diff options
Diffstat (limited to 'net/core')
-rw-r--r-- | net/core/Makefile | 1 | ||||
-rw-r--r-- | net/core/dev.c | 46 | ||||
-rw-r--r-- | net/core/devlink.c | 563 | ||||
-rw-r--r-- | net/core/filter.c | 21 | ||||
-rw-r--r-- | net/core/flow_dissector.c | 3 | ||||
-rw-r--r-- | net/core/neighbour.c | 196 | ||||
-rw-r--r-- | net/core/net-sysfs.c | 57 | ||||
-rw-r--r-- | net/core/net_namespace.c | 4 | ||||
-rw-r--r-- | net/core/of_net.c | 170 | ||||
-rw-r--r-- | net/core/rtnetlink.c | 4 | ||||
-rw-r--r-- | net/core/skbuff.c | 27 | ||||
-rw-r--r-- | net/core/sock.c | 104 | ||||
-rw-r--r-- | net/core/stream.c | 2 |
13 files changed, 799 insertions, 399 deletions
diff --git a/net/core/Makefile b/net/core/Makefile index 35ced6201814..4268846f2f47 100644 --- a/net/core/Makefile +++ b/net/core/Makefile @@ -36,3 +36,4 @@ obj-$(CONFIG_FAILOVER) += failover.o obj-$(CONFIG_NET_SOCK_MSG) += skmsg.o obj-$(CONFIG_BPF_SYSCALL) += sock_map.o obj-$(CONFIG_BPF_SYSCALL) += bpf_sk_storage.o +obj-$(CONFIG_OF) += of_net.o diff --git a/net/core/dev.c b/net/core/dev.c index 7ee9fecd3aff..eb61a8821b3a 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -303,6 +303,12 @@ static struct netdev_name_node *netdev_name_node_lookup_rcu(struct net *net, return NULL; } +bool netdev_name_in_use(struct net *net, const char *name) +{ + return netdev_name_node_lookup(net, name); +} +EXPORT_SYMBOL(netdev_name_in_use); + int netdev_name_node_alt_create(struct net_device *dev, const char *name) { struct netdev_name_node *name_node; @@ -1133,7 +1139,7 @@ static int __dev_alloc_name(struct net *net, const char *name, char *buf) } snprintf(buf, IFNAMSIZ, name, i); - if (!__dev_get_by_name(net, buf)) + if (!netdev_name_in_use(net, buf)) return i; /* It is possible to run out of possible slots @@ -1187,7 +1193,7 @@ static int dev_get_valid_name(struct net *net, struct net_device *dev, if (strchr(name, '%')) return dev_alloc_name_ns(net, dev, name); - else if (__dev_get_by_name(net, name)) + else if (netdev_name_in_use(net, name)) return -EEXIST; else if (dev->name != name) strlcpy(dev->name, name, IFNAMSIZ); @@ -2921,6 +2927,8 @@ int netif_set_real_num_tx_queues(struct net_device *dev, unsigned int txq) if (dev->num_tc) netif_setup_tc(dev, txq); + dev_qdisc_change_real_num_tx(dev, txq); + dev->real_num_tx_queues = txq; if (disabling) { @@ -5837,7 +5845,7 @@ static void gro_normal_one(struct napi_struct *napi, struct sk_buff *skb, int se gro_normal_list(napi); } -static int napi_gro_complete(struct napi_struct *napi, struct sk_buff *skb) +static void napi_gro_complete(struct napi_struct *napi, struct sk_buff *skb) { struct packet_offload *ptype; __be16 type = skb->protocol; @@ -5866,12 +5874,11 @@ static int napi_gro_complete(struct napi_struct *napi, struct sk_buff *skb) if (err) { WARN_ON(&ptype->list == head); kfree_skb(skb); - return NET_RX_SUCCESS; + return; } out: gro_normal_one(napi, skb, NAPI_GRO_CB(skb)->count); - return NET_RX_SUCCESS; } static void __napi_gro_flush_chain(struct napi_struct *napi, u32 index, @@ -6898,19 +6905,25 @@ EXPORT_SYMBOL(netif_napi_add); void napi_disable(struct napi_struct *n) { + unsigned long val, new; + might_sleep(); set_bit(NAPI_STATE_DISABLE, &n->state); - while (test_and_set_bit(NAPI_STATE_SCHED, &n->state)) - msleep(1); - while (test_and_set_bit(NAPI_STATE_NPSVC, &n->state)) - msleep(1); + do { + val = READ_ONCE(n->state); + if (val & (NAPIF_STATE_SCHED | NAPIF_STATE_NPSVC)) { + usleep_range(20, 200); + continue; + } + + new = val | NAPIF_STATE_SCHED | NAPIF_STATE_NPSVC; + new &= ~(NAPIF_STATE_THREADED | NAPIF_STATE_PREFER_BUSY_POLL); + } while (cmpxchg(&n->state, val, new) != val); hrtimer_cancel(&n->timer); - clear_bit(NAPI_STATE_PREFER_BUSY_POLL, &n->state); clear_bit(NAPI_STATE_DISABLE, &n->state); - clear_bit(NAPI_STATE_THREADED, &n->state); } EXPORT_SYMBOL(napi_disable); @@ -9152,14 +9165,11 @@ int dev_get_port_parent_id(struct net_device *dev, } err = devlink_compat_switch_id_get(dev, ppid); - if (!err || err != -EOPNOTSUPP) + if (!recurse || err != -EOPNOTSUPP) return err; - if (!recurse) - return -EOPNOTSUPP; - netdev_for_each_lower_dev(dev, lower_dev, iter) { - err = dev_get_port_parent_id(lower_dev, ppid, recurse); + err = dev_get_port_parent_id(lower_dev, ppid, true); if (err) break; if (!first.id_len) @@ -11146,7 +11156,7 @@ int __dev_change_net_namespace(struct net_device *dev, struct net *net, * we can use it in the destination network namespace. */ err = -EEXIST; - if (__dev_get_by_name(net, dev->name)) { + if (netdev_name_in_use(net, dev->name)) { /* We get here if we can't use the current device name */ if (!pat) goto out; @@ -11499,7 +11509,7 @@ static void __net_exit default_device_exit(struct net *net) /* Push remaining network devices to init_net */ snprintf(fb_name, IFNAMSIZ, "dev%d", dev->ifindex); - if (__dev_get_by_name(&init_net, fb_name)) + if (netdev_name_in_use(&init_net, fb_name)) snprintf(fb_name, IFNAMSIZ, "dev%%d"); err = dev_change_net_namespace(dev, &init_net, fb_name); if (err) { diff --git a/net/core/devlink.c b/net/core/devlink.c index a856ae401ea5..3ce6147a2fe8 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -30,6 +30,63 @@ #define CREATE_TRACE_POINTS #include <trace/events/devlink.h> +#define DEVLINK_RELOAD_STATS_ARRAY_SIZE \ + (__DEVLINK_RELOAD_LIMIT_MAX * __DEVLINK_RELOAD_ACTION_MAX) + +struct devlink_dev_stats { + u32 reload_stats[DEVLINK_RELOAD_STATS_ARRAY_SIZE]; + u32 remote_reload_stats[DEVLINK_RELOAD_STATS_ARRAY_SIZE]; +}; + +struct devlink { + u32 index; + struct list_head port_list; + struct list_head rate_list; + struct list_head sb_list; + struct list_head dpipe_table_list; + struct list_head resource_list; + struct list_head param_list; + struct list_head region_list; + 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; + struct list_head trap_policer_list; + const struct devlink_ops *ops; + u64 features; + struct xarray snapshot_ids; + struct devlink_dev_stats stats; + struct device *dev; + possible_net_t _net; + /* Serializes access to devlink instance specific objects such as + * port, sb, dpipe, resource, params, region, traps and more. + */ + struct mutex lock; + u8 reload_failed:1; + refcount_t refcount; + struct completion comp; + char priv[0] __aligned(NETDEV_ALIGN); +}; + +void *devlink_priv(struct devlink *devlink) +{ + return &devlink->priv; +} +EXPORT_SYMBOL_GPL(devlink_priv); + +struct devlink *priv_to_devlink(void *priv) +{ + return container_of(priv, struct devlink, priv); +} +EXPORT_SYMBOL_GPL(priv_to_devlink); + +struct device *devlink_to_dev(const struct devlink *devlink) +{ + return devlink->dev; +} +EXPORT_SYMBOL_GPL(devlink_to_dev); + static struct devlink_dpipe_field devlink_dpipe_fields_ethernet[] = { { .name = "destination mac", @@ -95,6 +152,22 @@ static const struct nla_policy devlink_function_nl_policy[DEVLINK_PORT_FUNCTION_ static DEFINE_XARRAY_FLAGS(devlinks, XA_FLAGS_ALLOC); #define DEVLINK_REGISTERED XA_MARK_1 +/* devlink instances are open to the access from the user space after + * devlink_register() call. Such logical barrier allows us to have certain + * expectations related to locking. + * + * Before *_register() - we are in initialization stage and no parallel + * access possible to the devlink instance. All drivers perform that phase + * by implicitly holding device_lock. + * + * After *_register() - users and driver can access devlink instance at + * the same time. + */ +#define ASSERT_DEVLINK_REGISTERED(d) \ + WARN_ON_ONCE(!xa_get_mark(&devlinks, (d)->index, DEVLINK_REGISTERED)) +#define ASSERT_DEVLINK_NOT_REGISTERED(d) \ + WARN_ON_ONCE(xa_get_mark(&devlinks, (d)->index, DEVLINK_REGISTERED)) + /* devlink_mutex * * An overall lock guarding every operation coming from userspace. @@ -742,6 +815,7 @@ static void devlink_notify(struct devlink *devlink, enum devlink_command cmd) int err; WARN_ON(cmd != DEVLINK_CMD_NEW && cmd != DEVLINK_CMD_DEL); + WARN_ON(!xa_get_mark(&devlinks, devlink->index, DEVLINK_REGISTERED)); msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) @@ -1040,11 +1114,15 @@ nla_put_failure: static void devlink_port_notify(struct devlink_port *devlink_port, enum devlink_command cmd) { + struct devlink *devlink = devlink_port->devlink; struct sk_buff *msg; int err; WARN_ON(cmd != DEVLINK_CMD_PORT_NEW && cmd != DEVLINK_CMD_PORT_DEL); + if (!xa_get_mark(&devlinks, devlink->index, DEVLINK_REGISTERED)) + return; + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return; @@ -1055,19 +1133,22 @@ static void devlink_port_notify(struct devlink_port *devlink_port, return; } - genlmsg_multicast_netns(&devlink_nl_family, - devlink_net(devlink_port->devlink), msg, 0, - DEVLINK_MCGRP_CONFIG, GFP_KERNEL); + genlmsg_multicast_netns(&devlink_nl_family, devlink_net(devlink), msg, + 0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL); } static void devlink_rate_notify(struct devlink_rate *devlink_rate, enum devlink_command cmd) { + struct devlink *devlink = devlink_rate->devlink; struct sk_buff *msg; int err; WARN_ON(cmd != DEVLINK_CMD_RATE_NEW && cmd != DEVLINK_CMD_RATE_DEL); + if (!xa_get_mark(&devlinks, devlink->index, DEVLINK_REGISTERED)) + return; + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return; @@ -1078,9 +1159,8 @@ static void devlink_rate_notify(struct devlink_rate *devlink_rate, return; } - genlmsg_multicast_netns(&devlink_nl_family, - devlink_net(devlink_rate->devlink), msg, 0, - DEVLINK_MCGRP_CONFIG, GFP_KERNEL); + genlmsg_multicast_netns(&devlink_nl_family, devlink_net(devlink), msg, + 0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL); } static int devlink_nl_cmd_rate_get_dumpit(struct sk_buff *msg, @@ -3952,9 +4032,6 @@ static int devlink_reload(struct devlink *devlink, struct net *dest_net, struct net *curr_net; int err; - if (!devlink->reload_enabled) - return -EOPNOTSUPP; - memcpy(remote_reload_stats, devlink->stats.remote_reload_stats, sizeof(remote_reload_stats)); @@ -4022,7 +4099,7 @@ static int devlink_nl_cmd_reload(struct sk_buff *skb, struct genl_info *info) u32 actions_performed; int err; - if (!devlink_reload_supported(devlink->ops)) + if (!(devlink->features & DEVLINK_F_RELOAD)) return -EOPNOTSUPP; err = devlink_resources_validate(devlink, NULL, info); @@ -4150,6 +4227,7 @@ static void __devlink_flash_update_notify(struct devlink *devlink, WARN_ON(cmd != DEVLINK_CMD_FLASH_UPDATE && cmd != DEVLINK_CMD_FLASH_UPDATE_END && cmd != DEVLINK_CMD_FLASH_UPDATE_STATUS); + WARN_ON(!xa_get_mark(&devlinks, devlink->index, DEVLINK_REGISTERED)); msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) @@ -5070,6 +5148,11 @@ static int devlink_nl_region_fill(struct sk_buff *msg, struct devlink *devlink, if (err) goto nla_put_failure; + err = nla_put_u32(msg, DEVLINK_ATTR_REGION_MAX_SNAPSHOTS, + region->max_snapshots); + if (err) + goto nla_put_failure; + err = devlink_nl_region_snapshots_id_put(msg, devlink, region); if (err) goto nla_put_failure; @@ -5145,17 +5228,19 @@ static void devlink_nl_region_notify(struct devlink_region *region, struct devlink_snapshot *snapshot, enum devlink_command cmd) { + struct devlink *devlink = region->devlink; struct sk_buff *msg; WARN_ON(cmd != DEVLINK_CMD_REGION_NEW && cmd != DEVLINK_CMD_REGION_DEL); + if (!xa_get_mark(&devlinks, devlink->index, DEVLINK_REGISTERED)) + return; msg = devlink_nl_region_notify_build(region, snapshot, cmd, 0, 0); if (IS_ERR(msg)) return; - genlmsg_multicast_netns(&devlink_nl_family, - devlink_net(region->devlink), msg, 0, - DEVLINK_MCGRP_CONFIG, GFP_KERNEL); + genlmsg_multicast_netns(&devlink_nl_family, devlink_net(devlink), msg, + 0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL); } /** @@ -6269,23 +6354,21 @@ static int devlink_fmsg_put_value(struct devlink_fmsg *fmsg, return 0; } -int devlink_fmsg_bool_put(struct devlink_fmsg *fmsg, bool value) +static int devlink_fmsg_bool_put(struct devlink_fmsg *fmsg, bool value) { if (fmsg->putting_binary) return -EINVAL; return devlink_fmsg_put_value(fmsg, &value, sizeof(value), NLA_FLAG); } -EXPORT_SYMBOL_GPL(devlink_fmsg_bool_put); -int devlink_fmsg_u8_put(struct devlink_fmsg *fmsg, u8 value) +static int devlink_fmsg_u8_put(struct devlink_fmsg *fmsg, u8 value) { if (fmsg->putting_binary) return -EINVAL; return devlink_fmsg_put_value(fmsg, &value, sizeof(value), NLA_U8); } -EXPORT_SYMBOL_GPL(devlink_fmsg_u8_put); int devlink_fmsg_u32_put(struct devlink_fmsg *fmsg, u32 value) { @@ -6296,14 +6379,13 @@ int devlink_fmsg_u32_put(struct devlink_fmsg *fmsg, u32 value) } EXPORT_SYMBOL_GPL(devlink_fmsg_u32_put); -int devlink_fmsg_u64_put(struct devlink_fmsg *fmsg, u64 value) +static int devlink_fmsg_u64_put(struct devlink_fmsg *fmsg, u64 value) { if (fmsg->putting_binary) return -EINVAL; return devlink_fmsg_put_value(fmsg, &value, sizeof(value), NLA_U64); } -EXPORT_SYMBOL_GPL(devlink_fmsg_u64_put); int devlink_fmsg_string_put(struct devlink_fmsg *fmsg, const char *value) { @@ -6923,10 +7005,12 @@ genlmsg_cancel: static void devlink_recover_notify(struct devlink_health_reporter *reporter, enum devlink_command cmd) { + struct devlink *devlink = reporter->devlink; struct sk_buff *msg; int err; WARN_ON(cmd != DEVLINK_CMD_HEALTH_REPORTER_RECOVER); + WARN_ON(!xa_get_mark(&devlinks, devlink->index, DEVLINK_REGISTERED)); msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) @@ -6938,9 +7022,8 @@ static void devlink_recover_notify(struct devlink_health_reporter *reporter, return; } - genlmsg_multicast_netns(&devlink_nl_family, - devlink_net(reporter->devlink), - msg, 0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL); + genlmsg_multicast_netns(&devlink_nl_family, devlink_net(devlink), msg, + 0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL); } void @@ -8900,6 +8983,25 @@ static bool devlink_reload_actions_valid(const struct devlink_ops *ops) } /** + * devlink_set_features - Set devlink supported features + * + * @devlink: devlink + * @features: devlink support features + * + * This interface allows us to set reload ops separatelly from + * the devlink_alloc. + */ +void devlink_set_features(struct devlink *devlink, u64 features) +{ + ASSERT_DEVLINK_NOT_REGISTERED(devlink); + + WARN_ON(features & DEVLINK_F_RELOAD && + !devlink_reload_supported(devlink->ops)); + devlink->features = features; +} +EXPORT_SYMBOL_GPL(devlink_set_features); + +/** * devlink_alloc_ns - Allocate new devlink instance resources * in specific namespace * @@ -8958,18 +9060,99 @@ struct devlink *devlink_alloc_ns(const struct devlink_ops *ops, } EXPORT_SYMBOL_GPL(devlink_alloc_ns); +static void +devlink_trap_policer_notify(struct devlink *devlink, + const struct devlink_trap_policer_item *policer_item, + enum devlink_command cmd); +static void +devlink_trap_group_notify(struct devlink *devlink, + const struct devlink_trap_group_item *group_item, + enum devlink_command cmd); +static void devlink_trap_notify(struct devlink *devlink, + const struct devlink_trap_item *trap_item, + enum devlink_command cmd); + +static void devlink_notify_register(struct devlink *devlink) +{ + struct devlink_trap_policer_item *policer_item; + struct devlink_trap_group_item *group_item; + struct devlink_trap_item *trap_item; + struct devlink_port *devlink_port; + struct devlink_rate *rate_node; + struct devlink_region *region; + + devlink_notify(devlink, DEVLINK_CMD_NEW); + list_for_each_entry(devlink_port, &devlink->port_list, list) + devlink_port_notify(devlink_port, DEVLINK_CMD_PORT_NEW); + + list_for_each_entry(policer_item, &devlink->trap_policer_list, list) + devlink_trap_policer_notify(devlink, policer_item, + DEVLINK_CMD_TRAP_POLICER_NEW); + + list_for_each_entry(group_item, &devlink->trap_group_list, list) + devlink_trap_group_notify(devlink, group_item, + DEVLINK_CMD_TRAP_GROUP_NEW); + + list_for_each_entry(trap_item, &devlink->trap_list, list) + devlink_trap_notify(devlink, trap_item, DEVLINK_CMD_TRAP_NEW); + + list_for_each_entry(rate_node, &devlink->rate_list, list) + devlink_rate_notify(rate_node, DEVLINK_CMD_RATE_NEW); + + list_for_each_entry(region, &devlink->region_list, list) + devlink_nl_region_notify(region, NULL, DEVLINK_CMD_REGION_NEW); + + devlink_params_publish(devlink); +} + +static void devlink_notify_unregister(struct devlink *devlink) +{ + struct devlink_trap_policer_item *policer_item; + struct devlink_trap_group_item *group_item; + struct devlink_trap_item *trap_item; + struct devlink_port *devlink_port; + struct devlink_rate *rate_node; + struct devlink_region *region; + + devlink_params_unpublish(devlink); + + list_for_each_entry_reverse(region, &devlink->region_list, list) + devlink_nl_region_notify(region, NULL, DEVLINK_CMD_REGION_DEL); + + list_for_each_entry_reverse(rate_node, &devlink->rate_list, list) + devlink_rate_notify(rate_node, DEVLINK_CMD_RATE_DEL); + + list_for_each_entry_reverse(trap_item, &devlink->trap_list, list) + devlink_trap_notify(devlink, trap_item, DEVLINK_CMD_TRAP_DEL); + + list_for_each_entry_reverse(group_item, &devlink->trap_group_list, list) + devlink_trap_group_notify(devlink, group_item, + DEVLINK_CMD_TRAP_GROUP_DEL); + list_for_each_entry_reverse(policer_item, &devlink->trap_policer_list, + list) + devlink_trap_policer_notify(devlink, policer_item, + DEVLINK_CMD_TRAP_POLICER_DEL); + + list_for_each_entry_reverse(devlink_port, &devlink->port_list, list) + devlink_port_notify(devlink_port, DEVLINK_CMD_PORT_DEL); + devlink_notify(devlink, DEVLINK_CMD_DEL); +} + /** * devlink_register - Register devlink instance * * @devlink: devlink */ -int devlink_register(struct devlink *devlink) +void devlink_register(struct devlink *devlink) { + ASSERT_DEVLINK_NOT_REGISTERED(devlink); + /* Make sure that we are in .probe() routine */ + device_lock_assert(devlink->dev); + mutex_lock(&devlink_mutex); xa_set_mark(&devlinks, devlink->index, DEVLINK_REGISTERED); - devlink_notify(devlink, DEVLINK_CMD_NEW); + devlink_notify_register(devlink); mutex_unlock(&devlink_mutex); - return 0; } EXPORT_SYMBOL_GPL(devlink_register); @@ -8980,60 +9163,29 @@ EXPORT_SYMBOL_GPL(devlink_register); */ void devlink_unregister(struct devlink *devlink) { + ASSERT_DEVLINK_REGISTERED(devlink); + /* Make sure that we are in .remove() routine */ + device_lock_assert(devlink->dev); + devlink_put(devlink); wait_for_completion(&devlink->comp); mutex_lock(&devlink_mutex); - WARN_ON(devlink_reload_supported(devlink->ops) && - devlink->reload_enabled); - devlink_notify(devlink, DEVLINK_CMD_DEL); + devlink_notify_unregister(devlink); xa_clear_mark(&devlinks, devlink->index, DEVLINK_REGISTERED); 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 * * @devlink: devlink */ void devlink_free(struct devlink *devlink) { + ASSERT_DEVLINK_NOT_REGISTERED(devlink); + mutex_destroy(&devlink->reporters_lock); mutex_destroy(&devlink->lock); WARN_ON(!list_empty(&devlink->trap_policer_list)); @@ -10090,6 +10242,9 @@ void devlink_params_publish(struct devlink *devlink) { struct devlink_param_item *param_item; + if (!xa_get_mark(&devlinks, devlink->index, DEVLINK_REGISTERED)) + return; + list_for_each_entry(param_item, &devlink->param_list, list) { if (param_item->published) continue; @@ -10122,102 +10277,25 @@ void devlink_params_unpublish(struct devlink *devlink) EXPORT_SYMBOL_GPL(devlink_params_unpublish); /** - * devlink_param_publish - publish one configuration parameter - * - * @devlink: devlink - * @param: one configuration parameter - * - * Publish previously registered configuration parameter. - */ -void devlink_param_publish(struct devlink *devlink, - const struct devlink_param *param) -{ - struct devlink_param_item *param_item; - - list_for_each_entry(param_item, &devlink->param_list, list) { - if (param_item->param != param || param_item->published) - continue; - param_item->published = true; - devlink_param_notify(devlink, 0, param_item, - DEVLINK_CMD_PARAM_NEW); - break; - } -} -EXPORT_SYMBOL_GPL(devlink_param_publish); - -/** - * devlink_param_unpublish - unpublish one configuration parameter + * devlink_param_driverinit_value_get - get configuration parameter + * value for driver initializing * - * @devlink: devlink - * @param: one configuration parameter + * @devlink: devlink + * @param_id: parameter ID + * @init_val: value of parameter in driverinit configuration mode * - * Unpublish previously registered configuration parameter. + * This function should be used by the driver to get driverinit + * configuration for initialization after reload command. */ -void devlink_param_unpublish(struct devlink *devlink, - const struct devlink_param *param) +int devlink_param_driverinit_value_get(struct devlink *devlink, u32 param_id, + union devlink_param_value *init_val) { struct devlink_param_item *param_item; - list_for_each_entry(param_item, &devlink->param_list, list) { - if (param_item->param != param || !param_item->published) - continue; - param_item->published = false; - devlink_param_notify(devlink, 0, param_item, - DEVLINK_CMD_PARAM_DEL); - break; - } -} -EXPORT_SYMBOL_GPL(devlink_param_unpublish); - -/** - * devlink_port_params_register - register port configuration parameters - * - * @devlink_port: devlink port - * @params: configuration parameters array - * @params_count: number of parameters provided - * - * Register the configuration parameters supported by the port. - */ -int devlink_port_params_register(struct devlink_port *devlink_port, - const struct devlink_param *params, - size_t params_count) -{ - return __devlink_params_register(devlink_port->devlink, - devlink_port->index, - &devlink_port->param_list, params, - params_count, - DEVLINK_CMD_PORT_PARAM_NEW, - DEVLINK_CMD_PORT_PARAM_DEL); -} -EXPORT_SYMBOL_GPL(devlink_port_params_register); - -/** - * devlink_port_params_unregister - unregister port configuration - * parameters - * - * @devlink_port: devlink port - * @params: configuration parameters array - * @params_count: number of parameters provided - */ -void devlink_port_params_unregister(struct devlink_port *devlink_port, - const struct devlink_param *params, - size_t params_count) -{ - return __devlink_params_unregister(devlink_port->devlink, - devlink_port->index, - &devlink_port->param_list, - params, params_count, - DEVLINK_CMD_PORT_PARAM_DEL); -} -EXPORT_SYMBOL_GPL(devlink_port_params_unregister); - -static int -__devlink_param_driverinit_value_get(struct list_head *param_list, u32 param_id, - union devlink_param_value *init_val) -{ - struct devlink_param_item *param_item; + if (!devlink_reload_supported(devlink->ops)) + return -EOPNOTSUPP; - param_item = devlink_param_find_by_id(param_list, param_id); + param_item = devlink_param_find_by_id(&devlink->param_list, param_id); if (!param_item) return -EINVAL; @@ -10233,54 +10311,6 @@ __devlink_param_driverinit_value_get(struct list_head *param_list, u32 param_id, return 0; } - -static int -__devlink_param_driverinit_value_set(struct devlink *devlink, - unsigned int port_index, - struct list_head *param_list, u32 param_id, - union devlink_param_value init_val, - enum devlink_command cmd) -{ - struct devlink_param_item *param_item; - - param_item = devlink_param_find_by_id(param_list, param_id); - if (!param_item) - return -EINVAL; - - if (!devlink_param_cmode_is_supported(param_item->param, - DEVLINK_PARAM_CMODE_DRIVERINIT)) - return -EOPNOTSUPP; - - if (param_item->param->type == DEVLINK_PARAM_TYPE_STRING) - strcpy(param_item->driverinit_value.vstr, init_val.vstr); - else - param_item->driverinit_value = init_val; - param_item->driverinit_value_valid = true; - - devlink_param_notify(devlink, port_index, param_item, cmd); - return 0; -} - -/** - * devlink_param_driverinit_value_get - get configuration parameter - * value for driver initializing - * - * @devlink: devlink - * @param_id: parameter ID - * @init_val: value of parameter in driverinit configuration mode - * - * This function should be used by the driver to get driverinit - * configuration for initialization after reload command. - */ -int devlink_param_driverinit_value_get(struct devlink *devlink, u32 param_id, - union devlink_param_value *init_val) -{ - if (!devlink_reload_supported(devlink->ops)) - return -EOPNOTSUPP; - - return __devlink_param_driverinit_value_get(&devlink->param_list, - param_id, init_val); -} EXPORT_SYMBOL_GPL(devlink_param_driverinit_value_get); /** @@ -10298,61 +10328,26 @@ EXPORT_SYMBOL_GPL(devlink_param_driverinit_value_get); int devlink_param_driverinit_value_set(struct devlink *devlink, u32 param_id, union devlink_param_value init_val) { - return __devlink_param_driverinit_value_set(devlink, 0, - &devlink->param_list, - param_id, init_val, - DEVLINK_CMD_PARAM_NEW); -} -EXPORT_SYMBOL_GPL(devlink_param_driverinit_value_set); + struct devlink_param_item *param_item; -/** - * devlink_port_param_driverinit_value_get - get configuration parameter - * value for driver initializing - * - * @devlink_port: devlink_port - * @param_id: parameter ID - * @init_val: value of parameter in driverinit configuration mode - * - * This function should be used by the driver to get driverinit - * configuration for initialization after reload command. - */ -int devlink_port_param_driverinit_value_get(struct devlink_port *devlink_port, - u32 param_id, - union devlink_param_value *init_val) -{ - struct devlink *devlink = devlink_port->devlink; + param_item = devlink_param_find_by_id(&devlink->param_list, param_id); + if (!param_item) + return -EINVAL; - if (!devlink_reload_supported(devlink->ops)) + if (!devlink_param_cmode_is_supported(param_item->param, + DEVLINK_PARAM_CMODE_DRIVERINIT)) return -EOPNOTSUPP; - return __devlink_param_driverinit_value_get(&devlink_port->param_list, - param_id, init_val); -} -EXPORT_SYMBOL_GPL(devlink_port_param_driverinit_value_get); + if (param_item->param->type == DEVLINK_PARAM_TYPE_STRING) + strcpy(param_item->driverinit_value.vstr, init_val.vstr); + else + param_item->driverinit_value = init_val; + param_item->driverinit_value_valid = true; -/** - * devlink_port_param_driverinit_value_set - set value of configuration - * parameter for driverinit - * configuration mode - * - * @devlink_port: devlink_port - * @param_id: parameter ID - * @init_val: value of parameter to set for driverinit configuration mode - * - * This function should be used by the driver to set driverinit - * configuration mode default value. - */ -int devlink_port_param_driverinit_value_set(struct devlink_port *devlink_port, - u32 param_id, - union devlink_param_value init_val) -{ - return __devlink_param_driverinit_value_set(devlink_port->devlink, - devlink_port->index, - &devlink_port->param_list, - param_id, init_val, - DEVLINK_CMD_PORT_PARAM_NEW); + devlink_param_notify(devlink, 0, param_item, DEVLINK_CMD_PARAM_NEW); + return 0; } -EXPORT_SYMBOL_GPL(devlink_port_param_driverinit_value_set); +EXPORT_SYMBOL_GPL(devlink_param_driverinit_value_set); /** * devlink_param_value_changed - notify devlink on a parameter's value @@ -10378,50 +10373,6 @@ void devlink_param_value_changed(struct devlink *devlink, u32 param_id) EXPORT_SYMBOL_GPL(devlink_param_value_changed); /** - * devlink_port_param_value_changed - notify devlink on a parameter's value - * change. Should be called by the driver - * right after the change. - * - * @devlink_port: devlink_port - * @param_id: parameter ID - * - * This function should be used by the driver to notify devlink on value - * change, excluding driverinit configuration mode. - * For driverinit configuration mode driver should use the function - * devlink_port_param_driverinit_value_set() instead. - */ -void devlink_port_param_value_changed(struct devlink_port *devlink_port, - u32 param_id) -{ - struct devlink_param_item *param_item; - - param_item = devlink_param_find_by_id(&devlink_port->param_list, - param_id); - WARN_ON(!param_item); - - devlink_param_notify(devlink_port->devlink, devlink_port->index, - param_item, DEVLINK_CMD_PORT_PARAM_NEW); -} -EXPORT_SYMBOL_GPL(devlink_port_param_value_changed); - -/** - * devlink_param_value_str_fill - Safely fill-up the string preventing - * from overflow of the preallocated buffer - * - * @dst_val: destination devlink_param_value - * @src: source buffer - */ -void devlink_param_value_str_fill(union devlink_param_value *dst_val, - const char *src) -{ - size_t len; - - len = strlcpy(dst_val->vstr, src, __DEVLINK_PARAM_MAX_STRING_VALUE); - WARN_ON(len >= __DEVLINK_PARAM_MAX_STRING_VALUE); -} -EXPORT_SYMBOL_GPL(devlink_param_value_str_fill); - -/** * devlink_region_create - create a new address region * * @devlink: devlink @@ -10839,6 +10790,8 @@ devlink_trap_group_notify(struct devlink *devlink, WARN_ON_ONCE(cmd != DEVLINK_CMD_TRAP_GROUP_NEW && cmd != DEVLINK_CMD_TRAP_GROUP_DEL); + if (!xa_get_mark(&devlinks, devlink->index, DEVLINK_REGISTERED)) + return; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) @@ -10880,6 +10833,8 @@ static void devlink_trap_notify(struct devlink *devlink, WARN_ON_ONCE(cmd != DEVLINK_CMD_TRAP_NEW && cmd != DEVLINK_CMD_TRAP_DEL); + if (!xa_get_mark(&devlinks, devlink->index, DEVLINK_REGISTERED)) + return; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) @@ -11261,6 +11216,8 @@ devlink_trap_policer_notify(struct devlink *devlink, WARN_ON_ONCE(cmd != DEVLINK_CMD_TRAP_POLICER_NEW && cmd != DEVLINK_CMD_TRAP_POLICER_DEL); + if (!xa_get_mark(&devlinks, devlink->index, DEVLINK_REGISTERED)) + return; msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) @@ -11429,6 +11386,24 @@ free_msg: nlmsg_free(msg); } +static struct devlink_port *netdev_to_devlink_port(struct net_device *dev) +{ + if (!dev->netdev_ops->ndo_get_devlink_port) + return NULL; + + return dev->netdev_ops->ndo_get_devlink_port(dev); +} + +static struct devlink *netdev_to_devlink(struct net_device *dev) +{ + struct devlink_port *devlink_port = netdev_to_devlink_port(dev); + + if (!devlink_port) + return NULL; + + return devlink_port->devlink; +} + void devlink_compat_running_version(struct net_device *dev, char *buf, size_t len) { @@ -11538,7 +11513,7 @@ static void __net_exit devlink_pernet_pre_exit(struct net *net) if (!net_eq(devlink_net(devlink), net)) goto retry; - WARN_ON(!devlink_reload_supported(devlink->ops)); + WARN_ON(!(devlink->features & DEVLINK_F_RELOAD)); err = devlink_reload(devlink, &init_net, DEVLINK_RELOAD_ACTION_DRIVER_REINIT, DEVLINK_RELOAD_LIMIT_UNSPEC, diff --git a/net/core/filter.c b/net/core/filter.c index 2e32cee2c469..4bace37a6a44 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -7765,6 +7765,10 @@ static bool bpf_skb_is_valid_access(int off, int size, enum bpf_access_type type break; case bpf_ctx_range_ptr(struct __sk_buff, flow_keys): return false; + case bpf_ctx_range(struct __sk_buff, hwtstamp): + if (type == BPF_WRITE || size != sizeof(__u64)) + return false; + break; case bpf_ctx_range(struct __sk_buff, tstamp): if (size != sizeof(__u64)) return false; @@ -7774,6 +7778,9 @@ static bool bpf_skb_is_valid_access(int off, int size, enum bpf_access_type type return false; info->reg_type = PTR_TO_SOCK_COMMON_OR_NULL; break; + case offsetofend(struct __sk_buff, gso_size) ... offsetof(struct __sk_buff, hwtstamp) - 1: + /* Explicitly prohibit access to padding in __sk_buff. */ + return false; default: /* Only narrow read access allowed for now. */ if (type == BPF_WRITE) { @@ -7802,6 +7809,7 @@ static bool sk_filter_is_valid_access(int off, int size, case bpf_ctx_range_till(struct __sk_buff, family, local_port): case bpf_ctx_range(struct __sk_buff, tstamp): case bpf_ctx_range(struct __sk_buff, wire_len): + case bpf_ctx_range(struct __sk_buff, hwtstamp): return false; } @@ -7872,6 +7880,7 @@ static bool lwt_is_valid_access(int off, int size, case bpf_ctx_range(struct __sk_buff, data_meta): case bpf_ctx_range(struct __sk_buff, tstamp): case bpf_ctx_range(struct __sk_buff, wire_len): + case bpf_ctx_range(struct __sk_buff, hwtstamp): return false; } @@ -8373,6 +8382,7 @@ static bool sk_skb_is_valid_access(int off, int size, case bpf_ctx_range(struct __sk_buff, data_meta): case bpf_ctx_range(struct __sk_buff, tstamp): case bpf_ctx_range(struct __sk_buff, wire_len): + case bpf_ctx_range(struct __sk_buff, hwtstamp): return false; } @@ -8884,6 +8894,17 @@ static u32 bpf_convert_ctx_access(enum bpf_access_type type, si->dst_reg, si->src_reg, offsetof(struct sk_buff, sk)); break; + case offsetof(struct __sk_buff, hwtstamp): + BUILD_BUG_ON(sizeof_field(struct skb_shared_hwtstamps, hwtstamp) != 8); + BUILD_BUG_ON(offsetof(struct skb_shared_hwtstamps, hwtstamp) != 0); + + insn = bpf_convert_shinfo_access(si, insn); + *insn++ = BPF_LDX_MEM(BPF_DW, + si->dst_reg, si->dst_reg, + bpf_target_off(struct skb_shared_info, + hwtstamps, 8, + target_size)); + break; } return insn - insn_buf; diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index bac0184cf3de..7d0a9f84aaf7 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -1196,9 +1196,8 @@ proto_again: break; } - proto = hdr->proto; nhoff += PPPOE_SES_HLEN; - switch (proto) { + switch (hdr->proto) { case htons(PPP_IP): proto = htons(ETH_P_IP); fdret = FLOW_DISSECT_RET_PROTO_AGAIN; diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 2d5bc3a75fae..eae73efa9245 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -122,6 +122,8 @@ static void neigh_mark_dead(struct neighbour *n) list_del_init(&n->gc_list); atomic_dec(&n->tbl->gc_entries); } + if (!list_empty(&n->managed_list)) + list_del_init(&n->managed_list); } static void neigh_update_gc_list(struct neighbour *n) @@ -130,7 +132,6 @@ static void neigh_update_gc_list(struct neighbour *n) write_lock_bh(&n->tbl->lock); write_lock(&n->lock); - if (n->dead) goto out; @@ -149,32 +150,59 @@ static void neigh_update_gc_list(struct neighbour *n) list_add_tail(&n->gc_list, &n->tbl->gc_list); atomic_inc(&n->tbl->gc_entries); } +out: + write_unlock(&n->lock); + write_unlock_bh(&n->tbl->lock); +} +static void neigh_update_managed_list(struct neighbour *n) +{ + bool on_managed_list, add_to_managed; + + write_lock_bh(&n->tbl->lock); + write_lock(&n->lock); + if (n->dead) + goto out; + + add_to_managed = n->flags & NTF_MANAGED; + on_managed_list = !list_empty(&n->managed_list); + + if (!add_to_managed && on_managed_list) + list_del_init(&n->managed_list); + else if (add_to_managed && !on_managed_list) + list_add_tail(&n->managed_list, &n->tbl->managed_list); out: write_unlock(&n->lock); write_unlock_bh(&n->tbl->lock); } -static bool neigh_update_ext_learned(struct neighbour *neigh, u32 flags, - int *notify) +static void neigh_update_flags(struct neighbour *neigh, u32 flags, int *notify, + bool *gc_update, bool *managed_update) { - bool rc = false; - u8 ndm_flags; + u32 ndm_flags, old_flags = neigh->flags; if (!(flags & NEIGH_UPDATE_F_ADMIN)) - return rc; + return; + + ndm_flags = (flags & NEIGH_UPDATE_F_EXT_LEARNED) ? NTF_EXT_LEARNED : 0; + ndm_flags |= (flags & NEIGH_UPDATE_F_MANAGED) ? NTF_MANAGED : 0; - ndm_flags = (flags & NEIGH_UPDATE_F_EXT_LEARNED) ? NTF_EXT_LEARNED : 0; - if ((neigh->flags ^ ndm_flags) & NTF_EXT_LEARNED) { + if ((old_flags ^ ndm_flags) & NTF_EXT_LEARNED) { if (ndm_flags & NTF_EXT_LEARNED) neigh->flags |= NTF_EXT_LEARNED; else neigh->flags &= ~NTF_EXT_LEARNED; - rc = true; *notify = 1; + *gc_update = true; + } + if ((old_flags ^ ndm_flags) & NTF_MANAGED) { + if (ndm_flags & NTF_MANAGED) + neigh->flags |= NTF_MANAGED; + else + neigh->flags &= ~NTF_MANAGED; + *notify = 1; + *managed_update = true; } - - return rc; } static bool neigh_del(struct neighbour *n, struct neighbour __rcu **np, @@ -379,7 +407,7 @@ EXPORT_SYMBOL(neigh_ifdown); static struct neighbour *neigh_alloc(struct neigh_table *tbl, struct net_device *dev, - bool exempt_from_gc) + u32 flags, bool exempt_from_gc) { struct neighbour *n = NULL; unsigned long now = jiffies; @@ -412,6 +440,7 @@ do_alloc: n->updated = n->used = now; n->nud_state = NUD_NONE; n->output = neigh_blackhole; + n->flags = flags; seqlock_init(&n->hh.hh_lock); n->parms = neigh_parms_clone(&tbl->parms); timer_setup(&n->timer, neigh_timer_handler, 0); @@ -421,6 +450,7 @@ do_alloc: refcount_set(&n->refcnt, 1); n->dead = 1; INIT_LIST_HEAD(&n->gc_list); + INIT_LIST_HEAD(&n->managed_list); atomic_inc(&tbl->entries); out: @@ -575,19 +605,18 @@ struct neighbour *neigh_lookup_nodev(struct neigh_table *tbl, struct net *net, } EXPORT_SYMBOL(neigh_lookup_nodev); -static struct neighbour *___neigh_create(struct neigh_table *tbl, - const void *pkey, - struct net_device *dev, - bool exempt_from_gc, bool want_ref) +static struct neighbour * +___neigh_create(struct neigh_table *tbl, const void *pkey, + struct net_device *dev, u32 flags, + bool exempt_from_gc, bool want_ref) { - struct neighbour *n1, *rc, *n = neigh_alloc(tbl, dev, exempt_from_gc); - u32 hash_val; - unsigned int key_len = tbl->key_len; - int error; + u32 hash_val, key_len = tbl->key_len; + struct neighbour *n1, *rc, *n; struct neigh_hash_table *nht; + int error; + n = neigh_alloc(tbl, dev, flags, exempt_from_gc); trace_neigh_create(tbl, dev, pkey, n, exempt_from_gc); - if (!n) { rc = ERR_PTR(-ENOBUFS); goto out; @@ -650,7 +679,8 @@ static struct neighbour *___neigh_create(struct neigh_table *tbl, n->dead = 0; if (!exempt_from_gc) list_add_tail(&n->gc_list, &n->tbl->gc_list); - + if (n->flags & NTF_MANAGED) + list_add_tail(&n->managed_list, &n->tbl->managed_list); if (want_ref) neigh_hold(n); rcu_assign_pointer(n->next, @@ -674,7 +704,7 @@ out_neigh_release: struct neighbour *__neigh_create(struct neigh_table *tbl, const void *pkey, struct net_device *dev, bool want_ref) { - return ___neigh_create(tbl, pkey, dev, false, want_ref); + return ___neigh_create(tbl, pkey, dev, 0, false, want_ref); } EXPORT_SYMBOL(__neigh_create); @@ -1205,8 +1235,6 @@ static void neigh_update_hhs(struct neighbour *neigh) } } - - /* Generic update routine. -- lladdr is new lladdr or NULL, if it is not supplied. -- new is new state. @@ -1217,7 +1245,8 @@ static void neigh_update_hhs(struct neighbour *neigh) lladdr instead of overriding it if it is different. NEIGH_UPDATE_F_ADMIN means that the change is administrative. - + NEIGH_UPDATE_F_USE means that the entry is user triggered. + NEIGH_UPDATE_F_MANAGED means that the entry will be auto-refreshed. NEIGH_UPDATE_F_OVERRIDE_ISROUTER allows to override existing NTF_ROUTER flag. NEIGH_UPDATE_F_ISROUTER indicates if the neighbour is known as @@ -1225,17 +1254,15 @@ static void neigh_update_hhs(struct neighbour *neigh) Caller MUST hold reference count on the entry. */ - static int __neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new, u32 flags, u32 nlmsg_pid, struct netlink_ext_ack *extack) { - bool ext_learn_change = false; - u8 old; - int err; - int notify = 0; - struct net_device *dev; + bool gc_update = false, managed_update = false; int update_isrouter = 0; + struct net_device *dev; + int err, notify = 0; + u8 old; trace_neigh_update(neigh, lladdr, new, flags, nlmsg_pid); @@ -1254,7 +1281,13 @@ static int __neigh_update(struct neighbour *neigh, const u8 *lladdr, (old & (NUD_NOARP | NUD_PERMANENT))) goto out; - ext_learn_change = neigh_update_ext_learned(neigh, flags, ¬ify); + neigh_update_flags(neigh, flags, ¬ify, &gc_update, &managed_update); + if (flags & (NEIGH_UPDATE_F_USE | NEIGH_UPDATE_F_MANAGED)) { + new = old & ~NUD_PERMANENT; + neigh->nud_state = new; + err = 0; + goto out; + } if (!(new & NUD_VALID)) { neigh_del_timer(neigh); @@ -1399,15 +1432,13 @@ out: if (update_isrouter) neigh_update_is_router(neigh, flags, ¬ify); write_unlock_bh(&neigh->lock); - - if (((new ^ old) & NUD_PERMANENT) || ext_learn_change) + if (((new ^ old) & NUD_PERMANENT) || gc_update) neigh_update_gc_list(neigh); - + if (managed_update) + neigh_update_managed_list(neigh); if (notify) neigh_update_notify(neigh, nlmsg_pid); - trace_neigh_update_done(neigh, err); - return err; } @@ -1533,6 +1564,20 @@ int neigh_direct_output(struct neighbour *neigh, struct sk_buff *skb) } EXPORT_SYMBOL(neigh_direct_output); +static void neigh_managed_work(struct work_struct *work) +{ + struct neigh_table *tbl = container_of(work, struct neigh_table, + managed_work.work); + struct neighbour *neigh; + + write_lock_bh(&tbl->lock); + list_for_each_entry(neigh, &tbl->managed_list, managed_list) + neigh_event_send(neigh, NULL); + queue_delayed_work(system_power_efficient_wq, &tbl->managed_work, + NEIGH_VAR(&tbl->parms, DELAY_PROBE_TIME)); + write_unlock_bh(&tbl->lock); +} + static void neigh_proxy_process(struct timer_list *t) { struct neigh_table *tbl = from_timer(tbl, t, proxy_timer); @@ -1679,6 +1724,8 @@ void neigh_table_init(int index, struct neigh_table *tbl) INIT_LIST_HEAD(&tbl->parms_list); INIT_LIST_HEAD(&tbl->gc_list); + INIT_LIST_HEAD(&tbl->managed_list); + list_add(&tbl->parms.list, &tbl->parms_list); write_pnet(&tbl->parms.net, &init_net); refcount_set(&tbl->parms.refcnt, 1); @@ -1710,9 +1757,13 @@ void neigh_table_init(int index, struct neigh_table *tbl) WARN_ON(tbl->entry_size % NEIGH_PRIV_ALIGN); rwlock_init(&tbl->lock); + INIT_DEFERRABLE_WORK(&tbl->gc_work, neigh_periodic_work); queue_delayed_work(system_power_efficient_wq, &tbl->gc_work, tbl->parms.reachable_time); + INIT_DEFERRABLE_WORK(&tbl->managed_work, neigh_managed_work); + queue_delayed_work(system_power_efficient_wq, &tbl->managed_work, 0); + timer_setup(&tbl->proxy_timer, neigh_proxy_process, 0); skb_queue_head_init_class(&tbl->proxy_queue, &neigh_table_proxy_queue_class); @@ -1783,6 +1834,7 @@ const struct nla_policy nda_policy[NDA_MAX+1] = { [NDA_MASTER] = { .type = NLA_U32 }, [NDA_PROTOCOL] = { .type = NLA_U8 }, [NDA_NH_ID] = { .type = NLA_U32 }, + [NDA_FLAGS_EXT] = { .type = NLA_U32 }, [NDA_FDB_EXT_ATTRS] = { .type = NLA_NESTED }, }; @@ -1855,7 +1907,7 @@ static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { int flags = NEIGH_UPDATE_F_ADMIN | NEIGH_UPDATE_F_OVERRIDE | - NEIGH_UPDATE_F_OVERRIDE_ISROUTER; + NEIGH_UPDATE_F_OVERRIDE_ISROUTER; struct net *net = sock_net(skb->sk); struct ndmsg *ndm; struct nlattr *tb[NDA_MAX+1]; @@ -1864,6 +1916,7 @@ static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh, struct neighbour *neigh; void *dst, *lladdr; u8 protocol = 0; + u32 ndm_flags; int err; ASSERT_RTNL(); @@ -1879,6 +1932,16 @@ static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh, } ndm = nlmsg_data(nlh); + ndm_flags = ndm->ndm_flags; + if (tb[NDA_FLAGS_EXT]) { + u32 ext = nla_get_u32(tb[NDA_FLAGS_EXT]); + + if (ext & ~NTF_EXT_MASK) { + NL_SET_ERR_MSG(extack, "Invalid extended flags"); + goto out; + } + ndm_flags |= (ext << NTF_EXT_SHIFT); + } if (ndm->ndm_ifindex) { dev = __dev_get_by_index(net, ndm->ndm_ifindex); if (dev == NULL) { @@ -1906,14 +1969,18 @@ static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh, if (tb[NDA_PROTOCOL]) protocol = nla_get_u8(tb[NDA_PROTOCOL]); - - if (ndm->ndm_flags & NTF_PROXY) { + if (ndm_flags & NTF_PROXY) { struct pneigh_entry *pn; + if (ndm_flags & NTF_MANAGED) { + NL_SET_ERR_MSG(extack, "Invalid NTF_* flag combination"); + goto out; + } + err = -ENOBUFS; pn = pneigh_lookup(tbl, net, dst, dev, 1); if (pn) { - pn->flags = ndm->ndm_flags; + pn->flags = ndm_flags; if (protocol) pn->protocol = protocol; err = 0; @@ -1941,8 +2008,11 @@ static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh, } exempt_from_gc = ndm->ndm_state & NUD_PERMANENT || - ndm->ndm_flags & NTF_EXT_LEARNED; - neigh = ___neigh_create(tbl, dst, dev, exempt_from_gc, true); + ndm_flags & NTF_EXT_LEARNED; + neigh = ___neigh_create(tbl, dst, dev, + ndm_flags & + (NTF_EXT_LEARNED | NTF_MANAGED), + exempt_from_gc, true); if (IS_ERR(neigh)) { err = PTR_ERR(neigh); goto out; @@ -1961,22 +2031,22 @@ static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh, if (protocol) neigh->protocol = protocol; - - if (ndm->ndm_flags & NTF_EXT_LEARNED) + if (ndm_flags & NTF_EXT_LEARNED) flags |= NEIGH_UPDATE_F_EXT_LEARNED; - - if (ndm->ndm_flags & NTF_ROUTER) + if (ndm_flags & NTF_ROUTER) flags |= NEIGH_UPDATE_F_ISROUTER; + if (ndm_flags & NTF_MANAGED) + flags |= NEIGH_UPDATE_F_MANAGED; + if (ndm_flags & NTF_USE) + flags |= NEIGH_UPDATE_F_USE; - if (ndm->ndm_flags & NTF_USE) { + err = __neigh_update(neigh, lladdr, ndm->ndm_state, flags, + NETLINK_CB(skb).portid, extack); + if (!err && ndm_flags & (NTF_USE | NTF_MANAGED)) { neigh_event_send(neigh, NULL); err = 0; - } else - err = __neigh_update(neigh, lladdr, ndm->ndm_state, flags, - NETLINK_CB(skb).portid, extack); - + } neigh_release(neigh); - out: return err; } @@ -2427,6 +2497,7 @@ out: static int neigh_fill_info(struct sk_buff *skb, struct neighbour *neigh, u32 pid, u32 seq, int type, unsigned int flags) { + u32 neigh_flags, neigh_flags_ext; unsigned long now = jiffies; struct nda_cacheinfo ci; struct nlmsghdr *nlh; @@ -2436,11 +2507,14 @@ static int neigh_fill_info(struct sk_buff *skb, struct neighbour *neigh, if (nlh == NULL) return -EMSGSIZE; + neigh_flags_ext = neigh->flags >> NTF_EXT_SHIFT; + neigh_flags = neigh->flags & NTF_OLD_MASK; + ndm = nlmsg_data(nlh); ndm->ndm_family = neigh->ops->family; ndm->ndm_pad1 = 0; ndm->ndm_pad2 = 0; - ndm->ndm_flags = neigh->flags; + ndm->ndm_flags = neigh_flags; ndm->ndm_type = neigh->type; ndm->ndm_ifindex = neigh->dev->ifindex; @@ -2471,6 +2545,8 @@ static int neigh_fill_info(struct sk_buff *skb, struct neighbour *neigh, if (neigh->protocol && nla_put_u8(skb, NDA_PROTOCOL, neigh->protocol)) goto nla_put_failure; + if (neigh_flags_ext && nla_put_u32(skb, NDA_FLAGS_EXT, neigh_flags_ext)) + goto nla_put_failure; nlmsg_end(skb, nlh); return 0; @@ -2484,6 +2560,7 @@ static int pneigh_fill_info(struct sk_buff *skb, struct pneigh_entry *pn, u32 pid, u32 seq, int type, unsigned int flags, struct neigh_table *tbl) { + u32 neigh_flags, neigh_flags_ext; struct nlmsghdr *nlh; struct ndmsg *ndm; @@ -2491,11 +2568,14 @@ static int pneigh_fill_info(struct sk_buff *skb, struct pneigh_entry *pn, if (nlh == NULL) return -EMSGSIZE; + neigh_flags_ext = pn->flags >> NTF_EXT_SHIFT; + neigh_flags = pn->flags & NTF_OLD_MASK; + ndm = nlmsg_data(nlh); ndm->ndm_family = tbl->family; ndm->ndm_pad1 = 0; ndm->ndm_pad2 = 0; - ndm->ndm_flags = pn->flags | NTF_PROXY; + ndm->ndm_flags = neigh_flags | NTF_PROXY; ndm->ndm_type = RTN_UNICAST; ndm->ndm_ifindex = pn->dev ? pn->dev->ifindex : 0; ndm->ndm_state = NUD_NONE; @@ -2505,6 +2585,8 @@ static int pneigh_fill_info(struct sk_buff *skb, struct pneigh_entry *pn, if (pn->protocol && nla_put_u8(skb, NDA_PROTOCOL, pn->protocol)) goto nla_put_failure; + if (neigh_flags_ext && nla_put_u32(skb, NDA_FLAGS_EXT, neigh_flags_ext)) + goto nla_put_failure; nlmsg_end(skb, nlh); return 0; @@ -2820,6 +2902,7 @@ static inline size_t neigh_nlmsg_size(void) + nla_total_size(MAX_ADDR_LEN) /* NDA_LLADDR */ + nla_total_size(sizeof(struct nda_cacheinfo)) + nla_total_size(4) /* NDA_PROBES */ + + nla_total_size(4) /* NDA_FLAGS_EXT */ + nla_total_size(1); /* NDA_PROTOCOL */ } @@ -2848,6 +2931,7 @@ static inline size_t pneigh_nlmsg_size(void) { return NLMSG_ALIGN(sizeof(struct ndmsg)) + nla_total_size(MAX_ADDR_LEN) /* NDA_DST */ + + nla_total_size(4) /* NDA_FLAGS_EXT */ + nla_total_size(1); /* NDA_PROTOCOL */ } diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index f6197774048b..d6e4e0b43beb 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -175,6 +175,14 @@ static int change_carrier(struct net_device *dev, unsigned long new_carrier) static ssize_t carrier_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t len) { + struct net_device *netdev = to_net_dev(dev); + + /* The check is also done in change_carrier; this helps returning early + * without hitting the trylock/restart in netdev_store. + */ + if (!netdev->netdev_ops->ndo_change_carrier) + return -EOPNOTSUPP; + return netdev_store(dev, attr, buf, len, change_carrier); } @@ -196,6 +204,12 @@ static ssize_t speed_show(struct device *dev, struct net_device *netdev = to_net_dev(dev); int ret = -EINVAL; + /* The check is also done in __ethtool_get_link_ksettings; this helps + * returning early without hitting the trylock/restart below. + */ + if (!netdev->ethtool_ops->get_link_ksettings) + return ret; + if (!rtnl_trylock()) return restart_syscall(); @@ -216,6 +230,12 @@ static ssize_t duplex_show(struct device *dev, struct net_device *netdev = to_net_dev(dev); int ret = -EINVAL; + /* The check is also done in __ethtool_get_link_ksettings; this helps + * returning early without hitting the trylock/restart below. + */ + if (!netdev->ethtool_ops->get_link_ksettings) + return ret; + if (!rtnl_trylock()) return restart_syscall(); @@ -468,6 +488,14 @@ static ssize_t proto_down_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t len) { + struct net_device *netdev = to_net_dev(dev); + + /* The check is also done in change_proto_down; this helps returning + * early without hitting the trylock/restart in netdev_store. + */ + if (!netdev->netdev_ops->ndo_change_proto_down) + return -EOPNOTSUPP; + return netdev_store(dev, attr, buf, len, change_proto_down); } NETDEVICE_SHOW_RW(proto_down, fmt_dec); @@ -478,6 +506,12 @@ static ssize_t phys_port_id_show(struct device *dev, struct net_device *netdev = to_net_dev(dev); ssize_t ret = -EINVAL; + /* The check is also done in dev_get_phys_port_id; this helps returning + * early without hitting the trylock/restart below. + */ + if (!netdev->netdev_ops->ndo_get_phys_port_id) + return -EOPNOTSUPP; + if (!rtnl_trylock()) return restart_syscall(); @@ -500,6 +534,13 @@ static ssize_t phys_port_name_show(struct device *dev, struct net_device *netdev = to_net_dev(dev); ssize_t ret = -EINVAL; + /* The checks are also done in dev_get_phys_port_name; this helps + * returning early without hitting the trylock/restart below. + */ + if (!netdev->netdev_ops->ndo_get_phys_port_name && + !netdev->netdev_ops->ndo_get_devlink_port) + return -EOPNOTSUPP; + if (!rtnl_trylock()) return restart_syscall(); @@ -522,6 +563,14 @@ static ssize_t phys_switch_id_show(struct device *dev, struct net_device *netdev = to_net_dev(dev); ssize_t ret = -EINVAL; + /* The checks are also done in dev_get_phys_port_name; this helps + * returning early without hitting the trylock/restart below. This works + * because recurse is false when calling dev_get_port_parent_id. + */ + if (!netdev->netdev_ops->ndo_get_port_parent_id && + !netdev->netdev_ops->ndo_get_devlink_port) + return -EOPNOTSUPP; + if (!rtnl_trylock()) return restart_syscall(); @@ -1226,6 +1275,12 @@ static ssize_t tx_maxrate_store(struct netdev_queue *queue, if (!capable(CAP_NET_ADMIN)) return -EPERM; + /* The check is also done later; this helps returning early without + * hitting the trylock/restart below. + */ + if (!dev->netdev_ops->ndo_set_tx_maxrate) + return -EOPNOTSUPP; + err = kstrtou32(buf, 10, &rate); if (err < 0) return err; @@ -1869,7 +1924,7 @@ static struct class net_class __ro_after_init = { .get_ownership = net_get_ownership, }; -#ifdef CONFIG_OF_NET +#ifdef CONFIG_OF static int of_dev_node_match(struct device *dev, const void *data) { for (; dev; dev = dev->parent) { diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index a448a9b5bb2d..202fa5eacd0f 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -473,7 +473,9 @@ struct net *copy_net_ns(unsigned long flags, if (rv < 0) { put_userns: +#ifdef CONFIG_KEYS key_remove_domain(net->key_domain); +#endif put_user_ns(user_ns); net_free(net); dec_ucounts: @@ -605,7 +607,9 @@ static void cleanup_net(struct work_struct *work) list_for_each_entry_safe(net, tmp, &net_exit_list, exit_list) { list_del_init(&net->exit_list); dec_net_namespaces(net->ucounts); +#ifdef CONFIG_KEYS key_remove_domain(net->key_domain); +#endif put_user_ns(net->user_ns); net_free(net); } diff --git a/net/core/of_net.c b/net/core/of_net.c new file mode 100644 index 000000000000..f1a9bf7578e7 --- /dev/null +++ b/net/core/of_net.c @@ -0,0 +1,170 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * OF helpers for network devices. + * + * Initially copied out of arch/powerpc/kernel/prom_parse.c + */ +#include <linux/etherdevice.h> +#include <linux/kernel.h> +#include <linux/of_net.h> +#include <linux/of_platform.h> +#include <linux/phy.h> +#include <linux/export.h> +#include <linux/device.h> +#include <linux/nvmem-consumer.h> + +/** + * of_get_phy_mode - Get phy mode for given device_node + * @np: Pointer to the given device_node + * @interface: Pointer to the result + * + * The function gets phy interface string from property 'phy-mode' or + * 'phy-connection-type'. The index in phy_modes table is set in + * interface and 0 returned. In case of error interface is set to + * PHY_INTERFACE_MODE_NA and an errno is returned, e.g. -ENODEV. + */ +int of_get_phy_mode(struct device_node *np, phy_interface_t *interface) +{ + const char *pm; + int err, i; + + *interface = PHY_INTERFACE_MODE_NA; + + err = of_property_read_string(np, "phy-mode", &pm); + if (err < 0) + err = of_property_read_string(np, "phy-connection-type", &pm); + if (err < 0) + return err; + + for (i = 0; i < PHY_INTERFACE_MODE_MAX; i++) + if (!strcasecmp(pm, phy_modes(i))) { + *interface = i; + return 0; + } + + return -ENODEV; +} +EXPORT_SYMBOL_GPL(of_get_phy_mode); + +static int of_get_mac_addr(struct device_node *np, const char *name, u8 *addr) +{ + struct property *pp = of_find_property(np, name, NULL); + + if (pp && pp->length == ETH_ALEN && is_valid_ether_addr(pp->value)) { + memcpy(addr, pp->value, ETH_ALEN); + return 0; + } + return -ENODEV; +} + +static int of_get_mac_addr_nvmem(struct device_node *np, u8 *addr) +{ + struct platform_device *pdev = of_find_device_by_node(np); + struct nvmem_cell *cell; + const void *mac; + size_t len; + int ret; + + /* Try lookup by device first, there might be a nvmem_cell_lookup + * associated with a given device. + */ + if (pdev) { + ret = nvmem_get_mac_address(&pdev->dev, addr); + put_device(&pdev->dev); + return ret; + } + + cell = of_nvmem_cell_get(np, "mac-address"); + if (IS_ERR(cell)) + return PTR_ERR(cell); + + mac = nvmem_cell_read(cell, &len); + nvmem_cell_put(cell); + + if (IS_ERR(mac)) + return PTR_ERR(mac); + + if (len != ETH_ALEN || !is_valid_ether_addr(mac)) { + kfree(mac); + return -EINVAL; + } + + memcpy(addr, mac, ETH_ALEN); + kfree(mac); + + return 0; +} + +/** + * of_get_mac_address() + * @np: Caller's Device Node + * @addr: Pointer to a six-byte array for the result + * + * Search the device tree for the best MAC address to use. 'mac-address' is + * checked first, because that is supposed to contain to "most recent" MAC + * address. If that isn't set, then 'local-mac-address' is checked next, + * because that is the default address. If that isn't set, then the obsolete + * 'address' is checked, just in case we're using an old device tree. If any + * of the above isn't set, then try to get MAC address from nvmem cell named + * 'mac-address'. + * + * Note that the 'address' property is supposed to contain a virtual address of + * the register set, but some DTS files have redefined that property to be the + * MAC address. + * + * All-zero MAC addresses are rejected, because those could be properties that + * exist in the device tree, but were not set by U-Boot. For example, the + * DTS could define 'mac-address' and 'local-mac-address', with zero MAC + * addresses. Some older U-Boots only initialized 'local-mac-address'. In + * this case, the real MAC is in 'local-mac-address', and 'mac-address' exists + * but is all zeros. + * + * Return: 0 on success and errno in case of error. +*/ +int of_get_mac_address(struct device_node *np, u8 *addr) +{ + int ret; + + if (!np) + return -ENODEV; + + ret = of_get_mac_addr(np, "mac-address", addr); + if (!ret) + return 0; + + ret = of_get_mac_addr(np, "local-mac-address", addr); + if (!ret) + return 0; + + ret = of_get_mac_addr(np, "address", addr); + if (!ret) + return 0; + + return of_get_mac_addr_nvmem(np, addr); +} +EXPORT_SYMBOL(of_get_mac_address); + +/** + * of_get_ethdev_address() + * @np: Caller's Device Node + * @dev: Pointer to netdevice which address will be updated + * + * Search the device tree for the best MAC address to use. + * If found set @dev->dev_addr to that address. + * + * See documentation of of_get_mac_address() for more information on how + * the best address is determined. + * + * Return: 0 on success and errno in case of error. + */ +int of_get_ethdev_address(struct device_node *np, struct net_device *dev) +{ + u8 addr[ETH_ALEN]; + int ret; + + ret = of_get_mac_address(np, addr); + if (!ret) + eth_hw_addr_set(dev, addr); + return ret; +} +EXPORT_SYMBOL(of_get_ethdev_address); diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 8ccce85562a1..2dc1b209ba91 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -301,7 +301,7 @@ int rtnl_unregister(int protocol, int msgtype) } link = rtnl_dereference(tab[msgindex]); - rcu_assign_pointer(tab[msgindex], NULL); + RCU_INIT_POINTER(tab[msgindex], NULL); rtnl_unlock(); kfree_rcu(link, rcu); @@ -337,7 +337,7 @@ void rtnl_unregister_all(int protocol) if (!link) continue; - rcu_assign_pointer(tab[msgindex], NULL); + RCU_INIT_POINTER(tab[msgindex], NULL); kfree_rcu(link, rcu); } rtnl_unlock(); diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 2170bea2c7de..74601bbc56ac 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -134,34 +134,31 @@ struct napi_alloc_cache { static DEFINE_PER_CPU(struct page_frag_cache, netdev_alloc_cache); static DEFINE_PER_CPU(struct napi_alloc_cache, napi_alloc_cache); -static void *__alloc_frag_align(unsigned int fragsz, gfp_t gfp_mask, - unsigned int align_mask) +void *__napi_alloc_frag_align(unsigned int fragsz, unsigned int align_mask) { struct napi_alloc_cache *nc = this_cpu_ptr(&napi_alloc_cache); - return page_frag_alloc_align(&nc->page, fragsz, gfp_mask, align_mask); -} - -void *__napi_alloc_frag_align(unsigned int fragsz, unsigned int align_mask) -{ fragsz = SKB_DATA_ALIGN(fragsz); - return __alloc_frag_align(fragsz, GFP_ATOMIC, align_mask); + return page_frag_alloc_align(&nc->page, fragsz, GFP_ATOMIC, align_mask); } EXPORT_SYMBOL(__napi_alloc_frag_align); void *__netdev_alloc_frag_align(unsigned int fragsz, unsigned int align_mask) { - struct page_frag_cache *nc; void *data; fragsz = SKB_DATA_ALIGN(fragsz); if (in_hardirq() || irqs_disabled()) { - nc = this_cpu_ptr(&netdev_alloc_cache); + struct page_frag_cache *nc = this_cpu_ptr(&netdev_alloc_cache); + data = page_frag_alloc_align(nc, fragsz, GFP_ATOMIC, align_mask); } else { + struct napi_alloc_cache *nc; + local_bh_disable(); - data = __alloc_frag_align(fragsz, GFP_ATOMIC, align_mask); + nc = this_cpu_ptr(&napi_alloc_cache); + data = page_frag_alloc_align(&nc->page, fragsz, GFP_ATOMIC, align_mask); local_bh_enable(); } return data; @@ -397,8 +394,9 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask, { struct kmem_cache *cache; struct sk_buff *skb; - u8 *data; + unsigned int osize; bool pfmemalloc; + u8 *data; cache = (flags & SKB_ALLOC_FCLONE) ? skbuff_fclone_cache : skbuff_head_cache; @@ -430,7 +428,8 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask, * Put skb_shared_info exactly at the end of allocated zone, * to allow max possible filling before reallocation. */ - size = SKB_WITH_OVERHEAD(ksize(data)); + osize = ksize(data); + size = SKB_WITH_OVERHEAD(osize); prefetchw(data + size); /* @@ -439,7 +438,7 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask, * the tail pointer in struct sk_buff! */ memset(skb, 0, offsetof(struct sk_buff, tail)); - __build_skb_around(skb, data, 0); + __build_skb_around(skb, data, osize); skb->pfmemalloc = pfmemalloc; if (flags & SKB_ALLOC_FCLONE) { diff --git a/net/core/sock.c b/net/core/sock.c index c1601f75ec4b..9862eefce21e 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -350,7 +350,7 @@ void sk_error_report(struct sock *sk) } EXPORT_SYMBOL(sk_error_report); -static int sock_get_timeout(long timeo, void *optval, bool old_timeval) +int sock_get_timeout(long timeo, void *optval, bool old_timeval) { struct __kernel_sock_timeval tv; @@ -379,12 +379,11 @@ static int sock_get_timeout(long timeo, void *optval, bool old_timeval) *(struct __kernel_sock_timeval *)optval = tv; return sizeof(tv); } +EXPORT_SYMBOL(sock_get_timeout); -static int sock_set_timeout(long *timeo_p, sockptr_t optval, int optlen, - bool old_timeval) +int sock_copy_user_timeval(struct __kernel_sock_timeval *tv, + sockptr_t optval, int optlen, bool old_timeval) { - struct __kernel_sock_timeval tv; - if (old_timeval && in_compat_syscall() && !COMPAT_USE_64BIT_TIME) { struct old_timeval32 tv32; @@ -393,8 +392,8 @@ static int sock_set_timeout(long *timeo_p, sockptr_t optval, int optlen, if (copy_from_sockptr(&tv32, optval, sizeof(tv32))) return -EFAULT; - tv.tv_sec = tv32.tv_sec; - tv.tv_usec = tv32.tv_usec; + tv->tv_sec = tv32.tv_sec; + tv->tv_usec = tv32.tv_usec; } else if (old_timeval) { struct __kernel_old_timeval old_tv; @@ -402,14 +401,28 @@ static int sock_set_timeout(long *timeo_p, sockptr_t optval, int optlen, return -EINVAL; if (copy_from_sockptr(&old_tv, optval, sizeof(old_tv))) return -EFAULT; - tv.tv_sec = old_tv.tv_sec; - tv.tv_usec = old_tv.tv_usec; + tv->tv_sec = old_tv.tv_sec; + tv->tv_usec = old_tv.tv_usec; } else { - if (optlen < sizeof(tv)) + if (optlen < sizeof(*tv)) return -EINVAL; - if (copy_from_sockptr(&tv, optval, sizeof(tv))) + if (copy_from_sockptr(tv, optval, sizeof(*tv))) return -EFAULT; } + + return 0; +} +EXPORT_SYMBOL(sock_copy_user_timeval); + +static int sock_set_timeout(long *timeo_p, sockptr_t optval, int optlen, + bool old_timeval) +{ + struct __kernel_sock_timeval tv; + int err = sock_copy_user_timeval(&tv, optval, optlen, old_timeval); + + if (err) + return err; + if (tv.tv_usec < 0 || tv.tv_usec >= USEC_PER_SEC) return -EDOM; @@ -947,6 +960,53 @@ void sock_set_mark(struct sock *sk, u32 val) } EXPORT_SYMBOL(sock_set_mark); +static void sock_release_reserved_memory(struct sock *sk, int bytes) +{ + /* Round down bytes to multiple of pages */ + bytes &= ~(SK_MEM_QUANTUM - 1); + + WARN_ON(bytes > sk->sk_reserved_mem); + sk->sk_reserved_mem -= bytes; + sk_mem_reclaim(sk); +} + +static int sock_reserve_memory(struct sock *sk, int bytes) +{ + long allocated; + bool charged; + int pages; + + if (!mem_cgroup_sockets_enabled || !sk->sk_memcg) + return -EOPNOTSUPP; + + if (!bytes) + return 0; + + pages = sk_mem_pages(bytes); + + /* pre-charge to memcg */ + charged = mem_cgroup_charge_skmem(sk->sk_memcg, pages, + GFP_KERNEL | __GFP_RETRY_MAYFAIL); + if (!charged) + return -ENOMEM; + + /* pre-charge to forward_alloc */ + allocated = sk_memory_allocated_add(sk, pages); + /* If the system goes into memory pressure with this + * precharge, give up and return error. + */ + if (allocated > sk_prot_mem_limits(sk, 1)) { + sk_memory_allocated_sub(sk, pages); + mem_cgroup_uncharge_skmem(sk->sk_memcg, pages); + return -ENOMEM; + } + sk->sk_forward_alloc += pages << SK_MEM_QUANTUM_SHIFT; + + sk->sk_reserved_mem += pages << SK_MEM_QUANTUM_SHIFT; + + return 0; +} + /* * This is meant for all protocols to use and covers goings on * at the socket level. Everything here is generic. @@ -1367,6 +1427,23 @@ set_sndbuf: ~SOCK_BUF_LOCK_MASK); break; + case SO_RESERVE_MEM: + { + int delta; + + if (val < 0) { + ret = -EINVAL; + break; + } + + delta = val - sk->sk_reserved_mem; + if (delta < 0) + sock_release_reserved_memory(sk, -delta); + else + ret = sock_reserve_memory(sk, delta); + break; + } + default: ret = -ENOPROTOOPT; break; @@ -1750,6 +1827,10 @@ int sock_getsockopt(struct socket *sock, int level, int optname, v.val = sk->sk_userlocks & SOCK_BUF_LOCK_MASK; break; + case SO_RESERVE_MEM: + v.val = sk->sk_reserved_mem; + break; + default: /* We implement the SO_SNDLOWAT etc to not be settable * (1003.1g 7). @@ -2063,6 +2144,7 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority) newsk->sk_dst_pending_confirm = 0; newsk->sk_wmem_queued = 0; newsk->sk_forward_alloc = 0; + newsk->sk_reserved_mem = 0; atomic_set(&newsk->sk_drops, 0); newsk->sk_send_head = NULL; newsk->sk_userlocks = sk->sk_userlocks & ~SOCK_BINDPORT_LOCK; diff --git a/net/core/stream.c b/net/core/stream.c index 4f1d4aa5fb38..e09ffd410685 100644 --- a/net/core/stream.c +++ b/net/core/stream.c @@ -202,7 +202,7 @@ void sk_stream_kill_queues(struct sock *sk) WARN_ON(!skb_queue_empty(&sk->sk_write_queue)); /* Account for returned memory. */ - sk_mem_reclaim(sk); + sk_mem_reclaim_final(sk); WARN_ON(sk->sk_wmem_queued); WARN_ON(sk->sk_forward_alloc); |