Linux-NVME Archive on lore.kernel.org
 help / color / mirror / Atom feed
From: Christoph Hellwig <hch@lst.de>
To: Ruozhu Li <david.li@jaguarmicro.com>
Cc: linux-nvme@lists.infradead.org, hch@lst.de, sagi@grimberg.me
Subject: Re: [PATCH] nvmet-rdma: recheck queue state is LIVE in state lock in recv done
Date: Thu, 13 Feb 2025 07:20:48 +0100	[thread overview]
Message-ID: <20250213062048.GD19608@lst.de> (raw)
In-Reply-To: <20250211034543.808-1-david.li@jaguarmicro.com>

> +++ b/drivers/nvme/target/rdma.c
> @@ -1042,12 +1042,16 @@ static void nvmet_rdma_recv_done(struct ib_cq *cq, struct ib_wc *wc)
>  		unsigned long flags;
>  
>  		spin_lock_irqsave(&queue->state_lock, flags);
> -		if (queue->state == NVMET_RDMA_Q_CONNECTING)
> -			list_add_tail(&rsp->wait_list, &queue->rsp_wait_list);
> -		else
> -			nvmet_rdma_put_rsp(rsp);
> +		if (queue->state != NVMET_RDMA_Q_LIVE) {

You'll want a comment based on the commit message that the first live
check is racy. 

> +			if (queue->state == NVMET_RDMA_Q_CONNECTING)
> +				list_add_tail(&rsp->wait_list, &queue->rsp_wait_list);
> +			else
> +				nvmet_rdma_put_rsp(rsp);
> +
> +			spin_unlock_irqrestore(&queue->state_lock, flags);
> +			return;

This gets a bit messy now.  What about a struture like this instead?

diff --git a/drivers/nvme/target/rdma.c b/drivers/nvme/target/rdma.c
index 1afd93026f9b..ae6a123ac63f 100644
--- a/drivers/nvme/target/rdma.c
+++ b/drivers/nvme/target/rdma.c
@@ -996,6 +996,23 @@ static void nvmet_rdma_handle_command(struct nvmet_rdma_queue *queue,
 	nvmet_req_complete(&cmd->req, status);
 }
 
+static bool nvmet_rdma_recv_not_live(struct nvmet_rdma_queue *queue,
+		struct nvmet_rdma_rsp *rsp)
+{
+	unsigned long flags;
+	bool ret = true;
+
+	spin_lock_irqsave(&queue->state_lock, flags);
+	if (queue->state == NVMET_RDMA_Q_LIVE)
+		ret = false;
+	else if (queue->state == NVMET_RDMA_Q_CONNECTING)
+		list_add_tail(&rsp->wait_list, &queue->rsp_wait_list);
+	else
+		nvmet_rdma_put_rsp(rsp);
+	spin_unlock_irqrestore(&queue->state_lock, flags);
+	return ret;
+}
+
 static void nvmet_rdma_recv_done(struct ib_cq *cq, struct ib_wc *wc)
 {
 	struct nvmet_rdma_cmd *cmd =
@@ -1038,18 +1055,9 @@ static void nvmet_rdma_recv_done(struct ib_cq *cq, struct ib_wc *wc)
 	rsp->n_rdma = 0;
 	rsp->invalidate_rkey = 0;
 
-	if (unlikely(queue->state != NVMET_RDMA_Q_LIVE)) {
-		unsigned long flags;
-
-		spin_lock_irqsave(&queue->state_lock, flags);
-		if (queue->state == NVMET_RDMA_Q_CONNECTING)
-			list_add_tail(&rsp->wait_list, &queue->rsp_wait_list);
-		else
-			nvmet_rdma_put_rsp(rsp);
-		spin_unlock_irqrestore(&queue->state_lock, flags);
+	if (unlikely(queue->state != NVMET_RDMA_Q_LIVE) &&
+	    nvmet_rdma_recv_not_live(queue, rsp))
 		return;
-	}
-
 	nvmet_rdma_handle_command(queue, rsp);
 }
 


  reply	other threads:[~2025-02-13  6:21 UTC|newest]

Thread overview: 3+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2025-02-11  3:45 [PATCH] nvmet-rdma: recheck queue state is LIVE in state lock in recv done Ruozhu Li
2025-02-13  6:20 ` Christoph Hellwig [this message]
2025-02-13 10:06   ` Ruozhu Li

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20250213062048.GD19608@lst.de \
    --to=hch@lst.de \
    --cc=david.li@jaguarmicro.com \
    --cc=linux-nvme@lists.infradead.org \
    --cc=sagi@grimberg.me \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox