diff --git a/drivers/net/ethernet/netronome/nfp/bpf/main.c b/drivers/net/ethernet/netronome/nfp/bpf/main.c index b95b94d008cf..458f49235d06 100644 --- a/drivers/net/ethernet/netronome/nfp/bpf/main.c +++ b/drivers/net/ethernet/netronome/nfp/bpf/main.c @@ -404,6 +404,20 @@ err_release_free: return -EINVAL; } +static int nfp_bpf_ndo_init(struct nfp_app *app, struct net_device *netdev) +{ + struct nfp_app_bpf *bpf = app->priv; + + return bpf_offload_dev_netdev_register(bpf->bpf_dev, netdev); +} + +static void nfp_bpf_ndo_uninit(struct nfp_app *app, struct net_device *netdev) +{ + struct nfp_app_bpf *bpf = app->priv; + + bpf_offload_dev_netdev_unregister(bpf->bpf_dev, netdev); +} + static int nfp_bpf_init(struct nfp_app *app) { struct nfp_app_bpf *bpf; @@ -427,6 +441,11 @@ static int nfp_bpf_init(struct nfp_app *app) if (err) goto err_free_neutral_maps; + bpf->bpf_dev = bpf_offload_dev_create(); + err = PTR_ERR_OR_ZERO(bpf->bpf_dev); + if (err) + goto err_free_neutral_maps; + return 0; err_free_neutral_maps: @@ -445,6 +464,7 @@ static void nfp_bpf_clean(struct nfp_app *app) { struct nfp_app_bpf *bpf = app->priv; + bpf_offload_dev_destroy(bpf->bpf_dev); WARN_ON(!skb_queue_empty(&bpf->cmsg_replies)); WARN_ON(!list_empty(&bpf->map_list)); WARN_ON(bpf->maps_in_use || bpf->map_elems_in_use); @@ -466,6 +486,9 @@ const struct nfp_app_type app_bpf = { .extra_cap = nfp_bpf_extra_cap, + .ndo_init = nfp_bpf_ndo_init, + .ndo_uninit = nfp_bpf_ndo_uninit, + .vnic_alloc = nfp_bpf_vnic_alloc, .vnic_free = nfp_bpf_vnic_free, diff --git a/drivers/net/ethernet/netronome/nfp/bpf/main.h b/drivers/net/ethernet/netronome/nfp/bpf/main.h index 9845c1a2d4c2..bec935468f90 100644 --- a/drivers/net/ethernet/netronome/nfp/bpf/main.h +++ b/drivers/net/ethernet/netronome/nfp/bpf/main.h @@ -110,6 +110,8 @@ enum pkt_vec { * struct nfp_app_bpf - bpf app priv structure * @app: backpointer to the app * + * @bpf_dev: BPF offload device handle + * * @tag_allocator: bitmap of control message tags in use * @tag_alloc_next: next tag bit to allocate * @tag_alloc_last: next tag bit to be freed @@ -150,6 +152,8 @@ enum pkt_vec { struct nfp_app_bpf { struct nfp_app *app; + struct bpf_offload_dev *bpf_dev; + DECLARE_BITMAP(tag_allocator, U16_MAX + 1); u16 tag_alloc_next; u16 tag_alloc_last; diff --git a/drivers/net/ethernet/netronome/nfp/bpf/offload.c b/drivers/net/ethernet/netronome/nfp/bpf/offload.c index 78f44c4d95b4..49b03f7dbf46 100644 --- a/drivers/net/ethernet/netronome/nfp/bpf/offload.c +++ b/drivers/net/ethernet/netronome/nfp/bpf/offload.c @@ -566,14 +566,8 @@ int nfp_net_bpf_offload(struct nfp_net *nn, struct bpf_prog *prog, { int err; - if (prog) { - struct bpf_prog_offload *offload = prog->aux->offload; - - if (!offload) - return -EINVAL; - if (offload->netdev != nn->dp.netdev) - return -EINVAL; - } + if (prog && !bpf_offload_dev_match(prog, nn->dp.netdev)) + return -EINVAL; if (prog && old_prog) { u8 cap; diff --git a/drivers/net/ethernet/netronome/nfp/nfp_app.c b/drivers/net/ethernet/netronome/nfp/nfp_app.c index f28b244f4ee7..69d4ae7a61f3 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_app.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_app.c @@ -86,6 +86,23 @@ const char *nfp_app_mip_name(struct nfp_app *app) return nfp_mip_name(app->pf->mip); } +int nfp_app_ndo_init(struct net_device *netdev) +{ + struct nfp_app *app = nfp_app_from_netdev(netdev); + + if (!app || !app->type->ndo_init) + return 0; + return app->type->ndo_init(app, netdev); +} + +void nfp_app_ndo_uninit(struct net_device *netdev) +{ + struct nfp_app *app = nfp_app_from_netdev(netdev); + + if (app && app->type->ndo_uninit) + app->type->ndo_uninit(app, netdev); +} + u64 *nfp_app_port_get_stats(struct nfp_port *port, u64 *data) { if (!port || !port->app || !port->app->type->port_get_stats) diff --git a/drivers/net/ethernet/netronome/nfp/nfp_app.h b/drivers/net/ethernet/netronome/nfp/nfp_app.h index ee74caacb015..afbc19aa66a8 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_app.h +++ b/drivers/net/ethernet/netronome/nfp/nfp_app.h @@ -78,6 +78,8 @@ extern const struct nfp_app_type app_abm; * @init: perform basic app checks and init * @clean: clean app state * @extra_cap: extra capabilities string + * @ndo_init: vNIC and repr netdev .ndo_init + * @ndo_uninit: vNIC and repr netdev .ndo_unint * @vnic_alloc: allocate vNICs (assign port types, etc.) * @vnic_free: free up app's vNIC state * @vnic_init: vNIC netdev was registered @@ -117,6 +119,9 @@ struct nfp_app_type { const char *(*extra_cap)(struct nfp_app *app, struct nfp_net *nn); + int (*ndo_init)(struct nfp_app *app, struct net_device *netdev); + void (*ndo_uninit)(struct nfp_app *app, struct net_device *netdev); + int (*vnic_alloc)(struct nfp_app *app, struct nfp_net *nn, unsigned int id); void (*vnic_free)(struct nfp_app *app, struct nfp_net *nn); @@ -200,6 +205,9 @@ static inline void nfp_app_clean(struct nfp_app *app) app->type->clean(app); } +int nfp_app_ndo_init(struct net_device *netdev); +void nfp_app_ndo_uninit(struct net_device *netdev); + static inline int nfp_app_vnic_alloc(struct nfp_app *app, struct nfp_net *nn, unsigned int id) { diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c index a712e83c3f0f..279b8ab8a17b 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c @@ -3480,6 +3480,8 @@ static int nfp_net_set_mac_address(struct net_device *netdev, void *addr) } const struct net_device_ops nfp_net_netdev_ops = { + .ndo_init = nfp_app_ndo_init, + .ndo_uninit = nfp_app_ndo_uninit, .ndo_open = nfp_net_netdev_open, .ndo_stop = nfp_net_netdev_close, .ndo_start_xmit = nfp_net_tx, diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c b/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c index d7b712f6362f..18a09cdcd9c6 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_repr.c @@ -262,6 +262,8 @@ err_port_disable: } const struct net_device_ops nfp_repr_netdev_ops = { + .ndo_init = nfp_app_ndo_init, + .ndo_uninit = nfp_app_ndo_uninit, .ndo_open = nfp_repr_open, .ndo_stop = nfp_repr_stop, .ndo_start_xmit = nfp_repr_xmit, diff --git a/drivers/net/netdevsim/bpf.c b/drivers/net/netdevsim/bpf.c index c36d2a768202..81444208b216 100644 --- a/drivers/net/netdevsim/bpf.c +++ b/drivers/net/netdevsim/bpf.c @@ -238,8 +238,8 @@ static int nsim_bpf_create_prog(struct netdevsim *ns, struct bpf_prog *prog) state->state = "verify"; /* Program id is not populated yet when we create the state. */ - sprintf(name, "%u", ns->prog_id_gen++); - state->ddir = debugfs_create_dir(name, ns->ddir_bpf_bound_progs); + sprintf(name, "%u", ns->sdev->prog_id_gen++); + state->ddir = debugfs_create_dir(name, ns->sdev->ddir_bpf_bound_progs); if (IS_ERR_OR_NULL(state->ddir)) { kfree(state); return -ENOMEM; @@ -250,7 +250,7 @@ static int nsim_bpf_create_prog(struct netdevsim *ns, struct bpf_prog *prog) &state->state, &nsim_bpf_string_fops); debugfs_create_bool("loaded", 0400, state->ddir, &state->is_loaded); - list_add_tail(&state->l, &ns->bpf_bound_progs); + list_add_tail(&state->l, &ns->sdev->bpf_bound_progs); prog->aux->offload->dev_priv = state; @@ -294,7 +294,7 @@ nsim_setup_prog_hw_checks(struct netdevsim *ns, struct netdev_bpf *bpf) NSIM_EA(bpf->extack, "xdpoffload of non-bound program"); return -EINVAL; } - if (bpf->prog->aux->offload->netdev != ns->netdev) { + if (!bpf_offload_dev_match(bpf->prog, ns->netdev)) { NSIM_EA(bpf->extack, "program bound to different dev"); return -EINVAL; } @@ -497,7 +497,7 @@ nsim_bpf_map_alloc(struct netdevsim *ns, struct bpf_offloaded_map *offmap) } offmap->dev_ops = &nsim_bpf_map_ops; - list_add_tail(&nmap->l, &ns->bpf_bound_maps); + list_add_tail(&nmap->l, &ns->sdev->bpf_bound_maps); return 0; @@ -582,8 +582,26 @@ int nsim_bpf(struct net_device *dev, struct netdev_bpf *bpf) int nsim_bpf_init(struct netdevsim *ns) { - INIT_LIST_HEAD(&ns->bpf_bound_progs); - INIT_LIST_HEAD(&ns->bpf_bound_maps); + int err; + + if (ns->sdev->refcnt == 1) { + INIT_LIST_HEAD(&ns->sdev->bpf_bound_progs); + INIT_LIST_HEAD(&ns->sdev->bpf_bound_maps); + + ns->sdev->ddir_bpf_bound_progs = + debugfs_create_dir("bpf_bound_progs", ns->sdev->ddir); + if (IS_ERR_OR_NULL(ns->sdev->ddir_bpf_bound_progs)) + return -ENOMEM; + + ns->sdev->bpf_dev = bpf_offload_dev_create(); + err = PTR_ERR_OR_ZERO(ns->sdev->bpf_dev); + if (err) + return err; + } + + err = bpf_offload_dev_netdev_register(ns->sdev->bpf_dev, ns->netdev); + if (err) + goto err_destroy_bdev; debugfs_create_u32("bpf_offloaded_id", 0400, ns->ddir, &ns->bpf_offloaded_id); @@ -593,10 +611,6 @@ int nsim_bpf_init(struct netdevsim *ns) &ns->bpf_bind_accept); debugfs_create_u32("bpf_bind_verifier_delay", 0600, ns->ddir, &ns->bpf_bind_verifier_delay); - ns->ddir_bpf_bound_progs = - debugfs_create_dir("bpf_bound_progs", ns->ddir); - if (IS_ERR_OR_NULL(ns->ddir_bpf_bound_progs)) - return -ENOMEM; ns->bpf_tc_accept = true; debugfs_create_bool("bpf_tc_accept", 0600, ns->ddir, @@ -615,13 +629,23 @@ int nsim_bpf_init(struct netdevsim *ns) &ns->bpf_map_accept); return 0; + +err_destroy_bdev: + if (ns->sdev->refcnt == 1) + bpf_offload_dev_destroy(ns->sdev->bpf_dev); + return err; } void nsim_bpf_uninit(struct netdevsim *ns) { - WARN_ON(!list_empty(&ns->bpf_bound_progs)); - WARN_ON(!list_empty(&ns->bpf_bound_maps)); WARN_ON(ns->xdp.prog); WARN_ON(ns->xdp_hw.prog); WARN_ON(ns->bpf_offloaded); + bpf_offload_dev_netdev_unregister(ns->sdev->bpf_dev, ns->netdev); + + if (ns->sdev->refcnt == 1) { + WARN_ON(!list_empty(&ns->sdev->bpf_bound_progs)); + WARN_ON(!list_empty(&ns->sdev->bpf_bound_maps)); + bpf_offload_dev_destroy(ns->sdev->bpf_dev); + } } diff --git a/drivers/net/netdevsim/netdev.c b/drivers/net/netdevsim/netdev.c index a7b179f0d954..2d244551298b 100644 --- a/drivers/net/netdevsim/netdev.c +++ b/drivers/net/netdevsim/netdev.c @@ -22,6 +22,7 @@ #include #include #include +#include #include "netdevsim.h" @@ -144,8 +145,29 @@ static struct device_type nsim_dev_type = { .release = nsim_dev_release, }; +static int +nsim_port_attr_get(struct net_device *dev, struct switchdev_attr *attr) +{ + struct netdevsim *ns = netdev_priv(dev); + + switch (attr->id) { + case SWITCHDEV_ATTR_ID_PORT_PARENT_ID: + attr->u.ppid.id_len = sizeof(ns->sdev->switch_id); + memcpy(&attr->u.ppid.id, &ns->sdev->switch_id, + attr->u.ppid.id_len); + return 0; + default: + return -EOPNOTSUPP; + } +} + +static const struct switchdev_ops nsim_switchdev_ops = { + .switchdev_port_attr_get = nsim_port_attr_get, +}; + static int nsim_init(struct net_device *dev) { + char sdev_ddir_name[10], sdev_link_name[32]; struct netdevsim *ns = netdev_priv(dev); int err; @@ -154,9 +176,32 @@ static int nsim_init(struct net_device *dev) if (IS_ERR_OR_NULL(ns->ddir)) return -ENOMEM; + if (!ns->sdev) { + ns->sdev = kzalloc(sizeof(*ns->sdev), GFP_KERNEL); + if (!ns->sdev) { + err = -ENOMEM; + goto err_debugfs_destroy; + } + ns->sdev->refcnt = 1; + ns->sdev->switch_id = nsim_dev_id; + sprintf(sdev_ddir_name, "%u", ns->sdev->switch_id); + ns->sdev->ddir = debugfs_create_dir(sdev_ddir_name, + nsim_sdev_ddir); + if (IS_ERR_OR_NULL(ns->sdev->ddir)) { + err = PTR_ERR_OR_ZERO(ns->sdev->ddir) ?: -EINVAL; + goto err_sdev_free; + } + } else { + sprintf(sdev_ddir_name, "%u", ns->sdev->switch_id); + ns->sdev->refcnt++; + } + + sprintf(sdev_link_name, "../../" DRV_NAME "_sdev/%s", sdev_ddir_name); + debugfs_create_symlink("sdev", ns->ddir, sdev_link_name); + err = nsim_bpf_init(ns); if (err) - goto err_debugfs_destroy; + goto err_sdev_destroy; ns->dev.id = nsim_dev_id++; ns->dev.bus = &nsim_bus; @@ -166,6 +211,7 @@ static int nsim_init(struct net_device *dev) goto err_bpf_uninit; SET_NETDEV_DEV(dev, &ns->dev); + SWITCHDEV_SET_OPS(dev, &nsim_switchdev_ops); err = nsim_devlink_setup(ns); if (err) @@ -179,6 +225,12 @@ err_unreg_dev: device_unregister(&ns->dev); err_bpf_uninit: nsim_bpf_uninit(ns); +err_sdev_destroy: + if (!--ns->sdev->refcnt) { + debugfs_remove_recursive(ns->sdev->ddir); +err_sdev_free: + kfree(ns->sdev); + } err_debugfs_destroy: debugfs_remove_recursive(ns->ddir); return err; @@ -192,6 +244,10 @@ static void nsim_uninit(struct net_device *dev) nsim_devlink_teardown(ns); debugfs_remove_recursive(ns->ddir); nsim_bpf_uninit(ns); + if (!--ns->sdev->refcnt) { + debugfs_remove_recursive(ns->sdev->ddir); + kfree(ns->sdev); + } } static void nsim_free(struct net_device *dev) @@ -470,14 +526,48 @@ static int nsim_validate(struct nlattr *tb[], struct nlattr *data[], return 0; } +static int nsim_newlink(struct net *src_net, struct net_device *dev, + struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) +{ + struct netdevsim *ns = netdev_priv(dev); + + if (tb[IFLA_LINK]) { + struct net_device *joindev; + struct netdevsim *joinns; + + joindev = __dev_get_by_index(src_net, + nla_get_u32(tb[IFLA_LINK])); + if (!joindev) + return -ENODEV; + if (joindev->netdev_ops != &nsim_netdev_ops) + return -EINVAL; + + joinns = netdev_priv(joindev); + if (!joinns->sdev || !joinns->sdev->refcnt) + return -EINVAL; + ns->sdev = joinns->sdev; + } + + return register_netdevice(dev); +} + +static void nsim_dellink(struct net_device *dev, struct list_head *head) +{ + unregister_netdevice_queue(dev, head); +} + static struct rtnl_link_ops nsim_link_ops __read_mostly = { .kind = DRV_NAME, .priv_size = sizeof(struct netdevsim), .setup = nsim_setup, .validate = nsim_validate, + .newlink = nsim_newlink, + .dellink = nsim_dellink, }; struct dentry *nsim_ddir; +struct dentry *nsim_sdev_ddir; static int __init nsim_module_init(void) { @@ -487,9 +577,15 @@ static int __init nsim_module_init(void) if (IS_ERR_OR_NULL(nsim_ddir)) return -ENOMEM; + nsim_sdev_ddir = debugfs_create_dir(DRV_NAME "_sdev", NULL); + if (IS_ERR_OR_NULL(nsim_sdev_ddir)) { + err = -ENOMEM; + goto err_debugfs_destroy; + } + err = bus_register(&nsim_bus); if (err) - goto err_debugfs_destroy; + goto err_sdir_destroy; err = nsim_devlink_init(); if (err) @@ -505,6 +601,8 @@ err_dl_fini: nsim_devlink_exit(); err_unreg_bus: bus_unregister(&nsim_bus); +err_sdir_destroy: + debugfs_remove_recursive(nsim_sdev_ddir); err_debugfs_destroy: debugfs_remove_recursive(nsim_ddir); return err; @@ -515,6 +613,7 @@ static void __exit nsim_module_exit(void) rtnl_link_unregister(&nsim_link_ops); nsim_devlink_exit(); bus_unregister(&nsim_bus); + debugfs_remove_recursive(nsim_sdev_ddir); debugfs_remove_recursive(nsim_ddir); } diff --git a/drivers/net/netdevsim/netdevsim.h b/drivers/net/netdevsim/netdevsim.h index 0aeabbe81cc6..02be199eb005 100644 --- a/drivers/net/netdevsim/netdevsim.h +++ b/drivers/net/netdevsim/netdevsim.h @@ -27,9 +27,25 @@ #define NSIM_EA(extack, msg) NL_SET_ERR_MSG_MOD((extack), msg) struct bpf_prog; +struct bpf_offload_dev; struct dentry; struct nsim_vf_config; +struct netdevsim_shared_dev { + unsigned int refcnt; + u32 switch_id; + + struct dentry *ddir; + + struct bpf_offload_dev *bpf_dev; + + struct dentry *ddir_bpf_bound_progs; + u32 prog_id_gen; + + struct list_head bpf_bound_progs; + struct list_head bpf_bound_maps; +}; + #define NSIM_IPSEC_MAX_SA_COUNT 33 #define NSIM_IPSEC_VALID BIT(31) @@ -59,6 +75,7 @@ struct netdevsim { struct u64_stats_sync syncp; struct device dev; + struct netdevsim_shared_dev *sdev; struct dentry *ddir; @@ -71,12 +88,8 @@ struct netdevsim { struct xdp_attachment_info xdp; struct xdp_attachment_info xdp_hw; - u32 prog_id_gen; - bool bpf_bind_accept; u32 bpf_bind_verifier_delay; - struct dentry *ddir_bpf_bound_progs; - struct list_head bpf_bound_progs; bool bpf_tc_accept; bool bpf_tc_non_bound_accept; @@ -84,7 +97,6 @@ struct netdevsim { bool bpf_xdpoffload_accept; bool bpf_map_accept; - struct list_head bpf_bound_maps; #if IS_ENABLED(CONFIG_NET_DEVLINK) struct devlink *devlink; #endif @@ -92,6 +104,7 @@ struct netdevsim { }; extern struct dentry *nsim_ddir; +extern struct dentry *nsim_sdev_ddir; #ifdef CONFIG_BPF_SYSCALL int nsim_bpf_init(struct netdevsim *ns); diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 8827e797ff97..5b5ad95cf339 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -85,6 +85,7 @@ struct bpf_map { char name[BPF_OBJ_NAME_LEN]; }; +struct bpf_offload_dev; struct bpf_offloaded_map; struct bpf_map_dev_ops { @@ -352,7 +353,7 @@ struct bpf_prog_array { struct bpf_prog *progs[0]; }; -struct bpf_prog_array __rcu *bpf_prog_array_alloc(u32 prog_cnt, gfp_t flags); +struct bpf_prog_array *bpf_prog_array_alloc(u32 prog_cnt, gfp_t flags); void bpf_prog_array_free(struct bpf_prog_array __rcu *progs); int bpf_prog_array_length(struct bpf_prog_array __rcu *progs); int bpf_prog_array_copy_to_user(struct bpf_prog_array __rcu *progs, @@ -648,7 +649,15 @@ int bpf_map_offload_delete_elem(struct bpf_map *map, void *key); int bpf_map_offload_get_next_key(struct bpf_map *map, void *key, void *next_key); -bool bpf_offload_dev_match(struct bpf_prog *prog, struct bpf_map *map); +bool bpf_offload_prog_map_match(struct bpf_prog *prog, struct bpf_map *map); + +struct bpf_offload_dev *bpf_offload_dev_create(void); +void bpf_offload_dev_destroy(struct bpf_offload_dev *offdev); +int bpf_offload_dev_netdev_register(struct bpf_offload_dev *offdev, + struct net_device *netdev); +void bpf_offload_dev_netdev_unregister(struct bpf_offload_dev *offdev, + struct net_device *netdev); +bool bpf_offload_dev_match(struct bpf_prog *prog, struct net_device *netdev); #if defined(CONFIG_NET) && defined(CONFIG_BPF_SYSCALL) int bpf_prog_offload_init(struct bpf_prog *prog, union bpf_attr *attr); diff --git a/kernel/bpf/cgroup.c b/kernel/bpf/cgroup.c index 3d83ee7df381..badabb0b435c 100644 --- a/kernel/bpf/cgroup.c +++ b/kernel/bpf/cgroup.c @@ -95,7 +95,7 @@ static int compute_effective_progs(struct cgroup *cgrp, enum bpf_attach_type type, struct bpf_prog_array __rcu **array) { - struct bpf_prog_array __rcu *progs; + struct bpf_prog_array *progs; struct bpf_prog_list *pl; struct cgroup *p = cgrp; int cnt = 0; @@ -120,13 +120,12 @@ static int compute_effective_progs(struct cgroup *cgrp, &p->bpf.progs[type], node) { if (!pl->prog) continue; - rcu_dereference_protected(progs, 1)-> - progs[cnt++] = pl->prog; + progs->progs[cnt++] = pl->prog; } p = cgroup_parent(p); } while (p); - *array = progs; + rcu_assign_pointer(*array, progs); return 0; } diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 1e5625d46414..253aa8e79c7b 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -1538,7 +1538,7 @@ static struct { .null_prog = NULL, }; -struct bpf_prog_array __rcu *bpf_prog_array_alloc(u32 prog_cnt, gfp_t flags) +struct bpf_prog_array *bpf_prog_array_alloc(u32 prog_cnt, gfp_t flags) { if (prog_cnt) return kzalloc(sizeof(struct bpf_prog_array) + diff --git a/kernel/bpf/offload.c b/kernel/bpf/offload.c index ac747d5cf7c6..177a52436394 100644 --- a/kernel/bpf/offload.c +++ b/kernel/bpf/offload.c @@ -18,19 +18,43 @@ #include #include #include +#include #include #include #include +#include #include #include -/* Protects bpf_prog_offload_devs, bpf_map_offload_devs and offload members +/* Protects offdevs, members of bpf_offload_netdev and offload members * of all progs. * RTNL lock cannot be taken when holding this lock. */ static DECLARE_RWSEM(bpf_devs_lock); -static LIST_HEAD(bpf_prog_offload_devs); -static LIST_HEAD(bpf_map_offload_devs); + +struct bpf_offload_dev { + struct list_head netdevs; +}; + +struct bpf_offload_netdev { + struct rhash_head l; + struct net_device *netdev; + struct bpf_offload_dev *offdev; + struct list_head progs; + struct list_head maps; + struct list_head offdev_netdevs; +}; + +static const struct rhashtable_params offdevs_params = { + .nelem_hint = 4, + .key_len = sizeof(struct net_device *), + .key_offset = offsetof(struct bpf_offload_netdev, netdev), + .head_offset = offsetof(struct bpf_offload_netdev, l), + .automatic_shrinking = true, +}; + +static struct rhashtable offdevs; +static bool offdevs_inited; static int bpf_dev_offload_check(struct net_device *netdev) { @@ -41,8 +65,19 @@ static int bpf_dev_offload_check(struct net_device *netdev) return 0; } +static struct bpf_offload_netdev * +bpf_offload_find_netdev(struct net_device *netdev) +{ + lockdep_assert_held(&bpf_devs_lock); + + if (!offdevs_inited) + return NULL; + return rhashtable_lookup_fast(&offdevs, &netdev, offdevs_params); +} + int bpf_prog_offload_init(struct bpf_prog *prog, union bpf_attr *attr) { + struct bpf_offload_netdev *ondev; struct bpf_prog_offload *offload; int err; @@ -66,12 +101,13 @@ int bpf_prog_offload_init(struct bpf_prog *prog, union bpf_attr *attr) goto err_maybe_put; down_write(&bpf_devs_lock); - if (offload->netdev->reg_state != NETREG_REGISTERED) { + ondev = bpf_offload_find_netdev(offload->netdev); + if (!ondev) { err = -EINVAL; goto err_unlock; } prog->aux->offload = offload; - list_add_tail(&offload->offloads, &bpf_prog_offload_devs); + list_add_tail(&offload->offloads, &ondev->progs); dev_put(offload->netdev); up_write(&bpf_devs_lock); @@ -294,6 +330,7 @@ static int bpf_map_offload_ndo(struct bpf_offloaded_map *offmap, struct bpf_map *bpf_map_offload_map_alloc(union bpf_attr *attr) { struct net *net = current->nsproxy->net_ns; + struct bpf_offload_netdev *ondev; struct bpf_offloaded_map *offmap; int err; @@ -316,11 +353,17 @@ struct bpf_map *bpf_map_offload_map_alloc(union bpf_attr *attr) if (err) goto err_unlock; + ondev = bpf_offload_find_netdev(offmap->netdev); + if (!ondev) { + err = -EINVAL; + goto err_unlock; + } + err = bpf_map_offload_ndo(offmap, BPF_OFFLOAD_MAP_ALLOC); if (err) goto err_unlock; - list_add_tail(&offmap->offloads, &bpf_map_offload_devs); + list_add_tail(&offmap->offloads, &ondev->maps); up_write(&bpf_devs_lock); rtnl_unlock(); @@ -468,77 +511,159 @@ int bpf_map_offload_info_fill(struct bpf_map_info *info, struct bpf_map *map) return 0; } -bool bpf_offload_dev_match(struct bpf_prog *prog, struct bpf_map *map) +static bool __bpf_offload_dev_match(struct bpf_prog *prog, + struct net_device *netdev) { - struct bpf_offloaded_map *offmap; + struct bpf_offload_netdev *ondev1, *ondev2; struct bpf_prog_offload *offload; - bool ret; if (!bpf_prog_is_dev_bound(prog->aux)) return false; - if (!bpf_map_is_dev_bound(map)) - return bpf_map_offload_neutral(map); + + offload = prog->aux->offload; + if (!offload) + return false; + if (offload->netdev == netdev) + return true; + + ondev1 = bpf_offload_find_netdev(offload->netdev); + ondev2 = bpf_offload_find_netdev(netdev); + + return ondev1 && ondev2 && ondev1->offdev == ondev2->offdev; +} + +bool bpf_offload_dev_match(struct bpf_prog *prog, struct net_device *netdev) +{ + bool ret; down_read(&bpf_devs_lock); - offload = prog->aux->offload; + ret = __bpf_offload_dev_match(prog, netdev); + up_read(&bpf_devs_lock); + + return ret; +} +EXPORT_SYMBOL_GPL(bpf_offload_dev_match); + +bool bpf_offload_prog_map_match(struct bpf_prog *prog, struct bpf_map *map) +{ + struct bpf_offloaded_map *offmap; + bool ret; + + if (!bpf_map_is_dev_bound(map)) + return bpf_map_offload_neutral(map); offmap = map_to_offmap(map); - ret = offload && offload->netdev == offmap->netdev; + down_read(&bpf_devs_lock); + ret = __bpf_offload_dev_match(prog, offmap->netdev); up_read(&bpf_devs_lock); return ret; } -static void bpf_offload_orphan_all_progs(struct net_device *netdev) +int bpf_offload_dev_netdev_register(struct bpf_offload_dev *offdev, + struct net_device *netdev) { - struct bpf_prog_offload *offload, *tmp; + struct bpf_offload_netdev *ondev; + int err; - list_for_each_entry_safe(offload, tmp, &bpf_prog_offload_devs, offloads) - if (offload->netdev == netdev) - __bpf_prog_offload_destroy(offload->prog); + ondev = kzalloc(sizeof(*ondev), GFP_KERNEL); + if (!ondev) + return -ENOMEM; + + ondev->netdev = netdev; + ondev->offdev = offdev; + INIT_LIST_HEAD(&ondev->progs); + INIT_LIST_HEAD(&ondev->maps); + + down_write(&bpf_devs_lock); + err = rhashtable_insert_fast(&offdevs, &ondev->l, offdevs_params); + if (err) { + netdev_warn(netdev, "failed to register for BPF offload\n"); + goto err_unlock_free; + } + + list_add(&ondev->offdev_netdevs, &offdev->netdevs); + up_write(&bpf_devs_lock); + return 0; + +err_unlock_free: + up_write(&bpf_devs_lock); + kfree(ondev); + return err; } +EXPORT_SYMBOL_GPL(bpf_offload_dev_netdev_register); -static void bpf_offload_orphan_all_maps(struct net_device *netdev) +void bpf_offload_dev_netdev_unregister(struct bpf_offload_dev *offdev, + struct net_device *netdev) { - struct bpf_offloaded_map *offmap, *tmp; - - list_for_each_entry_safe(offmap, tmp, &bpf_map_offload_devs, offloads) - if (offmap->netdev == netdev) - __bpf_map_offload_destroy(offmap); -} - -static int bpf_offload_notification(struct notifier_block *notifier, - ulong event, void *ptr) -{ - struct net_device *netdev = netdev_notifier_info_to_dev(ptr); + struct bpf_offload_netdev *ondev, *altdev; + struct bpf_offloaded_map *offmap, *mtmp; + struct bpf_prog_offload *offload, *ptmp; ASSERT_RTNL(); - switch (event) { - case NETDEV_UNREGISTER: - /* ignore namespace changes */ - if (netdev->reg_state != NETREG_UNREGISTERING) - break; + down_write(&bpf_devs_lock); + ondev = rhashtable_lookup_fast(&offdevs, &netdev, offdevs_params); + if (WARN_ON(!ondev)) + goto unlock; - down_write(&bpf_devs_lock); - bpf_offload_orphan_all_progs(netdev); - bpf_offload_orphan_all_maps(netdev); - up_write(&bpf_devs_lock); - break; - default: - break; + WARN_ON(rhashtable_remove_fast(&offdevs, &ondev->l, offdevs_params)); + list_del(&ondev->offdev_netdevs); + + /* Try to move the objects to another netdev of the device */ + altdev = list_first_entry_or_null(&offdev->netdevs, + struct bpf_offload_netdev, + offdev_netdevs); + if (altdev) { + list_for_each_entry(offload, &ondev->progs, offloads) + offload->netdev = altdev->netdev; + list_splice_init(&ondev->progs, &altdev->progs); + + list_for_each_entry(offmap, &ondev->maps, offloads) + offmap->netdev = altdev->netdev; + list_splice_init(&ondev->maps, &altdev->maps); + } else { + list_for_each_entry_safe(offload, ptmp, &ondev->progs, offloads) + __bpf_prog_offload_destroy(offload->prog); + list_for_each_entry_safe(offmap, mtmp, &ondev->maps, offloads) + __bpf_map_offload_destroy(offmap); } - return NOTIFY_OK; + + WARN_ON(!list_empty(&ondev->progs)); + WARN_ON(!list_empty(&ondev->maps)); + kfree(ondev); +unlock: + up_write(&bpf_devs_lock); } +EXPORT_SYMBOL_GPL(bpf_offload_dev_netdev_unregister); -static struct notifier_block bpf_offload_notifier = { - .notifier_call = bpf_offload_notification, -}; - -static int __init bpf_offload_init(void) +struct bpf_offload_dev *bpf_offload_dev_create(void) { - register_netdevice_notifier(&bpf_offload_notifier); - return 0; -} + struct bpf_offload_dev *offdev; + int err; -subsys_initcall(bpf_offload_init); + down_write(&bpf_devs_lock); + if (!offdevs_inited) { + err = rhashtable_init(&offdevs, &offdevs_params); + if (err) + return ERR_PTR(err); + offdevs_inited = true; + } + up_write(&bpf_devs_lock); + + offdev = kzalloc(sizeof(*offdev), GFP_KERNEL); + if (!offdev) + return ERR_PTR(-ENOMEM); + + INIT_LIST_HEAD(&offdev->netdevs); + + return offdev; +} +EXPORT_SYMBOL_GPL(bpf_offload_dev_create); + +void bpf_offload_dev_destroy(struct bpf_offload_dev *offdev) +{ + WARN_ON(!list_empty(&offdev->netdevs)); + kfree(offdev); +} +EXPORT_SYMBOL_GPL(bpf_offload_dev_destroy); diff --git a/kernel/bpf/sockmap.c b/kernel/bpf/sockmap.c index 98fb7938beea..0b38be5a955c 100644 --- a/kernel/bpf/sockmap.c +++ b/kernel/bpf/sockmap.c @@ -725,11 +725,8 @@ static int bpf_tcp_sendmsg_do_redirect(struct sock *sk, int send, { bool ingress = !!(md->flags & BPF_F_INGRESS); struct smap_psock *psock; - struct scatterlist *sg; int err = 0; - sg = md->sg_data; - rcu_read_lock(); psock = smap_psock_sk(sk); if (unlikely(!psock)) diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 63aaac52a265..25e47c195874 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -5054,7 +5054,7 @@ static int check_map_prog_compatibility(struct bpf_verifier_env *env, } if ((bpf_prog_is_dev_bound(prog->aux) || bpf_map_is_dev_bound(map)) && - !bpf_offload_dev_match(prog, map)) { + !bpf_offload_prog_map_match(prog, map)) { verbose(env, "offload device mismatch between prog and map\n"); return -EINVAL; } diff --git a/samples/bpf/bpf_load.c b/samples/bpf/bpf_load.c index 89161c9ed466..904e775d1a44 100644 --- a/samples/bpf/bpf_load.c +++ b/samples/bpf/bpf_load.c @@ -107,6 +107,9 @@ static int load_and_attach(const char *event, struct bpf_insn *prog, int size) return -1; } + if (prog_cnt == MAX_PROGS) + return -1; + fd = bpf_load_program(prog_type, prog, insns_cnt, license, kern_version, bpf_log_buf, BPF_LOG_BUF_SIZE); if (fd < 0) { diff --git a/samples/bpf/test_cgrp2_sock2.c b/samples/bpf/test_cgrp2_sock2.c index 3b5be2364975..a9277b118c33 100644 --- a/samples/bpf/test_cgrp2_sock2.c +++ b/samples/bpf/test_cgrp2_sock2.c @@ -51,7 +51,7 @@ int main(int argc, char **argv) if (argc > 3) filter_id = atoi(argv[3]); - if (filter_id > prog_cnt) { + if (filter_id >= prog_cnt) { printf("Invalid program id; program not found in file\n"); return EXIT_FAILURE; } diff --git a/tools/bpf/bpftool/Makefile b/tools/bpf/bpftool/Makefile index 6c4830e18879..74288a2197ab 100644 --- a/tools/bpf/bpftool/Makefile +++ b/tools/bpf/bpftool/Makefile @@ -26,7 +26,7 @@ LIBBPF = $(BPF_PATH)libbpf.a BPFTOOL_VERSION := $(shell make --no-print-directory -sC ../../.. kernelversion) $(LIBBPF): FORCE - $(Q)$(MAKE) -C $(BPF_DIR) OUTPUT=$(OUTPUT) $(OUTPUT)libbpf.a FEATURES_DUMP=$(FEATURE_DUMP_EXPORT) + $(Q)$(MAKE) -C $(BPF_DIR) OUTPUT=$(OUTPUT) $(OUTPUT)libbpf.a $(LIBBPF)-clean: $(call QUIET_CLEAN, libbpf) diff --git a/tools/lib/bpf/Makefile b/tools/lib/bpf/Makefile index 7a8e4c98ef1a..d49902e818b5 100644 --- a/tools/lib/bpf/Makefile +++ b/tools/lib/bpf/Makefile @@ -66,7 +66,7 @@ ifndef VERBOSE endif FEATURE_USER = .libbpf -FEATURE_TESTS = libelf libelf-getphdrnum libelf-mmap bpf reallocarray +FEATURE_TESTS = libelf libelf-mmap bpf reallocarray FEATURE_DISPLAY = libelf bpf INCLUDES = -I. -I$(srctree)/tools/include -I$(srctree)/tools/arch/$(ARCH)/include/uapi -I$(srctree)/tools/include/uapi -I$(srctree)/tools/perf @@ -116,10 +116,6 @@ ifeq ($(feature-libelf-mmap), 1) override CFLAGS += -DHAVE_LIBELF_MMAP_SUPPORT endif -ifeq ($(feature-libelf-getphdrnum), 1) - override CFLAGS += -DHAVE_ELF_GETPHDRNUM_SUPPORT -endif - ifeq ($(feature-reallocarray), 0) override CFLAGS += -DCOMPAT_NEED_REALLOCARRAY endif diff --git a/tools/testing/selftests/bpf/test_offload.py b/tools/testing/selftests/bpf/test_offload.py index b746227eaff2..d59642e70f56 100755 --- a/tools/testing/selftests/bpf/test_offload.py +++ b/tools/testing/selftests/bpf/test_offload.py @@ -158,8 +158,9 @@ def tool(name, args, flags, JSON=True, ns="", fail=True, include_stderr=False): else: return ret, out -def bpftool(args, JSON=True, ns="", fail=True): - return tool("bpftool", args, {"json":"-p"}, JSON=JSON, ns=ns, fail=fail) +def bpftool(args, JSON=True, ns="", fail=True, include_stderr=False): + return tool("bpftool", args, {"json":"-p"}, JSON=JSON, ns=ns, + fail=fail, include_stderr=include_stderr) def bpftool_prog_list(expected=None, ns=""): _, progs = bpftool("prog show", JSON=True, ns=ns, fail=True) @@ -201,6 +202,21 @@ def bpftool_map_list_wait(expected=0, n_retry=20): time.sleep(0.05) raise Exception("Time out waiting for map counts to stabilize want %d, have %d" % (expected, nmaps)) +def bpftool_prog_load(sample, file_name, maps=[], prog_type="xdp", dev=None, + fail=True, include_stderr=False): + args = "prog load %s %s" % (os.path.join(bpf_test_dir, sample), file_name) + if prog_type is not None: + args += " type " + prog_type + if dev is not None: + args += " dev " + dev + if len(maps): + args += " map " + " map ".join(maps) + + res = bpftool(args, fail=fail, include_stderr=include_stderr) + if res[0] == 0: + files.append(file_name) + return res + def ip(args, force=False, JSON=True, ns="", fail=True, include_stderr=False): if force: args = "-force " + args @@ -307,21 +323,25 @@ class NetdevSim: Class for netdevsim netdevice and its attributes. """ - def __init__(self): + def __init__(self, link=None): + self.link = link + self.dev = self._netdevsim_create() devs.append(self) self.ns = "" self.dfs_dir = '/sys/kernel/debug/netdevsim/%s' % (self.dev['ifname']) + self.sdev_dir = self.dfs_dir + '/sdev/' self.dfs_refresh() def __getitem__(self, key): return self.dev[key] def _netdevsim_create(self): + link = "" if self.link is None else "link " + self.link.dev['ifname'] _, old = ip("link show") - ip("link add sim%d type netdevsim") + ip("link add sim%d {link} type netdevsim".format(link=link)) _, new = ip("link show") for dev in new: @@ -345,12 +365,12 @@ class NetdevSim: return data.strip() def dfs_num_bound_progs(self): - path = os.path.join(self.dfs_dir, "bpf_bound_progs") + path = os.path.join(self.sdev_dir, "bpf_bound_progs") _, progs = cmd('ls %s' % (path)) return len(progs.split()) def dfs_get_bound_progs(self, expected): - progs = DebugfsDir(os.path.join(self.dfs_dir, "bpf_bound_progs")) + progs = DebugfsDir(os.path.join(self.sdev_dir, "bpf_bound_progs")) if expected is not None: if len(progs) != expected: fail(True, "%d BPF programs bound, expected %d" % @@ -847,6 +867,25 @@ try: sim.set_mtu(1500) sim.wait_for_flush() + start_test("Test non-offload XDP attaching to HW...") + bpftool_prog_load("sample_ret0.o", "/sys/fs/bpf/nooffload") + nooffload = bpf_pinned("/sys/fs/bpf/nooffload") + ret, _, err = sim.set_xdp(nooffload, "offload", + fail=False, include_stderr=True) + fail(ret == 0, "attached non-offloaded XDP program to HW") + check_extack_nsim(err, "xdpoffload of non-bound program.", args) + rm("/sys/fs/bpf/nooffload") + + start_test("Test offload XDP attaching to drv...") + bpftool_prog_load("sample_ret0.o", "/sys/fs/bpf/offload", + dev=sim['ifname']) + offload = bpf_pinned("/sys/fs/bpf/offload") + ret, _, err = sim.set_xdp(offload, "drv", fail=False, include_stderr=True) + fail(ret == 0, "attached offloaded XDP program to drv") + check_extack(err, "using device-bound program without HW_MODE flag is not supported.", args) + rm("/sys/fs/bpf/offload") + sim.wait_for_flush() + start_test("Test XDP offload...") _, _, err = sim.set_xdp(obj, "offload", verbose=True, include_stderr=True) ipl = sim.ip_link_show(xdp=True) @@ -1140,6 +1179,106 @@ try: fail(ret == 0, "netdevsim didn't refuse to create a map with offload disabled") + sim.remove() + + start_test("Test multi-dev ASIC program reuse...") + simA = NetdevSim() + simB1 = NetdevSim() + simB2 = NetdevSim(link=simB1) + simB3 = NetdevSim(link=simB1) + sims = (simA, simB1, simB2, simB3) + simB = (simB1, simB2, simB3) + + bpftool_prog_load("sample_map_ret0.o", "/sys/fs/bpf/nsimA", + dev=simA['ifname']) + progA = bpf_pinned("/sys/fs/bpf/nsimA") + bpftool_prog_load("sample_map_ret0.o", "/sys/fs/bpf/nsimB", + dev=simB1['ifname']) + progB = bpf_pinned("/sys/fs/bpf/nsimB") + + simA.set_xdp(progA, "offload", JSON=False) + for d in simB: + d.set_xdp(progB, "offload", JSON=False) + + start_test("Test multi-dev ASIC cross-dev replace...") + ret, _ = simA.set_xdp(progB, "offload", force=True, JSON=False, fail=False) + fail(ret == 0, "cross-ASIC program allowed") + for d in simB: + ret, _ = d.set_xdp(progA, "offload", force=True, JSON=False, fail=False) + fail(ret == 0, "cross-ASIC program allowed") + + start_test("Test multi-dev ASIC cross-dev install...") + for d in sims: + d.unset_xdp("offload") + + ret, _, err = simA.set_xdp(progB, "offload", force=True, JSON=False, + fail=False, include_stderr=True) + fail(ret == 0, "cross-ASIC program allowed") + check_extack_nsim(err, "program bound to different dev.", args) + for d in simB: + ret, _, err = d.set_xdp(progA, "offload", force=True, JSON=False, + fail=False, include_stderr=True) + fail(ret == 0, "cross-ASIC program allowed") + check_extack_nsim(err, "program bound to different dev.", args) + + start_test("Test multi-dev ASIC cross-dev map reuse...") + + mapA = bpftool("prog show %s" % (progA))[1]["map_ids"][0] + mapB = bpftool("prog show %s" % (progB))[1]["map_ids"][0] + + ret, _ = bpftool_prog_load("sample_map_ret0.o", "/sys/fs/bpf/nsimB_", + dev=simB3['ifname'], + maps=["idx 0 id %d" % (mapB)], + fail=False) + fail(ret != 0, "couldn't reuse a map on the same ASIC") + rm("/sys/fs/bpf/nsimB_") + + ret, _, err = bpftool_prog_load("sample_map_ret0.o", "/sys/fs/bpf/nsimA_", + dev=simA['ifname'], + maps=["idx 0 id %d" % (mapB)], + fail=False, include_stderr=True) + fail(ret == 0, "could reuse a map on a different ASIC") + fail(err.count("offload device mismatch between prog and map") == 0, + "error message missing for cross-ASIC map") + + ret, _, err = bpftool_prog_load("sample_map_ret0.o", "/sys/fs/bpf/nsimB_", + dev=simB1['ifname'], + maps=["idx 0 id %d" % (mapA)], + fail=False, include_stderr=True) + fail(ret == 0, "could reuse a map on a different ASIC") + fail(err.count("offload device mismatch between prog and map") == 0, + "error message missing for cross-ASIC map") + + start_test("Test multi-dev ASIC cross-dev destruction...") + bpftool_prog_list_wait(expected=2) + + simA.remove() + bpftool_prog_list_wait(expected=1) + + ifnameB = bpftool("prog show %s" % (progB))[1]["dev"]["ifname"] + fail(ifnameB != simB1['ifname'], "program not bound to originial device") + simB1.remove() + bpftool_prog_list_wait(expected=1) + + start_test("Test multi-dev ASIC cross-dev destruction - move...") + ifnameB = bpftool("prog show %s" % (progB))[1]["dev"]["ifname"] + fail(ifnameB not in (simB2['ifname'], simB3['ifname']), + "program not bound to remaining devices") + + simB2.remove() + ifnameB = bpftool("prog show %s" % (progB))[1]["dev"]["ifname"] + fail(ifnameB != simB3['ifname'], "program not bound to remaining device") + + simB3.remove() + bpftool_prog_list_wait(expected=0) + + start_test("Test multi-dev ASIC cross-dev destruction - orphaned...") + ret, out = bpftool("prog show %s" % (progB), fail=False) + fail(ret == 0, "got information about orphaned program") + fail("error" not in out, "no error reported for get info on orphaned") + fail(out["error"] != "can't get prog info: No such device", + "wrong error for get info on orphaned") + print("%s: OK" % (os.path.basename(__file__))) finally: