From: Majd Dibbiny Date: Tue, 30 Sep 2014 09:03:48 +0000 (+0300) Subject: net/mlx4_core: New init and exit flow for mlx4_core X-Git-Url: https://git.karo-electronics.de/?a=commitdiff_plain;h=e1c00e10e92c04aa637126db2e59b092bd4878f8;p=linux-beck.git net/mlx4_core: New init and exit flow for mlx4_core In the new flow, we separate the pci initialization and teardown from the initialization and teardown of the other resources. __mlx4_init_one handles the pci resources initialization. It then calls mlx4_load_one to initialize the remainder of the resources. When removing a device, mlx4_remove_one is invoked. However, now mlx4_remove_one calls mlx4_unload_one to free all the resources except the pci resources. When mlx4_unload_one returns, mlx4_remove_one then frees the pci resources. The above separation will allow us to implement 'reset flow' in the future. It will also enable more EQs for VFs and is a pre-step to the modern API to enable/disable SRIOV. Also added nvfs; an integer array of size MLX4_MAX_PORTS + 1; to the mlx4_dev struct. This new field is used to avoid parsing the num_vfs module parameter each time the mlx4_restart_one is called. Signed-off-by: Majd Dibbiny Signed-off-by: Or Gerlitz Signed-off-by: David S. Miller --- diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c index 4e9857b409f3..f6c32a947185 100644 --- a/drivers/net/ethernet/mellanox/mlx4/main.c +++ b/drivers/net/ethernet/mellanox/mlx4/main.c @@ -2259,116 +2259,18 @@ static void mlx4_free_ownership(struct mlx4_dev *dev) iounmap(owner); } -static int __mlx4_init_one(struct pci_dev *pdev, int pci_dev_data) +static int mlx4_load_one(struct pci_dev *pdev, int pci_dev_data, + int total_vfs, int *nvfs, struct mlx4_priv *priv) { - struct mlx4_priv *priv; struct mlx4_dev *dev; + unsigned sum = 0; int err; int port; - int nvfs[MLX4_MAX_PORTS + 1] = {0, 0, 0}; - int prb_vf[MLX4_MAX_PORTS + 1] = {0, 0, 0}; - const int param_map[MLX4_MAX_PORTS + 1][MLX4_MAX_PORTS + 1] = { - {2, 0, 0}, {0, 1, 2}, {0, 1, 2} }; - unsigned total_vfs = 0; - int sriov_initialized = 0; - unsigned int i; + int i; int existing_vfs = 0; - pr_info(DRV_NAME ": Initializing %s\n", pci_name(pdev)); - - err = pci_enable_device(pdev); - if (err) { - dev_err(&pdev->dev, "Cannot enable PCI device, aborting\n"); - return err; - } - - /* Due to requirement that all VFs and the PF are *guaranteed* 2 MACS - * per port, we must limit the number of VFs to 63 (since their are - * 128 MACs) - */ - for (i = 0; i < sizeof(nvfs)/sizeof(nvfs[0]) && i < num_vfs_argc; - total_vfs += nvfs[param_map[num_vfs_argc - 1][i]], i++) { - nvfs[param_map[num_vfs_argc - 1][i]] = num_vfs[i]; - if (nvfs[i] < 0) { - dev_err(&pdev->dev, "num_vfs module parameter cannot be negative\n"); - return -EINVAL; - } - } - for (i = 0; i < sizeof(prb_vf)/sizeof(prb_vf[0]) && i < probe_vfs_argc; - i++) { - prb_vf[param_map[probe_vfs_argc - 1][i]] = probe_vf[i]; - if (prb_vf[i] < 0 || prb_vf[i] > nvfs[i]) { - dev_err(&pdev->dev, "probe_vf module parameter cannot be negative or greater than num_vfs\n"); - return -EINVAL; - } - } - if (total_vfs >= MLX4_MAX_NUM_VF) { - dev_err(&pdev->dev, - "Requested more VF's (%d) than allowed (%d)\n", - total_vfs, MLX4_MAX_NUM_VF - 1); - return -EINVAL; - } - - for (i = 0; i < MLX4_MAX_PORTS; i++) { - if (nvfs[i] + nvfs[2] >= MLX4_MAX_NUM_VF_P_PORT) { - dev_err(&pdev->dev, - "Requested more VF's (%d) for port (%d) than allowed (%d)\n", - nvfs[i] + nvfs[2], i + 1, - MLX4_MAX_NUM_VF_P_PORT - 1); - return -EINVAL; - } - } - - - /* - * Check for BARs. - */ - if (!(pci_dev_data & MLX4_PCI_DEV_IS_VF) && - !(pci_resource_flags(pdev, 0) & IORESOURCE_MEM)) { - dev_err(&pdev->dev, "Missing DCS, aborting (driver_data: 0x%x, pci_resource_flags(pdev, 0):0x%lx)\n", - pci_dev_data, pci_resource_flags(pdev, 0)); - err = -ENODEV; - goto err_disable_pdev; - } - if (!(pci_resource_flags(pdev, 2) & IORESOURCE_MEM)) { - dev_err(&pdev->dev, "Missing UAR, aborting\n"); - err = -ENODEV; - goto err_disable_pdev; - } - - err = pci_request_regions(pdev, DRV_NAME); - if (err) { - dev_err(&pdev->dev, "Couldn't get PCI resources, aborting\n"); - goto err_disable_pdev; - } - - pci_set_master(pdev); + dev = &priv->dev; - err = pci_set_dma_mask(pdev, DMA_BIT_MASK(64)); - if (err) { - dev_warn(&pdev->dev, "Warning: couldn't set 64-bit PCI DMA mask\n"); - err = pci_set_dma_mask(pdev, DMA_BIT_MASK(32)); - if (err) { - dev_err(&pdev->dev, "Can't set PCI DMA mask, aborting\n"); - goto err_release_regions; - } - } - err = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(64)); - if (err) { - dev_warn(&pdev->dev, "Warning: couldn't set 64-bit consistent PCI DMA mask\n"); - err = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(32)); - if (err) { - dev_err(&pdev->dev, "Can't set consistent PCI DMA mask, aborting\n"); - goto err_release_regions; - } - } - - /* Allow large DMA segments, up to the firmware limit of 1 GB */ - dma_set_max_seg_size(&pdev->dev, 1024 * 1024 * 1024); - - dev = pci_get_drvdata(pdev); - priv = mlx4_priv(dev); - dev->pdev = pdev; INIT_LIST_HEAD(&priv->ctx_list); spin_lock_init(&priv->ctx_lock); @@ -2382,28 +2284,9 @@ static int __mlx4_init_one(struct pci_dev *pdev, int pci_dev_data) dev->rev_id = pdev->revision; dev->numa_node = dev_to_node(&pdev->dev); + /* Detect if this device is a virtual function */ if (pci_dev_data & MLX4_PCI_DEV_IS_VF) { - /* When acting as pf, we normally skip vfs unless explicitly - * requested to probe them. */ - if (total_vfs) { - unsigned vfs_offset = 0; - for (i = 0; i < sizeof(nvfs)/sizeof(nvfs[0]) && - vfs_offset + nvfs[i] < extended_func_num(pdev); - vfs_offset += nvfs[i], i++) - ; - if (i == sizeof(nvfs)/sizeof(nvfs[0])) { - err = -ENODEV; - goto err_free_dev; - } - if ((extended_func_num(pdev) - vfs_offset) - > prb_vf[i]) { - mlx4_warn(dev, "Skipping virtual function:%d\n", - extended_func_num(pdev)); - err = -ENODEV; - goto err_free_dev; - } - } mlx4_warn(dev, "Detected virtual function - running in slave mode\n"); dev->flags |= MLX4_FLAG_SLAVE; } else { @@ -2413,11 +2296,10 @@ static int __mlx4_init_one(struct pci_dev *pdev, int pci_dev_data) err = mlx4_get_ownership(dev); if (err) { if (err < 0) - goto err_free_dev; + return err; else { mlx4_warn(dev, "Multiple PFs not yet supported - Skipping PF\n"); - err = -EINVAL; - goto err_free_dev; + return -EINVAL; } } @@ -2429,7 +2311,8 @@ static int __mlx4_init_one(struct pci_dev *pdev, int pci_dev_data) GFP_KERNEL); if (NULL == dev->dev_vfs) { mlx4_err(dev, "Failed to allocate memory for VFs\n"); - err = 0; + err = -ENOMEM; + goto err_free_own; } else { atomic_inc(&pf_loading); existing_vfs = pci_num_vf(pdev); @@ -2445,13 +2328,11 @@ static int __mlx4_init_one(struct pci_dev *pdev, int pci_dev_data) mlx4_err(dev, "Failed to enable SR-IOV, continuing without SR-IOV (err = %d)\n", err); atomic_dec(&pf_loading); - err = 0; } else { mlx4_warn(dev, "Running in master mode\n"); dev->flags |= MLX4_FLAG_SRIOV | MLX4_FLAG_MASTER; dev->num_vfs = total_vfs; - sriov_initialized = 1; } } } @@ -2467,7 +2348,7 @@ static int __mlx4_init_one(struct pci_dev *pdev, int pci_dev_data) err = mlx4_reset(dev); if (err) { mlx4_err(dev, "Failed to reset HCA, aborting\n"); - goto err_rel_own; + goto err_sriov; } } @@ -2517,34 +2398,46 @@ slave_start: /* In master functions, the communication channel must be initialized * after obtaining its address from fw */ if (mlx4_is_master(dev)) { - unsigned sum = 0; - err = mlx4_multi_func_init(dev); - if (err) { - mlx4_err(dev, "Failed to init master mfunc interface, aborting\n"); + int ib_ports = 0; + + mlx4_foreach_port(i, dev, MLX4_PORT_TYPE_IB) + ib_ports++; + + if (ib_ports && + (num_vfs_argc > 1 || probe_vfs_argc > 1)) { + mlx4_err(dev, + "Invalid syntax of num_vfs/probe_vfs with IB port - single port VFs syntax is only supported when all ports are configured as ethernet\n"); + err = -EINVAL; + goto err_close; + } + if (dev->caps.num_ports < 2 && + num_vfs_argc > 1) { + err = -EINVAL; + mlx4_err(dev, + "Error: Trying to configure VFs on port 2, but HCA has only %d physical ports\n", + dev->caps.num_ports); goto err_close; } - if (sriov_initialized) { - int ib_ports = 0; - mlx4_foreach_port(i, dev, MLX4_PORT_TYPE_IB) - ib_ports++; + memcpy(dev->nvfs, nvfs, sizeof(dev->nvfs)); - if (ib_ports && - (num_vfs_argc > 1 || probe_vfs_argc > 1)) { - mlx4_err(dev, - "Invalid syntax of num_vfs/probe_vfs with IB port - single port VFs syntax is only supported when all ports are configured as ethernet\n"); - err = -EINVAL; - goto err_master_mfunc; - } - for (i = 0; i < sizeof(nvfs)/sizeof(nvfs[0]); i++) { - unsigned j; - for (j = 0; j < nvfs[i]; ++sum, ++j) { - dev->dev_vfs[sum].min_port = - i < 2 ? i + 1 : 1; - dev->dev_vfs[sum].n_ports = i < 2 ? 1 : - dev->caps.num_ports; - } + for (i = 0; i < sizeof(dev->nvfs)/sizeof(dev->nvfs[0]); i++) { + unsigned j; + + for (j = 0; j < dev->nvfs[i]; ++sum, ++j) { + dev->dev_vfs[sum].min_port = i < 2 ? i + 1 : 1; + dev->dev_vfs[sum].n_ports = i < 2 ? 1 : + dev->caps.num_ports; } } + + /* In master functions, the communication channel + * must be initialized after obtaining its address from fw + */ + err = mlx4_multi_func_init(dev); + if (err) { + mlx4_err(dev, "Failed to init master mfunc interface, aborting.\n"); + goto err_close; + } } err = mlx4_alloc_eq_table(dev); @@ -2565,7 +2458,7 @@ slave_start: if (!mlx4_is_slave(dev)) { err = mlx4_init_steering(dev); if (err) - goto err_free_eq; + goto err_disable_msix; } err = mlx4_setup_hca(dev); @@ -2625,6 +2518,10 @@ err_steer: if (!mlx4_is_slave(dev)) mlx4_clear_steering(dev); +err_disable_msix: + if (dev->flags & MLX4_FLAG_MSI_X) + pci_disable_msix(pdev); + err_free_eq: mlx4_free_eq_table(dev); @@ -2641,9 +2538,6 @@ err_master_mfunc: } err_close: - if (dev->flags & MLX4_FLAG_MSI_X) - pci_disable_msix(pdev); - mlx4_close_hca(dev); err_mfunc: @@ -2657,17 +2551,151 @@ err_sriov: if (dev->flags & MLX4_FLAG_SRIOV && !existing_vfs) pci_disable_sriov(pdev); -err_rel_own: - if (!mlx4_is_slave(dev)) - mlx4_free_ownership(dev); - if (mlx4_is_master(dev) && dev->num_vfs) atomic_dec(&pf_loading); kfree(priv->dev.dev_vfs); -err_free_dev: - kfree(priv); +err_free_own: + if (!mlx4_is_slave(dev)) + mlx4_free_ownership(dev); + + return err; +} + +static int __mlx4_init_one(struct pci_dev *pdev, int pci_dev_data, + struct mlx4_priv *priv) +{ + int err; + int nvfs[MLX4_MAX_PORTS + 1] = {0, 0, 0}; + int prb_vf[MLX4_MAX_PORTS + 1] = {0, 0, 0}; + const int param_map[MLX4_MAX_PORTS + 1][MLX4_MAX_PORTS + 1] = { + {2, 0, 0}, {0, 1, 2}, {0, 1, 2} }; + unsigned total_vfs = 0; + unsigned int i; + + pr_info(DRV_NAME ": Initializing %s\n", pci_name(pdev)); + + err = pci_enable_device(pdev); + if (err) { + dev_err(&pdev->dev, "Cannot enable PCI device, aborting\n"); + return err; + } + + /* Due to requirement that all VFs and the PF are *guaranteed* 2 MACS + * per port, we must limit the number of VFs to 63 (since their are + * 128 MACs) + */ + for (i = 0; i < sizeof(nvfs)/sizeof(nvfs[0]) && i < num_vfs_argc; + total_vfs += nvfs[param_map[num_vfs_argc - 1][i]], i++) { + nvfs[param_map[num_vfs_argc - 1][i]] = num_vfs[i]; + if (nvfs[i] < 0) { + dev_err(&pdev->dev, "num_vfs module parameter cannot be negative\n"); + err = -EINVAL; + goto err_disable_pdev; + } + } + for (i = 0; i < sizeof(prb_vf)/sizeof(prb_vf[0]) && i < probe_vfs_argc; + i++) { + prb_vf[param_map[probe_vfs_argc - 1][i]] = probe_vf[i]; + if (prb_vf[i] < 0 || prb_vf[i] > nvfs[i]) { + dev_err(&pdev->dev, "probe_vf module parameter cannot be negative or greater than num_vfs\n"); + err = -EINVAL; + goto err_disable_pdev; + } + } + if (total_vfs >= MLX4_MAX_NUM_VF) { + dev_err(&pdev->dev, + "Requested more VF's (%d) than allowed (%d)\n", + total_vfs, MLX4_MAX_NUM_VF - 1); + err = -EINVAL; + goto err_disable_pdev; + } + + for (i = 0; i < MLX4_MAX_PORTS; i++) { + if (nvfs[i] + nvfs[2] >= MLX4_MAX_NUM_VF_P_PORT) { + dev_err(&pdev->dev, + "Requested more VF's (%d) for port (%d) than allowed (%d)\n", + nvfs[i] + nvfs[2], i + 1, + MLX4_MAX_NUM_VF_P_PORT - 1); + err = -EINVAL; + goto err_disable_pdev; + } + } + + /* Check for BARs. */ + if (!(pci_dev_data & MLX4_PCI_DEV_IS_VF) && + !(pci_resource_flags(pdev, 0) & IORESOURCE_MEM)) { + dev_err(&pdev->dev, "Missing DCS, aborting (driver_data: 0x%x, pci_resource_flags(pdev, 0):0x%lx)\n", + pci_dev_data, pci_resource_flags(pdev, 0)); + err = -ENODEV; + goto err_disable_pdev; + } + if (!(pci_resource_flags(pdev, 2) & IORESOURCE_MEM)) { + dev_err(&pdev->dev, "Missing UAR, aborting\n"); + err = -ENODEV; + goto err_disable_pdev; + } + + err = pci_request_regions(pdev, DRV_NAME); + if (err) { + dev_err(&pdev->dev, "Couldn't get PCI resources, aborting\n"); + goto err_disable_pdev; + } + + pci_set_master(pdev); + + err = pci_set_dma_mask(pdev, DMA_BIT_MASK(64)); + if (err) { + dev_warn(&pdev->dev, "Warning: couldn't set 64-bit PCI DMA mask\n"); + err = pci_set_dma_mask(pdev, DMA_BIT_MASK(32)); + if (err) { + dev_err(&pdev->dev, "Can't set PCI DMA mask, aborting\n"); + goto err_release_regions; + } + } + err = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(64)); + if (err) { + dev_warn(&pdev->dev, "Warning: couldn't set 64-bit consistent PCI DMA mask\n"); + err = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(32)); + if (err) { + dev_err(&pdev->dev, "Can't set consistent PCI DMA mask, aborting\n"); + goto err_release_regions; + } + } + + /* Allow large DMA segments, up to the firmware limit of 1 GB */ + dma_set_max_seg_size(&pdev->dev, 1024 * 1024 * 1024); + /* Detect if this device is a virtual function */ + if (pci_dev_data & MLX4_PCI_DEV_IS_VF) { + /* When acting as pf, we normally skip vfs unless explicitly + * requested to probe them. + */ + if (total_vfs) { + unsigned vfs_offset = 0; + + for (i = 0; i < sizeof(nvfs)/sizeof(nvfs[0]) && + vfs_offset + nvfs[i] < extended_func_num(pdev); + vfs_offset += nvfs[i], i++) + ; + if (i == sizeof(nvfs)/sizeof(nvfs[0])) { + err = -ENODEV; + goto err_release_regions; + } + if ((extended_func_num(pdev) - vfs_offset) + > prb_vf[i]) { + dev_warn(&pdev->dev, "Skipping virtual function:%d\n", + extended_func_num(pdev)); + err = -ENODEV; + goto err_release_regions; + } + } + } + + err = mlx4_load_one(pdev, pci_dev_data, total_vfs, nvfs, priv); + if (err) + goto err_release_regions; + return 0; err_release_regions: pci_release_regions(pdev); @@ -2682,6 +2710,7 @@ static int mlx4_init_one(struct pci_dev *pdev, const struct pci_device_id *id) { struct mlx4_priv *priv; struct mlx4_dev *dev; + int ret; printk_once(KERN_INFO "%s", mlx4_version); @@ -2690,13 +2719,18 @@ static int mlx4_init_one(struct pci_dev *pdev, const struct pci_device_id *id) return -ENOMEM; dev = &priv->dev; + dev->pdev = pdev; pci_set_drvdata(pdev, dev); priv->pci_dev_data = id->driver_data; - return __mlx4_init_one(pdev, id->driver_data); + ret = __mlx4_init_one(pdev, id->driver_data, priv); + if (ret) + kfree(priv); + + return ret; } -static void __mlx4_remove_one(struct pci_dev *pdev) +static void mlx4_unload_one(struct pci_dev *pdev) { struct mlx4_dev *dev = pci_get_drvdata(pdev); struct mlx4_priv *priv = mlx4_priv(dev); @@ -2775,8 +2809,6 @@ static void __mlx4_remove_one(struct pci_dev *pdev) kfree(dev->caps.qp1_proxy); kfree(dev->dev_vfs); - pci_release_regions(pdev); - pci_disable_device(pdev); memset(priv, 0, sizeof(*priv)); priv->pci_dev_data = pci_dev_data; priv->removed = 1; @@ -2787,7 +2819,9 @@ static void mlx4_remove_one(struct pci_dev *pdev) struct mlx4_dev *dev = pci_get_drvdata(pdev); struct mlx4_priv *priv = mlx4_priv(dev); - __mlx4_remove_one(pdev); + mlx4_unload_one(pdev); + pci_release_regions(pdev); + pci_disable_device(pdev); kfree(priv); pci_set_drvdata(pdev, NULL); } @@ -2796,11 +2830,22 @@ int mlx4_restart_one(struct pci_dev *pdev) { struct mlx4_dev *dev = pci_get_drvdata(pdev); struct mlx4_priv *priv = mlx4_priv(dev); - int pci_dev_data; + int nvfs[MLX4_MAX_PORTS + 1] = {0, 0, 0}; + int pci_dev_data, err, total_vfs; pci_dev_data = priv->pci_dev_data; - __mlx4_remove_one(pdev); - return __mlx4_init_one(pdev, pci_dev_data); + total_vfs = dev->num_vfs; + memcpy(nvfs, dev->nvfs, sizeof(dev->nvfs)); + + mlx4_unload_one(pdev); + err = mlx4_load_one(pdev, pci_dev_data, total_vfs, nvfs, priv); + if (err) { + mlx4_err(dev, "%s: ERROR: mlx4_load_one failed, pci_name=%s, err=%d\n", + __func__, pci_name(pdev), err); + return err; + } + + return err; } static const struct pci_device_id mlx4_pci_table[] = { @@ -2854,7 +2899,7 @@ MODULE_DEVICE_TABLE(pci, mlx4_pci_table); static pci_ers_result_t mlx4_pci_err_detected(struct pci_dev *pdev, pci_channel_state_t state) { - __mlx4_remove_one(pdev); + mlx4_unload_one(pdev); return state == pci_channel_io_perm_failure ? PCI_ERS_RESULT_DISCONNECT : PCI_ERS_RESULT_NEED_RESET; @@ -2866,7 +2911,7 @@ static pci_ers_result_t mlx4_pci_slot_reset(struct pci_dev *pdev) struct mlx4_priv *priv = mlx4_priv(dev); int ret; - ret = __mlx4_init_one(pdev, priv->pci_dev_data); + ret = __mlx4_init_one(pdev, priv->pci_dev_data, priv); return ret ? PCI_ERS_RESULT_DISCONNECT : PCI_ERS_RESULT_RECOVERED; } @@ -2880,7 +2925,7 @@ static struct pci_driver mlx4_driver = { .name = DRV_NAME, .id_table = mlx4_pci_table, .probe = mlx4_init_one, - .shutdown = __mlx4_remove_one, + .shutdown = mlx4_unload_one, .remove = mlx4_remove_one, .err_handler = &mlx4_err_handler, }; diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index 03b5608a4329..b2f8ab9a57c4 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -707,6 +707,7 @@ struct mlx4_dev { u64 regid_promisc_array[MLX4_MAX_PORTS + 1]; u64 regid_allmulti_array[MLX4_MAX_PORTS + 1]; struct mlx4_vf_dev *dev_vfs; + int nvfs[MLX4_MAX_PORTS + 1]; }; struct mlx4_eqe {