From nobody Thu Apr 2 23:54:48 2026 Received: from mail-dl1-f46.google.com (mail-dl1-f46.google.com [74.125.82.46]) (using TLSv1.2 with cipher ECDHE-RSA-AES128-GCM-SHA256 (128/128 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 7A8972BFC73 for ; Sat, 14 Feb 2026 04:28:30 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=74.125.82.46 ARC-Seal: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1771043315; cv=none; b=I80sl3atSGSPbq5J7UpSd19i8V9G6fX27XwJ7PDNhmT6s/n3NuuuF4r8tU9HfLGVCQeshJrNxDJnc2vwWOnToFRaCihMbmW9PLzqQGec0xrWZoKn1l0AxbNMuiPEf0DKCvE5s9tgaMLqrAd79GzKGPsnZLWC5XYlfj4J2nIqQxA= ARC-Message-Signature: i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1771043315; c=relaxed/simple; bh=+pxtO/kUc1gXKagayS4/JiFTpp7PQT9pDtufAFD04og=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version; b=piVLNdc7k6ZTYJqM19+kvLAXTwSAH+u1dVjLWg1qjC6yhF9hpV0SgeA1SBsiUEF8zb3gMIfY1Mj+GGybxJBbphBw6rJaS50iUxqMwVkVNG377CCBEeNkxrm9gNdDzz67SSHyhunvYc4QOh74ZLGsBFTBu1Oyy8j1dak5QPVc8JM= ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=pass (p=reject dis=none) header.from=purestorage.com; spf=fail smtp.mailfrom=purestorage.com; dkim=pass (2048-bit key) header.d=purestorage.com header.i=@purestorage.com header.b=QrBE7Rek; arc=none smtp.client-ip=74.125.82.46 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=reject dis=none) header.from=purestorage.com Authentication-Results: smtp.subspace.kernel.org; spf=fail smtp.mailfrom=purestorage.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=purestorage.com header.i=@purestorage.com header.b="QrBE7Rek" Received: by mail-dl1-f46.google.com with SMTP id a92af1059eb24-12732165d1eso1959191c88.1 for ; Fri, 13 Feb 2026 20:28:30 -0800 (PST) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=purestorage.com; s=google2022; t=1771043310; x=1771648110; darn=vger.kernel.org; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:from:to:cc:subject:date :message-id:reply-to; bh=V6Jiwb+wqf39+Dhp+Oi0BJKLILh8l4FLgFLnd5UIyDU=; b=QrBE7Rekrqj4ukHY7kfFUwDk41M+bAIa8cvVFQjmx89lqIwl32b1LvpyGr9pHiW/cT TJC55pFBx7OIvnEsBrEYv+O2JPQMA5WUgqhcccvXS4awBP20jXQQh5jLUoe0WLLIEznG U+3FWmcYgrX6xvIxA3za1eG8Cmqw3cFb1Fp6zGwWweGlfRppgHXWzCKmp1hp9FaZIYQP qI+v3AAyP2OckGQq9kkzM3iuB2u93FuwPz9ZM2THxX+Q32cbpx3qIVkQFJvUIMwmYkp2 S5TeqS7YKjr5GYGvyGXyFnMK01TdJdPiiNW9wT1AbULRPw/ks54P7OlI09yu1tS5EorJ 2++g== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1771043310; x=1771648110; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:date:subject:cc:to:from:x-gm-gg:x-gm-message-state:from :to:cc:subject:date:message-id:reply-to; bh=V6Jiwb+wqf39+Dhp+Oi0BJKLILh8l4FLgFLnd5UIyDU=; b=RHeHhZrLQCxtxLEz/IFk7bEmq/uzwFSaF7LH3Em77XPKj7Mx3UtZzf+M/bVBLHH52+ YVknMuz2I23V71tHMTIY7HPq9tguK352eEF4B22FR+sQGjAStf8WVAm7BKIcej0m500+ bzWh1SP5Ym6qjlBJ6NhwMFRzYSqIs42aKWsTsB8ad7BV1m5HQe48WWedmXzow8qpIZv/ ML/Q9CnwEZPZ6u7V38hKQOPB4yJ78q6j3OQKiDLadu4K8TFWH4umkElnvtBn10cddloN 4ScCryOtYEFrbkhIrQ9X2W3lOCHM19ZZPBXv0AmicQGwiMiybbjtJUigFuBMp+C1+SBj 9VwA== X-Forwarded-Encrypted: i=1; AJvYcCUq8NaVGM9T4NajIHzh4+nJC6bVlDHjJ2EU2pWo06AowofCfylsCZZl7mNk85S9tU3tnVFQhelpcLYwdjo=@vger.kernel.org X-Gm-Message-State: AOJu0Ywi2rafqpkZi3p5H9hudLN5gHpYnapBb51bo4Z9JWIBU+DugiL1 fwqx7HRBTVlI5jPdxXS8PECFV1Qy7VKocDNYO0nt2Qu7mo7gYpOIvrSrWX1+ZDsGotI= X-Gm-Gg: AZuq6aIVKWlqFIHM4YgUzx1HMtVeG8tKUmaeVcjgeXiqfi1gx205S96J/D/d8QAy9xA c7FVYhYAUy+Tykc+D/JGLLPF5a5osCfXRm+YVBYAMbY3aaqmTz9nIMYIoQ9qe7I5VnoxeQ39Nva B3fg8dvKXNLjgPQuj+zIJfMQCC/zGtsACJEUJ5Sa1oHpey/g+aIusIBQcNqnq7GPDyq+hBoz/qT 8Tv1RcPJucPfXZktnkWtkTIQnTWmTlDd+Tr1pYsmCnxH3WOghFnHIbnsenGS4BtyDzG7o4OUUqE crAxBorqAVRVkQSVoizMtKowgIqEXRjxEgDhemGMesBCi1bd1dNu7wF+YQ9HmatP62BFcvKH2Yu Kbi0BWy1XkyBAdcGnvu/VKg98jsvNcPH3rAjebYseXbW+Dvw0xs9Th6BRyF7RDNMQy0/xF6lbzy DK3x0lNL5BUCTa0YSInT24UlcHsQwgt8n/x+si4PRhjQZqNg== X-Received: by 2002:a05:7022:6191:b0:123:2ee9:d1cc with SMTP id a92af1059eb24-1273aecf0e4mr1790771c88.48.1771043309383; Fri, 13 Feb 2026 20:28:29 -0800 (PST) Received: from apollo.purestorage.com ([208.88.152.253]) by smtp.googlemail.com with ESMTPSA id a92af1059eb24-12742cbc900sm1021042c88.14.2026.02.13.20.28.28 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Fri, 13 Feb 2026 20:28:29 -0800 (PST) From: Mohamed Khalfella To: Justin Tee , Naresh Gottumukkala , Paul Ely , Chaitanya Kulkarni , Christoph Hellwig , Jens Axboe , Keith Busch , Sagi Grimberg , James Smart , Hannes Reinecke Cc: Aaron Dailey , Randy Jennings , Dhaval Giani , linux-nvme@lists.infradead.org, linux-kernel@vger.kernel.org, Mohamed Khalfella Subject: [PATCH v3 10/21] nvme-tcp: Use CCR to recover controller that hits an error Date: Fri, 13 Feb 2026 20:25:11 -0800 Message-ID: <20260214042753.4073668-11-mkhalfella@purestorage.com> X-Mailer: git-send-email 2.52.0 In-Reply-To: <20260214042753.4073668-1-mkhalfella@purestorage.com> References: <20260214042753.4073668-1-mkhalfella@purestorage.com> Precedence: bulk X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Transfer-Encoding: quoted-printable Content-Type: text/plain; charset="utf-8" An alive nvme controller that hits an error now will move to FENCING state instead of RESETTING state. ctrl->fencing_work attempts CCR to terminate inflight IOs. Regardless of the success or failure of CCR operation the controller is transitioned to RESETTING state to continue error recovery process. Signed-off-by: Mohamed Khalfella Reviewed-by: Hannes Reinecke --- drivers/nvme/host/tcp.c | 32 +++++++++++++++++++++++++++++++- 1 file changed, 31 insertions(+), 1 deletion(-) diff --git a/drivers/nvme/host/tcp.c b/drivers/nvme/host/tcp.c index 69cb04406b47..229cfdffd848 100644 --- a/drivers/nvme/host/tcp.c +++ b/drivers/nvme/host/tcp.c @@ -193,6 +193,7 @@ struct nvme_tcp_ctrl { struct sockaddr_storage src_addr; struct nvme_ctrl ctrl; =20 + struct work_struct fencing_work; struct work_struct err_work; struct delayed_work connect_work; struct nvme_tcp_request async_req; @@ -611,6 +612,12 @@ static void nvme_tcp_init_recv_ctx(struct nvme_tcp_que= ue *queue) =20 static void nvme_tcp_error_recovery(struct nvme_ctrl *ctrl) { + if (nvme_change_ctrl_state(ctrl, NVME_CTRL_FENCING)) { + dev_warn(ctrl->device, "starting controller fencing\n"); + queue_work(nvme_wq, &to_tcp_ctrl(ctrl)->fencing_work); + return; + } + if (!nvme_change_ctrl_state(ctrl, NVME_CTRL_RESETTING)) return; =20 @@ -2470,12 +2477,31 @@ static void nvme_tcp_reconnect_ctrl_work(struct wor= k_struct *work) nvme_tcp_reconnect_or_remove(ctrl, ret); } =20 +static void nvme_tcp_fencing_work(struct work_struct *work) +{ + struct nvme_tcp_ctrl *tcp_ctrl =3D container_of(work, + struct nvme_tcp_ctrl, fencing_work); + struct nvme_ctrl *ctrl =3D &tcp_ctrl->ctrl; + unsigned long rem; + + rem =3D nvme_fence_ctrl(ctrl); + if (rem) { + dev_info(ctrl->device, + "CCR failed, skipping time-based recovery\n"); + } + + nvme_change_ctrl_state(ctrl, NVME_CTRL_FENCED); + if (nvme_change_ctrl_state(ctrl, NVME_CTRL_RESETTING)) + queue_work(nvme_reset_wq, &tcp_ctrl->err_work); +} + static void nvme_tcp_error_recovery_work(struct work_struct *work) { struct nvme_tcp_ctrl *tcp_ctrl =3D container_of(work, struct nvme_tcp_ctrl, err_work); struct nvme_ctrl *ctrl =3D &tcp_ctrl->ctrl; =20 + flush_work(&to_tcp_ctrl(ctrl)->fencing_work); if (nvme_tcp_key_revoke_needed(ctrl)) nvme_auth_revoke_tls_key(ctrl); nvme_stop_keep_alive(ctrl); @@ -2518,6 +2544,7 @@ static void nvme_reset_ctrl_work(struct work_struct *= work) container_of(work, struct nvme_ctrl, reset_work); int ret; =20 + flush_work(&to_tcp_ctrl(ctrl)->fencing_work); if (nvme_tcp_key_revoke_needed(ctrl)) nvme_auth_revoke_tls_key(ctrl); nvme_stop_ctrl(ctrl); @@ -2643,13 +2670,15 @@ static enum blk_eh_timer_return nvme_tcp_timeout(st= ruct request *rq) struct nvme_tcp_cmd_pdu *pdu =3D nvme_tcp_req_cmd_pdu(req); struct nvme_command *cmd =3D &pdu->cmd; int qid =3D nvme_tcp_queue_id(req->queue); + enum nvme_ctrl_state state; =20 dev_warn(ctrl->device, "I/O tag %d (%04x) type %d opcode %#x (%s) QID %d timeout\n", rq->tag, nvme_cid(rq), pdu->hdr.type, cmd->common.opcode, nvme_fabrics_opcode_str(qid, cmd), qid); =20 - if (nvme_ctrl_state(ctrl) !=3D NVME_CTRL_LIVE) { + state =3D nvme_ctrl_state(ctrl); + if (state !=3D NVME_CTRL_LIVE && state !=3D NVME_CTRL_FENCING) { /* * If we are resetting, connecting or deleting we should * complete immediately because we may block controller @@ -2904,6 +2933,7 @@ static struct nvme_tcp_ctrl *nvme_tcp_alloc_ctrl(stru= ct device *dev, =20 INIT_DELAYED_WORK(&ctrl->connect_work, nvme_tcp_reconnect_ctrl_work); + INIT_WORK(&ctrl->fencing_work, nvme_tcp_fencing_work); INIT_WORK(&ctrl->err_work, nvme_tcp_error_recovery_work); INIT_WORK(&ctrl->ctrl.reset_work, nvme_reset_ctrl_work); =20 --=20 2.52.0