From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from linux.microsoft.com (linux.microsoft.com [13.77.154.182]) by smtp.subspace.kernel.org (Postfix) with ESMTP id C8D014BE451; Wed, 7 Oct 2026 15:34:33 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=13.77.154.182 ARC-Seal:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1791387280; cv=none; b=UJltGbZsOPKJta7ne0YOkGQH0icQeWGmW1z6QzG//7emKO6PXzs4TghF67bF7xA/0aFfGVcufsO/1fncHeE8ovLqC0ylQ2vtztgdXNHDhge64e9pUbsgQfMz8KSV54DAwVT8FAMyS38JwmQzvFoShkD1sVJssGIm9BWguvu3D9s= ARC-Message-Signature:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1791387280; c=relaxed/simple; bh=vojZogvJeqECl5Km4NEjD2X6J89/yQUnpkKoMPKNyKI=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version; b=Sf8Pj2bDBbNZ1uOnhCTxOmSRyAlDmrmxxYIwqrEt31KGFfN3GiUUr2BR0R27cFD4Lmuk7gLIMzIg/GGkm9NN9teeOBf4vkPGE3RKTg9fFdNf3/5qN3Itjkz/3JnL/tUUyn+dr59uTjs69DA4JVPEMAgFH5VTV21OVZy3Z71KZos= ARC-Authentication-Results:i=1; smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=linux.microsoft.com; spf=pass smtp.mailfrom=linux.microsoft.com; dkim=pass (1024-bit key) header.d=linux.microsoft.com header.i=@linux.microsoft.com header.b=dfo1+Mkm; arc=none smtp.client-ip=13.77.154.182 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=linux.microsoft.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=linux.microsoft.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (1024-bit key) header.d=linux.microsoft.com header.i=@linux.microsoft.com header.b="dfo1+Mkm" Received: by linux.microsoft.com (Postfix, from userid 1186) id 3714920B716F; Wed, 7 Oct 2026 08:33:31 -0700 (PDT) DKIM-Filter: OpenDKIM Filter v2.11.0 linux.microsoft.com 3714920B716F DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=linux.microsoft.com; s=default; t=1791387211; bh=EkIXlfSAkUE8GnQWeDgcK2aTLj6kVEw8kzJN1AbNgIk=; h=From:To:Cc:Subject:Date:In-Reply-To:References:From; b=dfo1+Mkmne2I4LEPU5kKL6OKZr3rzPo79CufCrvjuAYF7YutUxieJzKXOExLAcv1j DPnr29OoRqDikclnl003YoNAb3/9OcaLmQ8hThoMH7D9tVJgZoOyOp3yMR+T8cFr42 v0SMuO9vsz/nHI2gxCBFfmovaFoswy316iBIbHK0= From: Konstantin Taranov To: kotaranov@microsoft.com, snsanghvi@microsoft.com, longli@microsoft.com, jgg@ziepe.ca, leon@kernel.org Cc: linux-rdma@vger.kernel.org, linux-kernel@vger.kernel.org Subject: [PATCH rdma-next v3 08/10] RDMA/mana_ib: Flush and notify CQs when kernel QPs enter ERR Date: Wed, 7 Oct 2026 08:33:28 -0700 Message-ID: <20261007153330.2979799-9-kotaranov@linux.microsoft.com> X-Mailer: git-send-email 2.43.7 In-Reply-To: <20261007153330.2979799-1-kotaranov@linux.microsoft.com> References: <20261007153330.2979799-1-kotaranov@linux.microsoft.com> Precedence: bulk X-Mailing-List: linux-kernel@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Transfer-Encoding: 8bit From: Konstantin Taranov Complete the RC software flush path by adding a kernel QP to the CQ error lists when it transitions to the ERR state. Invoke the CQ handlers after the transition to flush pending work requests. Signed-off-by: Konstantin Taranov --- v3: - Skip kernel state update handling for userspace QPs. - Warn and refuse to add userspace QPs to the CQ error lists. - Add mana_remove_qp_from_cqs() for UC v2: - Skip software CQ notifications for IB_POLL_DIRECT. drivers/infiniband/hw/mana/cq.c | 2 +- drivers/infiniband/hw/mana/mana_ib.h | 1 + drivers/infiniband/hw/mana/qp.c | 54 +++++++++++++++++++++++++--- 3 files changed, 52 insertions(+), 5 deletions(-) diff --git a/drivers/infiniband/hw/mana/cq.c b/drivers/infiniband/hw/mana/cq.c index 8f4303b329b4..7ad4eb35e598 100644 --- a/drivers/infiniband/hw/mana/cq.c +++ b/drivers/infiniband/hw/mana/cq.c @@ -586,7 +586,7 @@ static void mana_drain_gsi_sq(struct mana_ib_qp *qp) list_add_tail(&qp->send_err_node, &cq->send_err_qp_list); spin_unlock_irqrestore(&cq->cq_lock, flags); - if (cq->ibcq.comp_handler) + if (cq->ibcq.poll_ctx != IB_POLL_DIRECT && cq->ibcq.comp_handler) cq->ibcq.comp_handler(&cq->ibcq, cq->ibcq.cq_context); } diff --git a/drivers/infiniband/hw/mana/mana_ib.h b/drivers/infiniband/hw/mana/mana_ib.h index 1fc816792fc6..755fb87bfda1 100644 --- a/drivers/infiniband/hw/mana/mana_ib.h +++ b/drivers/infiniband/hw/mana/mana_ib.h @@ -269,6 +269,7 @@ struct mana_ib_qp { bool pending_mmq_fence; bool sq_sig_all; enum ib_mtu mtu; + enum ib_qp_state state; /* Serializes receive WR posting. */ spinlock_t rq_lock; diff --git a/drivers/infiniband/hw/mana/qp.c b/drivers/infiniband/hw/mana/qp.c index 65b0ebf4df3f..f26f73025d12 100644 --- a/drivers/infiniband/hw/mana/qp.c +++ b/drivers/infiniband/hw/mana/qp.c @@ -735,6 +735,27 @@ destroy_queues: return err; } +static void mana_add_qp_to_error_cqs(struct mana_ib_qp *qp) +{ + struct mana_ib_cq *send_cq = container_of(qp->ibqp.send_cq, struct mana_ib_cq, ibcq); + struct mana_ib_cq *recv_cq = container_of(qp->ibqp.recv_cq, struct mana_ib_cq, ibcq); + unsigned long flags; + + if (WARN_ON_ONCE(qp->ibqp.uobject)) + return; + + /* Keep ERR QPs linked until reset/destroy, including later drain WRs. */ + spin_lock_irqsave(&send_cq->cq_lock, flags); + if (list_empty(&qp->send_err_node)) + list_add_tail(&qp->send_err_node, &send_cq->send_err_qp_list); + spin_unlock_irqrestore(&send_cq->cq_lock, flags); + + spin_lock_irqsave(&recv_cq->cq_lock, flags); + if (list_empty(&qp->recv_err_node)) + list_add_tail(&qp->recv_err_node, &recv_cq->recv_err_qp_list); + spin_unlock_irqrestore(&recv_cq->cq_lock, flags); +} + static void mana_remove_qp_from_cqs(struct mana_ib_qp *qp, bool reset) { struct mana_ib_cq *send_cq = container_of(qp->ibqp.send_cq, struct mana_ib_cq, ibcq); @@ -1027,15 +1048,16 @@ static int mana_ib_gd_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr, return 0; } -static void mana_ib_modify_qp_state(struct ib_qp *ibqp, struct ib_qp_attr *attr, +static bool mana_ib_modify_qp_state(struct ib_qp *ibqp, struct ib_qp_attr *attr, int attr_mask, struct ib_udata *udata) { struct mana_ib_dev *mdev = container_of(ibqp->device, struct mana_ib_dev, ib_dev); struct mana_ib_qp *qp = container_of(ibqp, struct mana_ib_qp, ibqp); struct gdma_queue *rq; + bool notify = false; - if (udata) - return; + if (udata || ibqp->uobject) + return false; if (attr_mask & IB_QP_PATH_MTU) qp->mtu = attr->path_mtu; @@ -1048,6 +1070,11 @@ static void mana_ib_modify_qp_state(struct ib_qp *ibqp, struct ib_qp_attr *attr, default: break; } + qp->state = attr->qp_state; + if (attr->qp_state == IB_QPS_ERR) { + mana_add_qp_to_error_cqs(qp); + notify = true; + } } if (attr_mask & IB_QP_SQ_PSN) { @@ -1063,12 +1090,27 @@ static void mana_ib_modify_qp_state(struct ib_qp *ibqp, struct ib_qp_attr *attr, SET_ARM_BIT, MANA_PSN_CLIENT_OFFSET); } } + + return notify; +} + +static void mana_ib_notify_error_cqs(struct mana_ib_qp *qp) +{ + struct ib_cq *send_cq = qp->ibqp.send_cq; + struct ib_cq *recv_cq = qp->ibqp.recv_cq; + + if (send_cq->poll_ctx != IB_POLL_DIRECT && send_cq->comp_handler) + send_cq->comp_handler(send_cq, send_cq->cq_context); + if (recv_cq != send_cq && recv_cq->poll_ctx != IB_POLL_DIRECT && + recv_cq->comp_handler) + recv_cq->comp_handler(recv_cq, recv_cq->cq_context); } int mana_ib_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr, int attr_mask, struct ib_udata *udata) { struct mana_ib_qp *qp = container_of(ibqp, struct mana_ib_qp, ibqp); + bool notify = false; int ret; mutex_lock(&qp->modify_lock); @@ -1087,11 +1129,14 @@ int mana_ib_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr, goto out_unlock; } - mana_ib_modify_qp_state(ibqp, attr, attr_mask, udata); + notify = mana_ib_modify_qp_state(ibqp, attr, attr_mask, udata); out_unlock: mutex_unlock(&qp->modify_lock); + if (notify) + mana_ib_notify_error_cqs(qp); + return ret; } @@ -1213,6 +1258,7 @@ static int mana_ib_destroy_uc_qp(struct mana_ib_qp *qp, struct ib_udata *udata) return err; mana_table_remove_qp(mdev, qp); + mana_remove_qp_from_cqs(qp, false); /* Ignore return code as there is not much we can do about it. * The error message is printed inside. */ -- 2.43.0