From 3a5e523479c49b082b8ac291a1a9fbd035c06df5 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Fri, 9 Aug 2019 15:27:15 +0200 Subject: devlink: remove pointless data_len arg from region snapshot create The size of the snapshot has to be the same as the size of the region, therefore no need to pass it again during snapshot creation. Remove the arg and use region->size instead. Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- include/net/devlink.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include/net/devlink.h') diff --git a/include/net/devlink.h b/include/net/devlink.h index bc36f942a7d5..451268f64880 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -702,7 +702,7 @@ struct devlink_region *devlink_region_create(struct devlink *devlink, u64 region_size); void devlink_region_destroy(struct devlink_region *region); u32 devlink_region_shapshot_id_get(struct devlink *devlink); -int devlink_region_snapshot_create(struct devlink_region *region, u64 data_len, +int devlink_region_snapshot_create(struct devlink_region *region, u8 *data, u32 snapshot_id, devlink_snapshot_data_dest_t *data_destructor); int devlink_info_serial_number_put(struct devlink_info_req *req, -- cgit v1.2.3 From 0f420b6c52e9799f664429e739a421fb4c5527a3 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Sat, 17 Aug 2019 16:28:17 +0300 Subject: devlink: Add packet trap infrastructure Add the basic packet trap infrastructure that allows device drivers to register their supported packet traps and trap groups with devlink. Each driver is expected to provide basic information about each supported trap, such as name and ID, but also the supported metadata types that will accompany each packet trapped via the trap. The currently supported metadata type is just the input port, but more will be added in the future. For example, output port and traffic class. Trap groups allow users to set the action of all member traps. In addition, users can retrieve per-group statistics in case per-trap statistics are too narrow. In the future, the trap group object can be extended with more attributes, such as policer settings which will limit the amount of traffic generated by member traps towards the CPU. Beside registering their packet traps with devlink, drivers are also expected to report trapped packets to devlink along with relevant metadata. devlink will maintain packets and bytes statistics for each packet trap and will potentially report the trapped packet with its metadata to user space via drop monitor netlink channel. The interface towards the drivers is simple and allows devlink to set the action of the trap. Currently, only two actions are supported: 'trap' and 'drop'. When set to 'trap', the device is expected to provide the sole copy of the packet to the driver which will pass it to devlink. When set to 'drop', the device is expected to drop the packet and not send a copy to the driver. In the future, more actions can be added, such as 'mirror'. Signed-off-by: Ido Schimmel Acked-by: Jiri Pirko Signed-off-by: David S. Miller --- include/net/devlink.h | 129 +++++ include/uapi/linux/devlink.h | 62 +++ net/Kconfig | 1 + net/core/devlink.c | 1068 +++++++++++++++++++++++++++++++++++++++++- 4 files changed, 1255 insertions(+), 5 deletions(-) (limited to 'include/net/devlink.h') diff --git a/include/net/devlink.h b/include/net/devlink.h index 451268f64880..03b32e33e93e 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -14,6 +14,7 @@ #include #include #include +#include #include #include @@ -31,6 +32,8 @@ struct devlink { struct list_head reporter_list; struct mutex reporters_lock; /* protects reporter_list */ struct devlink_dpipe_headers *dpipe_headers; + struct list_head trap_list; + struct list_head trap_group_list; const struct devlink_ops *ops; struct device *dev; possible_net_t _net; @@ -497,6 +500,89 @@ struct devlink_health_reporter_ops { struct devlink_fmsg *fmsg); }; +/** + * struct devlink_trap_group - Immutable packet trap group attributes. + * @name: Trap group name. + * @id: Trap group identifier. + * @generic: Whether the trap group is generic or not. + * + * Describes immutable attributes of packet trap groups that drivers register + * with devlink. + */ +struct devlink_trap_group { + const char *name; + u16 id; + bool generic; +}; + +#define DEVLINK_TRAP_METADATA_TYPE_F_IN_PORT BIT(0) + +/** + * struct devlink_trap - Immutable packet trap attributes. + * @type: Trap type. + * @init_action: Initial trap action. + * @generic: Whether the trap is generic or not. + * @id: Trap identifier. + * @name: Trap name. + * @group: Immutable packet trap group attributes. + * @metadata_cap: Metadata types that can be provided by the trap. + * + * Describes immutable attributes of packet traps that drivers register with + * devlink. + */ +struct devlink_trap { + enum devlink_trap_type type; + enum devlink_trap_action init_action; + bool generic; + u16 id; + const char *name; + struct devlink_trap_group group; + u32 metadata_cap; +}; + +enum devlink_trap_generic_id { + /* Add new generic trap IDs above */ + __DEVLINK_TRAP_GENERIC_ID_MAX, + DEVLINK_TRAP_GENERIC_ID_MAX = __DEVLINK_TRAP_GENERIC_ID_MAX - 1, +}; + +enum devlink_trap_group_generic_id { + /* Add new generic trap group IDs above */ + __DEVLINK_TRAP_GROUP_GENERIC_ID_MAX, + DEVLINK_TRAP_GROUP_GENERIC_ID_MAX = + __DEVLINK_TRAP_GROUP_GENERIC_ID_MAX - 1, +}; + +#define DEVLINK_TRAP_GENERIC(_type, _init_action, _id, _group, _metadata_cap) \ + { \ + .type = DEVLINK_TRAP_TYPE_##_type, \ + .init_action = DEVLINK_TRAP_ACTION_##_init_action, \ + .generic = true, \ + .id = DEVLINK_TRAP_GENERIC_ID_##_id, \ + .name = DEVLINK_TRAP_GENERIC_NAME_##_id, \ + .group = _group, \ + .metadata_cap = _metadata_cap, \ + } + +#define DEVLINK_TRAP_DRIVER(_type, _init_action, _id, _name, _group, \ + _metadata_cap) \ + { \ + .type = DEVLINK_TRAP_TYPE_##_type, \ + .init_action = DEVLINK_TRAP_ACTION_##_init_action, \ + .generic = false, \ + .id = _id, \ + .name = _name, \ + .group = _group, \ + .metadata_cap = _metadata_cap, \ + } + +#define DEVLINK_TRAP_GROUP_GENERIC(_id) \ + { \ + .name = DEVLINK_TRAP_GROUP_GENERIC_NAME_##_id, \ + .id = DEVLINK_TRAP_GROUP_GENERIC_ID_##_id, \ + .generic = true, \ + } + struct devlink_ops { int (*reload)(struct devlink *devlink, struct netlink_ext_ack *extack); int (*port_type_set)(struct devlink_port *devlink_port, @@ -558,6 +644,38 @@ struct devlink_ops { int (*flash_update)(struct devlink *devlink, const char *file_name, const char *component, struct netlink_ext_ack *extack); + /** + * @trap_init: Trap initialization function. + * + * Should be used by device drivers to initialize the trap in the + * underlying device. Drivers should also store the provided trap + * context, so that they could efficiently pass it to + * devlink_trap_report() when the trap is triggered. + */ + int (*trap_init)(struct devlink *devlink, + const struct devlink_trap *trap, void *trap_ctx); + /** + * @trap_fini: Trap de-initialization function. + * + * Should be used by device drivers to de-initialize the trap in the + * underlying device. + */ + void (*trap_fini)(struct devlink *devlink, + const struct devlink_trap *trap, void *trap_ctx); + /** + * @trap_action_set: Trap action set function. + */ + int (*trap_action_set)(struct devlink *devlink, + const struct devlink_trap *trap, + enum devlink_trap_action action); + /** + * @trap_group_init: Trap group initialization function. + * + * Should be used by device drivers to initialize the trap group in the + * underlying device. + */ + int (*trap_group_init)(struct devlink *devlink, + const struct devlink_trap_group *group); }; static inline void *devlink_priv(struct devlink *devlink) @@ -774,6 +892,17 @@ void devlink_flash_update_status_notify(struct devlink *devlink, unsigned long done, unsigned long total); +int devlink_traps_register(struct devlink *devlink, + const struct devlink_trap *traps, + size_t traps_count, void *priv); +void devlink_traps_unregister(struct devlink *devlink, + const struct devlink_trap *traps, + size_t traps_count); +void devlink_trap_report(struct devlink *devlink, + struct sk_buff *skb, void *trap_ctx, + struct devlink_port *in_devlink_port); +void *devlink_trap_ctx_priv(void *trap_ctx); + #if IS_ENABLED(CONFIG_NET_DEVLINK) void devlink_compat_running_version(struct net_device *dev, diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h index ffc993256527..546e75dd74ac 100644 --- a/include/uapi/linux/devlink.h +++ b/include/uapi/linux/devlink.h @@ -107,6 +107,16 @@ enum devlink_command { DEVLINK_CMD_FLASH_UPDATE_END, /* notification only */ DEVLINK_CMD_FLASH_UPDATE_STATUS, /* notification only */ + DEVLINK_CMD_TRAP_GET, /* can dump */ + DEVLINK_CMD_TRAP_SET, + DEVLINK_CMD_TRAP_NEW, + DEVLINK_CMD_TRAP_DEL, + + DEVLINK_CMD_TRAP_GROUP_GET, /* can dump */ + DEVLINK_CMD_TRAP_GROUP_SET, + DEVLINK_CMD_TRAP_GROUP_NEW, + DEVLINK_CMD_TRAP_GROUP_DEL, + /* add new commands above here */ __DEVLINK_CMD_MAX, DEVLINK_CMD_MAX = __DEVLINK_CMD_MAX - 1 @@ -194,6 +204,47 @@ enum devlink_param_fw_load_policy_value { DEVLINK_PARAM_FW_LOAD_POLICY_VALUE_FLASH, }; +enum { + DEVLINK_ATTR_STATS_RX_PACKETS, /* u64 */ + DEVLINK_ATTR_STATS_RX_BYTES, /* u64 */ + + __DEVLINK_ATTR_STATS_MAX, + DEVLINK_ATTR_STATS_MAX = __DEVLINK_ATTR_STATS_MAX - 1 +}; + +/** + * enum devlink_trap_action - Packet trap action. + * @DEVLINK_TRAP_ACTION_DROP: Packet is dropped by the device and a copy is not + * sent to the CPU. + * @DEVLINK_TRAP_ACTION_TRAP: The sole copy of the packet is sent to the CPU. + */ +enum devlink_trap_action { + DEVLINK_TRAP_ACTION_DROP, + DEVLINK_TRAP_ACTION_TRAP, +}; + +/** + * enum devlink_trap_type - Packet trap type. + * @DEVLINK_TRAP_TYPE_DROP: Trap reason is a drop. Trapped packets are only + * processed by devlink and not injected to the + * kernel's Rx path. + * @DEVLINK_TRAP_TYPE_EXCEPTION: Trap reason is an exception. Packet was not + * forwarded as intended due to an exception + * (e.g., missing neighbour entry) and trapped to + * control plane for resolution. Trapped packets + * are processed by devlink and injected to + * the kernel's Rx path. + */ +enum devlink_trap_type { + DEVLINK_TRAP_TYPE_DROP, + DEVLINK_TRAP_TYPE_EXCEPTION, +}; + +enum { + /* Trap can report input port as metadata */ + DEVLINK_ATTR_TRAP_METADATA_TYPE_IN_PORT, +}; + enum devlink_attr { /* don't change the order or add anything between, this is ABI! */ DEVLINK_ATTR_UNSPEC, @@ -348,6 +399,17 @@ enum devlink_attr { DEVLINK_ATTR_PORT_PCI_PF_NUMBER, /* u16 */ DEVLINK_ATTR_PORT_PCI_VF_NUMBER, /* u16 */ + DEVLINK_ATTR_STATS, /* nested */ + + DEVLINK_ATTR_TRAP_NAME, /* string */ + /* enum devlink_trap_action */ + DEVLINK_ATTR_TRAP_ACTION, /* u8 */ + /* enum devlink_trap_type */ + DEVLINK_ATTR_TRAP_TYPE, /* u8 */ + DEVLINK_ATTR_TRAP_GENERIC, /* flag */ + DEVLINK_ATTR_TRAP_METADATA, /* nested */ + DEVLINK_ATTR_TRAP_GROUP_NAME, /* string */ + /* add new attributes above here, update the policy in devlink.c */ __DEVLINK_ATTR_MAX, diff --git a/net/Kconfig b/net/Kconfig index 57f51a279ad6..3101bfcbdd7a 100644 --- a/net/Kconfig +++ b/net/Kconfig @@ -430,6 +430,7 @@ config NET_SOCK_MSG config NET_DEVLINK bool default n + imply NET_DROP_MONITOR config PAGE_POOL bool diff --git a/net/core/devlink.c b/net/core/devlink.c index d3dbb904bf3b..960ceaec98d6 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -18,6 +18,8 @@ #include #include #include +#include +#include #include #include #include @@ -25,6 +27,7 @@ #include #include #include +#include #define CREATE_TRACE_POINTS #include @@ -551,7 +554,7 @@ static int devlink_nl_port_fill(struct sk_buff *msg, struct devlink *devlink, if (nla_put_u32(msg, DEVLINK_ATTR_PORT_INDEX, devlink_port->index)) goto nla_put_failure; - spin_lock(&devlink_port->type_lock); + spin_lock_bh(&devlink_port->type_lock); if (nla_put_u16(msg, DEVLINK_ATTR_PORT_TYPE, devlink_port->type)) goto nla_put_failure_type_locked; if (devlink_port->desired_type != DEVLINK_PORT_TYPE_NOTSET && @@ -576,7 +579,7 @@ static int devlink_nl_port_fill(struct sk_buff *msg, struct devlink *devlink, ibdev->name)) goto nla_put_failure_type_locked; } - spin_unlock(&devlink_port->type_lock); + spin_unlock_bh(&devlink_port->type_lock); if (devlink_nl_port_attrs_put(msg, devlink_port)) goto nla_put_failure; @@ -584,7 +587,7 @@ static int devlink_nl_port_fill(struct sk_buff *msg, struct devlink *devlink, return 0; nla_put_failure_type_locked: - spin_unlock(&devlink_port->type_lock); + spin_unlock_bh(&devlink_port->type_lock); nla_put_failure: genlmsg_cancel(msg, hdr); return -EMSGSIZE; @@ -5154,6 +5157,571 @@ devlink_nl_cmd_health_reporter_dump_clear_doit(struct sk_buff *skb, return 0; } +struct devlink_stats { + u64 rx_bytes; + u64 rx_packets; + struct u64_stats_sync syncp; +}; + +/** + * struct devlink_trap_group_item - Packet trap group attributes. + * @group: Immutable packet trap group attributes. + * @refcount: Number of trap items using the group. + * @list: trap_group_list member. + * @stats: Trap group statistics. + * + * Describes packet trap group attributes. Created by devlink during trap + * registration. + */ +struct devlink_trap_group_item { + const struct devlink_trap_group *group; + refcount_t refcount; + struct list_head list; + struct devlink_stats __percpu *stats; +}; + +/** + * struct devlink_trap_item - Packet trap attributes. + * @trap: Immutable packet trap attributes. + * @group_item: Associated group item. + * @list: trap_list member. + * @action: Trap action. + * @stats: Trap statistics. + * @priv: Driver private information. + * + * Describes both mutable and immutable packet trap attributes. Created by + * devlink during trap registration and used for all trap related operations. + */ +struct devlink_trap_item { + const struct devlink_trap *trap; + struct devlink_trap_group_item *group_item; + struct list_head list; + enum devlink_trap_action action; + struct devlink_stats __percpu *stats; + void *priv; +}; + +static struct devlink_trap_item * +devlink_trap_item_lookup(struct devlink *devlink, const char *name) +{ + struct devlink_trap_item *trap_item; + + list_for_each_entry(trap_item, &devlink->trap_list, list) { + if (!strcmp(trap_item->trap->name, name)) + return trap_item; + } + + return NULL; +} + +static struct devlink_trap_item * +devlink_trap_item_get_from_info(struct devlink *devlink, + struct genl_info *info) +{ + struct nlattr *attr; + + if (!info->attrs[DEVLINK_ATTR_TRAP_NAME]) + return NULL; + attr = info->attrs[DEVLINK_ATTR_TRAP_NAME]; + + return devlink_trap_item_lookup(devlink, nla_data(attr)); +} + +static int +devlink_trap_action_get_from_info(struct genl_info *info, + enum devlink_trap_action *p_trap_action) +{ + u8 val; + + val = nla_get_u8(info->attrs[DEVLINK_ATTR_TRAP_ACTION]); + switch (val) { + case DEVLINK_TRAP_ACTION_DROP: /* fall-through */ + case DEVLINK_TRAP_ACTION_TRAP: + *p_trap_action = val; + break; + default: + return -EINVAL; + } + + return 0; +} + +static int devlink_trap_metadata_put(struct sk_buff *msg, + const struct devlink_trap *trap) +{ + struct nlattr *attr; + + attr = nla_nest_start(msg, DEVLINK_ATTR_TRAP_METADATA); + if (!attr) + return -EMSGSIZE; + + if ((trap->metadata_cap & DEVLINK_TRAP_METADATA_TYPE_F_IN_PORT) && + nla_put_flag(msg, DEVLINK_ATTR_TRAP_METADATA_TYPE_IN_PORT)) + goto nla_put_failure; + + nla_nest_end(msg, attr); + + return 0; + +nla_put_failure: + nla_nest_cancel(msg, attr); + return -EMSGSIZE; +} + +static void devlink_trap_stats_read(struct devlink_stats __percpu *trap_stats, + struct devlink_stats *stats) +{ + int i; + + memset(stats, 0, sizeof(*stats)); + for_each_possible_cpu(i) { + struct devlink_stats *cpu_stats; + u64 rx_packets, rx_bytes; + unsigned int start; + + cpu_stats = per_cpu_ptr(trap_stats, i); + do { + start = u64_stats_fetch_begin_irq(&cpu_stats->syncp); + rx_packets = cpu_stats->rx_packets; + rx_bytes = cpu_stats->rx_bytes; + } while (u64_stats_fetch_retry_irq(&cpu_stats->syncp, start)); + + stats->rx_packets += rx_packets; + stats->rx_bytes += rx_bytes; + } +} + +static int devlink_trap_stats_put(struct sk_buff *msg, + struct devlink_stats __percpu *trap_stats) +{ + struct devlink_stats stats; + struct nlattr *attr; + + devlink_trap_stats_read(trap_stats, &stats); + + attr = nla_nest_start(msg, DEVLINK_ATTR_STATS); + if (!attr) + return -EMSGSIZE; + + if (nla_put_u64_64bit(msg, DEVLINK_ATTR_STATS_RX_PACKETS, + stats.rx_packets, DEVLINK_ATTR_PAD)) + goto nla_put_failure; + + if (nla_put_u64_64bit(msg, DEVLINK_ATTR_STATS_RX_BYTES, + stats.rx_bytes, DEVLINK_ATTR_PAD)) + goto nla_put_failure; + + nla_nest_end(msg, attr); + + return 0; + +nla_put_failure: + nla_nest_cancel(msg, attr); + return -EMSGSIZE; +} + +static int devlink_nl_trap_fill(struct sk_buff *msg, struct devlink *devlink, + const struct devlink_trap_item *trap_item, + enum devlink_command cmd, u32 portid, u32 seq, + int flags) +{ + struct devlink_trap_group_item *group_item = trap_item->group_item; + void *hdr; + int err; + + hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd); + if (!hdr) + return -EMSGSIZE; + + if (devlink_nl_put_handle(msg, devlink)) + goto nla_put_failure; + + if (nla_put_string(msg, DEVLINK_ATTR_TRAP_GROUP_NAME, + group_item->group->name)) + goto nla_put_failure; + + if (nla_put_string(msg, DEVLINK_ATTR_TRAP_NAME, trap_item->trap->name)) + goto nla_put_failure; + + if (nla_put_u8(msg, DEVLINK_ATTR_TRAP_TYPE, trap_item->trap->type)) + goto nla_put_failure; + + if (trap_item->trap->generic && + nla_put_flag(msg, DEVLINK_ATTR_TRAP_GENERIC)) + goto nla_put_failure; + + if (nla_put_u8(msg, DEVLINK_ATTR_TRAP_ACTION, trap_item->action)) + goto nla_put_failure; + + err = devlink_trap_metadata_put(msg, trap_item->trap); + if (err) + goto nla_put_failure; + + err = devlink_trap_stats_put(msg, trap_item->stats); + if (err) + goto nla_put_failure; + + genlmsg_end(msg, hdr); + + return 0; + +nla_put_failure: + genlmsg_cancel(msg, hdr); + return -EMSGSIZE; +} + +static int devlink_nl_cmd_trap_get_doit(struct sk_buff *skb, + struct genl_info *info) +{ + struct netlink_ext_ack *extack = info->extack; + struct devlink *devlink = info->user_ptr[0]; + struct devlink_trap_item *trap_item; + struct sk_buff *msg; + int err; + + if (list_empty(&devlink->trap_list)) + return -EOPNOTSUPP; + + trap_item = devlink_trap_item_get_from_info(devlink, info); + if (!trap_item) { + NL_SET_ERR_MSG_MOD(extack, "Device did not register this trap"); + return -ENOENT; + } + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return -ENOMEM; + + err = devlink_nl_trap_fill(msg, devlink, trap_item, + DEVLINK_CMD_TRAP_NEW, info->snd_portid, + info->snd_seq, 0); + if (err) + goto err_trap_fill; + + return genlmsg_reply(msg, info); + +err_trap_fill: + nlmsg_free(msg); + return err; +} + +static int devlink_nl_cmd_trap_get_dumpit(struct sk_buff *msg, + struct netlink_callback *cb) +{ + struct devlink_trap_item *trap_item; + struct devlink *devlink; + int start = cb->args[0]; + int idx = 0; + int err; + + mutex_lock(&devlink_mutex); + list_for_each_entry(devlink, &devlink_list, list) { + if (!net_eq(devlink_net(devlink), sock_net(msg->sk))) + continue; + mutex_lock(&devlink->lock); + list_for_each_entry(trap_item, &devlink->trap_list, list) { + if (idx < start) { + idx++; + continue; + } + err = devlink_nl_trap_fill(msg, devlink, trap_item, + DEVLINK_CMD_TRAP_NEW, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, + NLM_F_MULTI); + if (err) { + mutex_unlock(&devlink->lock); + goto out; + } + idx++; + } + mutex_unlock(&devlink->lock); + } +out: + mutex_unlock(&devlink_mutex); + + cb->args[0] = idx; + return msg->len; +} + +static int __devlink_trap_action_set(struct devlink *devlink, + struct devlink_trap_item *trap_item, + enum devlink_trap_action trap_action, + struct netlink_ext_ack *extack) +{ + int err; + + if (trap_item->action != trap_action && + trap_item->trap->type != DEVLINK_TRAP_TYPE_DROP) { + NL_SET_ERR_MSG_MOD(extack, "Cannot change action of non-drop traps. Skipping"); + return 0; + } + + err = devlink->ops->trap_action_set(devlink, trap_item->trap, + trap_action); + if (err) + return err; + + trap_item->action = trap_action; + + return 0; +} + +static int devlink_trap_action_set(struct devlink *devlink, + struct devlink_trap_item *trap_item, + struct genl_info *info) +{ + enum devlink_trap_action trap_action; + int err; + + if (!info->attrs[DEVLINK_ATTR_TRAP_ACTION]) + return 0; + + err = devlink_trap_action_get_from_info(info, &trap_action); + if (err) { + NL_SET_ERR_MSG_MOD(info->extack, "Invalid trap action"); + return -EINVAL; + } + + return __devlink_trap_action_set(devlink, trap_item, trap_action, + info->extack); +} + +static int devlink_nl_cmd_trap_set_doit(struct sk_buff *skb, + struct genl_info *info) +{ + struct netlink_ext_ack *extack = info->extack; + struct devlink *devlink = info->user_ptr[0]; + struct devlink_trap_item *trap_item; + int err; + + if (list_empty(&devlink->trap_list)) + return -EOPNOTSUPP; + + trap_item = devlink_trap_item_get_from_info(devlink, info); + if (!trap_item) { + NL_SET_ERR_MSG_MOD(extack, "Device did not register this trap"); + return -ENOENT; + } + + err = devlink_trap_action_set(devlink, trap_item, info); + if (err) + return err; + + return 0; +} + +static struct devlink_trap_group_item * +devlink_trap_group_item_lookup(struct devlink *devlink, const char *name) +{ + struct devlink_trap_group_item *group_item; + + list_for_each_entry(group_item, &devlink->trap_group_list, list) { + if (!strcmp(group_item->group->name, name)) + return group_item; + } + + return NULL; +} + +static struct devlink_trap_group_item * +devlink_trap_group_item_get_from_info(struct devlink *devlink, + struct genl_info *info) +{ + char *name; + + if (!info->attrs[DEVLINK_ATTR_TRAP_GROUP_NAME]) + return NULL; + name = nla_data(info->attrs[DEVLINK_ATTR_TRAP_GROUP_NAME]); + + return devlink_trap_group_item_lookup(devlink, name); +} + +static int +devlink_nl_trap_group_fill(struct sk_buff *msg, struct devlink *devlink, + const struct devlink_trap_group_item *group_item, + enum devlink_command cmd, u32 portid, u32 seq, + int flags) +{ + void *hdr; + int err; + + hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd); + if (!hdr) + return -EMSGSIZE; + + if (devlink_nl_put_handle(msg, devlink)) + goto nla_put_failure; + + if (nla_put_string(msg, DEVLINK_ATTR_TRAP_GROUP_NAME, + group_item->group->name)) + goto nla_put_failure; + + if (group_item->group->generic && + nla_put_flag(msg, DEVLINK_ATTR_TRAP_GENERIC)) + goto nla_put_failure; + + err = devlink_trap_stats_put(msg, group_item->stats); + if (err) + goto nla_put_failure; + + genlmsg_end(msg, hdr); + + return 0; + +nla_put_failure: + genlmsg_cancel(msg, hdr); + return -EMSGSIZE; +} + +static int devlink_nl_cmd_trap_group_get_doit(struct sk_buff *skb, + struct genl_info *info) +{ + struct netlink_ext_ack *extack = info->extack; + struct devlink *devlink = info->user_ptr[0]; + struct devlink_trap_group_item *group_item; + struct sk_buff *msg; + int err; + + if (list_empty(&devlink->trap_group_list)) + return -EOPNOTSUPP; + + group_item = devlink_trap_group_item_get_from_info(devlink, info); + if (!group_item) { + NL_SET_ERR_MSG_MOD(extack, "Device did not register this trap group"); + return -ENOENT; + } + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return -ENOMEM; + + err = devlink_nl_trap_group_fill(msg, devlink, group_item, + DEVLINK_CMD_TRAP_GROUP_NEW, + info->snd_portid, info->snd_seq, 0); + if (err) + goto err_trap_group_fill; + + return genlmsg_reply(msg, info); + +err_trap_group_fill: + nlmsg_free(msg); + return err; +} + +static int devlink_nl_cmd_trap_group_get_dumpit(struct sk_buff *msg, + struct netlink_callback *cb) +{ + enum devlink_command cmd = DEVLINK_CMD_TRAP_GROUP_NEW; + struct devlink_trap_group_item *group_item; + u32 portid = NETLINK_CB(cb->skb).portid; + struct devlink *devlink; + int start = cb->args[0]; + int idx = 0; + int err; + + mutex_lock(&devlink_mutex); + list_for_each_entry(devlink, &devlink_list, list) { + if (!net_eq(devlink_net(devlink), sock_net(msg->sk))) + continue; + mutex_lock(&devlink->lock); + list_for_each_entry(group_item, &devlink->trap_group_list, + list) { + if (idx < start) { + idx++; + continue; + } + err = devlink_nl_trap_group_fill(msg, devlink, + group_item, cmd, + portid, + cb->nlh->nlmsg_seq, + NLM_F_MULTI); + if (err) { + mutex_unlock(&devlink->lock); + goto out; + } + idx++; + } + mutex_unlock(&devlink->lock); + } +out: + mutex_unlock(&devlink_mutex); + + cb->args[0] = idx; + return msg->len; +} + +static int +__devlink_trap_group_action_set(struct devlink *devlink, + struct devlink_trap_group_item *group_item, + enum devlink_trap_action trap_action, + struct netlink_ext_ack *extack) +{ + const char *group_name = group_item->group->name; + struct devlink_trap_item *trap_item; + int err; + + list_for_each_entry(trap_item, &devlink->trap_list, list) { + if (strcmp(trap_item->trap->group.name, group_name)) + continue; + err = __devlink_trap_action_set(devlink, trap_item, + trap_action, extack); + if (err) + return err; + } + + return 0; +} + +static int +devlink_trap_group_action_set(struct devlink *devlink, + struct devlink_trap_group_item *group_item, + struct genl_info *info) +{ + enum devlink_trap_action trap_action; + int err; + + if (!info->attrs[DEVLINK_ATTR_TRAP_ACTION]) + return 0; + + err = devlink_trap_action_get_from_info(info, &trap_action); + if (err) { + NL_SET_ERR_MSG_MOD(info->extack, "Invalid trap action"); + return -EINVAL; + } + + err = __devlink_trap_group_action_set(devlink, group_item, trap_action, + info->extack); + if (err) + return err; + + return 0; +} + +static int devlink_nl_cmd_trap_group_set_doit(struct sk_buff *skb, + struct genl_info *info) +{ + struct netlink_ext_ack *extack = info->extack; + struct devlink *devlink = info->user_ptr[0]; + struct devlink_trap_group_item *group_item; + int err; + + if (list_empty(&devlink->trap_group_list)) + return -EOPNOTSUPP; + + group_item = devlink_trap_group_item_get_from_info(devlink, info); + if (!group_item) { + NL_SET_ERR_MSG_MOD(extack, "Device did not register this trap group"); + return -ENOENT; + } + + err = devlink_trap_group_action_set(devlink, group_item, info); + if (err) + return err; + + return 0; +} + static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = { [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING }, [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING }, @@ -5184,6 +5752,9 @@ static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = { [DEVLINK_ATTR_HEALTH_REPORTER_AUTO_RECOVER] = { .type = NLA_U8 }, [DEVLINK_ATTR_FLASH_UPDATE_FILE_NAME] = { .type = NLA_NUL_STRING }, [DEVLINK_ATTR_FLASH_UPDATE_COMPONENT] = { .type = NLA_NUL_STRING }, + [DEVLINK_ATTR_TRAP_NAME] = { .type = NLA_NUL_STRING }, + [DEVLINK_ATTR_TRAP_ACTION] = { .type = NLA_U8 }, + [DEVLINK_ATTR_TRAP_GROUP_NAME] = { .type = NLA_NUL_STRING }, }; static const struct genl_ops devlink_nl_ops[] = { @@ -5483,6 +6054,32 @@ static const struct genl_ops devlink_nl_ops[] = { .flags = GENL_ADMIN_PERM, .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK, }, + { + .cmd = DEVLINK_CMD_TRAP_GET, + .doit = devlink_nl_cmd_trap_get_doit, + .dumpit = devlink_nl_cmd_trap_get_dumpit, + .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK, + /* can be retrieved by unprivileged users */ + }, + { + .cmd = DEVLINK_CMD_TRAP_SET, + .doit = devlink_nl_cmd_trap_set_doit, + .flags = GENL_ADMIN_PERM, + .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK, + }, + { + .cmd = DEVLINK_CMD_TRAP_GROUP_GET, + .doit = devlink_nl_cmd_trap_group_get_doit, + .dumpit = devlink_nl_cmd_trap_group_get_dumpit, + .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK, + /* can be retrieved by unprivileged users */ + }, + { + .cmd = DEVLINK_CMD_TRAP_GROUP_SET, + .doit = devlink_nl_cmd_trap_group_set_doit, + .flags = GENL_ADMIN_PERM, + .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK, + }, }; static struct genl_family devlink_nl_family __ro_after_init = { @@ -5528,6 +6125,8 @@ struct devlink *devlink_alloc(const struct devlink_ops *ops, size_t priv_size) INIT_LIST_HEAD(&devlink->param_list); INIT_LIST_HEAD(&devlink->region_list); INIT_LIST_HEAD(&devlink->reporter_list); + INIT_LIST_HEAD(&devlink->trap_list); + INIT_LIST_HEAD(&devlink->trap_group_list); mutex_init(&devlink->lock); mutex_init(&devlink->reporters_lock); return devlink; @@ -5574,6 +6173,8 @@ void devlink_free(struct devlink *devlink) { mutex_destroy(&devlink->reporters_lock); mutex_destroy(&devlink->lock); + WARN_ON(!list_empty(&devlink->trap_group_list)); + WARN_ON(!list_empty(&devlink->trap_list)); WARN_ON(!list_empty(&devlink->reporter_list)); WARN_ON(!list_empty(&devlink->region_list)); WARN_ON(!list_empty(&devlink->param_list)); @@ -5678,10 +6279,10 @@ static void __devlink_port_type_set(struct devlink_port *devlink_port, if (WARN_ON(!devlink_port->registered)) return; devlink_port_type_warn_cancel(devlink_port); - spin_lock(&devlink_port->type_lock); + spin_lock_bh(&devlink_port->type_lock); devlink_port->type = type; devlink_port->type_dev = type_dev; - spin_unlock(&devlink_port->type_lock); + spin_unlock_bh(&devlink_port->type_lock); devlink_port_notify(devlink_port, DEVLINK_CMD_PORT_NEW); } @@ -6834,6 +7435,463 @@ unlock: } EXPORT_SYMBOL_GPL(devlink_region_snapshot_create); +#define DEVLINK_TRAP(_id, _type) \ + { \ + .type = DEVLINK_TRAP_TYPE_##_type, \ + .id = DEVLINK_TRAP_GENERIC_ID_##_id, \ + .name = DEVLINK_TRAP_GENERIC_NAME_##_id, \ + } + +static const struct devlink_trap devlink_trap_generic[] = { +}; + +#define DEVLINK_TRAP_GROUP(_id) \ + { \ + .id = DEVLINK_TRAP_GROUP_GENERIC_ID_##_id, \ + .name = DEVLINK_TRAP_GROUP_GENERIC_NAME_##_id, \ + } + +static const struct devlink_trap_group devlink_trap_group_generic[] = { +}; + +static int devlink_trap_generic_verify(const struct devlink_trap *trap) +{ + if (trap->id > DEVLINK_TRAP_GENERIC_ID_MAX) + return -EINVAL; + + if (strcmp(trap->name, devlink_trap_generic[trap->id].name)) + return -EINVAL; + + if (trap->type != devlink_trap_generic[trap->id].type) + return -EINVAL; + + return 0; +} + +static int devlink_trap_driver_verify(const struct devlink_trap *trap) +{ + int i; + + if (trap->id <= DEVLINK_TRAP_GENERIC_ID_MAX) + return -EINVAL; + + for (i = 0; i < ARRAY_SIZE(devlink_trap_generic); i++) { + if (!strcmp(trap->name, devlink_trap_generic[i].name)) + return -EEXIST; + } + + return 0; +} + +static int devlink_trap_verify(const struct devlink_trap *trap) +{ + if (!trap || !trap->name || !trap->group.name) + return -EINVAL; + + if (trap->generic) + return devlink_trap_generic_verify(trap); + else + return devlink_trap_driver_verify(trap); +} + +static int +devlink_trap_group_generic_verify(const struct devlink_trap_group *group) +{ + if (group->id > DEVLINK_TRAP_GROUP_GENERIC_ID_MAX) + return -EINVAL; + + if (strcmp(group->name, devlink_trap_group_generic[group->id].name)) + return -EINVAL; + + return 0; +} + +static int +devlink_trap_group_driver_verify(const struct devlink_trap_group *group) +{ + int i; + + if (group->id <= DEVLINK_TRAP_GROUP_GENERIC_ID_MAX) + return -EINVAL; + + for (i = 0; i < ARRAY_SIZE(devlink_trap_group_generic); i++) { + if (!strcmp(group->name, devlink_trap_group_generic[i].name)) + return -EEXIST; + } + + return 0; +} + +static int devlink_trap_group_verify(const struct devlink_trap_group *group) +{ + if (group->generic) + return devlink_trap_group_generic_verify(group); + else + return devlink_trap_group_driver_verify(group); +} + +static void +devlink_trap_group_notify(struct devlink *devlink, + const struct devlink_trap_group_item *group_item, + enum devlink_command cmd) +{ + struct sk_buff *msg; + int err; + + WARN_ON_ONCE(cmd != DEVLINK_CMD_TRAP_GROUP_NEW && + cmd != DEVLINK_CMD_TRAP_GROUP_DEL); + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return; + + err = devlink_nl_trap_group_fill(msg, devlink, group_item, cmd, 0, 0, + 0); + if (err) { + nlmsg_free(msg); + return; + } + + genlmsg_multicast_netns(&devlink_nl_family, devlink_net(devlink), + msg, 0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL); +} + +static struct devlink_trap_group_item * +devlink_trap_group_item_create(struct devlink *devlink, + const struct devlink_trap_group *group) +{ + struct devlink_trap_group_item *group_item; + int err; + + err = devlink_trap_group_verify(group); + if (err) + return ERR_PTR(err); + + group_item = kzalloc(sizeof(*group_item), GFP_KERNEL); + if (!group_item) + return ERR_PTR(-ENOMEM); + + group_item->stats = netdev_alloc_pcpu_stats(struct devlink_stats); + if (!group_item->stats) { + err = -ENOMEM; + goto err_stats_alloc; + } + + group_item->group = group; + refcount_set(&group_item->refcount, 1); + + if (devlink->ops->trap_group_init) { + err = devlink->ops->trap_group_init(devlink, group); + if (err) + goto err_group_init; + } + + list_add_tail(&group_item->list, &devlink->trap_group_list); + devlink_trap_group_notify(devlink, group_item, + DEVLINK_CMD_TRAP_GROUP_NEW); + + return group_item; + +err_group_init: + free_percpu(group_item->stats); +err_stats_alloc: + kfree(group_item); + return ERR_PTR(err); +} + +static void +devlink_trap_group_item_destroy(struct devlink *devlink, + struct devlink_trap_group_item *group_item) +{ + devlink_trap_group_notify(devlink, group_item, + DEVLINK_CMD_TRAP_GROUP_DEL); + list_del(&group_item->list); + free_percpu(group_item->stats); + kfree(group_item); +} + +static struct devlink_trap_group_item * +devlink_trap_group_item_get(struct devlink *devlink, + const struct devlink_trap_group *group) +{ + struct devlink_trap_group_item *group_item; + + group_item = devlink_trap_group_item_lookup(devlink, group->name); + if (group_item) { + refcount_inc(&group_item->refcount); + return group_item; + } + + return devlink_trap_group_item_create(devlink, group); +} + +static void +devlink_trap_group_item_put(struct devlink *devlink, + struct devlink_trap_group_item *group_item) +{ + if (!refcount_dec_and_test(&group_item->refcount)) + return; + + devlink_trap_group_item_destroy(devlink, group_item); +} + +static int +devlink_trap_item_group_link(struct devlink *devlink, + struct devlink_trap_item *trap_item) +{ + struct devlink_trap_group_item *group_item; + + group_item = devlink_trap_group_item_get(devlink, + &trap_item->trap->group); + if (IS_ERR(group_item)) + return PTR_ERR(group_item); + + trap_item->group_item = group_item; + + return 0; +} + +static void +devlink_trap_item_group_unlink(struct devlink *devlink, + struct devlink_trap_item *trap_item) +{ + devlink_trap_group_item_put(devlink, trap_item->group_item); +} + +static void devlink_trap_notify(struct devlink *devlink, + const struct devlink_trap_item *trap_item, + enum devlink_command cmd) +{ + struct sk_buff *msg; + int err; + + WARN_ON_ONCE(cmd != DEVLINK_CMD_TRAP_NEW && + cmd != DEVLINK_CMD_TRAP_DEL); + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return; + + err = devlink_nl_trap_fill(msg, devlink, trap_item, cmd, 0, 0, 0); + if (err) { + nlmsg_free(msg); + return; + } + + genlmsg_multicast_netns(&devlink_nl_family, devlink_net(devlink), + msg, 0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL); +} + +static int +devlink_trap_register(struct devlink *devlink, + const struct devlink_trap *trap, void *priv) +{ + struct devlink_trap_item *trap_item; + int err; + + if (devlink_trap_item_lookup(devlink, trap->name)) + return -EEXIST; + + trap_item = kzalloc(sizeof(*trap_item), GFP_KERNEL); + if (!trap_item) + return -ENOMEM; + + trap_item->stats = netdev_alloc_pcpu_stats(struct devlink_stats); + if (!trap_item->stats) { + err = -ENOMEM; + goto err_stats_alloc; + } + + trap_item->trap = trap; + trap_item->action = trap->init_action; + trap_item->priv = priv; + + err = devlink_trap_item_group_link(devlink, trap_item); + if (err) + goto err_group_link; + + err = devlink->ops->trap_init(devlink, trap, trap_item); + if (err) + goto err_trap_init; + + list_add_tail(&trap_item->list, &devlink->trap_list); + devlink_trap_notify(devlink, trap_item, DEVLINK_CMD_TRAP_NEW); + + return 0; + +err_trap_init: + devlink_trap_item_group_unlink(devlink, trap_item); +err_group_link: + free_percpu(trap_item->stats); +err_stats_alloc: + kfree(trap_item); + return err; +} + +static void devlink_trap_unregister(struct devlink *devlink, + const struct devlink_trap *trap) +{ + struct devlink_trap_item *trap_item; + + trap_item = devlink_trap_item_lookup(devlink, trap->name); + if (WARN_ON_ONCE(!trap_item)) + return; + + devlink_trap_notify(devlink, trap_item, DEVLINK_CMD_TRAP_DEL); + list_del(&trap_item->list); + if (devlink->ops->trap_fini) + devlink->ops->trap_fini(devlink, trap, trap_item); + devlink_trap_item_group_unlink(devlink, trap_item); + free_percpu(trap_item->stats); + kfree(trap_item); +} + +static void devlink_trap_disable(struct devlink *devlink, + const struct devlink_trap *trap) +{ + struct devlink_trap_item *trap_item; + + trap_item = devlink_trap_item_lookup(devlink, trap->name); + if (WARN_ON_ONCE(!trap_item)) + return; + + devlink->ops->trap_action_set(devlink, trap, DEVLINK_TRAP_ACTION_DROP); + trap_item->action = DEVLINK_TRAP_ACTION_DROP; +} + +/** + * devlink_traps_register - Register packet traps with devlink. + * @devlink: devlink. + * @traps: Packet traps. + * @traps_count: Count of provided packet traps. + * @priv: Driver private information. + * + * Return: Non-zero value on failure. + */ +int devlink_traps_register(struct devlink *devlink, + const struct devlink_trap *traps, + size_t traps_count, void *priv) +{ + int i, err; + + if (!devlink->ops->trap_init || !devlink->ops->trap_action_set) + return -EINVAL; + + mutex_lock(&devlink->lock); + for (i = 0; i < traps_count; i++) { + const struct devlink_trap *trap = &traps[i]; + + err = devlink_trap_verify(trap); + if (err) + goto err_trap_verify; + + err = devlink_trap_register(devlink, trap, priv); + if (err) + goto err_trap_register; + } + mutex_unlock(&devlink->lock); + + return 0; + +err_trap_register: +err_trap_verify: + for (i--; i >= 0; i--) + devlink_trap_unregister(devlink, &traps[i]); + mutex_unlock(&devlink->lock); + return err; +} +EXPORT_SYMBOL_GPL(devlink_traps_register); + +/** + * devlink_traps_unregister - Unregister packet traps from devlink. + * @devlink: devlink. + * @traps: Packet traps. + * @traps_count: Count of provided packet traps. + */ +void devlink_traps_unregister(struct devlink *devlink, + const struct devlink_trap *traps, + size_t traps_count) +{ + int i; + + mutex_lock(&devlink->lock); + /* Make sure we do not have any packets in-flight while unregistering + * traps by disabling all of them and waiting for a grace period. + */ + for (i = traps_count - 1; i >= 0; i--) + devlink_trap_disable(devlink, &traps[i]); + synchronize_rcu(); + for (i = traps_count - 1; i >= 0; i--) + devlink_trap_unregister(devlink, &traps[i]); + mutex_unlock(&devlink->lock); +} +EXPORT_SYMBOL_GPL(devlink_traps_unregister); + +static void +devlink_trap_stats_update(struct devlink_stats __percpu *trap_stats, + size_t skb_len) +{ + struct devlink_stats *stats; + + stats = this_cpu_ptr(trap_stats); + u64_stats_update_begin(&stats->syncp); + stats->rx_bytes += skb_len; + stats->rx_packets++; + u64_stats_update_end(&stats->syncp); +} + +static void +devlink_trap_report_metadata_fill(struct net_dm_hw_metadata *hw_metadata, + const struct devlink_trap_item *trap_item, + struct devlink_port *in_devlink_port) +{ + struct devlink_trap_group_item *group_item = trap_item->group_item; + + hw_metadata->trap_group_name = group_item->group->name; + hw_metadata->trap_name = trap_item->trap->name; + + spin_lock(&in_devlink_port->type_lock); + if (in_devlink_port->type == DEVLINK_PORT_TYPE_ETH) + hw_metadata->input_dev = in_devlink_port->type_dev; + spin_unlock(&in_devlink_port->type_lock); +} + +/** + * devlink_trap_report - Report trapped packet to drop monitor. + * @devlink: devlink. + * @skb: Trapped packet. + * @trap_ctx: Trap context. + * @in_devlink_port: Input devlink port. + */ +void devlink_trap_report(struct devlink *devlink, struct sk_buff *skb, + void *trap_ctx, struct devlink_port *in_devlink_port) +{ + struct devlink_trap_item *trap_item = trap_ctx; + struct net_dm_hw_metadata hw_metadata = {}; + + devlink_trap_stats_update(trap_item->stats, skb->len); + devlink_trap_stats_update(trap_item->group_item->stats, skb->len); + + devlink_trap_report_metadata_fill(&hw_metadata, trap_item, + in_devlink_port); + net_dm_hw_report(skb, &hw_metadata); +} +EXPORT_SYMBOL_GPL(devlink_trap_report); + +/** + * devlink_trap_ctx_priv - Trap context to driver private information. + * @trap_ctx: Trap context. + * + * Return: Driver private information passed during registration. + */ +void *devlink_trap_ctx_priv(void *trap_ctx) +{ + struct devlink_trap_item *trap_item = trap_ctx; + + return trap_item->priv; +} +EXPORT_SYMBOL_GPL(devlink_trap_ctx_priv); + static void __devlink_compat_running_version(struct devlink *devlink, char *buf, size_t len) { -- cgit v1.2.3 From 391203ab11df9b23cd0b867122bccbe33fe16f02 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Sat, 17 Aug 2019 16:28:18 +0300 Subject: devlink: Add generic packet traps and groups Add generic packet traps and groups that can report dropped packets as well as exceptions such as TTL error. Signed-off-by: Ido Schimmel Acked-by: Jiri Pirko Signed-off-by: David S. Miller --- include/net/devlink.h | 40 ++++++++++++++++++++++++++++++++++++++++ net/core/devlink.c | 12 ++++++++++++ 2 files changed, 52 insertions(+) (limited to 'include/net/devlink.h') diff --git a/include/net/devlink.h b/include/net/devlink.h index 03b32e33e93e..fb02e0e89f9d 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -541,18 +541,58 @@ struct devlink_trap { }; enum devlink_trap_generic_id { + DEVLINK_TRAP_GENERIC_ID_SMAC_MC, + DEVLINK_TRAP_GENERIC_ID_VLAN_TAG_MISMATCH, + DEVLINK_TRAP_GENERIC_ID_INGRESS_VLAN_FILTER, + DEVLINK_TRAP_GENERIC_ID_INGRESS_STP_FILTER, + DEVLINK_TRAP_GENERIC_ID_EMPTY_TX_LIST, + DEVLINK_TRAP_GENERIC_ID_PORT_LOOPBACK_FILTER, + DEVLINK_TRAP_GENERIC_ID_BLACKHOLE_ROUTE, + DEVLINK_TRAP_GENERIC_ID_TTL_ERROR, + DEVLINK_TRAP_GENERIC_ID_TAIL_DROP, + /* Add new generic trap IDs above */ __DEVLINK_TRAP_GENERIC_ID_MAX, DEVLINK_TRAP_GENERIC_ID_MAX = __DEVLINK_TRAP_GENERIC_ID_MAX - 1, }; enum devlink_trap_group_generic_id { + DEVLINK_TRAP_GROUP_GENERIC_ID_L2_DROPS, + DEVLINK_TRAP_GROUP_GENERIC_ID_L3_DROPS, + DEVLINK_TRAP_GROUP_GENERIC_ID_BUFFER_DROPS, + /* Add new generic trap group IDs above */ __DEVLINK_TRAP_GROUP_GENERIC_ID_MAX, DEVLINK_TRAP_GROUP_GENERIC_ID_MAX = __DEVLINK_TRAP_GROUP_GENERIC_ID_MAX - 1, }; +#define DEVLINK_TRAP_GENERIC_NAME_SMAC_MC \ + "source_mac_is_multicast" +#define DEVLINK_TRAP_GENERIC_NAME_VLAN_TAG_MISMATCH \ + "vlan_tag_mismatch" +#define DEVLINK_TRAP_GENERIC_NAME_INGRESS_VLAN_FILTER \ + "ingress_vlan_filter" +#define DEVLINK_TRAP_GENERIC_NAME_INGRESS_STP_FILTER \ + "ingress_spanning_tree_filter" +#define DEVLINK_TRAP_GENERIC_NAME_EMPTY_TX_LIST \ + "port_list_is_empty" +#define DEVLINK_TRAP_GENERIC_NAME_PORT_LOOPBACK_FILTER \ + "port_loopback_filter" +#define DEVLINK_TRAP_GENERIC_NAME_BLACKHOLE_ROUTE \ + "blackhole_route" +#define DEVLINK_TRAP_GENERIC_NAME_TTL_ERROR \ + "ttl_value_is_too_small" +#define DEVLINK_TRAP_GENERIC_NAME_TAIL_DROP \ + "tail_drop" + +#define DEVLINK_TRAP_GROUP_GENERIC_NAME_L2_DROPS \ + "l2_drops" +#define DEVLINK_TRAP_GROUP_GENERIC_NAME_L3_DROPS \ + "l3_drops" +#define DEVLINK_TRAP_GROUP_GENERIC_NAME_BUFFER_DROPS \ + "buffer_drops" + #define DEVLINK_TRAP_GENERIC(_type, _init_action, _id, _group, _metadata_cap) \ { \ .type = DEVLINK_TRAP_TYPE_##_type, \ diff --git a/net/core/devlink.c b/net/core/devlink.c index 960ceaec98d6..650f36379203 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -7443,6 +7443,15 @@ EXPORT_SYMBOL_GPL(devlink_region_snapshot_create); } static const struct devlink_trap devlink_trap_generic[] = { + DEVLINK_TRAP(SMAC_MC, DROP), + DEVLINK_TRAP(VLAN_TAG_MISMATCH, DROP), + DEVLINK_TRAP(INGRESS_VLAN_FILTER, DROP), + DEVLINK_TRAP(INGRESS_STP_FILTER, DROP), + DEVLINK_TRAP(EMPTY_TX_LIST, DROP), + DEVLINK_TRAP(PORT_LOOPBACK_FILTER, DROP), + DEVLINK_TRAP(BLACKHOLE_ROUTE, DROP), + DEVLINK_TRAP(TTL_ERROR, EXCEPTION), + DEVLINK_TRAP(TAIL_DROP, DROP), }; #define DEVLINK_TRAP_GROUP(_id) \ @@ -7452,6 +7461,9 @@ static const struct devlink_trap devlink_trap_generic[] = { } static const struct devlink_trap_group devlink_trap_group_generic[] = { + DEVLINK_TRAP_GROUP(L2_DROPS), + DEVLINK_TRAP_GROUP(L3_DROPS), + DEVLINK_TRAP_GROUP(BUFFER_DROPS), }; static int devlink_trap_generic_verify(const struct devlink_trap *trap) -- cgit v1.2.3 From f3047ca01f12bf997ef199710b51490b0f750b34 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Sat, 17 Aug 2019 16:28:19 +0300 Subject: Documentation: Add devlink-trap documentation Add initial documentation of the devlink-trap mechanism, explaining the background, motivation and the semantics of the interface. Signed-off-by: Ido Schimmel Acked-by: Jiri Pirko Signed-off-by: David S. Miller --- Documentation/networking/devlink-trap.rst | 187 ++++++++++++++++++++++++++++++ Documentation/networking/index.rst | 1 + include/net/devlink.h | 6 + 3 files changed, 194 insertions(+) create mode 100644 Documentation/networking/devlink-trap.rst (limited to 'include/net/devlink.h') diff --git a/Documentation/networking/devlink-trap.rst b/Documentation/networking/devlink-trap.rst new file mode 100644 index 000000000000..dbc7a3e00fd8 --- /dev/null +++ b/Documentation/networking/devlink-trap.rst @@ -0,0 +1,187 @@ +.. SPDX-License-Identifier: GPL-2.0 + +============ +Devlink Trap +============ + +Background +========== + +Devices capable of offloading the kernel's datapath and perform functions such +as bridging and routing must also be able to send specific packets to the +kernel (i.e., the CPU) for processing. + +For example, a device acting as a multicast-aware bridge must be able to send +IGMP membership reports to the kernel for processing by the bridge module. +Without processing such packets, the bridge module could never populate its +MDB. + +As another example, consider a device acting as router which has received an IP +packet with a TTL of 1. Upon routing the packet the device must send it to the +kernel so that it will route it as well and generate an ICMP Time Exceeded +error datagram. Without letting the kernel route such packets itself, utilities +such as ``traceroute`` could never work. + +The fundamental ability of sending certain packets to the kernel for processing +is called "packet trapping". + +Overview +======== + +The ``devlink-trap`` mechanism allows capable device drivers to register their +supported packet traps with ``devlink`` and report trapped packets to +``devlink`` for further analysis. + +Upon receiving trapped packets, ``devlink`` will perform a per-trap packets and +bytes accounting and potentially report the packet to user space via a netlink +event along with all the provided metadata (e.g., trap reason, timestamp, input +port). This is especially useful for drop traps (see :ref:`Trap-Types`) +as it allows users to obtain further visibility into packet drops that would +otherwise be invisible. + +The following diagram provides a general overview of ``devlink-trap``:: + + Netlink event: Packet w/ metadata + Or a summary of recent drops + ^ + | + Userspace | + +---------------------------------------------------+ + Kernel | + | + +-------+--------+ + | | + | drop_monitor | + | | + +-------^--------+ + | + | + | + +----+----+ + | | Kernel's Rx path + | devlink | (non-drop traps) + | | + +----^----+ ^ + | | + +-----------+ + | + +-------+-------+ + | | + | Device driver | + | | + +-------^-------+ + Kernel | + +---------------------------------------------------+ + Hardware | + | Trapped packet + | + +--+---+ + | | + | ASIC | + | | + +------+ + +.. _Trap-Types: + +Trap Types +========== + +The ``devlink-trap`` mechanism supports the following packet trap types: + + * ``drop``: Trapped packets were dropped by the underlying device. Packets + are only processed by ``devlink`` and not injected to the kernel's Rx path. + The trap action (see :ref:`Trap-Actions`) can be changed. + * ``exception``: Trapped packets were not forwarded as intended by the + underlying device due to an exception (e.g., TTL error, missing neighbour + entry) and trapped to the control plane for resolution. Packets are + processed by ``devlink`` and injected to the kernel's Rx path. Changing the + action of such traps is not allowed, as it can easily break the control + plane. + +.. _Trap-Actions: + +Trap Actions +============ + +The ``devlink-trap`` mechanism supports the following packet trap actions: + + * ``trap``: The sole copy of the packet is sent to the CPU. + * ``drop``: The packet is dropped by the underlying device and a copy is not + sent to the CPU. + +Generic Packet Traps +==================== + +Generic packet traps are used to describe traps that trap well-defined packets +or packets that are trapped due to well-defined conditions (e.g., TTL error). +Such traps can be shared by multiple device drivers and their description must +be added to the following table: + +.. list-table:: List of Generic Packet Traps + :widths: 5 5 90 + + * - Name + - Type + - Description + * - ``source_mac_is_multicast`` + - ``drop`` + - Traps incoming packets that the device decided to drop because of a + multicast source MAC + * - ``vlan_tag_mismatch`` + - ``drop`` + - Traps incoming packets that the device decided to drop in case of VLAN + tag mismatch: The ingress bridge port is not configured with a PVID and + the packet is untagged or prio-tagged + * - ``ingress_vlan_filter`` + - ``drop`` + - Traps incoming packets that the device decided to drop in case they are + tagged with a VLAN that is not configured on the ingress bridge port + * - ``ingress_spanning_tree_filter`` + - ``drop`` + - Traps incoming packets that the device decided to drop in case the STP + state of the ingress bridge port is not "forwarding" + * - ``port_list_is_empty`` + - ``drop`` + - Traps packets that the device decided to drop in case they need to be + flooded and the flood list is empty + * - ``port_loopback_filter`` + - ``drop`` + - Traps packets that the device decided to drop in case after layer 2 + forwarding the only port from which they should be transmitted through + is the port from which they were received + * - ``blackhole_route`` + - ``drop`` + - Traps packets that the device decided to drop in case they hit a + blackhole route + * - ``ttl_value_is_too_small`` + - ``exception`` + - Traps unicast packets that should be forwarded by the device whose TTL + was decremented to 0 or less + * - ``tail_drop`` + - ``drop`` + - Traps packets that the device decided to drop because they could not be + enqueued to a transmission queue which is full + +Generic Packet Trap Groups +========================== + +Generic packet trap groups are used to aggregate logically related packet +traps. These groups allow the user to batch operations such as setting the trap +action of all member traps. In addition, ``devlink-trap`` can report aggregated +per-group packets and bytes statistics, in case per-trap statistics are too +narrow. The description of these groups must be added to the following table: + +.. list-table:: List of Generic Packet Trap Groups + :widths: 10 90 + + * - Name + - Description + * - ``l2_drops`` + - Contains packet traps for packets that were dropped by the device during + layer 2 forwarding (i.e., bridge) + * - ``l3_drops`` + - Contains packet traps for packets that were dropped by the device or hit + an exception (e.g., TTL error) during layer 3 forwarding + * - ``buffer_drops`` + - Contains packet traps for packets that were dropped by the device due to + an enqueue decision diff --git a/Documentation/networking/index.rst b/Documentation/networking/index.rst index a46fca264bee..86a814e4d450 100644 --- a/Documentation/networking/index.rst +++ b/Documentation/networking/index.rst @@ -14,6 +14,7 @@ Contents: device_drivers/index dsa/index devlink-info-versions + devlink-trap ieee802154 kapi z8530book diff --git a/include/net/devlink.h b/include/net/devlink.h index fb02e0e89f9d..7f43c48f54cd 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -540,6 +540,9 @@ struct devlink_trap { u32 metadata_cap; }; +/* All traps must be documented in + * Documentation/networking/devlink-trap.rst + */ enum devlink_trap_generic_id { DEVLINK_TRAP_GENERIC_ID_SMAC_MC, DEVLINK_TRAP_GENERIC_ID_VLAN_TAG_MISMATCH, @@ -556,6 +559,9 @@ enum devlink_trap_generic_id { DEVLINK_TRAP_GENERIC_ID_MAX = __DEVLINK_TRAP_GENERIC_ID_MAX - 1, }; +/* All trap groups must be documented in + * Documentation/networking/devlink-trap.rst + */ enum devlink_trap_group_generic_id { DEVLINK_TRAP_GROUP_GENERIC_ID_L2_DROPS, DEVLINK_TRAP_GROUP_GENERIC_ID_L3_DROPS, -- cgit v1.2.3 From c7282b501f22a21ac8dfb6d3856aa1a92a7df5d5 Mon Sep 17 00:00:00 2001 From: Parav Pandit Date: Fri, 30 Aug 2019 05:39:44 -0500 Subject: devlink: Make port index data type as unsigned int Devlink port index attribute is returned to users as u32 through netlink response. Change index data type from 'unsigned' to 'unsigned int' to avoid below checkpatch.pl warning. WARNING: Prefer 'unsigned int' to bare use of 'unsigned' 81: FILE: include/net/devlink.h:81: + unsigned index; Acked-by: Jiri Pirko Signed-off-by: Parav Pandit Signed-off-by: David S. Miller --- include/net/devlink.h | 2 +- net/core/devlink.c | 5 +++-- 2 files changed, 4 insertions(+), 3 deletions(-) (limited to 'include/net/devlink.h') diff --git a/include/net/devlink.h b/include/net/devlink.h index 7f43c48f54cd..13523b0a0642 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -75,7 +75,7 @@ struct devlink_port { struct list_head list; struct list_head param_list; struct devlink *devlink; - unsigned index; + unsigned int index; bool registered; spinlock_t type_lock; /* Protects type and type_dev * pointer consistency. diff --git a/net/core/devlink.c b/net/core/devlink.c index 650f36379203..b7091329987a 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -136,7 +136,7 @@ static struct devlink *devlink_get_from_info(struct genl_info *info) } static struct devlink_port *devlink_port_get_by_index(struct devlink *devlink, - int port_index) + unsigned int port_index) { struct devlink_port *devlink_port; @@ -147,7 +147,8 @@ static struct devlink_port *devlink_port_get_by_index(struct devlink *devlink, return NULL; } -static bool devlink_port_index_exists(struct devlink *devlink, int port_index) +static bool devlink_port_index_exists(struct devlink *devlink, + unsigned int port_index) { return devlink_port_get_by_index(devlink, port_index); } -- cgit v1.2.3 From 7d5aa9a524db04c1bf65a49442ac0b5186f70857 Mon Sep 17 00:00:00 2001 From: Shannon Nelson Date: Tue, 3 Sep 2019 15:28:03 -0700 Subject: devlink: Add new info version tags for ASIC and FW The current tag set is still rather small and needs a couple more tags to help with ASIC identification and to have a more generic FW version. Cc: Jiri Pirko Acked-by: Jakub Kicinski Signed-off-by: Shannon Nelson Signed-off-by: David S. Miller --- Documentation/networking/devlink-info-versions.rst | 16 ++++++++++++++++ include/net/devlink.h | 7 +++++++ 2 files changed, 23 insertions(+) (limited to 'include/net/devlink.h') diff --git a/Documentation/networking/devlink-info-versions.rst b/Documentation/networking/devlink-info-versions.rst index 4316342b7746..4914f581b1fd 100644 --- a/Documentation/networking/devlink-info-versions.rst +++ b/Documentation/networking/devlink-info-versions.rst @@ -14,11 +14,27 @@ board.rev Board design revision. +asic.id +======= + +ASIC design identifier. + +asic.rev +======== + +ASIC design revision. + board.manufacture ================= An identifier of the company or the facility which produced the part. +fw +== + +Overall firmware version, often representing the collection of +fw.mgmt, fw.app, etc. + fw.mgmt ======= diff --git a/include/net/devlink.h b/include/net/devlink.h index 13523b0a0642..460bc629d1a4 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -458,6 +458,13 @@ enum devlink_param_generic_id { /* Maker of the board */ #define DEVLINK_INFO_VERSION_GENERIC_BOARD_MANUFACTURE "board.manufacture" +/* Part number, identifier of asic design */ +#define DEVLINK_INFO_VERSION_GENERIC_ASIC_ID "asic.id" +/* Revision of asic design */ +#define DEVLINK_INFO_VERSION_GENERIC_ASIC_REV "asic.rev" + +/* Overall FW version */ +#define DEVLINK_INFO_VERSION_GENERIC_FW "fw" /* Control processor FW version */ #define DEVLINK_INFO_VERSION_GENERIC_FW_MGMT "fw.mgmt" /* Data path microcode controlling high-speed packet processing */ -- cgit v1.2.3 From 5bbd21df5a075a59ab53030d25f9848ccca93d73 Mon Sep 17 00:00:00 2001 From: Dirk van der Merwe Date: Mon, 9 Sep 2019 00:54:18 +0100 Subject: devlink: add 'reset_dev_on_drv_probe' param Add the 'reset_dev_on_drv_probe' devlink parameter, controlling the device reset policy on driver probe. This parameter is useful in conjunction with the existing 'fw_load_policy' parameter. Signed-off-by: Dirk van der Merwe Signed-off-by: Jakub Kicinski Signed-off-by: Simon Horman Signed-off-by: David S. Miller --- Documentation/networking/devlink-params.txt | 14 ++++++++++++++ include/net/devlink.h | 5 +++++ include/uapi/linux/devlink.h | 7 +++++++ net/core/devlink.c | 5 +++++ 4 files changed, 31 insertions(+) (limited to 'include/net/devlink.h') diff --git a/Documentation/networking/devlink-params.txt b/Documentation/networking/devlink-params.txt index fadb5436188d..ddba3e9b55b1 100644 --- a/Documentation/networking/devlink-params.txt +++ b/Documentation/networking/devlink-params.txt @@ -51,3 +51,17 @@ fw_load_policy [DEVICE, GENERIC] * DEVLINK_PARAM_FW_LOAD_POLICY_VALUE_DISK (2) Load firmware currently available on host's disk. Type: u8 + +reset_dev_on_drv_probe [DEVICE, GENERIC] + Controls the device's reset policy on driver probe. + Valid values: + * DEVLINK_PARAM_RESET_DEV_ON_DRV_PROBE_VALUE_UNKNOWN (0) + Unknown or invalid value. + * DEVLINK_PARAM_RESET_DEV_ON_DRV_PROBE_VALUE_ALWAYS (1) + Always reset device on driver probe. + * DEVLINK_PARAM_RESET_DEV_ON_DRV_PROBE_VALUE_NEVER (2) + Never reset device on driver probe. + * DEVLINK_PARAM_RESET_DEV_ON_DRV_PROBE_VALUE_DISK (3) + Reset only if device firmware can be found in the + filesystem. + Type: u8 diff --git a/include/net/devlink.h b/include/net/devlink.h index 460bc629d1a4..03e4d9244ff3 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -398,6 +398,7 @@ enum devlink_param_generic_id { DEVLINK_PARAM_GENERIC_ID_MSIX_VEC_PER_PF_MAX, 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, /* add new param generic ids above here*/ __DEVLINK_PARAM_GENERIC_ID_MAX, @@ -428,6 +429,10 @@ enum devlink_param_generic_id { #define DEVLINK_PARAM_GENERIC_FW_LOAD_POLICY_NAME "fw_load_policy" #define DEVLINK_PARAM_GENERIC_FW_LOAD_POLICY_TYPE DEVLINK_PARAM_TYPE_U8 +#define DEVLINK_PARAM_GENERIC_RESET_DEV_ON_DRV_PROBE_NAME \ + "reset_dev_on_drv_probe" +#define DEVLINK_PARAM_GENERIC_RESET_DEV_ON_DRV_PROBE_TYPE DEVLINK_PARAM_TYPE_U8 + #define DEVLINK_PARAM_GENERIC(_id, _cmodes, _get, _set, _validate) \ { \ .id = DEVLINK_PARAM_GENERIC_ID_##_id, \ diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h index c25cc29a6647..1da3e83f1fd4 100644 --- a/include/uapi/linux/devlink.h +++ b/include/uapi/linux/devlink.h @@ -205,6 +205,13 @@ enum devlink_param_fw_load_policy_value { DEVLINK_PARAM_FW_LOAD_POLICY_VALUE_DISK, }; +enum devlink_param_reset_dev_on_drv_probe_value { + DEVLINK_PARAM_RESET_DEV_ON_DRV_PROBE_VALUE_UNKNOWN, + DEVLINK_PARAM_RESET_DEV_ON_DRV_PROBE_VALUE_ALWAYS, + DEVLINK_PARAM_RESET_DEV_ON_DRV_PROBE_VALUE_NEVER, + DEVLINK_PARAM_RESET_DEV_ON_DRV_PROBE_VALUE_DISK, +}; + enum { DEVLINK_ATTR_STATS_RX_PACKETS, /* u64 */ DEVLINK_ATTR_STATS_RX_BYTES, /* u64 */ diff --git a/net/core/devlink.c b/net/core/devlink.c index 6e52d639dac6..4a2fb94c44cf 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -2852,6 +2852,11 @@ static const struct devlink_param devlink_param_generic[] = { .name = DEVLINK_PARAM_GENERIC_FW_LOAD_POLICY_NAME, .type = DEVLINK_PARAM_GENERIC_FW_LOAD_POLICY_TYPE, }, + { + .id = DEVLINK_PARAM_GENERIC_ID_RESET_DEV_ON_DRV_PROBE, + .name = DEVLINK_PARAM_GENERIC_RESET_DEV_ON_DRV_PROBE_NAME, + .type = DEVLINK_PARAM_GENERIC_RESET_DEV_ON_DRV_PROBE_TYPE, + }, }; static int devlink_param_generic_verify(const struct devlink_param *param) -- cgit v1.2.3 From 97691069dc5a4135e413d3d92200d70b46df9fe5 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Thu, 12 Sep 2019 10:49:45 +0200 Subject: net: devlink: split reload op into two In order to properly implement failure indication during reload, split the reload op into two ops, one for down phase and one for up phase. Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlx4/main.c | 19 +++++++++++++++---- drivers/net/ethernet/mellanox/mlxsw/core.c | 19 +++++++++++++++---- drivers/net/netdevsim/dev.c | 13 ++++++++++--- include/net/devlink.h | 5 ++++- net/core/devlink.c | 16 ++++++++++++---- 5 files changed, 56 insertions(+), 16 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 a39c647c12dc..ef3f3d06ff1e 100644 --- a/drivers/net/ethernet/mellanox/mlx4/main.c +++ b/drivers/net/ethernet/mellanox/mlx4/main.c @@ -3935,17 +3935,27 @@ 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(struct devlink *devlink, - struct netlink_ext_ack *extack) +static int mlx4_devlink_reload_down(struct devlink *devlink, + 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; - int err; 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); + return 0; +} + +static int mlx4_devlink_reload_up(struct devlink *devlink, + 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; + int err; + err = mlx4_restart_one_up(persist->pdev, true, devlink); if (err) mlx4_err(persist->dev, "mlx4_restart_one_up failed, ret=%d\n", @@ -3956,7 +3966,8 @@ static int mlx4_devlink_reload(struct devlink *devlink, static const struct devlink_ops mlx4_devlink_ops = { .port_type_set = mlx4_devlink_port_type_set, - .reload = mlx4_devlink_reload, + .reload_down = mlx4_devlink_reload_down, + .reload_up = mlx4_devlink_reload_up, }; static int mlx4_init_one(struct pci_dev *pdev, const struct pci_device_id *id) diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c index 963a2b4b61b1..c71a1d9ea17b 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core.c @@ -984,16 +984,26 @@ mlxsw_devlink_info_get(struct devlink *devlink, struct devlink_info_req *req, return 0; } -static int mlxsw_devlink_core_bus_device_reload(struct devlink *devlink, - struct netlink_ext_ack *extack) +static int +mlxsw_devlink_core_bus_device_reload_down(struct devlink *devlink, + struct netlink_ext_ack *extack) { struct mlxsw_core *mlxsw_core = devlink_priv(devlink); - int err; if (!(mlxsw_core->bus->features & MLXSW_BUS_F_RESET)) return -EOPNOTSUPP; mlxsw_core_bus_device_unregister(mlxsw_core, true); + return 0; +} + +static int +mlxsw_devlink_core_bus_device_reload_up(struct devlink *devlink, + struct netlink_ext_ack *extack) +{ + struct mlxsw_core *mlxsw_core = devlink_priv(devlink); + int err; + err = mlxsw_core_bus_device_register(mlxsw_core->bus_info, mlxsw_core->bus, mlxsw_core->bus_priv, true, @@ -1066,7 +1076,8 @@ mlxsw_devlink_trap_group_init(struct devlink *devlink, } static const struct devlink_ops mlxsw_devlink_ops = { - .reload = mlxsw_devlink_core_bus_device_reload, + .reload_down = mlxsw_devlink_core_bus_device_reload_down, + .reload_up = mlxsw_devlink_core_bus_device_reload_up, .port_type_set = mlxsw_devlink_port_type_set, .port_split = mlxsw_devlink_port_split, .port_unsplit = mlxsw_devlink_port_unsplit, diff --git a/drivers/net/netdevsim/dev.c b/drivers/net/netdevsim/dev.c index 39cdb6c18ec0..7fba7b271a57 100644 --- a/drivers/net/netdevsim/dev.c +++ b/drivers/net/netdevsim/dev.c @@ -521,8 +521,14 @@ static void nsim_dev_traps_exit(struct devlink *devlink) kfree(nsim_dev->trap_data); } -static int nsim_dev_reload(struct devlink *devlink, - struct netlink_ext_ack *extack) +static int nsim_dev_reload_down(struct devlink *devlink, + struct netlink_ext_ack *extack) +{ + return 0; +} + +static int nsim_dev_reload_up(struct devlink *devlink, + struct netlink_ext_ack *extack) { enum nsim_resource_id res_ids[] = { NSIM_RESOURCE_IPV4_FIB, NSIM_RESOURCE_IPV4_FIB_RULES, @@ -638,7 +644,8 @@ nsim_dev_devlink_trap_action_set(struct devlink *devlink, } static const struct devlink_ops nsim_dev_devlink_ops = { - .reload = nsim_dev_reload, + .reload_down = nsim_dev_reload_down, + .reload_up = nsim_dev_reload_up, .flash_update = nsim_dev_flash_update, .trap_init = nsim_dev_devlink_trap_init, .trap_action_set = nsim_dev_devlink_trap_action_set, diff --git a/include/net/devlink.h b/include/net/devlink.h index 03e4d9244ff3..ab8d56d12ffd 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -642,7 +642,10 @@ enum devlink_trap_group_generic_id { } struct devlink_ops { - int (*reload)(struct devlink *devlink, struct netlink_ext_ack *extack); + int (*reload_down)(struct devlink *devlink, + struct netlink_ext_ack *extack); + int (*reload_up)(struct devlink *devlink, + struct netlink_ext_ack *extack); int (*port_type_set)(struct devlink_port *devlink_port, enum devlink_port_type port_type); int (*port_split)(struct devlink *devlink, unsigned int port_index, diff --git a/net/core/devlink.c b/net/core/devlink.c index 4a2fb94c44cf..9e522639693d 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -2672,12 +2672,17 @@ devlink_resources_validate(struct devlink *devlink, return err; } +static bool devlink_reload_supported(struct devlink *devlink) +{ + return devlink->ops->reload_down && devlink->ops->reload_up; +} + static int devlink_nl_cmd_reload(struct sk_buff *skb, struct genl_info *info) { struct devlink *devlink = info->user_ptr[0]; int err; - if (!devlink->ops->reload) + if (!devlink_reload_supported(devlink)) return -EOPNOTSUPP; err = devlink_resources_validate(devlink, NULL, info); @@ -2685,7 +2690,10 @@ 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; } - return devlink->ops->reload(devlink, info->extack); + err = devlink->ops->reload_down(devlink, info->extack); + if (err) + return err; + return devlink->ops->reload_up(devlink, info->extack); } static int devlink_nl_flash_update_fill(struct sk_buff *msg, @@ -7150,7 +7158,7 @@ __devlink_param_driverinit_value_set(struct devlink *devlink, int devlink_param_driverinit_value_get(struct devlink *devlink, u32 param_id, union devlink_param_value *init_val) { - if (!devlink->ops->reload) + if (!devlink_reload_supported(devlink)) return -EOPNOTSUPP; return __devlink_param_driverinit_value_get(&devlink->param_list, @@ -7197,7 +7205,7 @@ int devlink_port_param_driverinit_value_get(struct devlink_port *devlink_port, { struct devlink *devlink = devlink_port->devlink; - if (!devlink->ops->reload) + if (!devlink_reload_supported(devlink)) return -EOPNOTSUPP; return __devlink_param_driverinit_value_get(&devlink_port->param_list, -- cgit v1.2.3 From 2670ac2625f98557fd7e083f8aa22c297e49039e Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Thu, 12 Sep 2019 10:49:46 +0200 Subject: net: devlink: move reload fail indication to devlink core and expose to user Currently the fact that devlink reload failed is stored in drivers. Move this flag into devlink core. Also, expose it to the user. Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- drivers/net/ethernet/mellanox/mlxsw/core.c | 15 +++++---------- include/net/devlink.h | 3 +++ include/uapi/linux/devlink.h | 2 ++ net/core/devlink.c | 21 ++++++++++++++++++++- 4 files changed, 30 insertions(+), 11 deletions(-) (limited to 'include/net/devlink.h') diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c index c71a1d9ea17b..3fa96076e8a5 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core.c @@ -80,7 +80,6 @@ struct mlxsw_core { struct mlxsw_thermal *thermal; struct mlxsw_core_port *ports; unsigned int max_ports; - bool reload_fail; bool fw_flash_in_progress; unsigned long driver_priv[0]; /* driver_priv has to be always the last item */ @@ -1002,15 +1001,11 @@ mlxsw_devlink_core_bus_device_reload_up(struct devlink *devlink, struct netlink_ext_ack *extack) { struct mlxsw_core *mlxsw_core = devlink_priv(devlink); - int err; - - err = mlxsw_core_bus_device_register(mlxsw_core->bus_info, - mlxsw_core->bus, - mlxsw_core->bus_priv, true, - devlink); - mlxsw_core->reload_fail = !!err; - return err; + return mlxsw_core_bus_device_register(mlxsw_core->bus_info, + mlxsw_core->bus, + mlxsw_core->bus_priv, true, + devlink); } static int mlxsw_devlink_flash_update(struct devlink *devlink, @@ -1254,7 +1249,7 @@ void mlxsw_core_bus_device_unregister(struct mlxsw_core *mlxsw_core, { struct devlink *devlink = priv_to_devlink(mlxsw_core); - if (mlxsw_core->reload_fail) { + if (devlink_is_reload_failed(devlink)) { if (!reload) /* Only the parts that were not de-initialized in the * failed reload attempt need to be de-initialized. diff --git a/include/net/devlink.h b/include/net/devlink.h index ab8d56d12ffd..23e4b65ec9df 100644 --- a/include/net/devlink.h +++ b/include/net/devlink.h @@ -38,6 +38,7 @@ struct devlink { struct device *dev; possible_net_t _net; struct mutex lock; + bool reload_failed; char priv[0] __aligned(NETDEV_ALIGN); }; @@ -945,6 +946,8 @@ void devlink_health_reporter_state_update(struct devlink_health_reporter *reporter, enum devlink_health_reporter_state state); +bool devlink_is_reload_failed(const struct devlink *devlink); + void devlink_flash_update_begin_notify(struct devlink *devlink); void devlink_flash_update_end_notify(struct devlink *devlink); void devlink_flash_update_status_notify(struct devlink *devlink, diff --git a/include/uapi/linux/devlink.h b/include/uapi/linux/devlink.h index 8da5365850cd..580b7a2e40e1 100644 --- a/include/uapi/linux/devlink.h +++ b/include/uapi/linux/devlink.h @@ -419,6 +419,8 @@ enum devlink_attr { DEVLINK_ATTR_TRAP_METADATA, /* nested */ DEVLINK_ATTR_TRAP_GROUP_NAME, /* string */ + DEVLINK_ATTR_RELOAD_FAILED, /* u8 0 or 1 */ + /* 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 9e522639693d..e48680efe54a 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -471,6 +471,8 @@ static int devlink_nl_fill(struct sk_buff *msg, struct devlink *devlink, if (devlink_nl_put_handle(msg, devlink)) goto nla_put_failure; + if (nla_put_u8(msg, DEVLINK_ATTR_RELOAD_FAILED, devlink->reload_failed)) + goto nla_put_failure; genlmsg_end(msg, hdr); return 0; @@ -2677,6 +2679,21 @@ static bool devlink_reload_supported(struct devlink *devlink) return devlink->ops->reload_down && devlink->ops->reload_up; } +static void devlink_reload_failed_set(struct devlink *devlink, + bool reload_failed) +{ + if (devlink->reload_failed == reload_failed) + return; + devlink->reload_failed = reload_failed; + devlink_notify(devlink, DEVLINK_CMD_NEW); +} + +bool devlink_is_reload_failed(const struct devlink *devlink) +{ + return devlink->reload_failed; +} +EXPORT_SYMBOL_GPL(devlink_is_reload_failed); + static int devlink_nl_cmd_reload(struct sk_buff *skb, struct genl_info *info) { struct devlink *devlink = info->user_ptr[0]; @@ -2693,7 +2710,9 @@ static int devlink_nl_cmd_reload(struct sk_buff *skb, struct genl_info *info) err = devlink->ops->reload_down(devlink, info->extack); if (err) return err; - return devlink->ops->reload_up(devlink, info->extack); + err = devlink->ops->reload_up(devlink, info->extack); + devlink_reload_failed_set(devlink, !!err); + return err; } static int devlink_nl_flash_update_fill(struct sk_buff *msg, -- cgit v1.2.3