 +++++++++++++++++++++++++++++++++++------
 net/smc/smc_loopback.h |   3 ++
 2 files changed, 108 insertions(+), 15 deletions(-)

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 @@ 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_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 @@ 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_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);
-- 
2.32.0.3.g01195cf9f