From patchwork Fri Nov 6 03:09:31 2009 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Yevgeny Petrilin X-Patchwork-Id: 57959 Received: from vger.kernel.org (vger.kernel.org [209.132.176.167]) by demeter.kernel.org (8.14.2/8.14.2) with ESMTP id nA60C4fO027619 for ; Fri, 6 Nov 2009 00:12:04 GMT Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1759189AbZKFAL5 (ORCPT ); Thu, 5 Nov 2009 19:11:57 -0500 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1759192AbZKFAL5 (ORCPT ); Thu, 5 Nov 2009 19:11:57 -0500 Received: from mail.mellanox.co.il ([194.90.237.43]:43178 "EHLO mellanox.co.il" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1759186AbZKFAL4 (ORCPT ); Thu, 5 Nov 2009 19:11:56 -0500 Received: from Internal Mail-Server by MTLPINE1 (envelope-from yevgenyp@mellanox.co.il) with SMTP; 6 Nov 2009 02:17:48 +0200 Received: from [10.4.12.75] ([10.4.12.75]) by mtlexch01.mtl.com with Microsoft SMTPSVC(6.0.3790.3959); Fri, 6 Nov 2009 02:12:00 +0200 Message-ID: <4AF3936B.7080203@mellanox.co.il> Date: Fri, 06 Nov 2009 05:09:31 +0200 From: Yevgeny Petrilin User-Agent: Thunderbird 2.0.0.23 (X11/20090812) MIME-Version: 1.0 To: rdreier@cisco.com CC: linux-rdma@vger.kernel.org, netdev@vger.kernel.org, liranl@mellanox.co.il, tziporet@mellanox.co.il, yevgenyp@mellanox.co.il Subject: [PATCH 14/25 v2] mlx4_core: multi-function resource setup X-OriginalArrivalTime: 06 Nov 2009 00:12:00.0204 (UTC) FILETIME=[C29268C0:01CA5E75] Sender: linux-rdma-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: linux-rdma@vger.kernel.org diff --git a/drivers/net/mlx4/cq.c b/drivers/net/mlx4/cq.c index 9f9f246..b605041 100644 --- a/drivers/net/mlx4/cq.c +++ b/drivers/net/mlx4/cq.c @@ -353,6 +353,8 @@ int mlx4_init_cq_table(struct mlx4_dev *dev) spin_lock_init(&cq_table->lock); INIT_RADIX_TREE(&cq_table->tree, GFP_ATOMIC); + if (mlx4_is_slave(dev)) + return 0; err = mlx4_bitmap_init(&cq_table->bitmap, dev->caps.num_cqs, dev->caps.num_cqs - 1, dev->caps.reserved_cqs, 0); @@ -364,6 +366,8 @@ int mlx4_init_cq_table(struct mlx4_dev *dev) void mlx4_cleanup_cq_table(struct mlx4_dev *dev) { + if (mlx4_is_slave(dev)) + return; /* Nothing to do to clean up radix_tree */ mlx4_bitmap_cleanup(&mlx4_priv(dev)->cq_table.bitmap); } diff --git a/drivers/net/mlx4/eq.c b/drivers/net/mlx4/eq.c index 46064cc..b0c8022 100644 --- a/drivers/net/mlx4/eq.c +++ b/drivers/net/mlx4/eq.c @@ -732,39 +732,42 @@ int mlx4_init_eq_table(struct mlx4_dev *dev) goto err_out_free; } - err = mlx4_bitmap_init(&priv->eq_table.bitmap, dev->caps.num_eqs, - dev->caps.num_eqs - 1, dev->caps.reserved_eqs, 0); + err = mlx4_bitmap_init_no_mask(&priv->eq_table.bitmap, dev->caps.num_eqs, + dev->caps.reserved_eqs, 0); if (err) goto err_out_free; for (i = 0; i < mlx4_num_eq_uar(dev); ++i) priv->eq_table.uar_map[i] = NULL; - err = mlx4_map_clr_int(dev); - if (err) - goto err_out_bitmap; + if (!mlx4_is_slave(dev)) { + err = mlx4_map_clr_int(dev); + if (err) + goto err_out_bitmap; - priv->eq_table.clr_mask = - swab32(1 << (priv->eq_table.inta_pin & 31)); - priv->eq_table.clr_int = priv->clr_base + - (priv->eq_table.inta_pin < 32 ? 4 : 0); + priv->eq_table.clr_mask = + swab32(1 << (priv->eq_table.inta_pin & 31)); + priv->eq_table.clr_int = priv->clr_base + + (priv->eq_table.inta_pin < 32 ? 4 : 0); + } priv->eq_table.irq_names = kmalloc(MLX4_IRQNAME_SIZE * (dev->caps.num_comp_vectors + 1), GFP_KERNEL); if (!priv->eq_table.irq_names) { err = -ENOMEM; - goto err_out_bitmap; + i = 0; + goto err_out_unmap; } for (i = 0; i < dev->caps.num_comp_vectors; ++i) { - err = mlx4_create_eq(dev, dev->caps.num_cqs + MLX4_NUM_SPARE_EQE, + err = mlx4_create_eq(dev, dev->caps.num_cqs - + dev->caps.reserved_cqs + + MLX4_NUM_SPARE_EQE, (dev->flags & MLX4_FLAG_MSI_X) ? i : 0, &priv->eq_table.eq[i]); - if (err) { - --i; + if (err) goto err_out_unmap; - } } err = mlx4_create_eq(dev, MLX4_NUM_ASYNC_EQE + MLX4_NUM_SPARE_EQE, @@ -814,11 +817,13 @@ int mlx4_init_eq_table(struct mlx4_dev *dev) priv->eq_table.have_irq = 1; } - err = mlx4_MAP_EQ(dev, MLX4_ASYNC_EVENT_MASK, 0, - priv->eq_table.eq[dev->caps.num_comp_vectors].eqn); - if (err) - mlx4_warn(dev, "MAP_EQ for async EQ %d failed (%d)\n", - priv->eq_table.eq[dev->caps.num_comp_vectors].eqn, err); + if (!mlx4_is_slave(dev)) { /* hw async events cannot be shared */ + err = mlx4_MAP_EQ(dev, MLX4_ASYNC_EVENT_MASK, 0, + priv->eq_table.eq[dev->caps.num_comp_vectors].eqn); + if (err) + mlx4_warn(dev, "MAP_EQ for async EQ %d failed (%d)\n", + priv->eq_table.eq[dev->caps.num_comp_vectors].eqn, err); + } for (i = 0; i < dev->caps.num_comp_vectors + 1; ++i) eq_set_ci(&priv->eq_table.eq[i], 1); @@ -829,14 +834,15 @@ err_out_async: mlx4_free_eq(dev, &priv->eq_table.eq[dev->caps.num_comp_vectors]); err_out_comp: - i = dev->caps.num_comp_vectors - 1; + i = dev->caps.num_comp_vectors; err_out_unmap: - while (i >= 0) { - mlx4_free_eq(dev, &priv->eq_table.eq[i]); + while (i > 0) { --i; + mlx4_free_eq(dev, &priv->eq_table.eq[i]); } - mlx4_unmap_clr_int(dev); + if (!mlx4_is_slave(dev)) + mlx4_unmap_clr_int(dev); mlx4_free_irqs(dev); err_out_bitmap: @@ -853,15 +859,18 @@ void mlx4_cleanup_eq_table(struct mlx4_dev *dev) struct mlx4_priv *priv = mlx4_priv(dev); int i; - mlx4_MAP_EQ(dev, MLX4_ASYNC_EVENT_MASK, 1, - priv->eq_table.eq[dev->caps.num_comp_vectors].eqn); + if (!mlx4_is_slave(dev)) { + mlx4_MAP_EQ(dev, MLX4_ASYNC_EVENT_MASK, 1, + priv->eq_table.eq[dev->caps.num_comp_vectors].eqn); + } mlx4_free_irqs(dev); for (i = 0; i < dev->caps.num_comp_vectors + 1; ++i) mlx4_free_eq(dev, &priv->eq_table.eq[i]); - mlx4_unmap_clr_int(dev); + if (!mlx4_is_slave(dev)) + mlx4_unmap_clr_int(dev); for (i = 0; i < mlx4_num_eq_uar(dev); ++i) if (priv->eq_table.uar_map[i]) diff --git a/drivers/net/mlx4/main.c b/drivers/net/mlx4/main.c index d8143c6..2852445 100644 --- a/drivers/net/mlx4/main.c +++ b/drivers/net/mlx4/main.c @@ -904,11 +904,14 @@ static int mlx4_setup_hca(struct mlx4_dev *dev) goto err_mr_table_free; } - err = mlx4_cmd_use_events(dev); - if (err) { - mlx4_err(dev, "Failed to switch to event-driven " - "firmware commands, aborting.\n"); - goto err_eq_table_free; + /* CX1: no comm channel events */ + if (!mlx4_is_master(dev) && !mlx4_is_slave(dev)) { + err = mlx4_cmd_use_events(dev); + if (err) { + mlx4_err(dev, "Failed to switch to event-driven " + "firmware commands, aborting.\n"); + goto err_eq_table_free; + } } err = mlx4_NOP(dev); @@ -958,22 +961,23 @@ static int mlx4_setup_hca(struct mlx4_dev *dev) goto err_qp_table_free; } - for (port = 1; port <= dev->caps.num_ports; port++) { - ib_port_default_caps = 0; - err = mlx4_get_port_ib_caps(dev, port, &ib_port_default_caps); - if (err) - mlx4_warn(dev, "failed to get port %d default " - "ib capabilities (%d). Continuing with " - "caps = 0\n", port, err); - dev->caps.ib_port_def_cap[port] = ib_port_default_caps; - err = mlx4_SET_PORT(dev, port); - if (err) { - mlx4_err(dev, "Failed to set port %d, aborting\n", - port); - goto err_mcg_table_free; + if (!mlx4_is_slave(dev)) { + for (port = 1; port <= dev->caps.num_ports; port++) { + ib_port_default_caps = 0; + err = mlx4_get_port_ib_caps(dev, port, &ib_port_default_caps); + if (err) + mlx4_warn(dev, "failed to get port %d default " + "ib capabilities (%d). Continuing with " + "caps = 0\n", port, err); + dev->caps.ib_port_def_cap[port] = ib_port_default_caps; + err = mlx4_SET_PORT(dev, port); + if (err) { + mlx4_err(dev, "Failed to set port %d, aborting\n", + port); + goto err_mcg_table_free; + } } } - return 0; err_mcg_table_free: @@ -989,7 +993,8 @@ err_cq_table_free: mlx4_cleanup_cq_table(dev); err_cmd_poll: - mlx4_cmd_use_polling(dev); + if (!mlx4_is_master(dev) && !mlx4_is_slave(dev)) + mlx4_cmd_use_polling(dev); err_eq_table_free: mlx4_cleanup_eq_table(dev); diff --git a/drivers/net/mlx4/mcg.c b/drivers/net/mlx4/mcg.c index 96f09ed..daa08f1 100644 --- a/drivers/net/mlx4/mcg.c +++ b/drivers/net/mlx4/mcg.c @@ -393,6 +393,10 @@ int mlx4_init_mcg_table(struct mlx4_dev *dev) struct mlx4_priv *priv = mlx4_priv(dev); int err; + /* Nothing to do for slaves - mcg handling is para-virtualized */ + if (mlx4_is_slave(dev)) + return 0; + err = mlx4_bitmap_init(&priv->mcg_table.bitmap, dev->caps.num_amgms, dev->caps.num_amgms - 1, 0, 0); if (err) @@ -405,5 +409,7 @@ int mlx4_init_mcg_table(struct mlx4_dev *dev) void mlx4_cleanup_mcg_table(struct mlx4_dev *dev) { + if (mlx4_is_slave(dev)) + return; mlx4_bitmap_cleanup(&mlx4_priv(dev)->mcg_table.bitmap); } diff --git a/drivers/net/mlx4/mr.c b/drivers/net/mlx4/mr.c index aa1eba6..522d29a 100644 --- a/drivers/net/mlx4/mr.c +++ b/drivers/net/mlx4/mr.c @@ -612,6 +612,10 @@ int mlx4_init_mr_table(struct mlx4_dev *dev) struct mlx4_mr_table *mr_table = &mlx4_priv(dev)->mr_table; int err; + /* Nothing to do for slaves - all MR handling is forwarded to the master */ + if (mlx4_is_slave(dev)) + return 0; + err = mlx4_bitmap_init(&mr_table->mpt_bitmap, dev->caps.num_mpts, ~0, dev->caps.reserved_mrws, 0); if (err) @@ -646,6 +650,8 @@ void mlx4_cleanup_mr_table(struct mlx4_dev *dev) { struct mlx4_mr_table *mr_table = &mlx4_priv(dev)->mr_table; + if (mlx4_is_slave(dev)) + return; mlx4_buddy_cleanup(&mr_table->mtt_buddy); mlx4_bitmap_cleanup(&mr_table->mpt_bitmap); } diff --git a/drivers/net/mlx4/pd.c b/drivers/net/mlx4/pd.c index 08eaf08..db7e2f4 100644 --- a/drivers/net/mlx4/pd.c +++ b/drivers/net/mlx4/pd.c @@ -96,6 +96,10 @@ EXPORT_SYMBOL_GPL(mlx4_uar_free); int mlx4_init_uar_table(struct mlx4_dev *dev) { + /* CX1: master doesn't have UARs */ + if (mlx4_is_master(dev)) + return 0; + if (dev->caps.num_uars <= 128) { mlx4_err(dev, "Only %d UAR pages (need more than 128)\n", dev->caps.num_uars); @@ -103,12 +107,14 @@ int mlx4_init_uar_table(struct mlx4_dev *dev) return -ENODEV; } - return mlx4_bitmap_init(&mlx4_priv(dev)->uar_table.bitmap, - dev->caps.num_uars, dev->caps.num_uars - 1, - max(128, dev->caps.reserved_uars), 0); + return mlx4_bitmap_init_no_mask(&mlx4_priv(dev)->uar_table.bitmap, + dev->caps.num_uars, + dev->caps.reserved_uars, 0); } void mlx4_cleanup_uar_table(struct mlx4_dev *dev) { + if (mlx4_is_master(dev)) + return; mlx4_bitmap_cleanup(&mlx4_priv(dev)->uar_table.bitmap); } diff --git a/drivers/net/mlx4/qp.c b/drivers/net/mlx4/qp.c index 99b9ded..60c1d7f 100644 --- a/drivers/net/mlx4/qp.c +++ b/drivers/net/mlx4/qp.c @@ -406,6 +406,23 @@ int mlx4_init_qp_table(struct mlx4_dev *dev) spin_lock_init(&qp_table->lock); INIT_RADIX_TREE(&dev->qp_table_tree, GFP_ATOMIC); + if (mlx4_is_slave(dev)) { + /* For each slave, just allocate a normal 8-byte alligned special-QP + * range intead of mlx4_init_qp_table() reservation */ + err = mlx4_qp_reserve_range(dev, 8, 8, &dev->caps.sqp_start); + if (err) { + mlx4_err(dev, "Failed to allocate special QP range\n"); + return err; + } + + err = mlx4_CONF_SPECIAL_QP(dev, dev->caps.sqp_start); + if (err) { + mlx4_err(dev, "Failed to configure special QP range\n"); + mlx4_qp_release_range(dev, dev->caps.sqp_start, 8); + return err; + } + return 0; + } /* * We reserve 2 extra QPs per port for the special QPs. The @@ -415,6 +432,10 @@ int mlx4_init_qp_table(struct mlx4_dev *dev) dev->caps.sqp_start = ALIGN(dev->caps.reserved_qps_cnt[MLX4_QP_REGION_FW], 8); + /* If multi-function is enabled, we reserve an additional QP for qp0/1 tunneling. + * CX1: slave0 manages tunnel QP */ + dev->caps.tunnel_qpn = mlx4_is_master(dev) ? dev->caps.sqp_start + 8 : 0; + { int sort[MLX4_NUM_QP_REGION]; int i, j, tmp; @@ -444,17 +465,25 @@ int mlx4_init_qp_table(struct mlx4_dev *dev) } err = mlx4_bitmap_init(&qp_table->bitmap, dev->caps.num_qps, - (1 << 23) - 1, dev->caps.sqp_start + 8, - reserved_from_top); + (1 << 23) - 1, dev->caps.sqp_start + 8 + + 2 * !!dev->caps.tunnel_qpn, reserved_from_top); if (err) return err; + /* CX1: master has no QPs */ + if (mlx4_is_master(dev)) + return 0; + return mlx4_CONF_SPECIAL_QP(dev, dev->caps.sqp_start); } void mlx4_cleanup_qp_table(struct mlx4_dev *dev) { mlx4_CONF_SPECIAL_QP(dev, 0); + if (mlx4_is_slave(dev)) { + mlx4_qp_release_range(dev, dev->caps.sqp_start, 8); + return; + } mlx4_bitmap_cleanup(&mlx4_priv(dev)->qp_table.bitmap); } diff --git a/drivers/net/mlx4/srq.c b/drivers/net/mlx4/srq.c index ed11f18..3050318 100644 --- a/drivers/net/mlx4/srq.c +++ b/drivers/net/mlx4/srq.c @@ -287,6 +287,8 @@ int mlx4_init_srq_table(struct mlx4_dev *dev) spin_lock_init(&srq_table->lock); INIT_RADIX_TREE(&srq_table->tree, GFP_ATOMIC); + if (mlx4_is_slave(dev)) + return 0; err = mlx4_bitmap_init(&srq_table->bitmap, dev->caps.num_srqs, dev->caps.num_srqs - 1, dev->caps.reserved_srqs, 0); @@ -298,5 +300,7 @@ int mlx4_init_srq_table(struct mlx4_dev *dev) void mlx4_cleanup_srq_table(struct mlx4_dev *dev) { + if (mlx4_is_slave(dev)) + return; mlx4_bitmap_cleanup(&mlx4_priv(dev)->srq_table.bitmap); } diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index 4b9091a..bbd398b 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -204,6 +204,7 @@ struct mlx4_caps { int max_qp_init_rdma; int max_qp_dest_rdma; int sqp_start; + int tunnel_qpn; int num_srqs; int max_srq_wqes; int max_srq_sge;