From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from smtp.kernel.org (aws-us-west-2-korg-mail-1.web.codeaurora.org [10.30.226.201]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 1899A481DD; Wed, 5 Mar 2025 17:56:33 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=10.30.226.201 ARC-Seal:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1741197393; cv=none; b=qezgo1NHQlpaw3FD0+QY4gALm8z7rjZPLtG+aSOi0JEpL8hV1+gdKc0xMQGNhoSHP7LGdVofmd3YKTjF0IelkbP2KFFkBMvuK7XKku1wa1ZJi4cr5NWiCj8EhyxQ1UgiUZtVOLUDfz6XJmAGTCpqS+OVLUWPGCpYmodA7G45ky0= ARC-Message-Signature:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1741197393; c=relaxed/simple; bh=olzgO/hXRWvr6Onqb0LTqTs6h/xwoIvvQsIFx1It030=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version; b=tzSF/5dygjA/r+WwiH8Rs5M7PNbsRUlE6vE9xRtTOqoPxBAzgijdLUS313dMolPXszdcktQMec6A4uoayDHoilipNVEU+Pnio8Yy62IvVdYT5JX85UwRo2IWLpRLw4yxs6tn1dvwfebMFNC4+g/PgVdctJYTDPUU4Cb35N6Q4Cw= ARC-Authentication-Results:i=1; smtp.subspace.kernel.org; dkim=pass (1024-bit key) header.d=linuxfoundation.org header.i=@linuxfoundation.org header.b=SbeOOoa0; arc=none smtp.client-ip=10.30.226.201 Authentication-Results: smtp.subspace.kernel.org; dkim=pass (1024-bit key) header.d=linuxfoundation.org header.i=@linuxfoundation.org header.b="SbeOOoa0" Received: by smtp.kernel.org (Postfix) with ESMTPSA id 9550FC4CED1; Wed, 5 Mar 2025 17:56:32 +0000 (UTC) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=linuxfoundation.org; s=korg; t=1741197393; bh=olzgO/hXRWvr6Onqb0LTqTs6h/xwoIvvQsIFx1It030=; h=From:To:Cc:Subject:Date:In-Reply-To:References:From; b=SbeOOoa0+M5x0Ix7nt2NWdttNBhI/6xe7+0/GKAdoxqsFzBSwJFooZfeFNgNfs2KJ O0A5l1TAoPdoGmWzIYCiObtR/+/jMAvo+/WJi1jvqPnYfZNbgolv9XdocSumvLW3Bl wJrSeJ2suscpSwbi1U4J76gBYJ9W/eGXA1db7F5k= From: Greg Kroah-Hartman To: stable@vger.kernel.org Cc: Greg Kroah-Hartman , patches@lists.linux.dev, Mark Zhang , Patrisious Haddad , Leon Romanovsky , Sasha Levin Subject: [PATCH 6.1 109/176] RDMA/mlx: Calling qp event handler in workqueue context Date: Wed, 5 Mar 2025 18:47:58 +0100 Message-ID: <20250305174509.842851865@linuxfoundation.org> X-Mailer: git-send-email 2.48.1 In-Reply-To: <20250305174505.437358097@linuxfoundation.org> References: <20250305174505.437358097@linuxfoundation.org> User-Agent: quilt/0.68 X-stable: review X-Patchwork-Hint: ignore Precedence: bulk X-Mailing-List: stable@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Transfer-Encoding: 8bit 6.1-stable review patch. If anyone has any objections, please let me know. ------------------ From: Mark Zhang [ Upstream commit 312b8f79eb05479628ee71357749815b2eeeeea8 ] Move the call of qp event handler from atomic to workqueue context, so that the handler is able to block. This is needed by following patches. Signed-off-by: Mark Zhang Reviewed-by: Patrisious Haddad Link: https://lore.kernel.org/r/0cd17b8331e445f03942f4bb28d447f24ac5669d.1672821186.git.leonro@nvidia.com Signed-off-by: Leon Romanovsky Stable-dep-of: c534ffda781f ("RDMA/mlx5: Fix AH static rate parsing") Signed-off-by: Sasha Levin --- drivers/infiniband/hw/mlx4/main.c | 8 ++ drivers/infiniband/hw/mlx4/mlx4_ib.h | 3 + drivers/infiniband/hw/mlx4/qp.c | 121 +++++++++++++++++------- drivers/infiniband/hw/mlx5/main.c | 7 ++ drivers/infiniband/hw/mlx5/qp.c | 119 ++++++++++++++++------- drivers/infiniband/hw/mlx5/qp.h | 2 + drivers/infiniband/hw/mlx5/qpc.c | 3 +- drivers/net/ethernet/mellanox/mlx4/qp.c | 14 ++- include/linux/mlx4/qp.h | 1 + include/rdma/ib_verbs.h | 2 +- 10 files changed, 202 insertions(+), 78 deletions(-) diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c index 7c3dc86ab7f04..0f0b130cc8aac 100644 --- a/drivers/infiniband/hw/mlx4/main.c +++ b/drivers/infiniband/hw/mlx4/main.c @@ -3307,6 +3307,10 @@ static int __init mlx4_ib_init(void) if (!wq) return -ENOMEM; + err = mlx4_ib_qp_event_init(); + if (err) + goto clean_qp_event; + err = mlx4_ib_cm_init(); if (err) goto clean_wq; @@ -3328,6 +3332,9 @@ static int __init mlx4_ib_init(void) mlx4_ib_cm_destroy(); clean_wq: + mlx4_ib_qp_event_cleanup(); + +clean_qp_event: destroy_workqueue(wq); return err; } @@ -3337,6 +3344,7 @@ static void __exit mlx4_ib_cleanup(void) mlx4_unregister_interface(&mlx4_ib_interface); mlx4_ib_mcg_destroy(); mlx4_ib_cm_destroy(); + mlx4_ib_qp_event_cleanup(); destroy_workqueue(wq); } diff --git a/drivers/infiniband/hw/mlx4/mlx4_ib.h b/drivers/infiniband/hw/mlx4/mlx4_ib.h index 6a3b0f121045e..17fee1e73a45a 100644 --- a/drivers/infiniband/hw/mlx4/mlx4_ib.h +++ b/drivers/infiniband/hw/mlx4/mlx4_ib.h @@ -940,4 +940,7 @@ int mlx4_ib_umem_calc_optimal_mtt_size(struct ib_umem *umem, u64 start_va, int mlx4_ib_cm_init(void); void mlx4_ib_cm_destroy(void); +int mlx4_ib_qp_event_init(void); +void mlx4_ib_qp_event_cleanup(void); + #endif /* MLX4_IB_H */ diff --git a/drivers/infiniband/hw/mlx4/qp.c b/drivers/infiniband/hw/mlx4/qp.c index ac479e81ddee8..9d08aa99f3cb0 100644 --- a/drivers/infiniband/hw/mlx4/qp.c +++ b/drivers/infiniband/hw/mlx4/qp.c @@ -102,6 +102,14 @@ enum mlx4_ib_source_type { MLX4_IB_RWQ_SRC = 1, }; +struct mlx4_ib_qp_event_work { + struct work_struct work; + struct mlx4_qp *qp; + enum mlx4_event type; +}; + +static struct workqueue_struct *mlx4_ib_qp_event_wq; + static int is_tunnel_qp(struct mlx4_ib_dev *dev, struct mlx4_ib_qp *qp) { if (!mlx4_is_master(dev->dev)) @@ -200,50 +208,77 @@ static void stamp_send_wqe(struct mlx4_ib_qp *qp, int n) } } +static void mlx4_ib_handle_qp_event(struct work_struct *_work) +{ + struct mlx4_ib_qp_event_work *qpe_work = + container_of(_work, struct mlx4_ib_qp_event_work, work); + struct ib_qp *ibqp = &to_mibqp(qpe_work->qp)->ibqp; + struct ib_event event = {}; + + event.device = ibqp->device; + event.element.qp = ibqp; + + switch (qpe_work->type) { + case MLX4_EVENT_TYPE_PATH_MIG: + event.event = IB_EVENT_PATH_MIG; + break; + case MLX4_EVENT_TYPE_COMM_EST: + event.event = IB_EVENT_COMM_EST; + break; + case MLX4_EVENT_TYPE_SQ_DRAINED: + event.event = IB_EVENT_SQ_DRAINED; + break; + case MLX4_EVENT_TYPE_SRQ_QP_LAST_WQE: + event.event = IB_EVENT_QP_LAST_WQE_REACHED; + break; + case MLX4_EVENT_TYPE_WQ_CATAS_ERROR: + event.event = IB_EVENT_QP_FATAL; + break; + case MLX4_EVENT_TYPE_PATH_MIG_FAILED: + event.event = IB_EVENT_PATH_MIG_ERR; + break; + case MLX4_EVENT_TYPE_WQ_INVAL_REQ_ERROR: + event.event = IB_EVENT_QP_REQ_ERR; + break; + case MLX4_EVENT_TYPE_WQ_ACCESS_ERROR: + event.event = IB_EVENT_QP_ACCESS_ERR; + break; + default: + pr_warn("Unexpected event type %d on QP %06x\n", + qpe_work->type, qpe_work->qp->qpn); + goto out; + } + + ibqp->event_handler(&event, ibqp->qp_context); + +out: + mlx4_put_qp(qpe_work->qp); + kfree(qpe_work); +} + static void mlx4_ib_qp_event(struct mlx4_qp *qp, enum mlx4_event type) { - struct ib_event event; struct ib_qp *ibqp = &to_mibqp(qp)->ibqp; + struct mlx4_ib_qp_event_work *qpe_work; if (type == MLX4_EVENT_TYPE_PATH_MIG) to_mibqp(qp)->port = to_mibqp(qp)->alt_port; - if (ibqp->event_handler) { - event.device = ibqp->device; - event.element.qp = ibqp; - switch (type) { - case MLX4_EVENT_TYPE_PATH_MIG: - event.event = IB_EVENT_PATH_MIG; - break; - case MLX4_EVENT_TYPE_COMM_EST: - event.event = IB_EVENT_COMM_EST; - break; - case MLX4_EVENT_TYPE_SQ_DRAINED: - event.event = IB_EVENT_SQ_DRAINED; - break; - case MLX4_EVENT_TYPE_SRQ_QP_LAST_WQE: - event.event = IB_EVENT_QP_LAST_WQE_REACHED; - break; - case MLX4_EVENT_TYPE_WQ_CATAS_ERROR: - event.event = IB_EVENT_QP_FATAL; - break; - case MLX4_EVENT_TYPE_PATH_MIG_FAILED: - event.event = IB_EVENT_PATH_MIG_ERR; - break; - case MLX4_EVENT_TYPE_WQ_INVAL_REQ_ERROR: - event.event = IB_EVENT_QP_REQ_ERR; - break; - case MLX4_EVENT_TYPE_WQ_ACCESS_ERROR: - event.event = IB_EVENT_QP_ACCESS_ERR; - break; - default: - pr_warn("Unexpected event type %d " - "on QP %06x\n", type, qp->qpn); - return; - } + if (!ibqp->event_handler) + goto out_no_handler; - ibqp->event_handler(&event, ibqp->qp_context); - } + qpe_work = kzalloc(sizeof(*qpe_work), GFP_ATOMIC); + if (!qpe_work) + goto out_no_handler; + + qpe_work->qp = qp; + qpe_work->type = type; + INIT_WORK(&qpe_work->work, mlx4_ib_handle_qp_event); + queue_work(mlx4_ib_qp_event_wq, &qpe_work->work); + return; + +out_no_handler: + mlx4_put_qp(qp); } static void mlx4_ib_wq_event(struct mlx4_qp *qp, enum mlx4_event type) @@ -4472,3 +4507,17 @@ void mlx4_ib_drain_rq(struct ib_qp *qp) handle_drain_completion(cq, &rdrain, dev); } + +int mlx4_ib_qp_event_init(void) +{ + mlx4_ib_qp_event_wq = alloc_ordered_workqueue("mlx4_ib_qp_event_wq", 0); + if (!mlx4_ib_qp_event_wq) + return -ENOMEM; + + return 0; +} + +void mlx4_ib_qp_event_cleanup(void) +{ + destroy_workqueue(mlx4_ib_qp_event_wq); +} diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c index 45a414e8d35fa..a22649617e017 100644 --- a/drivers/infiniband/hw/mlx5/main.c +++ b/drivers/infiniband/hw/mlx5/main.c @@ -4410,6 +4410,10 @@ static int __init mlx5_ib_init(void) return -ENOMEM; } + ret = mlx5_ib_qp_event_init(); + if (ret) + goto qp_event_err; + mlx5_ib_odp_init(); ret = mlx5r_rep_init(); if (ret) @@ -4427,6 +4431,8 @@ static int __init mlx5_ib_init(void) mp_err: mlx5r_rep_cleanup(); rep_err: + mlx5_ib_qp_event_cleanup(); +qp_event_err: destroy_workqueue(mlx5_ib_event_wq); free_page((unsigned long)xlt_emergency_page); return ret; @@ -4438,6 +4444,7 @@ static void __exit mlx5_ib_cleanup(void) auxiliary_driver_unregister(&mlx5r_mp_driver); mlx5r_rep_cleanup(); + mlx5_ib_qp_event_cleanup(); destroy_workqueue(mlx5_ib_event_wq); free_page((unsigned long)xlt_emergency_page); } diff --git a/drivers/infiniband/hw/mlx5/qp.c b/drivers/infiniband/hw/mlx5/qp.c index d782a494abcda..43c0123babd10 100644 --- a/drivers/infiniband/hw/mlx5/qp.c +++ b/drivers/infiniband/hw/mlx5/qp.c @@ -71,6 +71,14 @@ struct mlx5_modify_raw_qp_param { u32 port; }; +struct mlx5_ib_qp_event_work { + struct work_struct work; + struct mlx5_core_qp *qp; + int type; +}; + +static struct workqueue_struct *mlx5_ib_qp_event_wq; + static void get_cqs(enum ib_qp_type qp_type, struct ib_cq *ib_send_cq, struct ib_cq *ib_recv_cq, struct mlx5_ib_cq **send_cq, struct mlx5_ib_cq **recv_cq); @@ -302,51 +310,78 @@ int mlx5_ib_read_wqe_srq(struct mlx5_ib_srq *srq, int wqe_index, void *buffer, return mlx5_ib_read_user_wqe_srq(srq, wqe_index, buffer, buflen, bc); } +static void mlx5_ib_handle_qp_event(struct work_struct *_work) +{ + struct mlx5_ib_qp_event_work *qpe_work = + container_of(_work, struct mlx5_ib_qp_event_work, work); + struct ib_qp *ibqp = &to_mibqp(qpe_work->qp)->ibqp; + struct ib_event event = {}; + + event.device = ibqp->device; + event.element.qp = ibqp; + switch (qpe_work->type) { + case MLX5_EVENT_TYPE_PATH_MIG: + event.event = IB_EVENT_PATH_MIG; + break; + case MLX5_EVENT_TYPE_COMM_EST: + event.event = IB_EVENT_COMM_EST; + break; + case MLX5_EVENT_TYPE_SQ_DRAINED: + event.event = IB_EVENT_SQ_DRAINED; + break; + case MLX5_EVENT_TYPE_SRQ_LAST_WQE: + event.event = IB_EVENT_QP_LAST_WQE_REACHED; + break; + case MLX5_EVENT_TYPE_WQ_CATAS_ERROR: + event.event = IB_EVENT_QP_FATAL; + break; + case MLX5_EVENT_TYPE_PATH_MIG_FAILED: + event.event = IB_EVENT_PATH_MIG_ERR; + break; + case MLX5_EVENT_TYPE_WQ_INVAL_REQ_ERROR: + event.event = IB_EVENT_QP_REQ_ERR; + break; + case MLX5_EVENT_TYPE_WQ_ACCESS_ERROR: + event.event = IB_EVENT_QP_ACCESS_ERR; + break; + default: + pr_warn("mlx5_ib: Unexpected event type %d on QP %06x\n", + qpe_work->type, qpe_work->qp->qpn); + goto out; + } + + ibqp->event_handler(&event, ibqp->qp_context); + +out: + mlx5_core_res_put(&qpe_work->qp->common); + kfree(qpe_work); +} + static void mlx5_ib_qp_event(struct mlx5_core_qp *qp, int type) { struct ib_qp *ibqp = &to_mibqp(qp)->ibqp; - struct ib_event event; + struct mlx5_ib_qp_event_work *qpe_work; if (type == MLX5_EVENT_TYPE_PATH_MIG) { /* This event is only valid for trans_qps */ to_mibqp(qp)->port = to_mibqp(qp)->trans_qp.alt_port; } - if (ibqp->event_handler) { - event.device = ibqp->device; - event.element.qp = ibqp; - switch (type) { - case MLX5_EVENT_TYPE_PATH_MIG: - event.event = IB_EVENT_PATH_MIG; - break; - case MLX5_EVENT_TYPE_COMM_EST: - event.event = IB_EVENT_COMM_EST; - break; - case MLX5_EVENT_TYPE_SQ_DRAINED: - event.event = IB_EVENT_SQ_DRAINED; - break; - case MLX5_EVENT_TYPE_SRQ_LAST_WQE: - event.event = IB_EVENT_QP_LAST_WQE_REACHED; - break; - case MLX5_EVENT_TYPE_WQ_CATAS_ERROR: - event.event = IB_EVENT_QP_FATAL; - break; - case MLX5_EVENT_TYPE_PATH_MIG_FAILED: - event.event = IB_EVENT_PATH_MIG_ERR; - break; - case MLX5_EVENT_TYPE_WQ_INVAL_REQ_ERROR: - event.event = IB_EVENT_QP_REQ_ERR; - break; - case MLX5_EVENT_TYPE_WQ_ACCESS_ERROR: - event.event = IB_EVENT_QP_ACCESS_ERR; - break; - default: - pr_warn("mlx5_ib: Unexpected event type %d on QP %06x\n", type, qp->qpn); - return; - } + if (!ibqp->event_handler) + goto out_no_handler; - ibqp->event_handler(&event, ibqp->qp_context); - } + qpe_work = kzalloc(sizeof(*qpe_work), GFP_ATOMIC); + if (!qpe_work) + goto out_no_handler; + + qpe_work->qp = qp; + qpe_work->type = type; + INIT_WORK(&qpe_work->work, mlx5_ib_handle_qp_event); + queue_work(mlx5_ib_qp_event_wq, &qpe_work->work); + return; + +out_no_handler: + mlx5_core_res_put(&qp->common); } static int set_rq_size(struct mlx5_ib_dev *dev, struct ib_qp_cap *cap, @@ -5752,3 +5787,17 @@ int mlx5_ib_qp_set_counter(struct ib_qp *qp, struct rdma_counter *counter) mutex_unlock(&mqp->mutex); return err; } + +int mlx5_ib_qp_event_init(void) +{ + mlx5_ib_qp_event_wq = alloc_ordered_workqueue("mlx5_ib_qp_event_wq", 0); + if (!mlx5_ib_qp_event_wq) + return -ENOMEM; + + return 0; +} + +void mlx5_ib_qp_event_cleanup(void) +{ + destroy_workqueue(mlx5_ib_qp_event_wq); +} diff --git a/drivers/infiniband/hw/mlx5/qp.h b/drivers/infiniband/hw/mlx5/qp.h index 5d4e140db99ce..fb2f4e030bb8f 100644 --- a/drivers/infiniband/hw/mlx5/qp.h +++ b/drivers/infiniband/hw/mlx5/qp.h @@ -44,4 +44,6 @@ void mlx5_core_res_put(struct mlx5_core_rsc_common *res); int mlx5_core_xrcd_alloc(struct mlx5_ib_dev *dev, u32 *xrcdn); int mlx5_core_xrcd_dealloc(struct mlx5_ib_dev *dev, u32 xrcdn); int mlx5_ib_qp_set_counter(struct ib_qp *qp, struct rdma_counter *counter); +int mlx5_ib_qp_event_init(void); +void mlx5_ib_qp_event_cleanup(void); #endif /* _MLX5_IB_QP_H */ diff --git a/drivers/infiniband/hw/mlx5/qpc.c b/drivers/infiniband/hw/mlx5/qpc.c index d4e7864c56f18..a824ff22f4615 100644 --- a/drivers/infiniband/hw/mlx5/qpc.c +++ b/drivers/infiniband/hw/mlx5/qpc.c @@ -135,7 +135,8 @@ static int rsc_event_notifier(struct notifier_block *nb, case MLX5_RES_SQ: qp = (struct mlx5_core_qp *)common; qp->event(qp, event_type); - break; + /* Need to put resource in event handler */ + return NOTIFY_OK; case MLX5_RES_DCT: dct = (struct mlx5_core_dct *)common; if (event_type == MLX5_EVENT_TYPE_DCT_DRAINED) diff --git a/drivers/net/ethernet/mellanox/mlx4/qp.c b/drivers/net/ethernet/mellanox/mlx4/qp.c index 48cfaa7eaf50c..913ed255990f4 100644 --- a/drivers/net/ethernet/mellanox/mlx4/qp.c +++ b/drivers/net/ethernet/mellanox/mlx4/qp.c @@ -46,6 +46,13 @@ #define MLX4_BF_QP_SKIP_MASK 0xc0 #define MLX4_MAX_BF_QP_RANGE 0x40 +void mlx4_put_qp(struct mlx4_qp *qp) +{ + if (refcount_dec_and_test(&qp->refcount)) + complete(&qp->free); +} +EXPORT_SYMBOL_GPL(mlx4_put_qp); + void mlx4_qp_event(struct mlx4_dev *dev, u32 qpn, int event_type) { struct mlx4_qp_table *qp_table = &mlx4_priv(dev)->qp_table; @@ -64,10 +71,8 @@ void mlx4_qp_event(struct mlx4_dev *dev, u32 qpn, int event_type) return; } + /* Need to call mlx4_put_qp() in event handler */ qp->event(qp, event_type); - - if (refcount_dec_and_test(&qp->refcount)) - complete(&qp->free); } /* used for INIT/CLOSE port logic */ @@ -523,8 +528,7 @@ EXPORT_SYMBOL_GPL(mlx4_qp_remove); void mlx4_qp_free(struct mlx4_dev *dev, struct mlx4_qp *qp) { - if (refcount_dec_and_test(&qp->refcount)) - complete(&qp->free); + mlx4_put_qp(qp); wait_for_completion(&qp->free); mlx4_qp_free_icm(dev, qp->qpn); diff --git a/include/linux/mlx4/qp.h b/include/linux/mlx4/qp.h index b6b626157b03a..b9a7b1319f5d3 100644 --- a/include/linux/mlx4/qp.h +++ b/include/linux/mlx4/qp.h @@ -504,4 +504,5 @@ static inline u16 folded_qp(u32 q) u16 mlx4_qp_roce_entropy(struct mlx4_dev *dev, u32 qpn); +void mlx4_put_qp(struct mlx4_qp *qp); #endif /* MLX4_QP_H */ diff --git a/include/rdma/ib_verbs.h b/include/rdma/ib_verbs.h index 5582509003264..68fd6d22adfd4 100644 --- a/include/rdma/ib_verbs.h +++ b/include/rdma/ib_verbs.h @@ -1162,7 +1162,7 @@ enum ib_qp_create_flags { */ struct ib_qp_init_attr { - /* Consumer's event_handler callback must not block */ + /* This callback occurs in workqueue context */ void (*event_handler)(struct ib_event *, void *); void *qp_context; -- 2.39.5