From 471f894f106573b0b086d1003ee6172253c67b59 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Thu, 3 Oct 2019 11:49:31 +0200 Subject: net: devlink: export devlink net getter Allow drivers to get net struct for devlink instance. Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/net/devlink.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/net/devlink.h') diff --git a/include/net/devlink.h b/include/net/devlink.h index 23e4b65ec9df..5ac2be0f0857 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -771,6 +771,7 @@ static inline struct devlink *netdev_to_devlink(struct net_device *dev) struct ib_device; +struct net *devlink_net(const struct devlink *devlink); struct devlink *devlink_alloc(const struct devlink_ops *ops, size_t priv_size); int devlink_register(struct devlink *devlink, struct device *dev); void devlink_unregister(struct devlink *devlink); -- cgit v1.2.3 From 070c63f20f6c739a3c534555f56c7327536bfcc2 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Thu, 3 Oct 2019 11:49:39 +0200 Subject: net: devlink: allow to change namespaces during reload All devlink instances are created in init_net and stay there for a lifetime. Allow user to be able to move devlink instances into namespaces during devlink reload operation. That ensures proper re-instantiation of driver objects, including netdevices. Signed-off-by: Jiri Pirko Acked-by: Jakub Kicinski Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx4/main.c | 6 +- drivers/net/ethernet/mellanox/mlxsw/core.c | 1 + drivers/net/netdevsim/dev.c | 2 +- include/net/devlink.h | 2 +- include/uapi/linux/devlink.h | 4 + net/core/devlink.c | 154 +++++++++++++++++++++++++++-- 6 files changed, 158 insertions(+), 11 deletions(-) (limited to 'include/net/devlink.h') diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c index fce9b3a24347..22c72fb7206a 100644 --- a/drivers/net/ethernet/mellanox/mlx4/main.c +++ b/drivers/net/ethernet/mellanox/mlx4/main.c @@ -3935,13 +3935,17 @@ static void mlx4_restart_one_down(struct pci_dev *pdev); static int mlx4_restart_one_up(struct pci_dev *pdev, bool reload, struct devlink *devlink); -static int mlx4_devlink_reload_down(struct devlink *devlink, +static int mlx4_devlink_reload_down(struct devlink *devlink, bool netns_change, struct netlink_ext_ack *extack) { struct mlx4_priv *priv = devlink_priv(devlink); struct mlx4_dev *dev = &priv->dev; struct mlx4_dev_persistent *persist = dev->persist; + if (netns_change) { + NL_SET_ERR_MSG_MOD(extack, "Namespace change is not supported"); + return -EOPNOTSUPP; + } if (persist->num_vfs) mlx4_warn(persist->dev, "Reload performed on PF, will cause reset on operating Virtual Functions\n"); mlx4_restart_one_down(persist->pdev); diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c index 1e61a012ca43..1c29522a2af3 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core.c @@ -985,6 +985,7 @@ mlxsw_devlink_info_get(struct devlink *devlink, struct devlink_info_req *req, static int mlxsw_devlink_core_bus_device_reload_down(struct devlink *devlink, + bool netns_change, struct netlink_ext_ack *extack) { struct mlxsw_core *mlxsw_core = devlink_priv(devlink); diff --git a/drivers/net/netdevsim/dev.c b/drivers/net/netdevsim/dev.c index 7de80faab047..3f3c7cc21077 100644 --- a/drivers/net/netdevsim/dev.c +++ b/drivers/net/netdevsim/dev.c @@ -473,7 +473,7 @@ static int nsim_dev_reload_create(struct nsim_dev *nsim_dev, struct netlink_ext_ack *extack); static void nsim_dev_reload_destroy(struct nsim_dev *nsim_dev); -static int nsim_dev_reload_down(struct devlink *devlink, +static int nsim_dev_reload_down(struct devlink *devlink, bool netns_change, struct netlink_ext_ack *extack) { struct nsim_dev *nsim_dev = devlink_priv(devlink); diff --git a/include/net/devlink.h b/include/net/devlink.h index 5ac2be0f0857..3c9d4a063c98 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -643,7 +643,7 @@ enum devlink_trap_group_generic_id { } struct devlink_ops { - int (*reload_down)(struct devlink *devlink, + int (*reload_down)(struct devlink *devlink, bool netns_change, struct netlink_ext_ack *extack); int (*reload_up)(struct devlink *devlink, struct netlink_ext_ack *extack); diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h index 580b7a2e40e1..b558ea88b766 100644 --- a/include/uapi/linux/devlink.h +++ b/include/uapi/linux/devlink.h @@ -421,6 +421,10 @@ enum devlink_attr { DEVLINK_ATTR_RELOAD_FAILED, /* u8 0 or 1 */ + DEVLINK_ATTR_NETNS_FD, /* u32 */ + DEVLINK_ATTR_NETNS_PID, /* u32 */ + DEVLINK_ATTR_NETNS_ID, /* u32 */ + /* add new attributes above here, update the policy in devlink.c */ __DEVLINK_ATTR_MAX, diff --git a/net/core/devlink.c b/net/core/devlink.c index 362cbbcca225..c4d8c4ab0fb5 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -435,8 +435,16 @@ static void devlink_nl_post_doit(const struct genl_ops *ops, { struct devlink *devlink; - devlink = devlink_get_from_info(info); - if (~ops->internal_flags & DEVLINK_NL_FLAG_NO_LOCK) + /* When devlink changes netns, it would not be found + * by devlink_get_from_info(). So try if it is stored first. + */ + if (ops->internal_flags & DEVLINK_NL_FLAG_NEED_DEVLINK) { + devlink = info->user_ptr[0]; + } else { + devlink = devlink_get_from_info(info); + WARN_ON(IS_ERR(devlink)); + } + if (!IS_ERR(devlink) && ~ops->internal_flags & DEVLINK_NL_FLAG_NO_LOCK) mutex_unlock(&devlink->lock); mutex_unlock(&devlink_mutex); } @@ -2675,6 +2683,72 @@ devlink_resources_validate(struct devlink *devlink, return err; } +static struct net *devlink_netns_get(struct sk_buff *skb, + struct genl_info *info) +{ + struct nlattr *netns_pid_attr = info->attrs[DEVLINK_ATTR_NETNS_PID]; + struct nlattr *netns_fd_attr = info->attrs[DEVLINK_ATTR_NETNS_FD]; + struct nlattr *netns_id_attr = info->attrs[DEVLINK_ATTR_NETNS_ID]; + struct net *net; + + if (!!netns_pid_attr + !!netns_fd_attr + !!netns_id_attr > 1) { + NL_SET_ERR_MSG(info->extack, "multiple netns identifying attributes specified"); + return ERR_PTR(-EINVAL); + } + + if (netns_pid_attr) { + net = get_net_ns_by_pid(nla_get_u32(netns_pid_attr)); + } else if (netns_fd_attr) { + net = get_net_ns_by_fd(nla_get_u32(netns_fd_attr)); + } else if (netns_id_attr) { + net = get_net_ns_by_id(sock_net(skb->sk), + nla_get_u32(netns_id_attr)); + if (!net) + net = ERR_PTR(-EINVAL); + } else { + WARN_ON(1); + net = ERR_PTR(-EINVAL); + } + if (IS_ERR(net)) { + NL_SET_ERR_MSG(info->extack, "Unknown network namespace"); + return ERR_PTR(-EINVAL); + } + if (!netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN)) { + put_net(net); + return ERR_PTR(-EPERM); + } + return net; +} + +static void devlink_param_notify(struct devlink *devlink, + unsigned int port_index, + struct devlink_param_item *param_item, + enum devlink_command cmd); + +static void devlink_reload_netns_change(struct devlink *devlink, + struct net *dest_net) +{ + struct devlink_param_item *param_item; + + /* Userspace needs to be notified about devlink objects + * removed from original and entering new network namespace. + * The rest of the devlink objects are re-created during + * reload process so the notifications are generated separatelly. + */ + + list_for_each_entry(param_item, &devlink->param_list, list) + devlink_param_notify(devlink, 0, param_item, + DEVLINK_CMD_PARAM_DEL); + devlink_notify(devlink, DEVLINK_CMD_DEL); + + devlink_net_set(devlink, dest_net); + + devlink_notify(devlink, DEVLINK_CMD_NEW); + list_for_each_entry(param_item, &devlink->param_list, list) + devlink_param_notify(devlink, 0, param_item, + DEVLINK_CMD_PARAM_NEW); +} + static bool devlink_reload_supported(struct devlink *devlink) { return devlink->ops->reload_down && devlink->ops->reload_up; @@ -2695,9 +2769,27 @@ bool devlink_is_reload_failed(const struct devlink *devlink) } EXPORT_SYMBOL_GPL(devlink_is_reload_failed); +static int devlink_reload(struct devlink *devlink, struct net *dest_net, + struct netlink_ext_ack *extack) +{ + int err; + + err = devlink->ops->reload_down(devlink, !!dest_net, extack); + if (err) + return err; + + if (dest_net && !net_eq(dest_net, devlink_net(devlink))) + devlink_reload_netns_change(devlink, dest_net); + + err = devlink->ops->reload_up(devlink, extack); + devlink_reload_failed_set(devlink, !!err); + return err; +} + static int devlink_nl_cmd_reload(struct sk_buff *skb, struct genl_info *info) { struct devlink *devlink = info->user_ptr[0]; + struct net *dest_net = NULL; int err; if (!devlink_reload_supported(devlink)) @@ -2708,11 +2800,20 @@ static int devlink_nl_cmd_reload(struct sk_buff *skb, struct genl_info *info) NL_SET_ERR_MSG_MOD(info->extack, "resources size validation failed"); return err; } - err = devlink->ops->reload_down(devlink, info->extack); - if (err) - return err; - err = devlink->ops->reload_up(devlink, info->extack); - devlink_reload_failed_set(devlink, !!err); + + if (info->attrs[DEVLINK_ATTR_NETNS_PID] || + info->attrs[DEVLINK_ATTR_NETNS_FD] || + info->attrs[DEVLINK_ATTR_NETNS_ID]) { + dest_net = devlink_netns_get(skb, info); + if (IS_ERR(dest_net)) + return PTR_ERR(dest_net); + } + + err = devlink_reload(devlink, dest_net, info->extack); + + if (dest_net) + put_net(dest_net); + return err; } @@ -5794,6 +5895,9 @@ static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = { [DEVLINK_ATTR_TRAP_NAME] = { .type = NLA_NUL_STRING }, [DEVLINK_ATTR_TRAP_ACTION] = { .type = NLA_U8 }, [DEVLINK_ATTR_TRAP_GROUP_NAME] = { .type = NLA_NUL_STRING }, + [DEVLINK_ATTR_NETNS_PID] = { .type = NLA_U32 }, + [DEVLINK_ATTR_NETNS_FD] = { .type = NLA_U32 }, + [DEVLINK_ATTR_NETNS_ID] = { .type = NLA_U32 }, }; static const struct genl_ops devlink_nl_ops[] = { @@ -8061,9 +8165,43 @@ int devlink_compat_switch_id_get(struct net_device *dev, return 0; } +static void __net_exit devlink_pernet_pre_exit(struct net *net) +{ + struct devlink *devlink; + int err; + + /* In case network namespace is getting destroyed, reload + * all devlink instances from this namespace into init_net. + */ + mutex_lock(&devlink_mutex); + list_for_each_entry(devlink, &devlink_list, list) { + if (net_eq(devlink_net(devlink), net)) { + if (WARN_ON(!devlink_reload_supported(devlink))) + continue; + err = devlink_reload(devlink, &init_net, NULL); + if (err) + pr_warn("Failed to reload devlink instance into init_net\n"); + } + } + mutex_unlock(&devlink_mutex); +} + +static struct pernet_operations devlink_pernet_ops __net_initdata = { + .pre_exit = devlink_pernet_pre_exit, +}; + static int __init devlink_init(void) { - return genl_register_family(&devlink_nl_family); + int err; + + err = genl_register_family(&devlink_nl_family); + if (err) + goto out; + err = register_pernet_subsys(&devlink_pernet_ops); + +out: + WARN_ON(err); + return err; } subsys_initcall(devlink_init); -- cgit v1.2.3 From 8273fd845447820c26b38821c8ac297f40a65260 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Sat, 5 Oct 2019 08:10:31 +0200 Subject: net: devlink: export devlink net setter For newly allocated devlink instance allow drivers to set net struct Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/net/devlink.h | 2 ++ net/core/devlink.c | 15 ++++++++++++--- 2 files changed, 14 insertions(+), 3 deletions(-) (limited to 'include/net/devlink.h') diff --git a/include/net/devlink.h b/include/net/devlink.h index 3c9d4a063c98..4095657fc23f 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -39,6 +39,7 @@ struct devlink { possible_net_t _net; struct mutex lock; bool reload_failed; + bool registered; char priv[0] __aligned(NETDEV_ALIGN); }; @@ -772,6 +773,7 @@ static inline struct devlink *netdev_to_devlink(struct net_device *dev) struct ib_device; struct net *devlink_net(const struct devlink *devlink); +void devlink_net_set(struct devlink *devlink, struct net *net); struct devlink *devlink_alloc(const struct devlink_ops *ops, size_t priv_size); int devlink_register(struct devlink *devlink, struct device *dev); void devlink_unregister(struct devlink *devlink); diff --git a/net/core/devlink.c b/net/core/devlink.c index 0e464d071172..76d835581687 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -101,11 +101,19 @@ struct net *devlink_net(const struct devlink *devlink) } EXPORT_SYMBOL_GPL(devlink_net); -static void devlink_net_set(struct devlink *devlink, struct net *net) +static void __devlink_net_set(struct devlink *devlink, struct net *net) { write_pnet(&devlink->_net, net); } +void devlink_net_set(struct devlink *devlink, struct net *net) +{ + if (WARN_ON(devlink->registered)) + return; + __devlink_net_set(devlink, net); +} +EXPORT_SYMBOL_GPL(devlink_net_set); + static struct devlink *devlink_get_from_attrs(struct net *net, struct nlattr **attrs) { @@ -2750,7 +2758,7 @@ static void devlink_reload_netns_change(struct devlink *devlink, DEVLINK_CMD_PARAM_DEL); devlink_notify(devlink, DEVLINK_CMD_DEL); - devlink_net_set(devlink, dest_net); + __devlink_net_set(devlink, dest_net); devlink_notify(devlink, DEVLINK_CMD_NEW); list_for_each_entry(param_item, &devlink->param_list, list) @@ -6278,7 +6286,7 @@ struct devlink *devlink_alloc(const struct devlink_ops *ops, size_t priv_size) if (!devlink) return NULL; devlink->ops = ops; - devlink_net_set(devlink, &init_net); + __devlink_net_set(devlink, &init_net); INIT_LIST_HEAD(&devlink->port_list); INIT_LIST_HEAD(&devlink->sb_list); INIT_LIST_HEAD_RCU(&devlink->dpipe_table_list); @@ -6304,6 +6312,7 @@ int devlink_register(struct devlink *devlink, struct device *dev) { mutex_lock(&devlink_mutex); devlink->dev = dev; + devlink->registered = true; list_add_tail(&devlink->list, &devlink_list); devlink_notify(devlink, DEVLINK_CMD_NEW); mutex_unlock(&devlink_mutex); -- cgit v1.2.3 From e7a981050a7fb9a14b652365c00d9c5a025704ce Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Thu, 10 Oct 2019 15:18:49 +0200 Subject: devlink: propagate extack down to health reporter ops During health reporter operations, driver might want to fill-up the extack message, so propagate extack down to the health reporter ops. Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c | 9 ++++++--- .../net/ethernet/mellanox/mlx5/core/en/reporter_rx.c | 6 ++++-- .../net/ethernet/mellanox/mlx5/core/en/reporter_tx.c | 6 ++++-- drivers/net/ethernet/mellanox/mlx5/core/health.c | 12 ++++++++---- include/net/devlink.h | 8 +++++--- net/core/devlink.c | 20 +++++++++++--------- 6 files changed, 38 insertions(+), 23 deletions(-) (limited to 'include/net/devlink.h') diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c index e664392dccc0..ff1bc0ec2e7c 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_devlink.c @@ -16,7 +16,8 @@ #include "bnxt_devlink.h" static int bnxt_fw_reporter_diagnose(struct devlink_health_reporter *reporter, - struct devlink_fmsg *fmsg) + struct devlink_fmsg *fmsg, + struct netlink_ext_ack *extack) { struct bnxt *bp = devlink_health_reporter_priv(reporter); struct bnxt_fw_health *health = bp->fw_health; @@ -66,7 +67,8 @@ static const struct devlink_health_reporter_ops bnxt_dl_fw_reporter_ops = { }; static int bnxt_fw_reset_recover(struct devlink_health_reporter *reporter, - void *priv_ctx) + void *priv_ctx, + struct netlink_ext_ack *extack) { struct bnxt *bp = devlink_health_reporter_priv(reporter); @@ -84,7 +86,8 @@ struct devlink_health_reporter_ops bnxt_dl_fw_reset_reporter_ops = { }; static int bnxt_fw_fatal_recover(struct devlink_health_reporter *reporter, - void *priv_ctx) + void *priv_ctx, + struct netlink_ext_ack *extack) { struct bnxt *bp = devlink_health_reporter_priv(reporter); struct bnxt_fw_reporter_ctx *fw_reporter_ctx = priv_ctx; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c index b860569d4247..6c72b592315b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_rx.c @@ -222,7 +222,8 @@ static int mlx5e_rx_reporter_recover_from_ctx(struct mlx5e_err_ctx *err_ctx) } static int mlx5e_rx_reporter_recover(struct devlink_health_reporter *reporter, - void *context) + void *context, + struct netlink_ext_ack *extack) { struct mlx5e_priv *priv = devlink_health_reporter_priv(reporter); struct mlx5e_err_ctx *err_ctx = context; @@ -301,7 +302,8 @@ static int mlx5e_rx_reporter_build_diagnose_output(struct mlx5e_rq *rq, } static int mlx5e_rx_reporter_diagnose(struct devlink_health_reporter *reporter, - struct devlink_fmsg *fmsg) + struct devlink_fmsg *fmsg, + struct netlink_ext_ack *extack) { struct mlx5e_priv *priv = devlink_health_reporter_priv(reporter); struct mlx5e_params *params = &priv->channels.params; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c index bfed558637c2..b468549e96ff 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c @@ -135,7 +135,8 @@ static int mlx5e_tx_reporter_recover_from_ctx(struct mlx5e_err_ctx *err_ctx) } static int mlx5e_tx_reporter_recover(struct devlink_health_reporter *reporter, - void *context) + void *context, + struct netlink_ext_ack *extack) { struct mlx5e_priv *priv = devlink_health_reporter_priv(reporter); struct mlx5e_err_ctx *err_ctx = context; @@ -205,7 +206,8 @@ mlx5e_tx_reporter_build_diagnose_output(struct devlink_fmsg *fmsg, } static int mlx5e_tx_reporter_diagnose(struct devlink_health_reporter *reporter, - struct devlink_fmsg *fmsg) + struct devlink_fmsg *fmsg, + struct netlink_ext_ack *extack) { struct mlx5e_priv *priv = devlink_health_reporter_priv(reporter); struct mlx5e_txqsq *generic_sq = priv->txq2sq[0]; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/health.c b/drivers/net/ethernet/mellanox/mlx5/core/health.c index d685122d9ff7..be3c3c704bfc 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/health.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c @@ -390,7 +390,8 @@ static void print_health_info(struct mlx5_core_dev *dev) static int mlx5_fw_reporter_diagnose(struct devlink_health_reporter *reporter, - struct devlink_fmsg *fmsg) + struct devlink_fmsg *fmsg, + struct netlink_ext_ack *extack) { struct mlx5_core_dev *dev = devlink_health_reporter_priv(reporter); struct mlx5_core_health *health = &dev->priv.health; @@ -491,7 +492,8 @@ mlx5_fw_reporter_heath_buffer_data_put(struct mlx5_core_dev *dev, static int mlx5_fw_reporter_dump(struct devlink_health_reporter *reporter, - struct devlink_fmsg *fmsg, void *priv_ctx) + struct devlink_fmsg *fmsg, void *priv_ctx, + struct netlink_ext_ack *extack) { struct mlx5_core_dev *dev = devlink_health_reporter_priv(reporter); int err; @@ -545,7 +547,8 @@ static const struct devlink_health_reporter_ops mlx5_fw_reporter_ops = { static int mlx5_fw_fatal_reporter_recover(struct devlink_health_reporter *reporter, - void *priv_ctx) + void *priv_ctx, + struct netlink_ext_ack *extack) { struct mlx5_core_dev *dev = devlink_health_reporter_priv(reporter); @@ -555,7 +558,8 @@ mlx5_fw_fatal_reporter_recover(struct devlink_health_reporter *reporter, #define MLX5_CR_DUMP_CHUNK_SIZE 256 static int mlx5_fw_fatal_reporter_dump(struct devlink_health_reporter *reporter, - struct devlink_fmsg *fmsg, void *priv_ctx) + struct devlink_fmsg *fmsg, void *priv_ctx, + struct netlink_ext_ack *extack) { struct mlx5_core_dev *dev = devlink_health_reporter_priv(reporter); u32 crdump_size = dev->priv.health.crdump_size; diff --git a/include/net/devlink.h b/include/net/devlink.h index 4095657fc23f..6bf3b9e0595a 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -507,11 +507,13 @@ enum devlink_health_reporter_state { struct devlink_health_reporter_ops { char *name; int (*recover)(struct devlink_health_reporter *reporter, - void *priv_ctx); + void *priv_ctx, struct netlink_ext_ack *extack); int (*dump)(struct devlink_health_reporter *reporter, - struct devlink_fmsg *fmsg, void *priv_ctx); + struct devlink_fmsg *fmsg, void *priv_ctx, + struct netlink_ext_ack *extack); int (*diagnose)(struct devlink_health_reporter *reporter, - struct devlink_fmsg *fmsg); + struct devlink_fmsg *fmsg, + struct netlink_ext_ack *extack); }; /** diff --git a/net/core/devlink.c b/net/core/devlink.c index 95887462eecf..97e9a2246929 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -4847,7 +4847,7 @@ EXPORT_SYMBOL_GPL(devlink_health_reporter_state_update); static int devlink_health_reporter_recover(struct devlink_health_reporter *reporter, - void *priv_ctx) + void *priv_ctx, struct netlink_ext_ack *extack) { int err; @@ -4857,7 +4857,7 @@ devlink_health_reporter_recover(struct devlink_health_reporter *reporter, if (!reporter->ops->recover) return -EOPNOTSUPP; - err = reporter->ops->recover(reporter, priv_ctx); + err = reporter->ops->recover(reporter, priv_ctx, extack); if (err) return err; @@ -4878,7 +4878,8 @@ devlink_health_dump_clear(struct devlink_health_reporter *reporter) } static int devlink_health_do_dump(struct devlink_health_reporter *reporter, - void *priv_ctx) + void *priv_ctx, + struct netlink_ext_ack *extack) { int err; @@ -4899,7 +4900,7 @@ static int devlink_health_do_dump(struct devlink_health_reporter *reporter, goto dump_err; err = reporter->ops->dump(reporter, reporter->dump_fmsg, - priv_ctx); + priv_ctx, extack); if (err) goto dump_err; @@ -4946,11 +4947,12 @@ int devlink_health_report(struct devlink_health_reporter *reporter, mutex_lock(&reporter->dump_lock); /* store current dump of current error, for later analysis */ - devlink_health_do_dump(reporter, priv_ctx); + devlink_health_do_dump(reporter, priv_ctx, NULL); mutex_unlock(&reporter->dump_lock); if (reporter->auto_recover) - return devlink_health_reporter_recover(reporter, priv_ctx); + return devlink_health_reporter_recover(reporter, + priv_ctx, NULL); return 0; } @@ -5188,7 +5190,7 @@ static int devlink_nl_cmd_health_reporter_recover_doit(struct sk_buff *skb, if (!reporter) return -EINVAL; - err = devlink_health_reporter_recover(reporter, NULL); + err = devlink_health_reporter_recover(reporter, NULL, info->extack); devlink_health_reporter_put(reporter); return err; @@ -5221,7 +5223,7 @@ static int devlink_nl_cmd_health_reporter_diagnose_doit(struct sk_buff *skb, if (err) goto out; - err = reporter->ops->diagnose(reporter, fmsg); + err = reporter->ops->diagnose(reporter, fmsg, info->extack); if (err) goto out; @@ -5256,7 +5258,7 @@ devlink_nl_cmd_health_reporter_dump_get_dumpit(struct sk_buff *skb, } mutex_lock(&reporter->dump_lock); if (!start) { - err = devlink_health_do_dump(reporter, NULL); + err = devlink_health_do_dump(reporter, NULL, cb->extack); if (err) goto unlock; cb->args[1] = reporter->dump_ts; -- cgit v1.2.3 From 6896cc4d8fe6fe6163d6f0baa02a270da68896e8 Mon Sep 17 00:00:00 2001 From: Amit Cohen Date: Thu, 7 Nov 2019 18:42:09 +0200 Subject: devlink: Add layer 3 generic packet traps Add packet traps that can report packets that were dropped during layer 3 forwarding. Signed-off-by: Amit Cohen Acked-by: Jiri Pirko Signed-off-by: Ido Schimmel Signed-off-by: David S. Miller --- Documentation/networking/devlink-trap.rst | 41 +++++++++++++++++++++++++++++++ include/net/devlink.h | 27 ++++++++++++++++++++ net/core/devlink.c | 9 +++++++ 3 files changed, 77 insertions(+) (limited to 'include/net/devlink.h') diff --git a/Documentation/networking/devlink-trap.rst b/Documentation/networking/devlink-trap.rst index 8e90a85f3bd5..dc3dc87217c9 100644 --- a/Documentation/networking/devlink-trap.rst +++ b/Documentation/networking/devlink-trap.rst @@ -162,6 +162,47 @@ be added to the following table: - ``drop`` - Traps packets that the device decided to drop because they could not be enqueued to a transmission queue which is full + * - ``non_ip`` + - ``drop`` + - Traps packets that the device decided to drop because they need to + undergo a layer 3 lookup, but are not IP or MPLS packets + * - ``uc_dip_over_mc_dmac`` + - ``drop`` + - Traps packets that the device decided to drop because they need to be + routed and they have a unicast destination IP and a multicast destination + MAC + * - ``dip_is_loopback_address`` + - ``drop`` + - Traps packets that the device decided to drop because they need to be + routed and their destination IP is the loopback address (i.e., 127.0.0.0/8 + and ::1/128) + * - ``sip_is_mc`` + - ``drop`` + - Traps packets that the device decided to drop because they need to be + routed and their source IP is multicast (i.e., 224.0.0.0/8 and ff::/8) + * - ``sip_is_loopback_address`` + - ``drop`` + - Traps packets that the device decided to drop because they need to be + routed and their source IP is the loopback address (i.e., 127.0.0.0/8 and ::1/128) + * - ``ip_header_corrupted`` + - ``drop`` + - Traps packets that the device decided to drop because they need to be + routed and their IP header is corrupted: wrong checksum, wrong IP version + or too short Internet Header Length (IHL) + * - ``ipv4_sip_is_limited_bc`` + - ``drop`` + - Traps packets that the device decided to drop because they need to be + routed and their source IP is limited broadcast (i.e., 255.255.255.255/32) + * - ``ipv6_mc_dip_reserved_scope`` + - ``drop`` + - Traps IPv6 packets that the device decided to drop because they need to + be routed and their IPv6 multicast destination IP has a reserved scope + (i.e., ffx0::/16) + * - ``ipv6_mc_dip_interface_local_scope`` + - ``drop`` + - Traps IPv6 packets that the device decided to drop because they need to + be routed and their IPv6 multicast destination IP has an interface-local scope + (i.e., ffx1::/16) Driver-specific Packet Traps ============================ diff --git a/include/net/devlink.h b/include/net/devlink.h index 6bf3b9e0595a..df7814d55bf9 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -569,6 +569,15 @@ enum devlink_trap_generic_id { DEVLINK_TRAP_GENERIC_ID_BLACKHOLE_ROUTE, DEVLINK_TRAP_GENERIC_ID_TTL_ERROR, DEVLINK_TRAP_GENERIC_ID_TAIL_DROP, + DEVLINK_TRAP_GENERIC_ID_NON_IP_PACKET, + DEVLINK_TRAP_GENERIC_ID_UC_DIP_MC_DMAC, + DEVLINK_TRAP_GENERIC_ID_DIP_LB, + DEVLINK_TRAP_GENERIC_ID_SIP_MC, + DEVLINK_TRAP_GENERIC_ID_SIP_LB, + DEVLINK_TRAP_GENERIC_ID_CORRUPTED_IP_HDR, + DEVLINK_TRAP_GENERIC_ID_IPV4_SIP_BC, + DEVLINK_TRAP_GENERIC_ID_IPV6_MC_DIP_RESERVED_SCOPE, + DEVLINK_TRAP_GENERIC_ID_IPV6_MC_DIP_INTERFACE_LOCAL_SCOPE, /* Add new generic trap IDs above */ __DEVLINK_TRAP_GENERIC_ID_MAX, @@ -607,6 +616,24 @@ enum devlink_trap_group_generic_id { "ttl_value_is_too_small" #define DEVLINK_TRAP_GENERIC_NAME_TAIL_DROP \ "tail_drop" +#define DEVLINK_TRAP_GENERIC_NAME_NON_IP_PACKET \ + "non_ip" +#define DEVLINK_TRAP_GENERIC_NAME_UC_DIP_MC_DMAC \ + "uc_dip_over_mc_dmac" +#define DEVLINK_TRAP_GENERIC_NAME_DIP_LB \ + "dip_is_loopback_address" +#define DEVLINK_TRAP_GENERIC_NAME_SIP_MC \ + "sip_is_mc" +#define DEVLINK_TRAP_GENERIC_NAME_SIP_LB \ + "sip_is_loopback_address" +#define DEVLINK_TRAP_GENERIC_NAME_CORRUPTED_IP_HDR \ + "ip_header_corrupted" +#define DEVLINK_TRAP_GENERIC_NAME_IPV4_SIP_BC \ + "ipv4_sip_is_limited_bc" +#define DEVLINK_TRAP_GENERIC_NAME_IPV6_MC_DIP_RESERVED_SCOPE \ + "ipv6_mc_dip_reserved_scope" +#define DEVLINK_TRAP_GENERIC_NAME_IPV6_MC_DIP_INTERFACE_LOCAL_SCOPE \ + "ipv6_mc_dip_interface_local_scope" #define DEVLINK_TRAP_GROUP_GENERIC_NAME_L2_DROPS \ "l2_drops" diff --git a/net/core/devlink.c b/net/core/devlink.c index 97e9a2246929..9bbe2162f22f 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -7602,6 +7602,15 @@ static const struct devlink_trap devlink_trap_generic[] = { DEVLINK_TRAP(BLACKHOLE_ROUTE, DROP), DEVLINK_TRAP(TTL_ERROR, EXCEPTION), DEVLINK_TRAP(TAIL_DROP, DROP), + DEVLINK_TRAP(NON_IP_PACKET, DROP), + DEVLINK_TRAP(UC_DIP_MC_DMAC, DROP), + DEVLINK_TRAP(DIP_LB, DROP), + DEVLINK_TRAP(SIP_MC, DROP), + DEVLINK_TRAP(SIP_LB, DROP), + DEVLINK_TRAP(CORRUPTED_IP_HDR, DROP), + DEVLINK_TRAP(IPV4_SIP_BC, DROP), + DEVLINK_TRAP(IPV6_MC_DIP_RESERVED_SCOPE, DROP), + DEVLINK_TRAP(IPV6_MC_DIP_INTERFACE_LOCAL_SCOPE, DROP), }; #define DEVLINK_TRAP_GROUP(_id) \ -- cgit v1.2.3 From 3b063ae57bdfec5e574ace440e6c3f34c4115a92 Mon Sep 17 00:00:00 2001 From: Amit Cohen Date: Thu, 7 Nov 2019 18:42:14 +0200 Subject: devlink: Add layer 3 generic packet exception traps Add layer 3 generic packet exception traps that can report trapped packets and documentation of the traps. Unlike drop traps, these exception traps also need to inject the packet to the kernel's receive path. For example, a packet that was trapped due to unreachable neighbour need to be injected into the kernel so that it will trigger an ARP request or a neighbour solicitation message. Signed-off-by: Amit Cohen Acked-by: Jiri Pirko Signed-off-by: Ido Schimmel Signed-off-by: David S. Miller --- Documentation/networking/devlink-trap.rst | 20 ++++++++++++++++++++ include/net/devlink.h | 18 ++++++++++++++++++ net/core/devlink.c | 6 ++++++ 3 files changed, 44 insertions(+) (limited to 'include/net/devlink.h') diff --git a/Documentation/networking/devlink-trap.rst b/Documentation/networking/devlink-trap.rst index dc3dc87217c9..dc9659ca06fa 100644 --- a/Documentation/networking/devlink-trap.rst +++ b/Documentation/networking/devlink-trap.rst @@ -203,6 +203,26 @@ be added to the following table: - Traps IPv6 packets that the device decided to drop because they need to be routed and their IPv6 multicast destination IP has an interface-local scope (i.e., ffx1::/16) + * - ``mtu_value_is_too_small`` + - ``exception`` + - Traps packets that should have been routed by the device, but were bigger + than the MTU of the egress interface + * - ``unresolved_neigh`` + - ``exception`` + - Traps packets that did not have a matching IP neighbour after routing + * - ``mc_reverse_path_forwarding`` + - ``exception`` + - Traps multicast IP packets that failed reverse-path forwarding (RPF) + check during multicast routing + * - ``reject_route`` + - ``exception`` + - Traps packets that hit reject routes (i.e., "unreachable", "prohibit") + * - ``ipv4_lpm_miss`` + - ``exception`` + - Traps unicast IPv4 packets that did not match any route + * - ``ipv6_lpm_miss`` + - ``exception`` + - Traps unicast IPv6 packets that did not match any route Driver-specific Packet Traps ============================ diff --git a/include/net/devlink.h b/include/net/devlink.h index df7814d55bf9..8d6b5846822c 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -578,6 +578,12 @@ enum devlink_trap_generic_id { DEVLINK_TRAP_GENERIC_ID_IPV4_SIP_BC, DEVLINK_TRAP_GENERIC_ID_IPV6_MC_DIP_RESERVED_SCOPE, DEVLINK_TRAP_GENERIC_ID_IPV6_MC_DIP_INTERFACE_LOCAL_SCOPE, + DEVLINK_TRAP_GENERIC_ID_MTU_ERROR, + DEVLINK_TRAP_GENERIC_ID_UNRESOLVED_NEIGH, + DEVLINK_TRAP_GENERIC_ID_RPF, + DEVLINK_TRAP_GENERIC_ID_REJECT_ROUTE, + DEVLINK_TRAP_GENERIC_ID_IPV4_LPM_UNICAST_MISS, + DEVLINK_TRAP_GENERIC_ID_IPV6_LPM_UNICAST_MISS, /* Add new generic trap IDs above */ __DEVLINK_TRAP_GENERIC_ID_MAX, @@ -634,6 +640,18 @@ enum devlink_trap_group_generic_id { "ipv6_mc_dip_reserved_scope" #define DEVLINK_TRAP_GENERIC_NAME_IPV6_MC_DIP_INTERFACE_LOCAL_SCOPE \ "ipv6_mc_dip_interface_local_scope" +#define DEVLINK_TRAP_GENERIC_NAME_MTU_ERROR \ + "mtu_value_is_too_small" +#define DEVLINK_TRAP_GENERIC_NAME_UNRESOLVED_NEIGH \ + "unresolved_neigh" +#define DEVLINK_TRAP_GENERIC_NAME_RPF \ + "mc_reverse_path_forwarding" +#define DEVLINK_TRAP_GENERIC_NAME_REJECT_ROUTE \ + "reject_route" +#define DEVLINK_TRAP_GENERIC_NAME_IPV4_LPM_UNICAST_MISS \ + "ipv4_lpm_miss" +#define DEVLINK_TRAP_GENERIC_NAME_IPV6_LPM_UNICAST_MISS \ + "ipv6_lpm_miss" #define DEVLINK_TRAP_GROUP_GENERIC_NAME_L2_DROPS \ "l2_drops" diff --git a/net/core/devlink.c b/net/core/devlink.c index 9bbe2162f22f..ff53f7d29dea 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -7611,6 +7611,12 @@ static const struct devlink_trap devlink_trap_generic[] = { DEVLINK_TRAP(IPV4_SIP_BC, DROP), DEVLINK_TRAP(IPV6_MC_DIP_RESERVED_SCOPE, DROP), DEVLINK_TRAP(IPV6_MC_DIP_INTERFACE_LOCAL_SCOPE, DROP), + DEVLINK_TRAP(MTU_ERROR, EXCEPTION), + DEVLINK_TRAP(UNRESOLVED_NEIGH, EXCEPTION), + DEVLINK_TRAP(RPF, EXCEPTION), + DEVLINK_TRAP(REJECT_ROUTE, EXCEPTION), + DEVLINK_TRAP(IPV4_LPM_UNICAST_MISS, EXCEPTION), + DEVLINK_TRAP(IPV6_LPM_UNICAST_MISS, EXCEPTION), }; #define DEVLINK_TRAP_GROUP(_id) \ -- cgit v1.2.3 From a0c76345e3d3dbc40c39de2e00d15a3b7eef7885 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Fri, 8 Nov 2019 21:42:43 +0100 Subject: devlink: disallow reload operation during device cleanup There is a race between driver code that does setup/cleanup of device and devlink reload operation that in some drivers works with the same code. Use after free could we easily obtained by running: while true; do echo 10 > /sys/bus/netdevsim/new_device devlink dev reload netdevsim/netdevsim10 & echo 10 > /sys/bus/netdevsim/del_device done Fix this by enabling reload only after setup of device is complete and disabling it at the beginning of the cleanup process. Reported-by: Ido Schimmel Fixes: 2d8dc5bbf4e7 ("devlink: Add support for reload") Signed-off-by: Jiri Pirko Acked-by: Jakub Kicinski Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx4/main.c | 3 +++ drivers/net/ethernet/mellanox/mlxsw/core.c | 6 ++++- drivers/net/netdevsim/dev.c | 3 +++ include/net/devlink.h | 7 +++-- net/core/devlink.c | 42 +++++++++++++++++++++++++++++- 5 files changed, 57 insertions(+), 4 deletions(-) (limited to 'include/net/devlink.h') diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c index 22c72fb7206a..77f056b0895e 100644 --- a/drivers/net/ethernet/mellanox/mlx4/main.c +++ b/drivers/net/ethernet/mellanox/mlx4/main.c @@ -4015,6 +4015,7 @@ static int mlx4_init_one(struct pci_dev *pdev, const struct pci_device_id *id) goto err_params_unregister; devlink_params_publish(devlink); + devlink_reload_enable(devlink); pci_save_state(pdev); return 0; @@ -4126,6 +4127,8 @@ static void mlx4_remove_one(struct pci_dev *pdev) struct devlink *devlink = priv_to_devlink(priv); int active_vfs = 0; + devlink_reload_disable(devlink); + if (mlx4_is_slave(dev)) persist->interface_state |= MLX4_INTERFACE_STATE_NOWAIT; diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c index e1a90f5bddd0..da436a6aad2f 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core.c @@ -1198,8 +1198,10 @@ __mlxsw_core_bus_device_register(const struct mlxsw_bus_info *mlxsw_bus_info, if (err) goto err_thermal_init; - if (mlxsw_driver->params_register) + if (mlxsw_driver->params_register) { devlink_params_publish(devlink); + devlink_reload_enable(devlink); + } return 0; @@ -1263,6 +1265,8 @@ void mlxsw_core_bus_device_unregister(struct mlxsw_core *mlxsw_core, { struct devlink *devlink = priv_to_devlink(mlxsw_core); + if (!reload) + devlink_reload_disable(devlink); if (devlink_is_reload_failed(devlink)) { if (!reload) /* Only the parts that were not de-initialized in the diff --git a/drivers/net/netdevsim/dev.c b/drivers/net/netdevsim/dev.c index 3da96c7e8265..059711edfc61 100644 --- a/drivers/net/netdevsim/dev.c +++ b/drivers/net/netdevsim/dev.c @@ -820,6 +820,7 @@ int nsim_dev_probe(struct nsim_bus_dev *nsim_bus_dev) goto err_bpf_dev_exit; devlink_params_publish(devlink); + devlink_reload_enable(devlink); return 0; err_bpf_dev_exit: @@ -865,6 +866,8 @@ void nsim_dev_remove(struct nsim_bus_dev *nsim_bus_dev) struct nsim_dev *nsim_dev = dev_get_drvdata(&nsim_bus_dev->dev); struct devlink *devlink = priv_to_devlink(nsim_dev); + devlink_reload_disable(devlink); + nsim_dev_reload_destroy(nsim_dev); nsim_bpf_dev_exit(nsim_dev); diff --git a/include/net/devlink.h b/include/net/devlink.h index 8d6b5846822c..7891611868e4 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -38,8 +38,9 @@ struct devlink { struct device *dev; possible_net_t _net; struct mutex lock; - bool reload_failed; - bool registered; + u8 reload_failed:1, + reload_enabled:1, + registered:1; char priv[0] __aligned(NETDEV_ALIGN); }; @@ -824,6 +825,8 @@ void devlink_net_set(struct devlink *devlink, struct net *net); struct devlink *devlink_alloc(const struct devlink_ops *ops, size_t priv_size); int devlink_register(struct devlink *devlink, struct device *dev); void devlink_unregister(struct devlink *devlink); +void devlink_reload_enable(struct devlink *devlink); +void devlink_reload_disable(struct devlink *devlink); void devlink_free(struct devlink *devlink); int devlink_port_register(struct devlink *devlink, struct devlink_port *devlink_port, diff --git a/net/core/devlink.c b/net/core/devlink.c index ff53f7d29dea..2e027c9436e0 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -2791,6 +2791,9 @@ static int devlink_reload(struct devlink *devlink, struct net *dest_net, { int err; + if (!devlink->reload_enabled) + return -EOPNOTSUPP; + err = devlink->ops->reload_down(devlink, !!dest_net, extack); if (err) return err; @@ -6308,12 +6311,49 @@ EXPORT_SYMBOL_GPL(devlink_register); void devlink_unregister(struct devlink *devlink) { mutex_lock(&devlink_mutex); + WARN_ON(devlink_reload_supported(devlink) && + devlink->reload_enabled); devlink_notify(devlink, DEVLINK_CMD_DEL); list_del(&devlink->list); mutex_unlock(&devlink_mutex); } EXPORT_SYMBOL_GPL(devlink_unregister); +/** + * devlink_reload_enable - Enable reload of devlink instance + * + * @devlink: devlink + * + * Should be called at end of device initialization + * process when reload operation is supported. + */ +void devlink_reload_enable(struct devlink *devlink) +{ + mutex_lock(&devlink_mutex); + devlink->reload_enabled = true; + mutex_unlock(&devlink_mutex); +} +EXPORT_SYMBOL_GPL(devlink_reload_enable); + +/** + * devlink_reload_disable - Disable reload of devlink instance + * + * @devlink: devlink + * + * Should be called at the beginning of device cleanup + * process when reload operation is supported. + */ +void devlink_reload_disable(struct devlink *devlink) +{ + mutex_lock(&devlink_mutex); + /* Mutex is taken which ensures that no reload operation is in + * progress while setting up forbidded flag. + */ + devlink->reload_enabled = false; + mutex_unlock(&devlink_mutex); +} +EXPORT_SYMBOL_GPL(devlink_reload_disable); + /** * devlink_free - Free devlink instance resources * @@ -8201,7 +8241,7 @@ static void __net_exit devlink_pernet_pre_exit(struct net *net) if (WARN_ON(!devlink_reload_supported(devlink))) continue; err = devlink_reload(devlink, &init_net, NULL); - if (err) + if (err && err != -EOPNOTSUPP) pr_warn("Failed to reload devlink instance into init_net\n"); } } -- cgit v1.2.3 From 6c7295e13ffd5623b02f1adc1442f1d8a3d52424 Mon Sep 17 00:00:00 2001 From: Michael Guralnik Date: Fri, 8 Nov 2019 23:45:20 +0000 Subject: devlink: Add new "enable_roce" generic device param New device parameter to enable/disable handling of RoCE traffic in the device. Signed-off-by: Michael Guralnik Acked-by: Jiri Pirko Reviewed-by: Maor Gottlieb Signed-off-by: Saeed Mahameed --- Documentation/networking/devlink-params.txt | 4 ++++ include/net/devlink.h | 4 ++++ net/core/devlink.c | 5 +++++ 3 files changed, 13 insertions(+) (limited to 'include/net/devlink.h') diff --git a/Documentation/networking/devlink-params.txt b/Documentation/networking/devlink-params.txt index ddba3e9b55b1..04e234e9acc9 100644 --- a/Documentation/networking/devlink-params.txt +++ b/Documentation/networking/devlink-params.txt @@ -65,3 +65,7 @@ reset_dev_on_drv_probe [DEVICE, GENERIC] Reset only if device firmware can be found in the filesystem. Type: u8 + +enable_roce [DEVICE, GENERIC] + Enable handling of RoCE traffic in the device. + Type: Boolean diff --git a/include/net/devlink.h b/include/net/devlink.h index 23e4b65ec9df..39fb4d957838 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -400,6 +400,7 @@ enum devlink_param_generic_id { DEVLINK_PARAM_GENERIC_ID_MSIX_VEC_PER_PF_MIN, DEVLINK_PARAM_GENERIC_ID_FW_LOAD_POLICY, DEVLINK_PARAM_GENERIC_ID_RESET_DEV_ON_DRV_PROBE, + DEVLINK_PARAM_GENERIC_ID_ENABLE_ROCE, /* add new param generic ids above here*/ __DEVLINK_PARAM_GENERIC_ID_MAX, @@ -434,6 +435,9 @@ enum devlink_param_generic_id { "reset_dev_on_drv_probe" #define DEVLINK_PARAM_GENERIC_RESET_DEV_ON_DRV_PROBE_TYPE DEVLINK_PARAM_TYPE_U8 +#define DEVLINK_PARAM_GENERIC_ENABLE_ROCE_NAME "enable_roce" +#define DEVLINK_PARAM_GENERIC_ENABLE_ROCE_TYPE DEVLINK_PARAM_TYPE_BOOL + #define DEVLINK_PARAM_GENERIC(_id, _cmodes, _get, _set, _validate) \ { \ .id = DEVLINK_PARAM_GENERIC_ID_##_id, \ diff --git a/net/core/devlink.c b/net/core/devlink.c index f80151eeaf51..0fbcd44aa64f 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -2884,6 +2884,11 @@ static const struct devlink_param devlink_param_generic[] = { .name = DEVLINK_PARAM_GENERIC_RESET_DEV_ON_DRV_PROBE_NAME, .type = DEVLINK_PARAM_GENERIC_RESET_DEV_ON_DRV_PROBE_TYPE, }, + { + .id = DEVLINK_PARAM_GENERIC_ID_ENABLE_ROCE, + .name = DEVLINK_PARAM_GENERIC_ENABLE_ROCE_NAME, + .type = DEVLINK_PARAM_GENERIC_ENABLE_ROCE_TYPE, + }, }; static int devlink_param_generic_verify(const struct devlink_param *param) -- cgit v1.2.3 From e2cde864a1d3e3626bfc8fa088fbc82b04ce66ed Mon Sep 17 00:00:00 2001 From: Aya Levin Date: Tue, 12 Nov 2019 14:07:49 +0200 Subject: devlink: Allow large formatted message of binary output Devlink supports pair output of name and value. When the value is binary, it must be presented in an array. If the length of the binary value exceeds fmsg limitation, break the value into chunks internally. Signed-off-by: Aya Levin Acked-by: Jiri Pirko Signed-off-by: David S. Miller --- include/net/devlink.h | 4 +--- net/core/devlink.c | 24 +++++++++++++++--------- 2 files changed, 16 insertions(+), 12 deletions(-) (limited to 'include/net/devlink.h') diff --git a/include/net/devlink.h b/include/net/devlink.h index 7891611868e4..7e72b2e71164 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -967,8 +967,6 @@ int devlink_fmsg_u8_put(struct devlink_fmsg *fmsg, u8 value); int devlink_fmsg_u32_put(struct devlink_fmsg *fmsg, u32 value); int devlink_fmsg_u64_put(struct devlink_fmsg *fmsg, u64 value); int devlink_fmsg_string_put(struct devlink_fmsg *fmsg, const char *value); -int devlink_fmsg_binary_put(struct devlink_fmsg *fmsg, const void *value, - u16 value_len); int devlink_fmsg_bool_pair_put(struct devlink_fmsg *fmsg, const char *name, bool value); @@ -981,7 +979,7 @@ int devlink_fmsg_u64_pair_put(struct devlink_fmsg *fmsg, const char *name, int devlink_fmsg_string_pair_put(struct devlink_fmsg *fmsg, const char *name, const char *value); int devlink_fmsg_binary_pair_put(struct devlink_fmsg *fmsg, const char *name, - const void *value, u16 value_len); + const void *value, u32 value_len); struct devlink_health_reporter * devlink_health_reporter_create(struct devlink *devlink, diff --git a/net/core/devlink.c b/net/core/devlink.c index 2e027c9436e0..9bad78388a07 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -4414,12 +4414,11 @@ int devlink_fmsg_string_put(struct devlink_fmsg *fmsg, const char *value) } EXPORT_SYMBOL_GPL(devlink_fmsg_string_put); -int devlink_fmsg_binary_put(struct devlink_fmsg *fmsg, const void *value, - u16 value_len) +static int devlink_fmsg_binary_put(struct devlink_fmsg *fmsg, const void *value, + u16 value_len) { return devlink_fmsg_put_value(fmsg, value, value_len, NLA_BINARY); } -EXPORT_SYMBOL_GPL(devlink_fmsg_binary_put); int devlink_fmsg_bool_pair_put(struct devlink_fmsg *fmsg, const char *name, bool value) @@ -4527,19 +4526,26 @@ int devlink_fmsg_string_pair_put(struct devlink_fmsg *fmsg, const char *name, EXPORT_SYMBOL_GPL(devlink_fmsg_string_pair_put); int devlink_fmsg_binary_pair_put(struct devlink_fmsg *fmsg, const char *name, - const void *value, u16 value_len) + const void *value, u32 value_len) { + u32 data_size; + u32 offset; int err; - err = devlink_fmsg_pair_nest_start(fmsg, name); + err = devlink_fmsg_arr_pair_nest_start(fmsg, name); if (err) return err; - err = devlink_fmsg_binary_put(fmsg, value, value_len); - if (err) - return err; + for (offset = 0; offset < value_len; offset += data_size) { + data_size = value_len - offset; + if (data_size > DEVLINK_FMSG_MAX_SIZE) + data_size = DEVLINK_FMSG_MAX_SIZE; + err = devlink_fmsg_binary_put(fmsg, value + offset, data_size); + if (err) + return err; + } - err = devlink_fmsg_pair_nest_end(fmsg); + err = devlink_fmsg_arr_pair_nest_end(fmsg); if (err) return err; -- cgit v1.2.3