Re: [RFC PATCH net-next v3 9/9] net/smc: Add interface implementation of loopback device

Re: [RFC PATCH net-next v3 9/9] net/smc: Add interface implementation of loopback device

[Wen Gu]

On 2023/2/22 22:09, Hillf Danton wrote:

> On Thu, 16 Feb 2023 00:18:25 +0800 Wen Gu <guwen@linux.alibaba.com>
>> @@ -124,12 +126,76 @@ static int smc_lo_unregister_dmb(struct smcd_dev *smcd, struct smcd_dmb *dmb)
>>   	write_unlock(&ldev->dmb_ht_lock);
>>   
>>   	clear_bit(dmb_node->sba_idx, ldev->sba_idx_mask);
>> +
>> +	/* wait for dmb refcnt to be 0 */
>> +	if (!refcount_dec_and_test(&dmb_node->refcnt))
>> +		wait_event(ldev->dmbs_release, !refcount_read(&dmb_node->refcnt));
> 
> Wait for zero refcnt with dmb node deleted from hash table.
> 
>>   	kfree(dmb_node->cpu_addr);
>>   	kfree(dmb_node);
>>   
>> +	if (atomic_dec_and_test(&ldev->dmb_cnt))
>> +		wake_up(&ldev->ldev_release);
>> +	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))
>> +		wake_up_all(&ldev->dmbs_release);
>>   	return 0;
>>   }
> 
> Given no wakeup without finding dmb node in hash table, the chance for
> missing wakeup is not zero.

Good catch! Will fix it.

Thanks,
Wen Gu

[RFC PATCH net-next v3 9/9] net/smc: Add interface implementation of loopback device

[Wen Gu]

This patch completes the specific implementation of loopback device
for the newly added SMC-D DMB-related interface.

The loopback device always provides mappable DMB because the device
users are in the same OS instance.

Signed-off-by: Wen Gu <guwen@linux.alibaba.com>
---
 net/smc/smc_loopback.c | 93 ++++++++++++++++++++++++++++++++++++++++++++++----
 net/smc/smc_loopback.h |  4 +++
 2 files changed, 90 insertions(+), 7 deletions(-)

diff --git a/net/smc/smc_loopback.c b/net/smc/smc_loopback.c
index 38bacd8..2fa2a73 100644
--- a/net/smc/smc_loopback.c
+++ b/net/smc/smc_loopback.c
@@ -77,6 +77,7 @@ static int smc_lo_register_dmb(struct smcd_dev *smcd, struct smcd_dmb *dmb,
 		goto err_node;
 	}
 	dmb_node->len = dmb->dmb_len;
+	refcount_set(&dmb_node->refcnt, 1);
 
 	/* TODO: token is random but not exclusive !
 	 * suppose to find token in dmb hask table, if has this token
@@ -87,6 +88,7 @@ static int smc_lo_register_dmb(struct smcd_dev *smcd, struct smcd_dmb *dmb,
 	write_lock(&ldev->dmb_ht_lock);
 	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;
@@ -124,12 +126,76 @@ static int smc_lo_unregister_dmb(struct smcd_dev *smcd, struct smcd_dmb *dmb)
 	write_unlock(&ldev->dmb_ht_lock);
 
 	clear_bit(dmb_node->sba_idx, ldev->sba_idx_mask);
+
+	/* wait for dmb refcnt to be 0 */
+	if (!refcount_dec_and_test(&dmb_node->refcnt))
+		wait_event(ldev->dmbs_release, !refcount_read(&dmb_node->refcnt));
 	kfree(dmb_node->cpu_addr);
 	kfree(dmb_node);
 
+	if (atomic_dec_and_test(&ldev->dmb_cnt))
+		wake_up(&ldev->ldev_release);
+	return 0;
+}
+
+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);
+	refcount_inc(&dmb_node->refcnt);
+
+	/* 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))
+		wake_up_all(&ldev->dmbs_release);
 	return 0;
 }
 
+static int smc_lo_get_dev_dmb_attr(struct smcd_dev *smcd)
+{
+	return (1 << ISM_DMB_MAPPABLE);
+}
+
 static int smc_lo_add_vlan_id(struct smcd_dev *smcd, u64 vlan_id)
 {
 	return -EOPNOTSUPP;
@@ -156,7 +222,15 @@ static int smc_lo_move_data(struct smcd_dev *smcd, u64 dmb_tok, unsigned int idx
 {
 	struct smc_lo_dmb_node *rmb_node = NULL, *tmp_node;
 	struct smc_lo_dev *ldev = smcd->priv;
-
+	struct smc_connection *conn;
+
+	if (!sf) {
+		/* local sndbuf shares the same physical memory with
+		 * peer RMB, so no need to copy data from local sndbuf
+		 * to peer RMB.
+		 */
+		return 0;
+	}
 	read_lock(&ldev->dmb_ht_lock);
 	hash_for_each_possible(ldev->dmb_ht, tmp_node, list, dmb_tok) {
 		if (tmp_node->token == dmb_tok) {
@@ -172,13 +246,10 @@ static int smc_lo_move_data(struct smcd_dev *smcd, u64 dmb_tok, unsigned int idx
 
 	memcpy((char *)rmb_node->cpu_addr + offset, data, size);
 
-	if (sf) {
-		struct smc_connection *conn =
-			smcd->conn[rmb_node->sba_idx];
+	conn = smcd->conn[rmb_node->sba_idx];
+	if (conn && !conn->killed)
+		smcd_cdc_rx_handler(conn);
 
-		if (conn && !conn->killed)
-			smcd_cdc_rx_handler(conn);
-	}
 	return 0;
 }
 
@@ -206,6 +277,8 @@ static struct device *smc_lo_get_dev(struct smcd_dev *smcd)
 	.query_remote_gid = smc_lo_query_rgid,
 	.register_dmb = smc_lo_register_dmb,
 	.unregister_dmb = smc_lo_unregister_dmb,
+	.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,
@@ -216,6 +289,7 @@ static struct device *smc_lo_get_dev(struct smcd_dev *smcd)
 	.get_local_gid = smc_lo_get_local_gid,
 	.get_chid = smc_lo_get_chid,
 	.get_dev = smc_lo_get_dev,
+	.get_dev_dmb_attr = smc_lo_get_dev_dmb_attr,
 };
 
 static struct smcd_dev *smcd_lo_alloc_dev(const struct smcd_ops *ops,
@@ -296,6 +370,9 @@ static int smc_lo_dev_init(struct smc_lo_dev *ldev)
 	smc_lo_gen_id(ldev);
 	rwlock_init(&ldev->dmb_ht_lock);
 	hash_init(ldev->dmb_ht);
+	atomic_set(&ldev->dmb_cnt, 0);
+	init_waitqueue_head(&ldev->dmbs_release);
+	init_waitqueue_head(&ldev->ldev_release);
 
 	return smcd_lo_register_dev(ldev);
 }
@@ -334,6 +411,8 @@ static int smc_lo_dev_probe(void)
 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_remove(void)
diff --git a/net/smc/smc_loopback.h b/net/smc/smc_loopback.h
index 9d34aba..0a09330 100644
--- a/net/smc/smc_loopback.h
+++ b/net/smc/smc_loopback.h
@@ -33,6 +33,7 @@ struct smc_lo_dmb_node {
 	u32 sba_idx;
 	void *cpu_addr;
 	dma_addr_t dma_addr;
+	refcount_t refcnt;
 };
 
 struct smc_lo_dev {
@@ -43,6 +44,9 @@ struct smc_lo_dev {
 	DECLARE_BITMAP(sba_idx_mask, SMC_LODEV_MAX_DMBS);
 	rwlock_t dmb_ht_lock;
 	DECLARE_HASHTABLE(dmb_ht, SMC_LODEV_MAX_DMBS_BUCKETS);
+	atomic_t dmb_cnt;
+	wait_queue_head_t dmbs_release;
+	wait_queue_head_t ldev_release;
 };
 
 int smc_loopback_init(void);
-- 
1.8.3.1