diff options
author | Stanislav Fomichev <sdf@google.com> | 2023-01-19 14:15:24 -0800 |
---|---|---|
committer | Martin KaFai Lau <martin.lau@kernel.org> | 2023-01-23 09:38:10 -0800 |
commit | 2b3486bc2d237ec345b3942b7be5deabf8c8fed1 (patch) | |
tree | ec8986e58d6d69dcd3572ec447c9727451418904 /kernel | |
parent | 89bbc53a4dbbbdd65962d4bbaeba6c7775ea0bf7 (diff) | |
download | linux-stable-2b3486bc2d237ec345b3942b7be5deabf8c8fed1.tar.gz linux-stable-2b3486bc2d237ec345b3942b7be5deabf8c8fed1.tar.bz2 linux-stable-2b3486bc2d237ec345b3942b7be5deabf8c8fed1.zip |
bpf: Introduce device-bound XDP programs
New flag BPF_F_XDP_DEV_BOUND_ONLY plus all the infra to have a way
to associate a netdev with a BPF program at load time.
netdevsim checks are dropped in favor of generic check in dev_xdp_attach.
Cc: John Fastabend <john.fastabend@gmail.com>
Cc: David Ahern <dsahern@gmail.com>
Cc: Martin KaFai Lau <martin.lau@linux.dev>
Cc: Jakub Kicinski <kuba@kernel.org>
Cc: Willem de Bruijn <willemb@google.com>
Cc: Jesper Dangaard Brouer <brouer@redhat.com>
Cc: Anatoly Burakov <anatoly.burakov@intel.com>
Cc: Alexander Lobakin <alexandr.lobakin@intel.com>
Cc: Magnus Karlsson <magnus.karlsson@gmail.com>
Cc: Maryam Tahhan <mtahhan@redhat.com>
Cc: xdp-hints@xdp-project.net
Cc: netdev@vger.kernel.org
Signed-off-by: Stanislav Fomichev <sdf@google.com>
Link: https://lore.kernel.org/r/20230119221536.3349901-6-sdf@google.com
Signed-off-by: Martin KaFai Lau <martin.lau@kernel.org>
Diffstat (limited to 'kernel')
-rw-r--r-- | kernel/bpf/core.c | 4 | ||||
-rw-r--r-- | kernel/bpf/offload.c | 95 | ||||
-rw-r--r-- | kernel/bpf/syscall.c | 9 |
3 files changed, 78 insertions, 30 deletions
diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index 515f4f08591c..1cf19da3c128 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -2553,8 +2553,8 @@ static void bpf_prog_free_deferred(struct work_struct *work) #endif bpf_free_used_maps(aux); bpf_free_used_btfs(aux); - if (bpf_prog_is_offloaded(aux)) - bpf_prog_offload_destroy(aux->prog); + if (bpf_prog_is_dev_bound(aux)) + bpf_prog_dev_bound_destroy(aux->prog); #ifdef CONFIG_PERF_EVENTS if (aux->prog->has_callchain_buf) put_callchain_buffers(); diff --git a/kernel/bpf/offload.c b/kernel/bpf/offload.c index deb06498da0b..f767455ed732 100644 --- a/kernel/bpf/offload.c +++ b/kernel/bpf/offload.c @@ -41,7 +41,7 @@ struct bpf_offload_dev { struct bpf_offload_netdev { struct rhash_head l; struct net_device *netdev; - struct bpf_offload_dev *offdev; + struct bpf_offload_dev *offdev; /* NULL when bound-only */ struct list_head progs; struct list_head maps; struct list_head offdev_netdevs; @@ -89,19 +89,17 @@ static int __bpf_offload_dev_netdev_register(struct bpf_offload_dev *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; + goto err_free; } - list_add(&ondev->offdev_netdevs, &offdev->netdevs); - up_write(&bpf_devs_lock); + if (offdev) + list_add(&ondev->offdev_netdevs, &offdev->netdevs); return 0; -err_unlock_free: - up_write(&bpf_devs_lock); +err_free: kfree(ondev); return err; } @@ -149,24 +147,26 @@ static void __bpf_map_offload_destroy(struct bpf_offloaded_map *offmap) static void __bpf_offload_dev_netdev_unregister(struct bpf_offload_dev *offdev, struct net_device *netdev) { - struct bpf_offload_netdev *ondev, *altdev; + struct bpf_offload_netdev *ondev, *altdev = NULL; struct bpf_offloaded_map *offmap, *mtmp; struct bpf_prog_offload *offload, *ptmp; ASSERT_RTNL(); - down_write(&bpf_devs_lock); ondev = rhashtable_lookup_fast(&offdevs, &netdev, offdevs_params); if (WARN_ON(!ondev)) - goto unlock; + return; 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 (offdev) { + list_del(&ondev->offdev_netdevs); + 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; @@ -185,11 +185,9 @@ static void __bpf_offload_dev_netdev_unregister(struct bpf_offload_dev *offdev, WARN_ON(!list_empty(&ondev->progs)); WARN_ON(!list_empty(&ondev->maps)); kfree(ondev); -unlock: - up_write(&bpf_devs_lock); } -int bpf_prog_offload_init(struct bpf_prog *prog, union bpf_attr *attr) +int bpf_prog_dev_bound_init(struct bpf_prog *prog, union bpf_attr *attr) { struct bpf_offload_netdev *ondev; struct bpf_prog_offload *offload; @@ -199,7 +197,11 @@ int bpf_prog_offload_init(struct bpf_prog *prog, union bpf_attr *attr) attr->prog_type != BPF_PROG_TYPE_XDP) return -EINVAL; - if (attr->prog_flags) + if (attr->prog_flags & ~BPF_F_XDP_DEV_BOUND_ONLY) + return -EINVAL; + + if (attr->prog_type == BPF_PROG_TYPE_SCHED_CLS && + attr->prog_flags & BPF_F_XDP_DEV_BOUND_ONLY) return -EINVAL; offload = kzalloc(sizeof(*offload), GFP_USER); @@ -214,11 +216,23 @@ int bpf_prog_offload_init(struct bpf_prog *prog, union bpf_attr *attr) if (err) goto err_maybe_put; + prog->aux->offload_requested = !(attr->prog_flags & BPF_F_XDP_DEV_BOUND_ONLY); + down_write(&bpf_devs_lock); ondev = bpf_offload_find_netdev(offload->netdev); if (!ondev) { - err = -EINVAL; - goto err_unlock; + if (bpf_prog_is_offloaded(prog->aux)) { + err = -EINVAL; + goto err_unlock; + } + + /* When only binding to the device, explicitly + * create an entry in the hashtable. + */ + err = __bpf_offload_dev_netdev_register(NULL, offload->netdev); + if (err) + goto err_unlock; + ondev = bpf_offload_find_netdev(offload->netdev); } offload->offdev = ondev->offdev; prog->aux->offload = offload; @@ -321,12 +335,25 @@ bpf_prog_offload_remove_insns(struct bpf_verifier_env *env, u32 off, u32 cnt) up_read(&bpf_devs_lock); } -void bpf_prog_offload_destroy(struct bpf_prog *prog) +void bpf_prog_dev_bound_destroy(struct bpf_prog *prog) { + struct bpf_offload_netdev *ondev; + struct net_device *netdev; + + rtnl_lock(); down_write(&bpf_devs_lock); - if (prog->aux->offload) + if (prog->aux->offload) { + list_del_init(&prog->aux->offload->offloads); + + netdev = prog->aux->offload->netdev; __bpf_prog_offload_destroy(prog); + + ondev = bpf_offload_find_netdev(netdev); + if (!ondev->offdev && list_empty(&ondev->progs)) + __bpf_offload_dev_netdev_unregister(NULL, netdev); + } up_write(&bpf_devs_lock); + rtnl_unlock(); } static int bpf_prog_offload_translate(struct bpf_prog *prog) @@ -621,7 +648,7 @@ static bool __bpf_offload_dev_match(struct bpf_prog *prog, struct bpf_offload_netdev *ondev1, *ondev2; struct bpf_prog_offload *offload; - if (!bpf_prog_is_offloaded(prog->aux)) + if (!bpf_prog_is_dev_bound(prog->aux)) return false; offload = prog->aux->offload; @@ -667,14 +694,21 @@ bool bpf_offload_prog_map_match(struct bpf_prog *prog, struct bpf_map *map) int bpf_offload_dev_netdev_register(struct bpf_offload_dev *offdev, struct net_device *netdev) { - return __bpf_offload_dev_netdev_register(offdev, netdev); + int err; + + down_write(&bpf_devs_lock); + err = __bpf_offload_dev_netdev_register(offdev, netdev); + up_write(&bpf_devs_lock); + return err; } EXPORT_SYMBOL_GPL(bpf_offload_dev_netdev_register); void bpf_offload_dev_netdev_unregister(struct bpf_offload_dev *offdev, struct net_device *netdev) { + down_write(&bpf_devs_lock); __bpf_offload_dev_netdev_unregister(offdev, netdev); + up_write(&bpf_devs_lock); } EXPORT_SYMBOL_GPL(bpf_offload_dev_netdev_unregister); @@ -708,6 +742,19 @@ void *bpf_offload_dev_priv(struct bpf_offload_dev *offdev) } EXPORT_SYMBOL_GPL(bpf_offload_dev_priv); +void bpf_dev_bound_netdev_unregister(struct net_device *dev) +{ + struct bpf_offload_netdev *ondev; + + ASSERT_RTNL(); + + down_write(&bpf_devs_lock); + ondev = bpf_offload_find_netdev(dev); + if (ondev && !ondev->offdev) + __bpf_offload_dev_netdev_unregister(NULL, ondev->netdev); + up_write(&bpf_devs_lock); +} + static int __init bpf_offload_init(void) { return rhashtable_init(&offdevs, &offdevs_params); diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 5e90b697f908..fdf4ff3d5a7f 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -2491,7 +2491,8 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr) BPF_F_TEST_STATE_FREQ | BPF_F_SLEEPABLE | BPF_F_TEST_RND_HI32 | - BPF_F_XDP_HAS_FRAGS)) + BPF_F_XDP_HAS_FRAGS | + BPF_F_XDP_DEV_BOUND_ONLY)) return -EINVAL; if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS) && @@ -2575,7 +2576,7 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr) prog->aux->attach_btf = attach_btf; prog->aux->attach_btf_id = attr->attach_btf_id; prog->aux->dst_prog = dst_prog; - prog->aux->offload_requested = !!attr->prog_ifindex; + prog->aux->dev_bound = !!attr->prog_ifindex; prog->aux->sleepable = attr->prog_flags & BPF_F_SLEEPABLE; prog->aux->xdp_has_frags = attr->prog_flags & BPF_F_XDP_HAS_FRAGS; @@ -2598,8 +2599,8 @@ static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr) atomic64_set(&prog->aux->refcnt, 1); prog->gpl_compatible = is_gpl ? 1 : 0; - if (bpf_prog_is_offloaded(prog->aux)) { - err = bpf_prog_offload_init(prog, attr); + if (bpf_prog_is_dev_bound(prog->aux)) { + err = bpf_prog_dev_bound_init(prog, attr); if (err) goto free_prog_sec; } |