diff options
Diffstat (limited to 'kernel/bpf/devmap.c')
| -rw-r--r-- | kernel/bpf/devmap.c | 1078 |
1 files changed, 852 insertions, 226 deletions
diff --git a/kernel/bpf/devmap.c b/kernel/bpf/devmap.c index 191b79948424..2625601de76e 100644 --- a/kernel/bpf/devmap.c +++ b/kernel/bpf/devmap.c @@ -1,13 +1,5 @@ +// SPDX-License-Identifier: GPL-2.0-only /* Copyright (c) 2017 Covalent IO, Inc. http://covalent.io - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of version 2 of the GNU General Public - * License as published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, but - * WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. */ /* Devmaps primary use is as a backend map for XDP BPF helper call @@ -25,9 +17,8 @@ * datapath always has a valid copy. However, the datapath does a "flush" * operation that pushes any pending packets in the driver outside the RCU * critical section. Each bpf_dtab_netdev tracks these pending operations using - * an atomic per-cpu bitmap. The bpf_dtab_netdev object will not be destroyed - * until all bits are cleared indicating outstanding flush operations have - * completed. + * a per-cpu flush list. The bpf_dtab_netdev object will not be destroyed until + * this list is empty, indicating outstanding flush operations have completed. * * BPF syscalls may race with BPF program calls on any of the update, delete * or lookup operations. As noted above the xchg() operation also keep the @@ -46,150 +37,218 @@ * notifier hook walks the map we know that new dev references can not be * added by the user because core infrastructure ensures dev_get_by_index() * calls will fail at this point. + * + * The devmap_hash type is a map type which interprets keys as ifindexes and + * indexes these using a hashmap. This allows maps that use ifindex as key to be + * densely packed instead of having holes in the lookup array for unused + * ifindexes. The setup and packet enqueue/send code is shared between the two + * types of devmap; only the lookup and insertion is different. */ #include <linux/bpf.h> #include <net/xdp.h> #include <linux/filter.h> #include <trace/events/xdp.h> +#include <linux/btf_ids.h> #define DEV_CREATE_FLAG_MASK \ (BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY) -#define DEV_MAP_BULK_SIZE 16 -struct xdp_bulk_queue { +struct xdp_dev_bulk_queue { struct xdp_frame *q[DEV_MAP_BULK_SIZE]; + struct list_head flush_node; + struct net_device *dev; struct net_device *dev_rx; + struct bpf_prog *xdp_prog; unsigned int count; }; struct bpf_dtab_netdev { struct net_device *dev; /* must be first member, due to tracepoint */ - struct bpf_dtab *dtab; - unsigned int bit; - struct xdp_bulk_queue __percpu *bulkq; + struct hlist_node index_hlist; + struct bpf_prog *xdp_prog; struct rcu_head rcu; + unsigned int idx; + struct bpf_devmap_val val; }; struct bpf_dtab { struct bpf_map map; - struct bpf_dtab_netdev **netdev_map; - unsigned long __percpu *flush_needed; + struct bpf_dtab_netdev __rcu **netdev_map; /* DEVMAP type only */ struct list_head list; + + /* these are only used for DEVMAP_HASH type maps */ + struct hlist_head *dev_index_head; + spinlock_t index_lock; + unsigned int items; + u32 n_buckets; }; static DEFINE_SPINLOCK(dev_map_lock); static LIST_HEAD(dev_map_list); -static u64 dev_map_bitmap_size(const union bpf_attr *attr) +static struct hlist_head *dev_map_create_hash(unsigned int entries, + int numa_node) { - return BITS_TO_LONGS((u64) attr->max_entries) * sizeof(unsigned long); + int i; + struct hlist_head *hash; + + hash = bpf_map_area_alloc((u64) entries * sizeof(*hash), numa_node); + if (hash != NULL) + for (i = 0; i < entries; i++) + INIT_HLIST_HEAD(&hash[i]); + + return hash; } -static struct bpf_map *dev_map_alloc(union bpf_attr *attr) +static inline struct hlist_head *dev_map_index_hash(struct bpf_dtab *dtab, + int idx) { - struct bpf_dtab *dtab; - int err = -EINVAL; - u64 cost; + return &dtab->dev_index_head[idx & (dtab->n_buckets - 1)]; +} - if (!capable(CAP_NET_ADMIN)) - return ERR_PTR(-EPERM); +static int dev_map_alloc_check(union bpf_attr *attr) +{ + u32 valsize = attr->value_size; - /* check sanity of attributes */ + /* check sanity of attributes. 2 value sizes supported: + * 4 bytes: ifindex + * 8 bytes: ifindex + prog fd + */ if (attr->max_entries == 0 || attr->key_size != 4 || - attr->value_size != 4 || attr->map_flags & ~DEV_CREATE_FLAG_MASK) - return ERR_PTR(-EINVAL); + (valsize != offsetofend(struct bpf_devmap_val, ifindex) && + valsize != offsetofend(struct bpf_devmap_val, bpf_prog.fd)) || + attr->map_flags & ~DEV_CREATE_FLAG_MASK) + return -EINVAL; - dtab = kzalloc(sizeof(*dtab), GFP_USER); - if (!dtab) - return ERR_PTR(-ENOMEM); + if (attr->map_type == BPF_MAP_TYPE_DEVMAP_HASH) { + /* Hash table size must be power of 2; roundup_pow_of_two() + * can overflow into UB on 32-bit arches + */ + if (attr->max_entries > 1UL << 31) + return -EINVAL; + } + + return 0; +} +static int dev_map_init_map(struct bpf_dtab *dtab, union bpf_attr *attr) +{ + /* Lookup returns a pointer straight to dev->ifindex, so make sure the + * verifier prevents writes from the BPF side + */ + attr->map_flags |= BPF_F_RDONLY_PROG; bpf_map_init_from_attr(&dtab->map, attr); - /* make sure page count doesn't overflow */ - cost = (u64) dtab->map.max_entries * sizeof(struct bpf_dtab_netdev *); - cost += dev_map_bitmap_size(attr) * num_possible_cpus(); - if (cost >= U32_MAX - PAGE_SIZE) - goto free_dtab; + if (attr->map_type == BPF_MAP_TYPE_DEVMAP_HASH) { + /* Hash table size must be power of 2 */ + dtab->n_buckets = roundup_pow_of_two(dtab->map.max_entries); + dtab->dev_index_head = dev_map_create_hash(dtab->n_buckets, + dtab->map.numa_node); + if (!dtab->dev_index_head) + return -ENOMEM; - dtab->map.pages = round_up(cost, PAGE_SIZE) >> PAGE_SHIFT; + spin_lock_init(&dtab->index_lock); + } else { + dtab->netdev_map = bpf_map_area_alloc((u64) dtab->map.max_entries * + sizeof(struct bpf_dtab_netdev *), + dtab->map.numa_node); + if (!dtab->netdev_map) + return -ENOMEM; + } - /* if map size is larger than memlock limit, reject it early */ - err = bpf_map_precharge_memlock(dtab->map.pages); - if (err) - goto free_dtab; + return 0; +} - err = -ENOMEM; +static struct bpf_map *dev_map_alloc(union bpf_attr *attr) +{ + struct bpf_dtab *dtab; + int err; - /* A per cpu bitfield with a bit per possible net device */ - dtab->flush_needed = __alloc_percpu_gfp(dev_map_bitmap_size(attr), - __alignof__(unsigned long), - GFP_KERNEL | __GFP_NOWARN); - if (!dtab->flush_needed) - goto free_dtab; + dtab = bpf_map_area_alloc(sizeof(*dtab), NUMA_NO_NODE); + if (!dtab) + return ERR_PTR(-ENOMEM); - dtab->netdev_map = bpf_map_area_alloc(dtab->map.max_entries * - sizeof(struct bpf_dtab_netdev *), - dtab->map.numa_node); - if (!dtab->netdev_map) - goto free_dtab; + err = dev_map_init_map(dtab, attr); + if (err) { + bpf_map_area_free(dtab); + return ERR_PTR(err); + } spin_lock(&dev_map_lock); list_add_tail_rcu(&dtab->list, &dev_map_list); spin_unlock(&dev_map_lock); return &dtab->map; -free_dtab: - free_percpu(dtab->flush_needed); - kfree(dtab); - return ERR_PTR(err); } static void dev_map_free(struct bpf_map *map) { struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); - int i, cpu; + u32 i; /* At this point bpf_prog->aux->refcnt == 0 and this map->refcnt == 0, * so the programs (can be more than one that used this map) were - * disconnected from events. Wait for outstanding critical sections in - * these programs to complete. The rcu critical section only guarantees - * no further reads against netdev_map. It does __not__ ensure pending - * flush operations (if any) are complete. + * disconnected from events. The following synchronize_rcu() guarantees + * both rcu read critical sections complete and waits for + * preempt-disable regions (NAPI being the relevant context here) so we + * are certain there will be no further reads against the netdev_map and + * all flush operations are complete. Flush operations can only be done + * from NAPI context for this reason. */ spin_lock(&dev_map_lock); list_del_rcu(&dtab->list); spin_unlock(&dev_map_lock); - bpf_clear_redirect_map(map); + /* bpf_redirect_info->map is assigned in __bpf_xdp_redirect_map() + * during NAPI callback and cleared after the XDP redirect. There is no + * explicit RCU read section which protects bpf_redirect_info->map but + * local_bh_disable() also marks the beginning an RCU section. This + * makes the complete softirq callback RCU protected. Thus after + * following synchronize_rcu() there no bpf_redirect_info->map == map + * assignment. + */ synchronize_rcu(); - /* To ensure all pending flush operations have completed wait for flush - * bitmap to indicate all flush_needed bits to be zero on _all_ cpus. - * Because the above synchronize_rcu() ensures the map is disconnected - * from the program we can assume no new bits will be set. - */ - for_each_online_cpu(cpu) { - unsigned long *bitmap = per_cpu_ptr(dtab->flush_needed, cpu); + /* Make sure prior __dev_map_entry_free() have completed. */ + rcu_barrier(); - while (!bitmap_empty(bitmap, dtab->map.max_entries)) - cond_resched(); - } + if (dtab->map.map_type == BPF_MAP_TYPE_DEVMAP_HASH) { + for (i = 0; i < dtab->n_buckets; i++) { + struct bpf_dtab_netdev *dev; + struct hlist_head *head; + struct hlist_node *next; - for (i = 0; i < dtab->map.max_entries; i++) { - struct bpf_dtab_netdev *dev; + head = dev_map_index_hash(dtab, i); + + hlist_for_each_entry_safe(dev, next, head, index_hlist) { + hlist_del_rcu(&dev->index_hlist); + if (dev->xdp_prog) + bpf_prog_put(dev->xdp_prog); + dev_put(dev->dev); + kfree(dev); + } + } - dev = dtab->netdev_map[i]; - if (!dev) - continue; + bpf_map_area_free(dtab->dev_index_head); + } else { + for (i = 0; i < dtab->map.max_entries; i++) { + struct bpf_dtab_netdev *dev; + + dev = rcu_dereference_raw(dtab->netdev_map[i]); + if (!dev) + continue; + + if (dev->xdp_prog) + bpf_prog_put(dev->xdp_prog); + dev_put(dev->dev); + kfree(dev); + } - dev_put(dev->dev); - kfree(dev); + bpf_map_area_free(dtab->netdev_map); } - free_percpu(dtab->flush_needed); - bpf_map_area_free(dtab->netdev_map); - kfree(dtab); + bpf_map_area_free(dtab); } static int dev_map_get_next_key(struct bpf_map *map, void *key, void *next_key) @@ -209,97 +268,175 @@ static int dev_map_get_next_key(struct bpf_map *map, void *key, void *next_key) return 0; } -void __dev_map_insert_ctx(struct bpf_map *map, u32 bit) +/* Elements are kept alive by RCU; either by rcu_read_lock() (from syscall) or + * by local_bh_disable() (from XDP calls inside NAPI). The + * rcu_read_lock_bh_held() below makes lockdep accept both. + */ +static void *__dev_map_hash_lookup_elem(struct bpf_map *map, u32 key) { struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); - unsigned long *bitmap = this_cpu_ptr(dtab->flush_needed); + struct hlist_head *head = dev_map_index_hash(dtab, key); + struct bpf_dtab_netdev *dev; + + hlist_for_each_entry_rcu(dev, head, index_hlist, + lockdep_is_held(&dtab->index_lock)) + if (dev->idx == key) + return dev; - __set_bit(bit, bitmap); + return NULL; } -static int bq_xmit_all(struct bpf_dtab_netdev *obj, - struct xdp_bulk_queue *bq, u32 flags, - bool in_napi_ctx) +static int dev_map_hash_get_next_key(struct bpf_map *map, void *key, + void *next_key) { - struct net_device *dev = obj->dev; - int sent = 0, drops = 0, err = 0; - int i; + struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); + u32 idx, *next = next_key; + struct bpf_dtab_netdev *dev, *next_dev; + struct hlist_head *head; + int i = 0; - if (unlikely(!bq->count)) + if (!key) + goto find_first; + + idx = *(u32 *)key; + + dev = __dev_map_hash_lookup_elem(map, idx); + if (!dev) + goto find_first; + + next_dev = hlist_entry_safe(rcu_dereference_raw(hlist_next_rcu(&dev->index_hlist)), + struct bpf_dtab_netdev, index_hlist); + + if (next_dev) { + *next = next_dev->idx; return 0; + } - for (i = 0; i < bq->count; i++) { + i = idx & (dtab->n_buckets - 1); + i++; + + find_first: + for (; i < dtab->n_buckets; i++) { + head = dev_map_index_hash(dtab, i); + + next_dev = hlist_entry_safe(rcu_dereference_raw(hlist_first_rcu(head)), + struct bpf_dtab_netdev, + index_hlist); + if (next_dev) { + *next = next_dev->idx; + return 0; + } + } + + return -ENOENT; +} + +static int dev_map_bpf_prog_run(struct bpf_prog *xdp_prog, + struct xdp_frame **frames, int n, + struct net_device *tx_dev, + struct net_device *rx_dev) +{ + struct xdp_txq_info txq = { .dev = tx_dev }; + struct xdp_rxq_info rxq = { .dev = rx_dev }; + struct xdp_buff xdp; + int i, nframes = 0; + + for (i = 0; i < n; i++) { + struct xdp_frame *xdpf = frames[i]; + u32 act; + int err; + + xdp_convert_frame_to_buff(xdpf, &xdp); + xdp.txq = &txq; + xdp.rxq = &rxq; + + act = bpf_prog_run_xdp(xdp_prog, &xdp); + switch (act) { + case XDP_PASS: + err = xdp_update_frame_from_buff(&xdp, xdpf); + if (unlikely(err < 0)) + xdp_return_frame_rx_napi(xdpf); + else + frames[nframes++] = xdpf; + break; + default: + bpf_warn_invalid_xdp_action(NULL, xdp_prog, act); + fallthrough; + case XDP_ABORTED: + trace_xdp_exception(tx_dev, xdp_prog, act); + fallthrough; + case XDP_DROP: + xdp_return_frame_rx_napi(xdpf); + break; + } + } + return nframes; /* sent frames count */ +} + +static void bq_xmit_all(struct xdp_dev_bulk_queue *bq, u32 flags) +{ + struct net_device *dev = bq->dev; + unsigned int cnt = bq->count; + int sent = 0, err = 0; + int to_send = cnt; + int i; + + if (unlikely(!cnt)) + return; + + for (i = 0; i < cnt; i++) { struct xdp_frame *xdpf = bq->q[i]; prefetch(xdpf); } - sent = dev->netdev_ops->ndo_xdp_xmit(dev, bq->count, bq->q, flags); + if (bq->xdp_prog) { + to_send = dev_map_bpf_prog_run(bq->xdp_prog, bq->q, cnt, dev, bq->dev_rx); + if (!to_send) + goto out; + } + + sent = dev->netdev_ops->ndo_xdp_xmit(dev, to_send, bq->q, flags); if (sent < 0) { + /* If ndo_xdp_xmit fails with an errno, no frames have + * been xmit'ed. + */ err = sent; sent = 0; - goto error; } - drops = bq->count - sent; -out: - bq->count = 0; - trace_xdp_devmap_xmit(&obj->dtab->map, obj->bit, - sent, drops, bq->dev_rx, dev, err); - bq->dev_rx = NULL; - return 0; -error: - /* If ndo_xdp_xmit fails with an errno, no frames have been - * xmit'ed and it's our responsibility to them free all. + /* If not all frames have been transmitted, it is our + * responsibility to free them */ - for (i = 0; i < bq->count; i++) { - struct xdp_frame *xdpf = bq->q[i]; + for (i = sent; unlikely(i < to_send); i++) + xdp_return_frame_rx_napi(bq->q[i]); - /* RX path under NAPI protection, can return frames faster */ - if (likely(in_napi_ctx)) - xdp_return_frame_rx_napi(xdpf); - else - xdp_return_frame(xdpf); - drops++; - } - goto out; +out: + bq->count = 0; + trace_xdp_devmap_xmit(bq->dev_rx, dev, sent, cnt - sent, err); } -/* __dev_map_flush is called from xdp_do_flush_map() which _must_ be signaled - * from the driver before returning from its napi->poll() routine. The poll() - * routine is called either from busy_poll context or net_rx_action signaled - * from NET_RX_SOFTIRQ. Either way the poll routine must complete before the - * net device can be torn down. On devmap tear down we ensure the ctx bitmap - * is zeroed before completing to ensure all flush operations have completed. +/* __dev_flush is called from xdp_do_flush() which _must_ be signalled from the + * driver before returning from its napi->poll() routine. See the comment above + * xdp_do_flush() in filter.c. */ -void __dev_map_flush(struct bpf_map *map) +void __dev_flush(struct list_head *flush_list) { - struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); - unsigned long *bitmap = this_cpu_ptr(dtab->flush_needed); - u32 bit; + struct xdp_dev_bulk_queue *bq, *tmp; - for_each_set_bit(bit, bitmap, map->max_entries) { - struct bpf_dtab_netdev *dev = READ_ONCE(dtab->netdev_map[bit]); - struct xdp_bulk_queue *bq; - - /* This is possible if the dev entry is removed by user space - * between xdp redirect and flush op. - */ - if (unlikely(!dev)) - continue; - - __clear_bit(bit, bitmap); - - bq = this_cpu_ptr(dev->bulkq); - bq_xmit_all(dev, bq, XDP_XMIT_FLUSH, true); + list_for_each_entry_safe(bq, tmp, flush_list, flush_node) { + bq_xmit_all(bq, XDP_XMIT_FLUSH); + bq->dev_rx = NULL; + bq->xdp_prog = NULL; + __list_del_clearprev(&bq->flush_node); } } -/* rcu_read_lock (from syscall and BPF contexts) ensures that if a delete and/or - * update happens in parallel here a dev_put wont happen until after reading the - * ifindex. +/* Elements are kept alive by RCU; either by rcu_read_lock() (from syscall) or + * by local_bh_disable() (from XDP calls inside NAPI). The + * rcu_read_lock_bh_held() below makes lockdep accept both. */ -struct bpf_dtab_netdev *__dev_map_lookup_elem(struct bpf_map *map, u32 key) +static void *__dev_map_lookup_elem(struct bpf_map *map, u32 key) { struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); struct bpf_dtab_netdev *obj; @@ -307,92 +444,366 @@ struct bpf_dtab_netdev *__dev_map_lookup_elem(struct bpf_map *map, u32 key) if (key >= map->max_entries) return NULL; - obj = READ_ONCE(dtab->netdev_map[key]); + obj = rcu_dereference_check(dtab->netdev_map[key], + rcu_read_lock_bh_held()); return obj; } -/* Runs under RCU-read-side, plus in softirq under NAPI protection. - * Thus, safe percpu variable access. +/* Runs in NAPI, i.e., softirq under local_bh_disable(). Thus, safe percpu + * variable access, and map elements stick around. See comment above + * xdp_do_flush() in filter.c. */ -static int bq_enqueue(struct bpf_dtab_netdev *obj, struct xdp_frame *xdpf, - struct net_device *dev_rx) - +static void bq_enqueue(struct net_device *dev, struct xdp_frame *xdpf, + struct net_device *dev_rx, struct bpf_prog *xdp_prog) { - struct xdp_bulk_queue *bq = this_cpu_ptr(obj->bulkq); + struct xdp_dev_bulk_queue *bq = this_cpu_ptr(dev->xdp_bulkq); if (unlikely(bq->count == DEV_MAP_BULK_SIZE)) - bq_xmit_all(obj, bq, 0, true); + bq_xmit_all(bq, 0); /* Ingress dev_rx will be the same for all xdp_frame's in * bulk_queue, because bq stored per-CPU and must be flushed * from net_device drivers NAPI func end. + * + * Do the same with xdp_prog and flush_list since these fields + * are only ever modified together. */ - if (!bq->dev_rx) + if (!bq->dev_rx) { + struct list_head *flush_list = bpf_net_ctx_get_dev_flush_list(); + bq->dev_rx = dev_rx; + bq->xdp_prog = xdp_prog; + list_add(&bq->flush_node, flush_list); + } bq->q[bq->count++] = xdpf; - return 0; } -int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_buff *xdp, - struct net_device *dev_rx) +static inline int __xdp_enqueue(struct net_device *dev, struct xdp_frame *xdpf, + struct net_device *dev_rx, + struct bpf_prog *xdp_prog) { - struct net_device *dev = dst->dev; - struct xdp_frame *xdpf; int err; - if (!dev->netdev_ops->ndo_xdp_xmit) + if (!(dev->xdp_features & NETDEV_XDP_ACT_NDO_XMIT)) return -EOPNOTSUPP; - err = xdp_ok_fwd_dev(dev, xdp->data_end - xdp->data); + if (unlikely(!(dev->xdp_features & NETDEV_XDP_ACT_NDO_XMIT_SG) && + xdp_frame_has_frags(xdpf))) + return -EOPNOTSUPP; + + err = xdp_ok_fwd_dev(dev, xdp_get_frame_len(xdpf)); if (unlikely(err)) return err; - xdpf = convert_to_xdp_frame(xdp); - if (unlikely(!xdpf)) - return -EOVERFLOW; + bq_enqueue(dev, xdpf, dev_rx, xdp_prog); + return 0; +} + +static u32 dev_map_bpf_prog_run_skb(struct sk_buff *skb, struct bpf_dtab_netdev *dst) +{ + struct xdp_txq_info txq = { .dev = dst->dev }; + struct xdp_buff xdp; + u32 act; + + if (!dst->xdp_prog) + return XDP_PASS; + + __skb_pull(skb, skb->mac_len); + xdp.txq = &txq; + + act = bpf_prog_run_generic_xdp(skb, &xdp, dst->xdp_prog); + switch (act) { + case XDP_PASS: + __skb_push(skb, skb->mac_len); + break; + default: + bpf_warn_invalid_xdp_action(NULL, dst->xdp_prog, act); + fallthrough; + case XDP_ABORTED: + trace_xdp_exception(dst->dev, dst->xdp_prog, act); + fallthrough; + case XDP_DROP: + kfree_skb(skb); + break; + } + + return act; +} - return bq_enqueue(dst, xdpf, dev_rx); +int dev_xdp_enqueue(struct net_device *dev, struct xdp_frame *xdpf, + struct net_device *dev_rx) +{ + return __xdp_enqueue(dev, xdpf, dev_rx, NULL); +} + +int dev_map_enqueue(struct bpf_dtab_netdev *dst, struct xdp_frame *xdpf, + struct net_device *dev_rx) +{ + struct net_device *dev = dst->dev; + + return __xdp_enqueue(dev, xdpf, dev_rx, dst->xdp_prog); +} + +static bool is_valid_dst(struct bpf_dtab_netdev *obj, struct xdp_frame *xdpf) +{ + if (!obj) + return false; + + if (!(obj->dev->xdp_features & NETDEV_XDP_ACT_NDO_XMIT)) + return false; + + if (unlikely(!(obj->dev->xdp_features & NETDEV_XDP_ACT_NDO_XMIT_SG) && + xdp_frame_has_frags(xdpf))) + return false; + + if (xdp_ok_fwd_dev(obj->dev, xdp_get_frame_len(xdpf))) + return false; + + return true; +} + +static int dev_map_enqueue_clone(struct bpf_dtab_netdev *obj, + struct net_device *dev_rx, + struct xdp_frame *xdpf) +{ + struct xdp_frame *nxdpf; + + nxdpf = xdpf_clone(xdpf); + if (!nxdpf) + return -ENOMEM; + + bq_enqueue(obj->dev, nxdpf, dev_rx, obj->xdp_prog); + + return 0; +} + +static inline bool is_ifindex_excluded(int *excluded, int num_excluded, int ifindex) +{ + while (num_excluded--) { + if (ifindex == excluded[num_excluded]) + return true; + } + return false; +} + +/* Get ifindex of each upper device. 'indexes' must be able to hold at + * least MAX_NEST_DEV elements. + * Returns the number of ifindexes added. + */ +static int get_upper_ifindexes(struct net_device *dev, int *indexes) +{ + struct net_device *upper; + struct list_head *iter; + int n = 0; + + netdev_for_each_upper_dev_rcu(dev, upper, iter) { + indexes[n++] = upper->ifindex; + } + return n; +} + +int dev_map_enqueue_multi(struct xdp_frame *xdpf, struct net_device *dev_rx, + struct bpf_map *map, bool exclude_ingress) +{ + struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); + struct bpf_dtab_netdev *dst, *last_dst = NULL; + int excluded_devices[1+MAX_NEST_DEV]; + struct hlist_head *head; + int num_excluded = 0; + unsigned int i; + int err; + + if (exclude_ingress) { + num_excluded = get_upper_ifindexes(dev_rx, excluded_devices); + excluded_devices[num_excluded++] = dev_rx->ifindex; + } + + if (map->map_type == BPF_MAP_TYPE_DEVMAP) { + for (i = 0; i < map->max_entries; i++) { + dst = rcu_dereference_check(dtab->netdev_map[i], + rcu_read_lock_bh_held()); + if (!is_valid_dst(dst, xdpf)) + continue; + + if (is_ifindex_excluded(excluded_devices, num_excluded, dst->dev->ifindex)) + continue; + + /* we only need n-1 clones; last_dst enqueued below */ + if (!last_dst) { + last_dst = dst; + continue; + } + + err = dev_map_enqueue_clone(last_dst, dev_rx, xdpf); + if (err) + return err; + + last_dst = dst; + } + } else { /* BPF_MAP_TYPE_DEVMAP_HASH */ + for (i = 0; i < dtab->n_buckets; i++) { + head = dev_map_index_hash(dtab, i); + hlist_for_each_entry_rcu(dst, head, index_hlist, + lockdep_is_held(&dtab->index_lock)) { + if (!is_valid_dst(dst, xdpf)) + continue; + + if (is_ifindex_excluded(excluded_devices, num_excluded, + dst->dev->ifindex)) + continue; + + /* we only need n-1 clones; last_dst enqueued below */ + if (!last_dst) { + last_dst = dst; + continue; + } + + err = dev_map_enqueue_clone(last_dst, dev_rx, xdpf); + if (err) + return err; + + last_dst = dst; + } + } + } + + /* consume the last copy of the frame */ + if (last_dst) + bq_enqueue(last_dst->dev, xdpf, dev_rx, last_dst->xdp_prog); + else + xdp_return_frame_rx_napi(xdpf); /* dtab is empty */ + + return 0; } int dev_map_generic_redirect(struct bpf_dtab_netdev *dst, struct sk_buff *skb, - struct bpf_prog *xdp_prog) + const struct bpf_prog *xdp_prog) { int err; err = xdp_ok_fwd_dev(dst->dev, skb->len); if (unlikely(err)) return err; + + /* Redirect has already succeeded semantically at this point, so we just + * return 0 even if packet is dropped. Helper below takes care of + * freeing skb. + */ + if (dev_map_bpf_prog_run_skb(skb, dst) != XDP_PASS) + return 0; + skb->dev = dst->dev; generic_xdp_tx(skb, xdp_prog); return 0; } -static void *dev_map_lookup_elem(struct bpf_map *map, void *key) +static int dev_map_redirect_clone(struct bpf_dtab_netdev *dst, + struct sk_buff *skb, + const struct bpf_prog *xdp_prog) { - struct bpf_dtab_netdev *obj = __dev_map_lookup_elem(map, *(u32 *)key); - struct net_device *dev = obj ? obj->dev : NULL; + struct sk_buff *nskb; + int err; + + nskb = skb_clone(skb, GFP_ATOMIC); + if (!nskb) + return -ENOMEM; + + err = dev_map_generic_redirect(dst, nskb, xdp_prog); + if (unlikely(err)) { + consume_skb(nskb); + return err; + } - return dev ? &dev->ifindex : NULL; + return 0; } -static void dev_map_flush_old(struct bpf_dtab_netdev *dev) +int dev_map_redirect_multi(struct net_device *dev, struct sk_buff *skb, + const struct bpf_prog *xdp_prog, + struct bpf_map *map, bool exclude_ingress) { - if (dev->dev->netdev_ops->ndo_xdp_xmit) { - struct xdp_bulk_queue *bq; - unsigned long *bitmap; + struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); + struct bpf_dtab_netdev *dst, *last_dst = NULL; + int excluded_devices[1+MAX_NEST_DEV]; + struct hlist_head *head; + struct hlist_node *next; + int num_excluded = 0; + unsigned int i; + int err; + + if (exclude_ingress) { + num_excluded = get_upper_ifindexes(dev, excluded_devices); + excluded_devices[num_excluded++] = dev->ifindex; + } + + if (map->map_type == BPF_MAP_TYPE_DEVMAP) { + for (i = 0; i < map->max_entries; i++) { + dst = rcu_dereference_check(dtab->netdev_map[i], + rcu_read_lock_bh_held()); + if (!dst) + continue; + + if (is_ifindex_excluded(excluded_devices, num_excluded, dst->dev->ifindex)) + continue; + + /* we only need n-1 clones; last_dst enqueued below */ + if (!last_dst) { + last_dst = dst; + continue; + } - int cpu; + err = dev_map_redirect_clone(last_dst, skb, xdp_prog); + if (err) + return err; - for_each_online_cpu(cpu) { - bitmap = per_cpu_ptr(dev->dtab->flush_needed, cpu); - __clear_bit(dev->bit, bitmap); + last_dst = dst; - bq = per_cpu_ptr(dev->bulkq, cpu); - bq_xmit_all(dev, bq, XDP_XMIT_FLUSH, false); + } + } else { /* BPF_MAP_TYPE_DEVMAP_HASH */ + for (i = 0; i < dtab->n_buckets; i++) { + head = dev_map_index_hash(dtab, i); + hlist_for_each_entry_safe(dst, next, head, index_hlist) { + if (is_ifindex_excluded(excluded_devices, num_excluded, + dst->dev->ifindex)) + continue; + + /* we only need n-1 clones; last_dst enqueued below */ + if (!last_dst) { + last_dst = dst; + continue; + } + + err = dev_map_redirect_clone(last_dst, skb, xdp_prog); + if (err) + return err; + + last_dst = dst; + } } } + + /* consume the first skb and return */ + if (last_dst) + return dev_map_generic_redirect(last_dst, skb, xdp_prog); + + /* dtab is empty */ + consume_skb(skb); + return 0; +} + +static void *dev_map_lookup_elem(struct bpf_map *map, void *key) +{ + struct bpf_dtab_netdev *obj = __dev_map_lookup_elem(map, *(u32 *)key); + + return obj ? &obj->val : NULL; +} + +static void *dev_map_hash_lookup_elem(struct bpf_map *map, void *key) +{ + struct bpf_dtab_netdev *obj = __dev_map_hash_lookup_elem(map, + *(u32 *)key); + return obj ? &obj->val : NULL; } static void __dev_map_entry_free(struct rcu_head *rcu) @@ -400,44 +811,106 @@ static void __dev_map_entry_free(struct rcu_head *rcu) struct bpf_dtab_netdev *dev; dev = container_of(rcu, struct bpf_dtab_netdev, rcu); - dev_map_flush_old(dev); - free_percpu(dev->bulkq); + if (dev->xdp_prog) + bpf_prog_put(dev->xdp_prog); dev_put(dev->dev); kfree(dev); } -static int dev_map_delete_elem(struct bpf_map *map, void *key) +static long dev_map_delete_elem(struct bpf_map *map, void *key) { struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); struct bpf_dtab_netdev *old_dev; - int k = *(u32 *)key; + u32 k = *(u32 *)key; if (k >= map->max_entries) return -EINVAL; - /* Use call_rcu() here to ensure any rcu critical sections have - * completed, but this does not guarantee a flush has happened - * yet. Because driver side rcu_read_lock/unlock only protects the - * running XDP program. However, for pending flush operations the - * dev and ctx are stored in another per cpu map. And additionally, - * the driver tear down ensures all soft irqs are complete before - * removing the net device in the case of dev_put equals zero. - */ - old_dev = xchg(&dtab->netdev_map[k], NULL); - if (old_dev) + old_dev = unrcu_pointer(xchg(&dtab->netdev_map[k], NULL)); + if (old_dev) { call_rcu(&old_dev->rcu, __dev_map_entry_free); + atomic_dec((atomic_t *)&dtab->items); + } return 0; } -static int dev_map_update_elem(struct bpf_map *map, void *key, void *value, - u64 map_flags) +static long dev_map_hash_delete_elem(struct bpf_map *map, void *key) +{ + struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); + struct bpf_dtab_netdev *old_dev; + u32 k = *(u32 *)key; + unsigned long flags; + int ret = -ENOENT; + + spin_lock_irqsave(&dtab->index_lock, flags); + + old_dev = __dev_map_hash_lookup_elem(map, k); + if (old_dev) { + dtab->items--; + hlist_del_init_rcu(&old_dev->index_hlist); + call_rcu(&old_dev->rcu, __dev_map_entry_free); + ret = 0; + } + spin_unlock_irqrestore(&dtab->index_lock, flags); + + return ret; +} + +static struct bpf_dtab_netdev *__dev_map_alloc_node(struct net *net, + struct bpf_dtab *dtab, + struct bpf_devmap_val *val, + unsigned int idx) +{ + struct bpf_prog *prog = NULL; + struct bpf_dtab_netdev *dev; + + dev = bpf_map_kmalloc_node(&dtab->map, sizeof(*dev), + GFP_NOWAIT, + dtab->map.numa_node); + if (!dev) + return ERR_PTR(-ENOMEM); + + dev->dev = dev_get_by_index(net, val->ifindex); + if (!dev->dev) + goto err_out; + + if (val->bpf_prog.fd > 0) { + prog = bpf_prog_get_type_dev(val->bpf_prog.fd, + BPF_PROG_TYPE_XDP, false); + if (IS_ERR(prog)) + goto err_put_dev; + if (prog->expected_attach_type != BPF_XDP_DEVMAP || + !bpf_prog_map_compatible(&dtab->map, prog)) + goto err_put_prog; + } + + dev->idx = idx; + if (prog) { + dev->xdp_prog = prog; + dev->val.bpf_prog.id = prog->aux->id; + } else { + dev->xdp_prog = NULL; + dev->val.bpf_prog.id = 0; + } + dev->val.ifindex = val->ifindex; + + return dev; +err_put_prog: + bpf_prog_put(prog); +err_put_dev: + dev_put(dev->dev); +err_out: + kfree(dev); + return ERR_PTR(-EINVAL); +} + +static long __dev_map_update_elem(struct net *net, struct bpf_map *map, + void *key, void *value, u64 map_flags) { struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); - struct net *net = current->nsproxy->net_ns; - gfp_t gfp = GFP_ATOMIC | __GFP_NOWARN; struct bpf_dtab_netdev *dev, *old_dev; + struct bpf_devmap_val val = {}; u32 i = *(u32 *)key; - u32 ifindex = *(u32 *)value; if (unlikely(map_flags > BPF_EXIST)) return -EINVAL; @@ -446,43 +919,132 @@ static int dev_map_update_elem(struct bpf_map *map, void *key, void *value, if (unlikely(map_flags == BPF_NOEXIST)) return -EEXIST; - if (!ifindex) { - dev = NULL; - } else { - dev = kmalloc_node(sizeof(*dev), gfp, map->numa_node); - if (!dev) - return -ENOMEM; - - dev->bulkq = __alloc_percpu_gfp(sizeof(*dev->bulkq), - sizeof(void *), gfp); - if (!dev->bulkq) { - kfree(dev); - return -ENOMEM; - } + /* already verified value_size <= sizeof val */ + memcpy(&val, value, map->value_size); - dev->dev = dev_get_by_index(net, ifindex); - if (!dev->dev) { - free_percpu(dev->bulkq); - kfree(dev); + if (!val.ifindex) { + dev = NULL; + /* can not specify fd if ifindex is 0 */ + if (val.bpf_prog.fd > 0) return -EINVAL; - } - - dev->bit = i; - dev->dtab = dtab; + } else { + dev = __dev_map_alloc_node(net, dtab, &val, i); + if (IS_ERR(dev)) + return PTR_ERR(dev); } /* Use call_rcu() here to ensure rcu critical sections have completed * Remembering the driver side flush operation will happen before the * net device is removed. */ - old_dev = xchg(&dtab->netdev_map[i], dev); + old_dev = unrcu_pointer(xchg(&dtab->netdev_map[i], RCU_INITIALIZER(dev))); + if (old_dev) + call_rcu(&old_dev->rcu, __dev_map_entry_free); + else + atomic_inc((atomic_t *)&dtab->items); + + return 0; +} + +static long dev_map_update_elem(struct bpf_map *map, void *key, void *value, + u64 map_flags) +{ + return __dev_map_update_elem(current->nsproxy->net_ns, + map, key, value, map_flags); +} + +static long __dev_map_hash_update_elem(struct net *net, struct bpf_map *map, + void *key, void *value, u64 map_flags) +{ + struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); + struct bpf_dtab_netdev *dev, *old_dev; + struct bpf_devmap_val val = {}; + u32 idx = *(u32 *)key; + unsigned long flags; + int err = -EEXIST; + + /* already verified value_size <= sizeof val */ + memcpy(&val, value, map->value_size); + + if (unlikely(map_flags > BPF_EXIST || !val.ifindex)) + return -EINVAL; + + spin_lock_irqsave(&dtab->index_lock, flags); + + old_dev = __dev_map_hash_lookup_elem(map, idx); + if (old_dev && (map_flags & BPF_NOEXIST)) + goto out_err; + + dev = __dev_map_alloc_node(net, dtab, &val, idx); + if (IS_ERR(dev)) { + err = PTR_ERR(dev); + goto out_err; + } + + if (old_dev) { + hlist_del_rcu(&old_dev->index_hlist); + } else { + if (dtab->items >= dtab->map.max_entries) { + spin_unlock_irqrestore(&dtab->index_lock, flags); + call_rcu(&dev->rcu, __dev_map_entry_free); + return -E2BIG; + } + dtab->items++; + } + + hlist_add_head_rcu(&dev->index_hlist, + dev_map_index_hash(dtab, idx)); + spin_unlock_irqrestore(&dtab->index_lock, flags); + if (old_dev) call_rcu(&old_dev->rcu, __dev_map_entry_free); return 0; + +out_err: + spin_unlock_irqrestore(&dtab->index_lock, flags); + return err; +} + +static long dev_map_hash_update_elem(struct bpf_map *map, void *key, void *value, + u64 map_flags) +{ + return __dev_map_hash_update_elem(current->nsproxy->net_ns, + map, key, value, map_flags); +} + +static long dev_map_redirect(struct bpf_map *map, u64 ifindex, u64 flags) +{ + return __bpf_xdp_redirect_map(map, ifindex, flags, + BPF_F_BROADCAST | BPF_F_EXCLUDE_INGRESS, + __dev_map_lookup_elem); +} + +static long dev_hash_map_redirect(struct bpf_map *map, u64 ifindex, u64 flags) +{ + return __bpf_xdp_redirect_map(map, ifindex, flags, + BPF_F_BROADCAST | BPF_F_EXCLUDE_INGRESS, + __dev_map_hash_lookup_elem); +} + +static u64 dev_map_mem_usage(const struct bpf_map *map) +{ + struct bpf_dtab *dtab = container_of(map, struct bpf_dtab, map); + u64 usage = sizeof(struct bpf_dtab); + + if (map->map_type == BPF_MAP_TYPE_DEVMAP_HASH) + usage += (u64)dtab->n_buckets * sizeof(struct hlist_head); + else + usage += (u64)map->max_entries * sizeof(struct bpf_dtab_netdev *); + usage += atomic_read((atomic_t *)&dtab->items) * + (u64)sizeof(struct bpf_dtab_netdev); + return usage; } +BTF_ID_LIST_SINGLE(dev_map_btf_ids, struct, bpf_dtab) const struct bpf_map_ops dev_map_ops = { + .map_meta_equal = bpf_map_meta_equal, + .map_alloc_check = dev_map_alloc_check, .map_alloc = dev_map_alloc, .map_free = dev_map_free, .map_get_next_key = dev_map_get_next_key, @@ -490,16 +1052,72 @@ const struct bpf_map_ops dev_map_ops = { .map_update_elem = dev_map_update_elem, .map_delete_elem = dev_map_delete_elem, .map_check_btf = map_check_no_btf, + .map_mem_usage = dev_map_mem_usage, + .map_btf_id = &dev_map_btf_ids[0], + .map_redirect = dev_map_redirect, }; +const struct bpf_map_ops dev_map_hash_ops = { + .map_meta_equal = bpf_map_meta_equal, + .map_alloc_check = dev_map_alloc_check, + .map_alloc = dev_map_alloc, + .map_free = dev_map_free, + .map_get_next_key = dev_map_hash_get_next_key, + .map_lookup_elem = dev_map_hash_lookup_elem, + .map_update_elem = dev_map_hash_update_elem, + .map_delete_elem = dev_map_hash_delete_elem, + .map_check_btf = map_check_no_btf, + .map_mem_usage = dev_map_mem_usage, + .map_btf_id = &dev_map_btf_ids[0], + .map_redirect = dev_hash_map_redirect, +}; + +static void dev_map_hash_remove_netdev(struct bpf_dtab *dtab, + struct net_device *netdev) +{ + unsigned long flags; + u32 i; + + spin_lock_irqsave(&dtab->index_lock, flags); + for (i = 0; i < dtab->n_buckets; i++) { + struct bpf_dtab_netdev *dev; + struct hlist_head *head; + struct hlist_node *next; + + head = dev_map_index_hash(dtab, i); + + hlist_for_each_entry_safe(dev, next, head, index_hlist) { + if (netdev != dev->dev) + continue; + + dtab->items--; + hlist_del_rcu(&dev->index_hlist); + call_rcu(&dev->rcu, __dev_map_entry_free); + } + } + spin_unlock_irqrestore(&dtab->index_lock, flags); +} + static int dev_map_notification(struct notifier_block *notifier, ulong event, void *ptr) { struct net_device *netdev = netdev_notifier_info_to_dev(ptr); struct bpf_dtab *dtab; - int i; + int i, cpu; switch (event) { + case NETDEV_REGISTER: + if (!netdev->netdev_ops->ndo_xdp_xmit || netdev->xdp_bulkq) + break; + + /* will be freed in free_netdev() */ + netdev->xdp_bulkq = alloc_percpu(struct xdp_dev_bulk_queue); + if (!netdev->xdp_bulkq) + return NOTIFY_BAD; + + for_each_possible_cpu(cpu) + per_cpu_ptr(netdev->xdp_bulkq, cpu)->dev = netdev; + break; case NETDEV_UNREGISTER: /* This rcu_read_lock/unlock pair is needed because * dev_map_list is an RCU list AND to ensure a delete @@ -508,16 +1126,23 @@ static int dev_map_notification(struct notifier_block *notifier, */ rcu_read_lock(); list_for_each_entry_rcu(dtab, &dev_map_list, list) { + if (dtab->map.map_type == BPF_MAP_TYPE_DEVMAP_HASH) { + dev_map_hash_remove_netdev(dtab, netdev); + continue; + } + for (i = 0; i < dtab->map.max_entries; i++) { struct bpf_dtab_netdev *dev, *odev; - dev = READ_ONCE(dtab->netdev_map[i]); + dev = rcu_dereference(dtab->netdev_map[i]); if (!dev || netdev != dev->dev) continue; - odev = cmpxchg(&dtab->netdev_map[i], dev, NULL); - if (dev == odev) + odev = unrcu_pointer(cmpxchg(&dtab->netdev_map[i], RCU_INITIALIZER(dev), NULL)); + if (dev == odev) { call_rcu(&dev->rcu, __dev_map_entry_free); + atomic_dec((atomic_t *)&dtab->items); + } } } rcu_read_unlock(); @@ -538,6 +1163,7 @@ static int __init dev_map_init(void) BUILD_BUG_ON(offsetof(struct bpf_dtab_netdev, dev) != offsetof(struct _bpf_dtab_netdev, dev)); register_netdevice_notifier(&dev_map_notifier); + return 0; } |