diff options
Diffstat (limited to 'net/core')
| -rw-r--r-- | net/core/bpf_sk_storage.c | 836 | ||||
| -rw-r--r-- | net/core/datagram.c | 33 | ||||
| -rw-r--r-- | net/core/dev.c | 179 | ||||
| -rw-r--r-- | net/core/devlink.c | 896 | ||||
| -rw-r--r-- | net/core/drop_monitor.c | 139 | ||||
| -rw-r--r-- | net/core/filter.c | 962 | ||||
| -rw-r--r-- | net/core/flow_dissector.c | 10 | ||||
| -rw-r--r-- | net/core/net-procfs.c | 15 | ||||
| -rw-r--r-- | net/core/net-sysfs.c | 4 | ||||
| -rw-r--r-- | net/core/net_namespace.c | 12 | ||||
| -rw-r--r-- | net/core/netpoll.c | 2 | ||||
| -rw-r--r-- | net/core/pktgen.c | 10 | ||||
| -rw-r--r-- | net/core/ptp_classifier.c | 30 | ||||
| -rw-r--r-- | net/core/skbuff.c | 79 | ||||
| -rw-r--r-- | net/core/skmsg.c | 195 | ||||
| -rw-r--r-- | net/core/sock.c | 21 | ||||
| -rw-r--r-- | net/core/sock_diag.c | 9 | ||||
| -rw-r--r-- | net/core/sock_map.c | 419 | ||||
| -rw-r--r-- | net/core/sysctl_net_core.c | 17 |
19 files changed, 2686 insertions, 1182 deletions
diff --git a/net/core/bpf_sk_storage.c b/net/core/bpf_sk_storage.c index b988f48153a4..c907f0dc7f87 100644 --- a/net/core/bpf_sk_storage.c +++ b/net/core/bpf_sk_storage.c @@ -7,97 +7,13 @@ #include <linux/spinlock.h> #include <linux/bpf.h> #include <linux/btf_ids.h> +#include <linux/bpf_local_storage.h> #include <net/bpf_sk_storage.h> #include <net/sock.h> #include <uapi/linux/sock_diag.h> #include <uapi/linux/btf.h> -#define SK_STORAGE_CREATE_FLAG_MASK \ - (BPF_F_NO_PREALLOC | BPF_F_CLONE) - -struct bucket { - struct hlist_head list; - raw_spinlock_t lock; -}; - -/* Thp map is not the primary owner of a bpf_sk_storage_elem. - * Instead, the sk->sk_bpf_storage is. - * - * The map (bpf_sk_storage_map) is for two purposes - * 1. Define the size of the "sk local storage". It is - * the map's value_size. - * - * 2. Maintain a list to keep track of all elems such - * that they can be cleaned up during the map destruction. - * - * When a bpf local storage is being looked up for a - * particular sk, the "bpf_map" pointer is actually used - * as the "key" to search in the list of elem in - * sk->sk_bpf_storage. - * - * Hence, consider sk->sk_bpf_storage is the mini-map - * with the "bpf_map" pointer as the searching key. - */ -struct bpf_sk_storage_map { - struct bpf_map map; - /* Lookup elem does not require accessing the map. - * - * Updating/Deleting requires a bucket lock to - * link/unlink the elem from the map. Having - * multiple buckets to improve contention. - */ - struct bucket *buckets; - u32 bucket_log; - u16 elem_size; - u16 cache_idx; -}; - -struct bpf_sk_storage_data { - /* smap is used as the searching key when looking up - * from sk->sk_bpf_storage. - * - * Put it in the same cacheline as the data to minimize - * the number of cachelines access during the cache hit case. - */ - struct bpf_sk_storage_map __rcu *smap; - u8 data[] __aligned(8); -}; - -/* Linked to bpf_sk_storage and bpf_sk_storage_map */ -struct bpf_sk_storage_elem { - struct hlist_node map_node; /* Linked to bpf_sk_storage_map */ - struct hlist_node snode; /* Linked to bpf_sk_storage */ - struct bpf_sk_storage __rcu *sk_storage; - struct rcu_head rcu; - /* 8 bytes hole */ - /* The data is stored in aother cacheline to minimize - * the number of cachelines access during a cache hit. - */ - struct bpf_sk_storage_data sdata ____cacheline_aligned; -}; - -#define SELEM(_SDATA) container_of((_SDATA), struct bpf_sk_storage_elem, sdata) -#define SDATA(_SELEM) (&(_SELEM)->sdata) -#define BPF_SK_STORAGE_CACHE_SIZE 16 - -static DEFINE_SPINLOCK(cache_idx_lock); -static u64 cache_idx_usage_counts[BPF_SK_STORAGE_CACHE_SIZE]; - -struct bpf_sk_storage { - struct bpf_sk_storage_data __rcu *cache[BPF_SK_STORAGE_CACHE_SIZE]; - struct hlist_head list; /* List of bpf_sk_storage_elem */ - struct sock *sk; /* The sk that owns the the above "list" of - * bpf_sk_storage_elem. - */ - struct rcu_head rcu; - raw_spinlock_t lock; /* Protect adding/removing from the "list" */ -}; - -static struct bucket *select_bucket(struct bpf_sk_storage_map *smap, - struct bpf_sk_storage_elem *selem) -{ - return &smap->buckets[hash_ptr(selem, smap->bucket_log)]; -} +DEFINE_BPF_STORAGE_CACHE(sk_cache); static int omem_charge(struct sock *sk, unsigned int size) { @@ -111,445 +27,38 @@ static int omem_charge(struct sock *sk, unsigned int size) return -ENOMEM; } -static bool selem_linked_to_sk(const struct bpf_sk_storage_elem *selem) -{ - return !hlist_unhashed(&selem->snode); -} - -static bool selem_linked_to_map(const struct bpf_sk_storage_elem *selem) -{ - return !hlist_unhashed(&selem->map_node); -} - -static struct bpf_sk_storage_elem *selem_alloc(struct bpf_sk_storage_map *smap, - struct sock *sk, void *value, - bool charge_omem) -{ - struct bpf_sk_storage_elem *selem; - - if (charge_omem && omem_charge(sk, smap->elem_size)) - return NULL; - - selem = kzalloc(smap->elem_size, GFP_ATOMIC | __GFP_NOWARN); - if (selem) { - if (value) - memcpy(SDATA(selem)->data, value, smap->map.value_size); - return selem; - } - - if (charge_omem) - atomic_sub(smap->elem_size, &sk->sk_omem_alloc); - - return NULL; -} - -/* sk_storage->lock must be held and selem->sk_storage == sk_storage. - * The caller must ensure selem->smap is still valid to be - * dereferenced for its smap->elem_size and smap->cache_idx. - */ -static bool __selem_unlink_sk(struct bpf_sk_storage *sk_storage, - struct bpf_sk_storage_elem *selem, - bool uncharge_omem) -{ - struct bpf_sk_storage_map *smap; - bool free_sk_storage; - struct sock *sk; - - smap = rcu_dereference(SDATA(selem)->smap); - sk = sk_storage->sk; - - /* All uncharging on sk->sk_omem_alloc must be done first. - * sk may be freed once the last selem is unlinked from sk_storage. - */ - if (uncharge_omem) - atomic_sub(smap->elem_size, &sk->sk_omem_alloc); - - free_sk_storage = hlist_is_singular_node(&selem->snode, - &sk_storage->list); - if (free_sk_storage) { - atomic_sub(sizeof(struct bpf_sk_storage), &sk->sk_omem_alloc); - sk_storage->sk = NULL; - /* After this RCU_INIT, sk may be freed and cannot be used */ - RCU_INIT_POINTER(sk->sk_bpf_storage, NULL); - - /* sk_storage is not freed now. sk_storage->lock is - * still held and raw_spin_unlock_bh(&sk_storage->lock) - * will be done by the caller. - * - * Although the unlock will be done under - * rcu_read_lock(), it is more intutivie to - * read if kfree_rcu(sk_storage, rcu) is done - * after the raw_spin_unlock_bh(&sk_storage->lock). - * - * Hence, a "bool free_sk_storage" is returned - * to the caller which then calls the kfree_rcu() - * after unlock. - */ - } - hlist_del_init_rcu(&selem->snode); - if (rcu_access_pointer(sk_storage->cache[smap->cache_idx]) == - SDATA(selem)) - RCU_INIT_POINTER(sk_storage->cache[smap->cache_idx], NULL); - - kfree_rcu(selem, rcu); - - return free_sk_storage; -} - -static void selem_unlink_sk(struct bpf_sk_storage_elem *selem) -{ - struct bpf_sk_storage *sk_storage; - bool free_sk_storage = false; - - if (unlikely(!selem_linked_to_sk(selem))) - /* selem has already been unlinked from sk */ - return; - - sk_storage = rcu_dereference(selem->sk_storage); - raw_spin_lock_bh(&sk_storage->lock); - if (likely(selem_linked_to_sk(selem))) - free_sk_storage = __selem_unlink_sk(sk_storage, selem, true); - raw_spin_unlock_bh(&sk_storage->lock); - - if (free_sk_storage) - kfree_rcu(sk_storage, rcu); -} - -static void __selem_link_sk(struct bpf_sk_storage *sk_storage, - struct bpf_sk_storage_elem *selem) -{ - RCU_INIT_POINTER(selem->sk_storage, sk_storage); - hlist_add_head(&selem->snode, &sk_storage->list); -} - -static void selem_unlink_map(struct bpf_sk_storage_elem *selem) -{ - struct bpf_sk_storage_map *smap; - struct bucket *b; - - if (unlikely(!selem_linked_to_map(selem))) - /* selem has already be unlinked from smap */ - return; - - smap = rcu_dereference(SDATA(selem)->smap); - b = select_bucket(smap, selem); - raw_spin_lock_bh(&b->lock); - if (likely(selem_linked_to_map(selem))) - hlist_del_init_rcu(&selem->map_node); - raw_spin_unlock_bh(&b->lock); -} - -static void selem_link_map(struct bpf_sk_storage_map *smap, - struct bpf_sk_storage_elem *selem) -{ - struct bucket *b = select_bucket(smap, selem); - - raw_spin_lock_bh(&b->lock); - RCU_INIT_POINTER(SDATA(selem)->smap, smap); - hlist_add_head_rcu(&selem->map_node, &b->list); - raw_spin_unlock_bh(&b->lock); -} - -static void selem_unlink(struct bpf_sk_storage_elem *selem) -{ - /* Always unlink from map before unlinking from sk_storage - * because selem will be freed after successfully unlinked from - * the sk_storage. - */ - selem_unlink_map(selem); - selem_unlink_sk(selem); -} - -static struct bpf_sk_storage_data * -__sk_storage_lookup(struct bpf_sk_storage *sk_storage, - struct bpf_sk_storage_map *smap, - bool cacheit_lockit) -{ - struct bpf_sk_storage_data *sdata; - struct bpf_sk_storage_elem *selem; - - /* Fast path (cache hit) */ - sdata = rcu_dereference(sk_storage->cache[smap->cache_idx]); - if (sdata && rcu_access_pointer(sdata->smap) == smap) - return sdata; - - /* Slow path (cache miss) */ - hlist_for_each_entry_rcu(selem, &sk_storage->list, snode) - if (rcu_access_pointer(SDATA(selem)->smap) == smap) - break; - - if (!selem) - return NULL; - - sdata = SDATA(selem); - if (cacheit_lockit) { - /* spinlock is needed to avoid racing with the - * parallel delete. Otherwise, publishing an already - * deleted sdata to the cache will become a use-after-free - * problem in the next __sk_storage_lookup(). - */ - raw_spin_lock_bh(&sk_storage->lock); - if (selem_linked_to_sk(selem)) - rcu_assign_pointer(sk_storage->cache[smap->cache_idx], - sdata); - raw_spin_unlock_bh(&sk_storage->lock); - } - - return sdata; -} - -static struct bpf_sk_storage_data * +static struct bpf_local_storage_data * sk_storage_lookup(struct sock *sk, struct bpf_map *map, bool cacheit_lockit) { - struct bpf_sk_storage *sk_storage; - struct bpf_sk_storage_map *smap; + struct bpf_local_storage *sk_storage; + struct bpf_local_storage_map *smap; sk_storage = rcu_dereference(sk->sk_bpf_storage); if (!sk_storage) return NULL; - smap = (struct bpf_sk_storage_map *)map; - return __sk_storage_lookup(sk_storage, smap, cacheit_lockit); -} - -static int check_flags(const struct bpf_sk_storage_data *old_sdata, - u64 map_flags) -{ - if (old_sdata && (map_flags & ~BPF_F_LOCK) == BPF_NOEXIST) - /* elem already exists */ - return -EEXIST; - - if (!old_sdata && (map_flags & ~BPF_F_LOCK) == BPF_EXIST) - /* elem doesn't exist, cannot update it */ - return -ENOENT; - - return 0; -} - -static int sk_storage_alloc(struct sock *sk, - struct bpf_sk_storage_map *smap, - struct bpf_sk_storage_elem *first_selem) -{ - struct bpf_sk_storage *prev_sk_storage, *sk_storage; - int err; - - err = omem_charge(sk, sizeof(*sk_storage)); - if (err) - return err; - - sk_storage = kzalloc(sizeof(*sk_storage), GFP_ATOMIC | __GFP_NOWARN); - if (!sk_storage) { - err = -ENOMEM; - goto uncharge; - } - INIT_HLIST_HEAD(&sk_storage->list); - raw_spin_lock_init(&sk_storage->lock); - sk_storage->sk = sk; - - __selem_link_sk(sk_storage, first_selem); - selem_link_map(smap, first_selem); - /* Publish sk_storage to sk. sk->sk_lock cannot be acquired. - * Hence, atomic ops is used to set sk->sk_bpf_storage - * from NULL to the newly allocated sk_storage ptr. - * - * From now on, the sk->sk_bpf_storage pointer is protected - * by the sk_storage->lock. Hence, when freeing - * the sk->sk_bpf_storage, the sk_storage->lock must - * be held before setting sk->sk_bpf_storage to NULL. - */ - prev_sk_storage = cmpxchg((struct bpf_sk_storage **)&sk->sk_bpf_storage, - NULL, sk_storage); - if (unlikely(prev_sk_storage)) { - selem_unlink_map(first_selem); - err = -EAGAIN; - goto uncharge; - - /* Note that even first_selem was linked to smap's - * bucket->list, first_selem can be freed immediately - * (instead of kfree_rcu) because - * bpf_sk_storage_map_free() does a - * synchronize_rcu() before walking the bucket->list. - * Hence, no one is accessing selem from the - * bucket->list under rcu_read_lock(). - */ - } - - return 0; - -uncharge: - kfree(sk_storage); - atomic_sub(sizeof(*sk_storage), &sk->sk_omem_alloc); - return err; -} - -/* sk cannot be going away because it is linking new elem - * to sk->sk_bpf_storage. (i.e. sk->sk_refcnt cannot be 0). - * Otherwise, it will become a leak (and other memory issues - * during map destruction). - */ -static struct bpf_sk_storage_data *sk_storage_update(struct sock *sk, - struct bpf_map *map, - void *value, - u64 map_flags) -{ - struct bpf_sk_storage_data *old_sdata = NULL; - struct bpf_sk_storage_elem *selem; - struct bpf_sk_storage *sk_storage; - struct bpf_sk_storage_map *smap; - int err; - - /* BPF_EXIST and BPF_NOEXIST cannot be both set */ - if (unlikely((map_flags & ~BPF_F_LOCK) > BPF_EXIST) || - /* BPF_F_LOCK can only be used in a value with spin_lock */ - unlikely((map_flags & BPF_F_LOCK) && !map_value_has_spin_lock(map))) - return ERR_PTR(-EINVAL); - - smap = (struct bpf_sk_storage_map *)map; - sk_storage = rcu_dereference(sk->sk_bpf_storage); - if (!sk_storage || hlist_empty(&sk_storage->list)) { - /* Very first elem for this sk */ - err = check_flags(NULL, map_flags); - if (err) - return ERR_PTR(err); - - selem = selem_alloc(smap, sk, value, true); - if (!selem) - return ERR_PTR(-ENOMEM); - - err = sk_storage_alloc(sk, smap, selem); - if (err) { - kfree(selem); - atomic_sub(smap->elem_size, &sk->sk_omem_alloc); - return ERR_PTR(err); - } - - return SDATA(selem); - } - - if ((map_flags & BPF_F_LOCK) && !(map_flags & BPF_NOEXIST)) { - /* Hoping to find an old_sdata to do inline update - * such that it can avoid taking the sk_storage->lock - * and changing the lists. - */ - old_sdata = __sk_storage_lookup(sk_storage, smap, false); - err = check_flags(old_sdata, map_flags); - if (err) - return ERR_PTR(err); - if (old_sdata && selem_linked_to_sk(SELEM(old_sdata))) { - copy_map_value_locked(map, old_sdata->data, - value, false); - return old_sdata; - } - } - - raw_spin_lock_bh(&sk_storage->lock); - - /* Recheck sk_storage->list under sk_storage->lock */ - if (unlikely(hlist_empty(&sk_storage->list))) { - /* A parallel del is happening and sk_storage is going - * away. It has just been checked before, so very - * unlikely. Return instead of retry to keep things - * simple. - */ - err = -EAGAIN; - goto unlock_err; - } - - old_sdata = __sk_storage_lookup(sk_storage, smap, false); - err = check_flags(old_sdata, map_flags); - if (err) - goto unlock_err; - - if (old_sdata && (map_flags & BPF_F_LOCK)) { - copy_map_value_locked(map, old_sdata->data, value, false); - selem = SELEM(old_sdata); - goto unlock; - } - - /* sk_storage->lock is held. Hence, we are sure - * we can unlink and uncharge the old_sdata successfully - * later. Hence, instead of charging the new selem now - * and then uncharge the old selem later (which may cause - * a potential but unnecessary charge failure), avoid taking - * a charge at all here (the "!old_sdata" check) and the - * old_sdata will not be uncharged later during __selem_unlink_sk(). - */ - selem = selem_alloc(smap, sk, value, !old_sdata); - if (!selem) { - err = -ENOMEM; - goto unlock_err; - } - - /* First, link the new selem to the map */ - selem_link_map(smap, selem); - - /* Second, link (and publish) the new selem to sk_storage */ - __selem_link_sk(sk_storage, selem); - - /* Third, remove old selem, SELEM(old_sdata) */ - if (old_sdata) { - selem_unlink_map(SELEM(old_sdata)); - __selem_unlink_sk(sk_storage, SELEM(old_sdata), false); - } - -unlock: - raw_spin_unlock_bh(&sk_storage->lock); - return SDATA(selem); - -unlock_err: - raw_spin_unlock_bh(&sk_storage->lock); - return ERR_PTR(err); + smap = (struct bpf_local_storage_map *)map; + return bpf_local_storage_lookup(sk_storage, smap, cacheit_lockit); } static int sk_storage_delete(struct sock *sk, struct bpf_map *map) { - struct bpf_sk_storage_data *sdata; + struct bpf_local_storage_data *sdata; sdata = sk_storage_lookup(sk, map, false); if (!sdata) return -ENOENT; - selem_unlink(SELEM(sdata)); + bpf_selem_unlink(SELEM(sdata)); return 0; } -static u16 cache_idx_get(void) -{ - u64 min_usage = U64_MAX; - u16 i, res = 0; - - spin_lock(&cache_idx_lock); - - for (i = 0; i < BPF_SK_STORAGE_CACHE_SIZE; i++) { - if (cache_idx_usage_counts[i] < min_usage) { - min_usage = cache_idx_usage_counts[i]; - res = i; - - /* Found a free cache_idx */ - if (!min_usage) - break; - } - } - cache_idx_usage_counts[res]++; - - spin_unlock(&cache_idx_lock); - - return res; -} - -static void cache_idx_free(u16 idx) -{ - spin_lock(&cache_idx_lock); - cache_idx_usage_counts[idx]--; - spin_unlock(&cache_idx_lock); -} - /* Called by __sk_destruct() & bpf_sk_storage_clone() */ void bpf_sk_storage_free(struct sock *sk) { - struct bpf_sk_storage_elem *selem; - struct bpf_sk_storage *sk_storage; + struct bpf_local_storage_elem *selem; + struct bpf_local_storage *sk_storage; bool free_sk_storage = false; struct hlist_node *n; @@ -565,7 +74,7 @@ void bpf_sk_storage_free(struct sock *sk) * Thus, no elem can be added-to or deleted-from the * sk_storage->list by the bpf_prog or by the bpf-map's syscall. * - * It is racing with bpf_sk_storage_map_free() alone + * It is racing with bpf_local_storage_map_free() alone * when unlinking elem from the sk_storage->list and * the map's bucket->list. */ @@ -574,8 +83,9 @@ void bpf_sk_storage_free(struct sock *sk) /* Always unlink from map before unlinking from * sk_storage. */ - selem_unlink_map(selem); - free_sk_storage = __selem_unlink_sk(sk_storage, selem, true); + bpf_selem_unlink_map(selem); + free_sk_storage = bpf_selem_unlink_storage_nolock(sk_storage, + selem, true); } raw_spin_unlock_bh(&sk_storage->lock); rcu_read_unlock(); @@ -584,132 +94,24 @@ void bpf_sk_storage_free(struct sock *sk) kfree_rcu(sk_storage, rcu); } -static void bpf_sk_storage_map_free(struct bpf_map *map) -{ - struct bpf_sk_storage_elem *selem; - struct bpf_sk_storage_map *smap; - struct bucket *b; - unsigned int i; - - smap = (struct bpf_sk_storage_map *)map; - - cache_idx_free(smap->cache_idx); - - /* Note that this map might be concurrently cloned from - * bpf_sk_storage_clone. Wait for any existing bpf_sk_storage_clone - * RCU read section to finish before proceeding. New RCU - * read sections should be prevented via bpf_map_inc_not_zero. - */ - synchronize_rcu(); - - /* bpf prog and the userspace can no longer access this map - * now. No new selem (of this map) can be added - * to the sk->sk_bpf_storage or to the map bucket's list. - * - * The elem of this map can be cleaned up here - * or - * by bpf_sk_storage_free() during __sk_destruct(). - */ - for (i = 0; i < (1U << smap->bucket_log); i++) { - b = &smap->buckets[i]; - - rcu_read_lock(); - /* No one is adding to b->list now */ - while ((selem = hlist_entry_safe(rcu_dereference_raw(hlist_first_rcu(&b->list)), - struct bpf_sk_storage_elem, - map_node))) { - selem_unlink(selem); - cond_resched_rcu(); - } - rcu_read_unlock(); - } - - /* bpf_sk_storage_free() may still need to access the map. - * e.g. bpf_sk_storage_free() has unlinked selem from the map - * which then made the above while((selem = ...)) loop - * exited immediately. - * - * However, the bpf_sk_storage_free() still needs to access - * the smap->elem_size to do the uncharging in - * __selem_unlink_sk(). - * - * Hence, wait another rcu grace period for the - * bpf_sk_storage_free() to finish. - */ - synchronize_rcu(); - - kvfree(smap->buckets); - kfree(map); -} - -/* U16_MAX is much more than enough for sk local storage - * considering a tcp_sock is ~2k. - */ -#define MAX_VALUE_SIZE \ - min_t(u32, \ - (KMALLOC_MAX_SIZE - MAX_BPF_STACK - sizeof(struct bpf_sk_storage_elem)), \ - (U16_MAX - sizeof(struct bpf_sk_storage_elem))) - -static int bpf_sk_storage_map_alloc_check(union bpf_attr *attr) +static void sk_storage_map_free(struct bpf_map *map) { - if (attr->map_flags & ~SK_STORAGE_CREATE_FLAG_MASK || - !(attr->map_flags & BPF_F_NO_PREALLOC) || - attr->max_entries || - attr->key_size != sizeof(int) || !attr->value_size || - /* Enforce BTF for userspace sk dumping */ - !attr->btf_key_type_id || !attr->btf_value_type_id) - return -EINVAL; - - if (!bpf_capable()) - return -EPERM; - - if (attr->value_size > MAX_VALUE_SIZE) - return -E2BIG; + struct bpf_local_storage_map *smap; - return 0; + smap = (struct bpf_local_storage_map *)map; + bpf_local_storage_cache_idx_free(&sk_cache, smap->cache_idx); + bpf_local_storage_map_free(smap); } -static struct bpf_map *bpf_sk_storage_map_alloc(union bpf_attr *attr) +static struct bpf_map *sk_storage_map_alloc(union bpf_attr *attr) { - struct bpf_sk_storage_map *smap; - unsigned int i; - u32 nbuckets; - u64 cost; - int ret; - - smap = kzalloc(sizeof(*smap), GFP_USER | __GFP_NOWARN); - if (!smap) - return ERR_PTR(-ENOMEM); - bpf_map_init_from_attr(&smap->map, attr); - - nbuckets = roundup_pow_of_two(num_possible_cpus()); - /* Use at least 2 buckets, select_bucket() is undefined behavior with 1 bucket */ - nbuckets = max_t(u32, 2, nbuckets); - smap->bucket_log = ilog2(nbuckets); - cost = sizeof(*smap->buckets) * nbuckets + sizeof(*smap); - - ret = bpf_map_charge_init(&smap->map.memory, cost); - if (ret < 0) { - kfree(smap); - return ERR_PTR(ret); - } + struct bpf_local_storage_map *smap; - smap->buckets = kvcalloc(sizeof(*smap->buckets), nbuckets, - GFP_USER | __GFP_NOWARN); - if (!smap->buckets) { - bpf_map_charge_finish(&smap->map.memory); - kfree(smap); - return ERR_PTR(-ENOMEM); - } - - for (i = 0; i < nbuckets; i++) { - INIT_HLIST_HEAD(&smap->buckets[i].list); - raw_spin_lock_init(&smap->buckets[i].lock); - } - - smap->elem_size = sizeof(struct bpf_sk_storage_elem) + attr->value_size; - smap->cache_idx = cache_idx_get(); + smap = bpf_local_storage_map_alloc(attr); + if (IS_ERR(smap)) + return ERR_CAST(smap); + smap->cache_idx = bpf_local_storage_cache_idx_get(&sk_cache); return &smap->map; } @@ -719,26 +121,9 @@ static int notsupp_get_next_key(struct bpf_map *map, void *key, return -ENOTSUPP; } -static int bpf_sk_storage_map_check_btf(const struct bpf_map *map, - const struct btf *btf, - const struct btf_type *key_type, - const struct btf_type *value_type) -{ - u32 int_data; - - if (BTF_INFO_KIND(key_type->info) != BTF_KIND_INT) - return -EINVAL; - - int_data = *(u32 *)(key_type + 1); - if (BTF_INT_BITS(int_data) != 32 || BTF_INT_OFFSET(int_data)) - return -EINVAL; - - return 0; -} - static void *bpf_fd_sk_storage_lookup_elem(struct bpf_map *map, void *key) { - struct bpf_sk_storage_data *sdata; + struct bpf_local_storage_data *sdata; struct socket *sock; int fd, err; @@ -756,14 +141,16 @@ static void *bpf_fd_sk_storage_lookup_elem(struct bpf_map *map, void *key) static int bpf_fd_sk_storage_update_elem(struct bpf_map *map, void *key, void *value, u64 map_flags) { - struct bpf_sk_storage_data *sdata; + struct bpf_local_storage_data *sdata; struct socket *sock; int fd, err; fd = *(int *)key; sock = sockfd_lookup(fd, &err); if (sock) { - sdata = sk_storage_update(sock->sk, map, value, map_flags); + sdata = bpf_local_storage_update( + sock->sk, (struct bpf_local_storage_map *)map, value, + map_flags); sockfd_put(sock); return PTR_ERR_OR_ZERO(sdata); } @@ -787,14 +174,14 @@ static int bpf_fd_sk_storage_delete_elem(struct bpf_map *map, void *key) return err; } -static struct bpf_sk_storage_elem * +static struct bpf_local_storage_elem * bpf_sk_storage_clone_elem(struct sock *newsk, - struct bpf_sk_storage_map *smap, - struct bpf_sk_storage_elem *selem) + struct bpf_local_storage_map *smap, + struct bpf_local_storage_elem *selem) { - struct bpf_sk_storage_elem *copy_selem; + struct bpf_local_storage_elem *copy_selem; - copy_selem = selem_alloc(smap, newsk, NULL, true); + copy_selem = bpf_selem_alloc(smap, newsk, NULL, true); if (!copy_selem) return NULL; @@ -810,9 +197,9 @@ bpf_sk_storage_clone_elem(struct sock *newsk, int bpf_sk_storage_clone(const struct sock *sk, struct sock *newsk) { - struct bpf_sk_storage *new_sk_storage = NULL; - struct bpf_sk_storage *sk_storage; - struct bpf_sk_storage_elem *selem; + struct bpf_local_storage *new_sk_storage = NULL; + struct bpf_local_storage *sk_storage; + struct bpf_local_storage_elem *selem; int ret = 0; RCU_INIT_POINTER(newsk->sk_bpf_storage, NULL); @@ -824,8 +211,8 @@ int bpf_sk_storage_clone(const struct sock *sk, struct sock *newsk) goto out; hlist_for_each_entry_rcu(selem, &sk_storage->list, snode) { - struct bpf_sk_storage_elem *copy_selem; - struct bpf_sk_storage_map *smap; + struct bpf_local_storage_elem *copy_selem; + struct bpf_local_storage_map *smap; struct bpf_map *map; smap = rcu_dereference(SDATA(selem)->smap); @@ -833,7 +220,7 @@ int bpf_sk_storage_clone(const struct sock *sk, struct sock *newsk) continue; /* Note that for lockless listeners adding new element - * here can race with cleanup in bpf_sk_storage_map_free. + * here can race with cleanup in bpf_local_storage_map_free. * Try to grab map refcnt to make sure that it's still * alive and prevent concurrent removal. */ @@ -849,10 +236,10 @@ int bpf_sk_storage_clone(const struct sock *sk, struct sock *newsk) } if (new_sk_storage) { - selem_link_map(smap, copy_selem); - __selem_link_sk(new_sk_storage, copy_selem); + bpf_selem_link_map(smap, copy_selem); + bpf_selem_link_storage_nolock(new_sk_storage, copy_selem); } else { - ret = sk_storage_alloc(newsk, smap, copy_selem); + ret = bpf_local_storage_alloc(newsk, smap, copy_selem); if (ret) { kfree(copy_selem); atomic_sub(smap->elem_size, @@ -861,7 +248,8 @@ int bpf_sk_storage_clone(const struct sock *sk, struct sock *newsk) goto out; } - new_sk_storage = rcu_dereference(copy_selem->sk_storage); + new_sk_storage = + rcu_dereference(copy_selem->local_storage); } bpf_map_put(map); } @@ -879,9 +267,9 @@ out: BPF_CALL_4(bpf_sk_storage_get, struct bpf_map *, map, struct sock *, sk, void *, value, u64, flags) { - struct bpf_sk_storage_data *sdata; + struct bpf_local_storage_data *sdata; - if (flags > BPF_SK_STORAGE_GET_F_CREATE) + if (!sk || !sk_fullsock(sk) || flags > BPF_SK_STORAGE_GET_F_CREATE) return (unsigned long)NULL; sdata = sk_storage_lookup(sk, map, true); @@ -895,7 +283,9 @@ BPF_CALL_4(bpf_sk_storage_get, struct bpf_map *, map, struct sock *, sk, * destruction). */ refcount_inc_not_zero(&sk->sk_refcnt)) { - sdata = sk_storage_update(sk, map, value, BPF_NOEXIST); + sdata = bpf_local_storage_update( + sk, (struct bpf_local_storage_map *)map, value, + BPF_NOEXIST); /* sk must be a fullsock (guaranteed by verifier), * so sock_gen_put() is unnecessary. */ @@ -909,6 +299,9 @@ BPF_CALL_4(bpf_sk_storage_get, struct bpf_map *, map, struct sock *, sk, BPF_CALL_2(bpf_sk_storage_delete, struct bpf_map *, map, struct sock *, sk) { + if (!sk || !sk_fullsock(sk)) + return -EINVAL; + if (refcount_inc_not_zero(&sk->sk_refcnt)) { int err; @@ -920,18 +313,44 @@ BPF_CALL_2(bpf_sk_storage_delete, struct bpf_map *, map, struct sock *, sk) return -ENOENT; } +static int sk_storage_charge(struct bpf_local_storage_map *smap, + void *owner, u32 size) +{ + return omem_charge(owner, size); +} + +static void sk_storage_uncharge(struct bpf_local_storage_map *smap, + void *owner, u32 size) +{ + struct sock *sk = owner; + + atomic_sub(size, &sk->sk_omem_alloc); +} + +static struct bpf_local_storage __rcu ** +sk_storage_ptr(void *owner) +{ + struct sock *sk = owner; + + return &sk->sk_bpf_storage; +} + static int sk_storage_map_btf_id; const struct bpf_map_ops sk_storage_map_ops = { - .map_alloc_check = bpf_sk_storage_map_alloc_check, - .map_alloc = bpf_sk_storage_map_alloc, - .map_free = bpf_sk_storage_map_free, + .map_meta_equal = bpf_map_meta_equal, + .map_alloc_check = bpf_local_storage_map_alloc_check, + .map_alloc = sk_storage_map_alloc, + .map_free = sk_storage_map_free, .map_get_next_key = notsupp_get_next_key, .map_lookup_elem = bpf_fd_sk_storage_lookup_elem, .map_update_elem = bpf_fd_sk_storage_update_elem, .map_delete_elem = bpf_fd_sk_storage_delete_elem, - .map_check_btf = bpf_sk_storage_map_check_btf, - .map_btf_name = "bpf_sk_storage_map", + .map_check_btf = bpf_local_storage_map_check_btf, + .map_btf_name = "bpf_local_storage_map", .map_btf_id = &sk_storage_map_btf_id, + .map_local_storage_charge = sk_storage_charge, + .map_local_storage_uncharge = sk_storage_uncharge, + .map_owner_storage_ptr = sk_storage_ptr, }; const struct bpf_func_proto bpf_sk_storage_get_proto = { @@ -939,7 +358,7 @@ const struct bpf_func_proto bpf_sk_storage_get_proto = { .gpl_only = false, .ret_type = RET_PTR_TO_MAP_VALUE_OR_NULL, .arg1_type = ARG_CONST_MAP_PTR, - .arg2_type = ARG_PTR_TO_SOCKET, + .arg2_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, .arg3_type = ARG_PTR_TO_MAP_VALUE_OR_NULL, .arg4_type = ARG_ANYTHING, }; @@ -959,7 +378,7 @@ const struct bpf_func_proto bpf_sk_storage_delete_proto = { .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_CONST_MAP_PTR, - .arg2_type = ARG_PTR_TO_SOCKET, + .arg2_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, }; struct bpf_sk_storage_diag { @@ -1022,7 +441,7 @@ bpf_sk_storage_diag_alloc(const struct nlattr *nla_stgs) u32 nr_maps = 0; int rem, err; - /* bpf_sk_storage_map is currently limited to CAP_SYS_ADMIN as + /* bpf_local_storage_map is currently limited to CAP_SYS_ADMIN as * the map_alloc_check() side also does. */ if (!bpf_capable()) @@ -1072,13 +491,13 @@ err_free: } EXPORT_SYMBOL_GPL(bpf_sk_storage_diag_alloc); -static int diag_get(struct bpf_sk_storage_data *sdata, struct sk_buff *skb) +static int diag_get(struct bpf_local_storage_data *sdata, struct sk_buff *skb) { struct nlattr *nla_stg, *nla_value; - struct bpf_sk_storage_map *smap; + struct bpf_local_storage_map *smap; /* It cannot exceed max nlattr's payload */ - BUILD_BUG_ON(U16_MAX - NLA_HDRLEN < MAX_VALUE_SIZE); + BUILD_BUG_ON(U16_MAX - NLA_HDRLEN < BPF_LOCAL_STORAGE_MAX_VALUE_SIZE); nla_stg = nla_nest_start(skb, SK_DIAG_BPF_STORAGE); if (!nla_stg) @@ -1114,9 +533,9 @@ static int bpf_sk_storage_diag_put_all(struct sock *sk, struct sk_buff *skb, { /* stg_array_type (e.g. INET_DIAG_BPF_SK_STORAGES) */ unsigned int diag_size = nla_total_size(0); - struct bpf_sk_storage *sk_storage; - struct bpf_sk_storage_elem *selem; - struct bpf_sk_storage_map *smap; + struct bpf_local_storage *sk_storage; + struct bpf_local_storage_elem *selem; + struct bpf_local_storage_map *smap; struct nlattr *nla_stgs; unsigned int saved_len; int err = 0; @@ -1169,8 +588,8 @@ int bpf_sk_storage_diag_put(struct bpf_sk_storage_diag *diag, { /* stg_array_type (e.g. INET_DIAG_BPF_SK_STORAGES) */ unsigned int diag_size = nla_total_size(0); - struct bpf_sk_storage *sk_storage; - struct bpf_sk_storage_data *sdata; + struct bpf_local_storage *sk_storage; + struct bpf_local_storage_data *sdata; struct nlattr *nla_stgs; unsigned int saved_len; int err = 0; @@ -1197,8 +616,8 @@ int bpf_sk_storage_diag_put(struct bpf_sk_storage_diag *diag, saved_len = skb->len; for (i = 0; i < diag->nr_maps; i++) { - sdata = __sk_storage_lookup(sk_storage, - (struct bpf_sk_storage_map *)diag->maps[i], + sdata = bpf_local_storage_lookup(sk_storage, + (struct bpf_local_storage_map *)diag->maps[i], false); if (!sdata) @@ -1235,19 +654,20 @@ struct bpf_iter_seq_sk_storage_map_info { unsigned skip_elems; }; -static struct bpf_sk_storage_elem * +static struct bpf_local_storage_elem * bpf_sk_storage_map_seq_find_next(struct bpf_iter_seq_sk_storage_map_info *info, - struct bpf_sk_storage_elem *prev_selem) + struct bpf_local_storage_elem *prev_selem) + __acquires(RCU) __releases(RCU) { - struct bpf_sk_storage *sk_storage; - struct bpf_sk_storage_elem *selem; + struct bpf_local_storage *sk_storage; + struct bpf_local_storage_elem *selem; u32 skip_elems = info->skip_elems; - struct bpf_sk_storage_map *smap; + struct bpf_local_storage_map *smap; u32 bucket_id = info->bucket_id; u32 i, count, n_buckets; - struct bucket *b; + struct bpf_local_storage_map_bucket *b; - smap = (struct bpf_sk_storage_map *)info->map; + smap = (struct bpf_local_storage_map *)info->map; n_buckets = 1U << smap->bucket_log; if (bucket_id >= n_buckets) return NULL; @@ -1256,16 +676,16 @@ bpf_sk_storage_map_seq_find_next(struct bpf_iter_seq_sk_storage_map_info *info, selem = prev_selem; count = 0; while (selem) { - selem = hlist_entry_safe(selem->map_node.next, - struct bpf_sk_storage_elem, map_node); + selem = hlist_entry_safe(rcu_dereference(hlist_next_rcu(&selem->map_node)), + struct bpf_local_storage_elem, map_node); if (!selem) { /* not found, unlock and go to the next bucket */ b = &smap->buckets[bucket_id++]; - raw_spin_unlock_bh(&b->lock); + rcu_read_unlock(); skip_elems = 0; break; } - sk_storage = rcu_dereference_raw(selem->sk_storage); + sk_storage = rcu_dereference(selem->local_storage); if (sk_storage) { info->skip_elems = skip_elems + count; return selem; @@ -1275,10 +695,10 @@ bpf_sk_storage_map_seq_find_next(struct bpf_iter_seq_sk_storage_map_info *info, for (i = bucket_id; i < (1U << smap->bucket_log); i++) { b = &smap->buckets[i]; - raw_spin_lock_bh(&b->lock); + rcu_read_lock(); count = 0; - hlist_for_each_entry(selem, &b->list, map_node) { - sk_storage = rcu_dereference_raw(selem->sk_storage); + hlist_for_each_entry_rcu(selem, &b->list, map_node) { + sk_storage = rcu_dereference(selem->local_storage); if (sk_storage && count >= skip_elems) { info->bucket_id = i; info->skip_elems = count; @@ -1286,7 +706,7 @@ bpf_sk_storage_map_seq_find_next(struct bpf_iter_seq_sk_storage_map_info *info, } count++; } - raw_spin_unlock_bh(&b->lock); + rcu_read_unlock(); skip_elems = 0; } @@ -1297,7 +717,7 @@ bpf_sk_storage_map_seq_find_next(struct bpf_iter_seq_sk_storage_map_info *info, static void *bpf_sk_storage_map_seq_start(struct seq_file *seq, loff_t *pos) { - struct bpf_sk_storage_elem *selem; + struct bpf_local_storage_elem *selem; selem = bpf_sk_storage_map_seq_find_next(seq->private, NULL); if (!selem) @@ -1330,11 +750,11 @@ DEFINE_BPF_ITER_FUNC(bpf_sk_storage_map, struct bpf_iter_meta *meta, void *value) static int __bpf_sk_storage_map_seq_show(struct seq_file *seq, - struct bpf_sk_storage_elem *selem) + struct bpf_local_storage_elem *selem) { struct bpf_iter_seq_sk_storage_map_info *info = seq->private; struct bpf_iter__bpf_sk_storage_map ctx = {}; - struct bpf_sk_storage *sk_storage; + struct bpf_local_storage *sk_storage; struct bpf_iter_meta meta; struct bpf_prog *prog; int ret = 0; @@ -1345,8 +765,8 @@ static int __bpf_sk_storage_map_seq_show(struct seq_file *seq, ctx.meta = &meta; ctx.map = info->map; if (selem) { - sk_storage = rcu_dereference_raw(selem->sk_storage); - ctx.sk = sk_storage->sk; + sk_storage = rcu_dereference(selem->local_storage); + ctx.sk = sk_storage->owner; ctx.value = SDATA(selem)->data; } ret = bpf_iter_run_prog(prog, &ctx); @@ -1361,18 +781,12 @@ static int bpf_sk_storage_map_seq_show(struct seq_file *seq, void *v) } static void bpf_sk_storage_map_seq_stop(struct seq_file *seq, void *v) + __releases(RCU) { - struct bpf_iter_seq_sk_storage_map_info *info = seq->private; - struct bpf_sk_storage_map *smap; - struct bucket *b; - - if (!v) { + if (!v) (void)__bpf_sk_storage_map_seq_show(seq, v); - } else { - smap = (struct bpf_sk_storage_map *)info->map; - b = &smap->buckets[info->bucket_id]; - raw_spin_unlock_bh(&b->lock); - } + else + rcu_read_unlock(); } static int bpf_iter_init_sk_storage_map(void *priv_data, @@ -1437,6 +851,8 @@ static struct bpf_iter_reg bpf_sk_storage_map_reg_info = { .target = "bpf_sk_storage_map", .attach_target = bpf_iter_attach_map, .detach_target = bpf_iter_detach_map, + .show_fdinfo = bpf_iter_map_show_fdinfo, + .fill_link_info = bpf_iter_map_fill_link_info, .ctx_arg_info_size = 2, .ctx_arg_info = { { offsetof(struct bpf_iter__bpf_sk_storage_map, sk), diff --git a/net/core/datagram.c b/net/core/datagram.c index 639745d4f3b9..9fcaa544f11a 100644 --- a/net/core/datagram.c +++ b/net/core/datagram.c @@ -623,10 +623,11 @@ int __zerocopy_sg_from_iter(struct sock *sk, struct sk_buff *skb, while (length && iov_iter_count(from)) { struct page *pages[MAX_SKB_FRAGS]; + struct page *last_head = NULL; size_t start; ssize_t copied; unsigned long truesize; - int n = 0; + int refs, n = 0; if (frag == MAX_SKB_FRAGS) return -EMSGSIZE; @@ -649,13 +650,37 @@ int __zerocopy_sg_from_iter(struct sock *sk, struct sk_buff *skb, } else { refcount_add(truesize, &skb->sk->sk_wmem_alloc); } - while (copied) { + for (refs = 0; copied != 0; start = 0) { int size = min_t(int, copied, PAGE_SIZE - start); - skb_fill_page_desc(skb, frag++, pages[n], start, size); - start = 0; + struct page *head = compound_head(pages[n]); + + start += (pages[n] - head) << PAGE_SHIFT; copied -= size; n++; + if (frag) { + skb_frag_t *last = &skb_shinfo(skb)->frags[frag - 1]; + + if (head == skb_frag_page(last) && + start == skb_frag_off(last) + skb_frag_size(last)) { + skb_frag_size_add(last, size); + /* We combined this page, we need to release + * a reference. Since compound pages refcount + * is shared among many pages, batch the refcount + * adjustments to limit false sharing. + */ + last_head = head; + refs++; + continue; + } + } + if (refs) { + page_ref_sub(last_head, refs); + refs = 0; + } + skb_fill_page_desc(skb, frag++, head, start, size); } + if (refs) + page_ref_sub(last_head, refs); } return 0; } diff --git a/net/core/dev.c b/net/core/dev.c index 4906b44af850..751e5264fd49 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -98,6 +98,7 @@ #include <net/busy_poll.h> #include <linux/rtnetlink.h> #include <linux/stat.h> +#include <net/dsa.h> #include <net/dst.h> #include <net/dst_metadata.h> #include <net/pkt_sched.h> @@ -1130,7 +1131,7 @@ EXPORT_SYMBOL(__dev_get_by_flags); * @name: name string * * Network device names need to be valid file names to - * to allow sysfs to work. We also disallow any kind of + * allow sysfs to work. We also disallow any kind of * whitespace. */ bool dev_valid_name(const char *name) @@ -4840,6 +4841,21 @@ int netif_rx_ni(struct sk_buff *skb) } EXPORT_SYMBOL(netif_rx_ni); +int netif_rx_any_context(struct sk_buff *skb) +{ + /* + * If invoked from contexts which do not invoke bottom half + * processing either at return from interrupt or when softrqs are + * reenabled, use netif_rx_ni() which invokes bottomhalf processing + * directly. + */ + if (in_interrupt()) + return netif_rx(skb); + else + return netif_rx_ni(skb); +} +EXPORT_SYMBOL(netif_rx_any_context); + static __latent_entropy void net_tx_action(struct softirq_action *h) { struct softnet_data *sd = this_cpu_ptr(&softnet_data); @@ -4914,7 +4930,7 @@ EXPORT_SYMBOL_GPL(br_fdb_test_addr_hook); static inline struct sk_buff * sch_handle_ingress(struct sk_buff *skb, struct packet_type **pt_prev, int *ret, - struct net_device *orig_dev) + struct net_device *orig_dev, bool *another) { #ifdef CONFIG_NET_CLS_ACT struct mini_Qdisc *miniq = rcu_dereference_bh(skb->dev->miniq_ingress); @@ -4958,7 +4974,11 @@ sch_handle_ingress(struct sk_buff *skb, struct packet_type **pt_prev, int *ret, * redirecting to another netdev */ __skb_push(skb, skb->mac_len); - skb_do_redirect(skb); + if (skb_do_redirect(skb) == -EAGAIN) { + __skb_pull(skb, skb->mac_len); + *another = true; + break; + } return NULL; case TC_ACT_CONSUMED: return NULL; @@ -5147,7 +5167,12 @@ another_round: skip_taps: #ifdef CONFIG_NET_INGRESS if (static_branch_unlikely(&ingress_needed_key)) { - skb = sch_handle_ingress(skb, &pt_prev, &ret, orig_dev); + bool another = false; + + skb = sch_handle_ingress(skb, &pt_prev, &ret, orig_dev, + &another); + if (another) + goto another_round; if (!skb) goto out; @@ -5192,7 +5217,7 @@ skip_classify: } } - if (unlikely(skb_vlan_tag_present(skb))) { + if (unlikely(skb_vlan_tag_present(skb)) && !netdev_uses_dsa(skb->dev)) { check_vlan_id: if (skb_vlan_tag_get_id(skb)) { /* Vlan id is non 0 and vlan_do_receive() above couldn't @@ -5441,15 +5466,20 @@ static int generic_xdp_install(struct net_device *dev, struct netdev_bpf *xdp) if (new) { u32 i; + mutex_lock(&new->aux->used_maps_mutex); + /* generic XDP does not work with DEVMAPs that can * have a bpf_prog installed on an entry */ for (i = 0; i < new->aux->used_map_cnt; i++) { - if (dev_map_can_have_prog(new->aux->used_maps[i])) - return -EINVAL; - if (cpu_map_prog_allowed(new->aux->used_maps[i])) + if (dev_map_can_have_prog(new->aux->used_maps[i]) || + cpu_map_prog_allowed(new->aux->used_maps[i])) { + mutex_unlock(&new->aux->used_maps_mutex); return -EINVAL; + } } + + mutex_unlock(&new->aux->used_maps_mutex); } switch (xdp->command) { @@ -5621,17 +5651,60 @@ static void flush_backlog(struct work_struct *work) local_bh_enable(); } +static bool flush_required(int cpu) +{ +#if IS_ENABLED(CONFIG_RPS) + struct softnet_data *sd = &per_cpu(softnet_data, cpu); + bool do_flush; + + local_irq_disable(); + rps_lock(sd); + + /* as insertion into process_queue happens with the rps lock held, + * process_queue access may race only with dequeue + */ + do_flush = !skb_queue_empty(&sd->input_pkt_queue) || + !skb_queue_empty_lockless(&sd->process_queue); + rps_unlock(sd); + local_irq_enable(); + + return do_flush; +#endif + /* without RPS we can't safely check input_pkt_queue: during a + * concurrent remote skb_queue_splice() we can detect as empty both + * input_pkt_queue and process_queue even if the latter could end-up + * containing a lot of packets. + */ + return true; +} + static void flush_all_backlogs(void) { + static cpumask_t flush_cpus; unsigned int cpu; + /* since we are under rtnl lock protection we can use static data + * for the cpumask and avoid allocating on stack the possibly + * large mask + */ + ASSERT_RTNL(); + get_online_cpus(); - for_each_online_cpu(cpu) - queue_work_on(cpu, system_highpri_wq, - per_cpu_ptr(&flush_works, cpu)); + cpumask_clear(&flush_cpus); + for_each_online_cpu(cpu) { + if (flush_required(cpu)) { + queue_work_on(cpu, system_highpri_wq, + per_cpu_ptr(&flush_works, cpu)); + cpumask_set_cpu(cpu, &flush_cpus); + } + } - for_each_online_cpu(cpu) + /* we can have in flight packet[s] on the cpus we are not flushing, + * synchronize_net() in rollback_registered_many() will take care of + * them + */ + for_each_cpu(cpu, &flush_cpus) flush_work(per_cpu_ptr(&flush_works, cpu)); put_online_cpus(); @@ -6293,7 +6366,7 @@ EXPORT_SYMBOL(__napi_schedule); * @n: napi context * * Test if NAPI routine is already running, and if not mark - * it as running. This is used as a condition variable + * it as running. This is used as a condition variable to * insure only one NAPI poll instance runs. We also make * sure there is no pending NAPI disable. */ @@ -6533,8 +6606,7 @@ EXPORT_SYMBOL(napi_busy_loop); static void napi_hash_add(struct napi_struct *napi) { - if (test_bit(NAPI_STATE_NO_BUSY_POLL, &napi->state) || - test_and_set_bit(NAPI_STATE_HASHED, &napi->state)) + if (test_bit(NAPI_STATE_NO_BUSY_POLL, &napi->state)) return; spin_lock(&napi_hash_lock); @@ -6555,20 +6627,14 @@ static void napi_hash_add(struct napi_struct *napi) /* Warning : caller is responsible to make sure rcu grace period * is respected before freeing memory containing @napi */ -bool napi_hash_del(struct napi_struct *napi) +static void napi_hash_del(struct napi_struct *napi) { - bool rcu_sync_needed = false; - spin_lock(&napi_hash_lock); - if (test_and_clear_bit(NAPI_STATE_HASHED, &napi->state)) { - rcu_sync_needed = true; - hlist_del_rcu(&napi->napi_hash_node); - } + hlist_del_init_rcu(&napi->napi_hash_node); + spin_unlock(&napi_hash_lock); - return rcu_sync_needed; } -EXPORT_SYMBOL_GPL(napi_hash_del); static enum hrtimer_restart napi_watchdog(struct hrtimer *timer) { @@ -6600,7 +6666,11 @@ static void init_gro_hash(struct napi_struct *napi) void netif_napi_add(struct net_device *dev, struct napi_struct *napi, int (*poll)(struct napi_struct *, int), int weight) { + if (WARN_ON(test_and_set_bit(NAPI_STATE_LISTED, &napi->state))) + return; + INIT_LIST_HEAD(&napi->poll_list); + INIT_HLIST_NODE(&napi->napi_hash_node); hrtimer_init(&napi->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_PINNED); napi->timer.function = napi_watchdog; init_gro_hash(napi); @@ -6653,18 +6723,19 @@ static void flush_gro_hash(struct napi_struct *napi) } /* Must be called in process context */ -void netif_napi_del(struct napi_struct *napi) +void __netif_napi_del(struct napi_struct *napi) { - might_sleep(); - if (napi_hash_del(napi)) - synchronize_net(); - list_del_init(&napi->dev_list); + if (!test_and_clear_bit(NAPI_STATE_LISTED, &napi->state)) + return; + + napi_hash_del(napi); + list_del_rcu(&napi->dev_list); napi_free_frags(napi); flush_gro_hash(napi); napi->gro_bitmask = 0; } -EXPORT_SYMBOL(netif_napi_del); +EXPORT_SYMBOL(__netif_napi_del); static int napi_poll(struct napi_struct *n, struct list_head *repoll) { @@ -9533,7 +9604,7 @@ int __netdev_update_features(struct net_device *dev) /* driver might be less strict about feature dependencies */ features = netdev_fix_features(dev, features); - /* some features can't be enabled if they're off an an upper device */ + /* some features can't be enabled if they're off on an upper device */ netdev_for_each_upper_dev_rcu(dev, upper, iter) features = netdev_sync_upper_features(dev, upper, features); @@ -10037,6 +10108,8 @@ int netdev_refcnt_read(const struct net_device *dev) } EXPORT_SYMBOL(netdev_refcnt_read); +#define WAIT_REFS_MIN_MSECS 1 +#define WAIT_REFS_MAX_MSECS 250 /** * netdev_wait_allrefs - wait until all references are gone. * @dev: target net_device @@ -10052,7 +10125,7 @@ EXPORT_SYMBOL(netdev_refcnt_read); static void netdev_wait_allrefs(struct net_device *dev) { unsigned long rebroadcast_time, warning_time; - int refcnt; + int wait = 0, refcnt; linkwatch_forget_dev(dev); @@ -10086,7 +10159,13 @@ static void netdev_wait_allrefs(struct net_device *dev) rebroadcast_time = jiffies; } - msleep(250); + if (!wait) { + rcu_barrier(); + wait = WAIT_REFS_MIN_MSECS; + } else { + msleep(wait); + wait = min(wait << 1, WAIT_REFS_MAX_MSECS); + } refcnt = netdev_refcnt_read(dev); @@ -10249,6 +10328,40 @@ struct rtnl_link_stats64 *dev_get_stats(struct net_device *dev, } EXPORT_SYMBOL(dev_get_stats); +/** + * dev_fetch_sw_netstats - get per-cpu network device statistics + * @s: place to store stats + * @netstats: per-cpu network stats to read from + * + * Read per-cpu network statistics and populate the related fields in @s. + */ +void dev_fetch_sw_netstats(struct rtnl_link_stats64 *s, + const struct pcpu_sw_netstats __percpu *netstats) +{ + int cpu; + + for_each_possible_cpu(cpu) { + const struct pcpu_sw_netstats *stats; + struct pcpu_sw_netstats tmp; + unsigned int start; + + stats = per_cpu_ptr(netstats, cpu); + do { + start = u64_stats_fetch_begin_irq(&stats->syncp); + tmp.rx_packets = stats->rx_packets; + tmp.rx_bytes = stats->rx_bytes; + tmp.tx_packets = stats->tx_packets; + tmp.tx_bytes = stats->tx_bytes; + } while (u64_stats_fetch_retry_irq(&stats->syncp, start)); + + s->rx_packets += tmp.rx_packets; + s->rx_bytes += tmp.rx_bytes; + s->tx_packets += tmp.tx_packets; + s->tx_bytes += tmp.tx_bytes; + } +} +EXPORT_SYMBOL_GPL(dev_fetch_sw_netstats); + struct netdev_queue *dev_ingress_queue_create(struct net_device *dev) { struct netdev_queue *queue = dev_ingress_queue(dev); diff --git a/net/core/devlink.c b/net/core/devlink.c index 80ec1cd81c64..a578634052a3 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -27,7 +27,6 @@ #include <net/net_namespace.h> #include <net/sock.h> #include <net/devlink.h> -#include <net/drop_monitor.h> #define CREATE_TRACE_POINTS #include <trace/events/devlink.h> @@ -84,6 +83,7 @@ EXPORT_SYMBOL(devlink_dpipe_header_ipv6); EXPORT_TRACEPOINT_SYMBOL_GPL(devlink_hwmsg); EXPORT_TRACEPOINT_SYMBOL_GPL(devlink_hwerr); +EXPORT_TRACEPOINT_SYMBOL_GPL(devlink_trap_report); static const struct nla_policy devlink_function_nl_policy[DEVLINK_PORT_FUNCTION_ATTR_MAX + 1] = { [DEVLINK_PORT_FUNCTION_ATTR_HW_ADDR] = { .type = NLA_BINARY }, @@ -347,8 +347,12 @@ devlink_sb_tc_index_get_from_info(struct devlink_sb *devlink_sb, struct devlink_region { struct devlink *devlink; + struct devlink_port *port; struct list_head list; - const struct devlink_region_ops *ops; + union { + const struct devlink_region_ops *ops; + const struct devlink_port_region_ops *port_ops; + }; struct list_head snapshot_list; u32 max_snapshots; u32 cur_snapshots; @@ -374,6 +378,19 @@ devlink_region_get_by_name(struct devlink *devlink, const char *region_name) return NULL; } +static struct devlink_region * +devlink_port_region_get_by_name(struct devlink_port *port, + const char *region_name) +{ + struct devlink_region *region; + + list_for_each_entry(region, &port->region_list, list) + if (!strcmp(region->ops->name, region_name)) + return region; + + return NULL; +} + static struct devlink_snapshot * devlink_region_snapshot_get_by_id(struct devlink_region *region, u32 id) { @@ -462,10 +479,115 @@ static int devlink_nl_put_handle(struct sk_buff *msg, struct devlink *devlink) return 0; } +struct devlink_reload_combination { + enum devlink_reload_action action; + enum devlink_reload_limit limit; +}; + +static const struct devlink_reload_combination devlink_reload_invalid_combinations[] = { + { + /* can't reinitialize driver with no down time */ + .action = DEVLINK_RELOAD_ACTION_DRIVER_REINIT, + .limit = DEVLINK_RELOAD_LIMIT_NO_RESET, + }, +}; + +static bool +devlink_reload_combination_is_invalid(enum devlink_reload_action action, + enum devlink_reload_limit limit) +{ + int i; + + for (i = 0; i < ARRAY_SIZE(devlink_reload_invalid_combinations); i++) + if (devlink_reload_invalid_combinations[i].action == action && + devlink_reload_invalid_combinations[i].limit == limit) + return true; + return false; +} + +static bool +devlink_reload_action_is_supported(struct devlink *devlink, enum devlink_reload_action action) +{ + return test_bit(action, &devlink->ops->reload_actions); +} + +static bool +devlink_reload_limit_is_supported(struct devlink *devlink, enum devlink_reload_limit limit) +{ + return test_bit(limit, &devlink->ops->reload_limits); +} + +static int devlink_reload_stat_put(struct sk_buff *msg, enum devlink_reload_action action, + enum devlink_reload_limit limit, u32 value) +{ + struct nlattr *reload_stats_entry; + + reload_stats_entry = nla_nest_start(msg, DEVLINK_ATTR_RELOAD_STATS_ENTRY); + if (!reload_stats_entry) + return -EMSGSIZE; + + if (nla_put_u8(msg, DEVLINK_ATTR_RELOAD_ACTION, action) || + nla_put_u8(msg, DEVLINK_ATTR_RELOAD_STATS_LIMIT, limit) || + nla_put_u32(msg, DEVLINK_ATTR_RELOAD_STATS_VALUE, value)) + goto nla_put_failure; + nla_nest_end(msg, reload_stats_entry); + return 0; + +nla_put_failure: + nla_nest_cancel(msg, reload_stats_entry); + return -EMSGSIZE; +} + +static int devlink_reload_stats_put(struct sk_buff *msg, struct devlink *devlink, bool is_remote) +{ + struct nlattr *reload_stats_attr; + int i, j, stat_idx; + u32 value; + + if (!is_remote) + reload_stats_attr = nla_nest_start(msg, DEVLINK_ATTR_RELOAD_STATS); + else + reload_stats_attr = nla_nest_start(msg, DEVLINK_ATTR_REMOTE_RELOAD_STATS); + + if (!reload_stats_attr) + return -EMSGSIZE; + + for (j = 0; j <= DEVLINK_RELOAD_LIMIT_MAX; j++) { + /* Remote stats are shown even if not locally supported. Stats + * of actions with unspecified limit are shown though drivers + * don't need to register unspecified limit. + */ + if (!is_remote && j != DEVLINK_RELOAD_LIMIT_UNSPEC && + !devlink_reload_limit_is_supported(devlink, j)) + continue; + for (i = 0; i <= DEVLINK_RELOAD_ACTION_MAX; i++) { + if ((!is_remote && !devlink_reload_action_is_supported(devlink, i)) || + i == DEVLINK_RELOAD_ACTION_UNSPEC || + devlink_reload_combination_is_invalid(i, j)) + continue; + + stat_idx = j * __DEVLINK_RELOAD_ACTION_MAX + i; + if (!is_remote) + value = devlink->stats.reload_stats[stat_idx]; + else + value = devlink->stats.remote_reload_stats[stat_idx]; + if (devlink_reload_stat_put(msg, i, j, value)) + goto nla_put_failure; + } + } + nla_nest_end(msg, reload_stats_attr); + return 0; + +nla_put_failure: + nla_nest_cancel(msg, reload_stats_attr); + return -EMSGSIZE; +} + static int devlink_nl_fill(struct sk_buff *msg, struct devlink *devlink, enum devlink_command cmd, u32 portid, u32 seq, int flags) { + struct nlattr *dev_stats; void *hdr; hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd); @@ -477,9 +599,21 @@ static int devlink_nl_fill(struct sk_buff *msg, struct devlink *devlink, if (nla_put_u8(msg, DEVLINK_ATTR_RELOAD_FAILED, devlink->reload_failed)) goto nla_put_failure; + dev_stats = nla_nest_start(msg, DEVLINK_ATTR_DEV_STATS); + if (!dev_stats) + goto nla_put_failure; + + if (devlink_reload_stats_put(msg, devlink, false)) + goto dev_stats_nest_cancel; + if (devlink_reload_stats_put(msg, devlink, true)) + goto dev_stats_nest_cancel; + + nla_nest_end(msg, dev_stats); genlmsg_end(msg, hdr); return 0; +dev_stats_nest_cancel: + nla_nest_cancel(msg, dev_stats); nla_put_failure: genlmsg_cancel(msg, hdr); return -EMSGSIZE; @@ -523,15 +657,20 @@ static int devlink_nl_port_attrs_put(struct sk_buff *msg, return -EMSGSIZE; switch (devlink_port->attrs.flavour) { case DEVLINK_PORT_FLAVOUR_PCI_PF: - if (nla_put_u16(msg, DEVLINK_ATTR_PORT_PCI_PF_NUMBER, - attrs->pci_pf.pf)) + if (nla_put_u32(msg, DEVLINK_ATTR_PORT_CONTROLLER_NUMBER, + attrs->pci_pf.controller) || + nla_put_u16(msg, DEVLINK_ATTR_PORT_PCI_PF_NUMBER, attrs->pci_pf.pf)) + return -EMSGSIZE; + if (nla_put_u8(msg, DEVLINK_ATTR_PORT_EXTERNAL, attrs->pci_pf.external)) return -EMSGSIZE; break; case DEVLINK_PORT_FLAVOUR_PCI_VF: - if (nla_put_u16(msg, DEVLINK_ATTR_PORT_PCI_PF_NUMBER, - attrs->pci_vf.pf) || - nla_put_u16(msg, DEVLINK_ATTR_PORT_PCI_VF_NUMBER, - attrs->pci_vf.vf)) + if (nla_put_u32(msg, DEVLINK_ATTR_PORT_CONTROLLER_NUMBER, + attrs->pci_vf.controller) || + nla_put_u16(msg, DEVLINK_ATTR_PORT_PCI_PF_NUMBER, attrs->pci_vf.pf) || + nla_put_u16(msg, DEVLINK_ATTR_PORT_PCI_VF_NUMBER, attrs->pci_vf.vf)) + return -EMSGSIZE; + if (nla_put_u8(msg, DEVLINK_ATTR_PORT_EXTERNAL, attrs->pci_vf.external)) return -EMSGSIZE; break; case DEVLINK_PORT_FLAVOUR_PHYSICAL: @@ -806,8 +945,6 @@ static int devlink_port_type_set(struct devlink *devlink, int err; if (devlink->ops->port_type_set) { - if (port_type == DEVLINK_PORT_TYPE_NOTSET) - return -EINVAL; if (port_type == devlink_port->type) return 0; err = devlink->ops->port_type_set(devlink_port, port_type); @@ -2943,9 +3080,9 @@ static void devlink_reload_netns_change(struct devlink *devlink, DEVLINK_CMD_PARAM_NEW); } -static bool devlink_reload_supported(const struct devlink *devlink) +static bool devlink_reload_supported(const struct devlink_ops *ops) { - return devlink->ops->reload_down && devlink->ops->reload_up; + return ops->reload_down && ops->reload_up; } static void devlink_reload_failed_set(struct devlink *devlink, @@ -2963,33 +3100,132 @@ bool devlink_is_reload_failed(const struct devlink *devlink) } EXPORT_SYMBOL_GPL(devlink_is_reload_failed); +static void +__devlink_reload_stats_update(struct devlink *devlink, u32 *reload_stats, + enum devlink_reload_limit limit, u32 actions_performed) +{ + unsigned long actions = actions_performed; + int stat_idx; + int action; + + for_each_set_bit(action, &actions, __DEVLINK_RELOAD_ACTION_MAX) { + stat_idx = limit * __DEVLINK_RELOAD_ACTION_MAX + action; + reload_stats[stat_idx]++; + } + devlink_notify(devlink, DEVLINK_CMD_NEW); +} + +static void +devlink_reload_stats_update(struct devlink *devlink, enum devlink_reload_limit limit, + u32 actions_performed) +{ + __devlink_reload_stats_update(devlink, devlink->stats.reload_stats, limit, + actions_performed); +} + +/** + * devlink_remote_reload_actions_performed - Update devlink on reload actions + * performed which are not a direct result of devlink reload call. + * + * This should be called by a driver after performing reload actions in case it was not + * a result of devlink reload call. For example fw_activate was performed as a result + * of devlink reload triggered fw_activate on another host. + * The motivation for this function is to keep data on reload actions performed on this + * function whether it was done due to direct devlink reload call or not. + * + * @devlink: devlink + * @limit: reload limit + * @actions_performed: bitmask of actions performed + */ +void devlink_remote_reload_actions_performed(struct devlink *devlink, + enum devlink_reload_limit limit, + u32 actions_performed) +{ + if (WARN_ON(!actions_performed || + actions_performed & BIT(DEVLINK_RELOAD_ACTION_UNSPEC) || + actions_performed >= BIT(__DEVLINK_RELOAD_ACTION_MAX) || + limit > DEVLINK_RELOAD_LIMIT_MAX)) + return; + + __devlink_reload_stats_update(devlink, devlink->stats.remote_reload_stats, limit, + actions_performed); +} +EXPORT_SYMBOL_GPL(devlink_remote_reload_actions_performed); + static int devlink_reload(struct devlink *devlink, struct net *dest_net, - struct netlink_ext_ack *extack) + enum devlink_reload_action action, enum devlink_reload_limit limit, + u32 *actions_performed, struct netlink_ext_ack *extack) { + u32 remote_reload_stats[DEVLINK_RELOAD_STATS_ARRAY_SIZE]; int err; if (!devlink->reload_enabled) return -EOPNOTSUPP; - err = devlink->ops->reload_down(devlink, !!dest_net, extack); + memcpy(remote_reload_stats, devlink->stats.remote_reload_stats, + sizeof(remote_reload_stats)); + err = devlink->ops->reload_down(devlink, !!dest_net, action, limit, extack); if (err) return err; if (dest_net && !net_eq(dest_net, devlink_net(devlink))) devlink_reload_netns_change(devlink, dest_net); - err = devlink->ops->reload_up(devlink, extack); + err = devlink->ops->reload_up(devlink, action, limit, actions_performed, extack); devlink_reload_failed_set(devlink, !!err); - return err; + if (err) + return err; + + WARN_ON(!(*actions_performed & BIT(action))); + /* Catch driver on updating the remote action within devlink reload */ + WARN_ON(memcmp(remote_reload_stats, devlink->stats.remote_reload_stats, + sizeof(remote_reload_stats))); + devlink_reload_stats_update(devlink, limit, *actions_performed); + return 0; +} + +static int +devlink_nl_reload_actions_performed_snd(struct devlink *devlink, u32 actions_performed, + enum devlink_command cmd, struct genl_info *info) +{ + struct sk_buff *msg; + void *hdr; + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return -ENOMEM; + + hdr = genlmsg_put(msg, info->snd_portid, info->snd_seq, &devlink_nl_family, 0, cmd); + if (!hdr) + goto free_msg; + + if (devlink_nl_put_handle(msg, devlink)) + goto nla_put_failure; + + if (nla_put_bitfield32(msg, DEVLINK_ATTR_RELOAD_ACTIONS_PERFORMED, actions_performed, + actions_performed)) + goto nla_put_failure; + genlmsg_end(msg, hdr); + + return genlmsg_reply(msg, info); + +nla_put_failure: + genlmsg_cancel(msg, hdr); +free_msg: + nlmsg_free(msg); + return -EMSGSIZE; } static int devlink_nl_cmd_reload(struct sk_buff *skb, struct genl_info *info) { struct devlink *devlink = info->user_ptr[0]; + enum devlink_reload_action action; + enum devlink_reload_limit limit; struct net *dest_net = NULL; + u32 actions_performed; int err; - if (!devlink_reload_supported(devlink)) + if (!devlink_reload_supported(devlink->ops)) return -EOPNOTSUPP; err = devlink_resources_validate(devlink, NULL, info); @@ -3006,20 +3242,67 @@ static int devlink_nl_cmd_reload(struct sk_buff *skb, struct genl_info *info) return PTR_ERR(dest_net); } - err = devlink_reload(devlink, dest_net, info->extack); + if (info->attrs[DEVLINK_ATTR_RELOAD_ACTION]) + action = nla_get_u8(info->attrs[DEVLINK_ATTR_RELOAD_ACTION]); + else + action = DEVLINK_RELOAD_ACTION_DRIVER_REINIT; + + if (!devlink_reload_action_is_supported(devlink, action)) { + NL_SET_ERR_MSG_MOD(info->extack, + "Requested reload action is not supported by the driver"); + return -EOPNOTSUPP; + } + + limit = DEVLINK_RELOAD_LIMIT_UNSPEC; + if (info->attrs[DEVLINK_ATTR_RELOAD_LIMITS]) { + struct nla_bitfield32 limits; + u32 limits_selected; + + limits = nla_get_bitfield32(info->attrs[DEVLINK_ATTR_RELOAD_LIMITS]); + limits_selected = limits.value & limits.selector; + if (!limits_selected) { + NL_SET_ERR_MSG_MOD(info->extack, "Invalid limit selected"); + return -EINVAL; + } + for (limit = 0 ; limit <= DEVLINK_RELOAD_LIMIT_MAX ; limit++) + if (limits_selected & BIT(limit)) + break; + /* UAPI enables multiselection, but currently it is not used */ + if (limits_selected != BIT(limit)) { + NL_SET_ERR_MSG_MOD(info->extack, + "Multiselection of limit is not supported"); + return -EOPNOTSUPP; + } + if (!devlink_reload_limit_is_supported(devlink, limit)) { + NL_SET_ERR_MSG_MOD(info->extack, + "Requested limit is not supported by the driver"); + return -EOPNOTSUPP; + } + if (devlink_reload_combination_is_invalid(action, limit)) { + NL_SET_ERR_MSG_MOD(info->extack, + "Requested limit is invalid for this action"); + return -EINVAL; + } + } + err = devlink_reload(devlink, dest_net, action, limit, &actions_performed, info->extack); if (dest_net) put_net(dest_net); - return err; + if (err) + return err; + /* For backward compatibility generate reply only if attributes used by user */ + if (!info->attrs[DEVLINK_ATTR_RELOAD_ACTION] && !info->attrs[DEVLINK_ATTR_RELOAD_LIMITS]) + return 0; + + return devlink_nl_reload_actions_performed_snd(devlink, actions_performed, + DEVLINK_CMD_RELOAD, info); } static int devlink_nl_flash_update_fill(struct sk_buff *msg, struct devlink *devlink, enum devlink_command cmd, - const char *status_msg, - const char *component, - unsigned long done, unsigned long total) + struct devlink_flash_notify *params) { void *hdr; @@ -3033,19 +3316,22 @@ static int devlink_nl_flash_update_fill(struct sk_buff *msg, if (cmd != DEVLINK_CMD_FLASH_UPDATE_STATUS) goto out; - if (status_msg && + if (params->status_msg && nla_put_string(msg, DEVLINK_ATTR_FLASH_UPDATE_STATUS_MSG, - status_msg)) + params->status_msg)) goto nla_put_failure; - if (component && + if (params->component && nla_put_string(msg, DEVLINK_ATTR_FLASH_UPDATE_COMPONENT, - component)) + params->component)) goto nla_put_failure; if (nla_put_u64_64bit(msg, DEVLINK_ATTR_FLASH_UPDATE_STATUS_DONE, - done, DEVLINK_ATTR_PAD)) + params->done, DEVLINK_ATTR_PAD)) goto nla_put_failure; if (nla_put_u64_64bit(msg, DEVLINK_ATTR_FLASH_UPDATE_STATUS_TOTAL, - total, DEVLINK_ATTR_PAD)) + params->total, DEVLINK_ATTR_PAD)) + goto nla_put_failure; + if (nla_put_u64_64bit(msg, DEVLINK_ATTR_FLASH_UPDATE_STATUS_TIMEOUT, + params->timeout, DEVLINK_ATTR_PAD)) goto nla_put_failure; out: @@ -3059,10 +3345,7 @@ nla_put_failure: static void __devlink_flash_update_notify(struct devlink *devlink, enum devlink_command cmd, - const char *status_msg, - const char *component, - unsigned long done, - unsigned long total) + struct devlink_flash_notify *params) { struct sk_buff *msg; int err; @@ -3075,8 +3358,7 @@ static void __devlink_flash_update_notify(struct devlink *devlink, if (!msg) return; - err = devlink_nl_flash_update_fill(msg, devlink, cmd, status_msg, - component, done, total); + err = devlink_nl_flash_update_fill(msg, devlink, cmd, params); if (err) goto out_free_msg; @@ -3090,17 +3372,21 @@ out_free_msg: void devlink_flash_update_begin_notify(struct devlink *devlink) { + struct devlink_flash_notify params = { 0 }; + __devlink_flash_update_notify(devlink, DEVLINK_CMD_FLASH_UPDATE, - NULL, NULL, 0, 0); + ¶ms); } EXPORT_SYMBOL_GPL(devlink_flash_update_begin_notify); void devlink_flash_update_end_notify(struct devlink *devlink) { + struct devlink_flash_notify params = { 0 }; + __devlink_flash_update_notify(devlink, DEVLINK_CMD_FLASH_UPDATE_END, - NULL, NULL, 0, 0); + ¶ms); } EXPORT_SYMBOL_GPL(devlink_flash_update_end_notify); @@ -3110,31 +3396,78 @@ void devlink_flash_update_status_notify(struct devlink *devlink, unsigned long done, unsigned long total) { + struct devlink_flash_notify params = { + .status_msg = status_msg, + .component = component, + .done = done, + .total = total, + }; + __devlink_flash_update_notify(devlink, DEVLINK_CMD_FLASH_UPDATE_STATUS, - status_msg, component, done, total); + ¶ms); } EXPORT_SYMBOL_GPL(devlink_flash_update_status_notify); +void devlink_flash_update_timeout_notify(struct devlink *devlink, + const char *status_msg, + const char *component, + unsigned long timeout) +{ + struct devlink_flash_notify params = { + .status_msg = status_msg, + .component = component, + .timeout = timeout, + }; + + __devlink_flash_update_notify(devlink, + DEVLINK_CMD_FLASH_UPDATE_STATUS, + ¶ms); +} +EXPORT_SYMBOL_GPL(devlink_flash_update_timeout_notify); + static int devlink_nl_cmd_flash_update(struct sk_buff *skb, struct genl_info *info) { + struct nlattr *nla_component, *nla_overwrite_mask; + struct devlink_flash_update_params params = {}; struct devlink *devlink = info->user_ptr[0]; - const char *file_name, *component; - struct nlattr *nla_component; + u32 supported_params; if (!devlink->ops->flash_update) return -EOPNOTSUPP; if (!info->attrs[DEVLINK_ATTR_FLASH_UPDATE_FILE_NAME]) return -EINVAL; - file_name = nla_data(info->attrs[DEVLINK_ATTR_FLASH_UPDATE_FILE_NAME]); + + supported_params = devlink->ops->supported_flash_update_params; + + params.file_name = nla_data(info->attrs[DEVLINK_ATTR_FLASH_UPDATE_FILE_NAME]); nla_component = info->attrs[DEVLINK_ATTR_FLASH_UPDATE_COMPONENT]; - component = nla_component ? nla_data(nla_component) : NULL; + if (nla_component) { + if (!(supported_params & DEVLINK_SUPPORT_FLASH_UPDATE_COMPONENT)) { + NL_SET_ERR_MSG_ATTR(info->extack, nla_component, + "component update is not supported by this device"); + return -EOPNOTSUPP; + } + params.component = nla_data(nla_component); + } + + nla_overwrite_mask = info->attrs[DEVLINK_ATTR_FLASH_UPDATE_OVERWRITE_MASK]; + if (nla_overwrite_mask) { + struct nla_bitfield32 sections; + + if (!(supported_params & DEVLINK_SUPPORT_FLASH_UPDATE_OVERWRITE_MASK)) { + NL_SET_ERR_MSG_ATTR(info->extack, nla_overwrite_mask, + "overwrite settings are not supported by this device"); + return -EOPNOTSUPP; + } + sections = nla_get_bitfield32(nla_overwrite_mask); + params.overwrite_mask = sections.value & sections.selector; + } - return devlink->ops->flash_update(devlink, file_name, component, - info->extack); + return devlink->ops->flash_update(devlink, ¶ms, info->extack); } static const struct devlink_param devlink_param_generic[] = { @@ -3188,6 +3521,11 @@ static const struct devlink_param devlink_param_generic[] = { .name = DEVLINK_PARAM_GENERIC_ENABLE_ROCE_NAME, .type = DEVLINK_PARAM_GENERIC_ENABLE_ROCE_TYPE, }, + { + .id = DEVLINK_PARAM_GENERIC_ID_ENABLE_REMOTE_DEV_RESET, + .name = DEVLINK_PARAM_GENERIC_ENABLE_REMOTE_DEV_RESET_NAME, + .type = DEVLINK_PARAM_GENERIC_ENABLE_REMOTE_DEV_RESET_TYPE, + }, }; static int devlink_param_generic_verify(const struct devlink_param *param) @@ -3875,6 +4213,11 @@ static int devlink_nl_region_fill(struct sk_buff *msg, struct devlink *devlink, if (err) goto nla_put_failure; + if (region->port) + if (nla_put_u32(msg, DEVLINK_ATTR_PORT_INDEX, + region->port->index)) + goto nla_put_failure; + err = nla_put_string(msg, DEVLINK_ATTR_REGION_NAME, region->ops->name); if (err) goto nla_put_failure; @@ -3922,6 +4265,11 @@ devlink_nl_region_notify_build(struct devlink_region *region, if (err) goto out_cancel_msg; + if (region->port) + if (nla_put_u32(msg, DEVLINK_ATTR_PORT_INDEX, + region->port->index)) + goto out_cancel_msg; + err = nla_put_string(msg, DEVLINK_ATTR_REGION_NAME, region->ops->name); if (err) @@ -4168,16 +4516,30 @@ static int devlink_nl_cmd_region_get_doit(struct sk_buff *skb, struct genl_info *info) { struct devlink *devlink = info->user_ptr[0]; + struct devlink_port *port = NULL; struct devlink_region *region; const char *region_name; struct sk_buff *msg; + unsigned int index; int err; if (!info->attrs[DEVLINK_ATTR_REGION_NAME]) return -EINVAL; + if (info->attrs[DEVLINK_ATTR_PORT_INDEX]) { + index = nla_get_u32(info->attrs[DEVLINK_ATTR_PORT_INDEX]); + + port = devlink_port_get_by_index(devlink, index); + if (!port) + return -ENODEV; + } + region_name = nla_data(info->attrs[DEVLINK_ATTR_REGION_NAME]); - region = devlink_region_get_by_name(devlink, region_name); + if (port) + region = devlink_port_region_get_by_name(port, region_name); + else + region = devlink_region_get_by_name(devlink, region_name); + if (!region) return -EINVAL; @@ -4196,10 +4558,75 @@ static int devlink_nl_cmd_region_get_doit(struct sk_buff *skb, return genlmsg_reply(msg, info); } +static int devlink_nl_cmd_region_get_port_dumpit(struct sk_buff *msg, + struct netlink_callback *cb, + struct devlink_port *port, + int *idx, + int start) +{ + struct devlink_region *region; + int err = 0; + + list_for_each_entry(region, &port->region_list, list) { + if (*idx < start) { + (*idx)++; + continue; + } + err = devlink_nl_region_fill(msg, port->devlink, + DEVLINK_CMD_REGION_GET, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, + NLM_F_MULTI, region); + if (err) + goto out; + (*idx)++; + } + +out: + return err; +} + +static int devlink_nl_cmd_region_get_devlink_dumpit(struct sk_buff *msg, + struct netlink_callback *cb, + struct devlink *devlink, + int *idx, + int start) +{ + struct devlink_region *region; + struct devlink_port *port; + int err = 0; + + mutex_lock(&devlink->lock); + list_for_each_entry(region, &devlink->region_list, list) { + if (*idx < start) { + (*idx)++; + continue; + } + err = devlink_nl_region_fill(msg, devlink, + DEVLINK_CMD_REGION_GET, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, + NLM_F_MULTI, region); + if (err) + goto out; + (*idx)++; + } + + list_for_each_entry(port, &devlink->port_list, list) { + err = devlink_nl_cmd_region_get_port_dumpit(msg, cb, port, idx, + start); + if (err) + goto out; + } + +out: + mutex_unlock(&devlink->lock); + return err; +} + static int devlink_nl_cmd_region_get_dumpit(struct sk_buff *msg, struct netlink_callback *cb) { - struct devlink_region *region; struct devlink *devlink; int start = cb->args[0]; int idx = 0; @@ -4209,25 +4636,10 @@ static int devlink_nl_cmd_region_get_dumpit(struct sk_buff *msg, list_for_each_entry(devlink, &devlink_list, list) { if (!net_eq(devlink_net(devlink), sock_net(msg->sk))) continue; - - mutex_lock(&devlink->lock); - list_for_each_entry(region, &devlink->region_list, list) { - if (idx < start) { - idx++; - continue; - } - err = devlink_nl_region_fill(msg, devlink, - DEVLINK_CMD_REGION_GET, - NETLINK_CB(cb->skb).portid, - cb->nlh->nlmsg_seq, - NLM_F_MULTI, region); - if (err) { - mutex_unlock(&devlink->lock); - goto out; - } - idx++; - } - mutex_unlock(&devlink->lock); + err = devlink_nl_cmd_region_get_devlink_dumpit(msg, cb, devlink, + &idx, start); + if (err) + goto out; } out: mutex_unlock(&devlink_mutex); @@ -4240,8 +4652,10 @@ static int devlink_nl_cmd_region_del(struct sk_buff *skb, { struct devlink *devlink = info->user_ptr[0]; struct devlink_snapshot *snapshot; + struct devlink_port *port = NULL; struct devlink_region *region; const char *region_name; + unsigned int index; u32 snapshot_id; if (!info->attrs[DEVLINK_ATTR_REGION_NAME] || @@ -4251,7 +4665,19 @@ static int devlink_nl_cmd_region_del(struct sk_buff *skb, region_name = nla_data(info->attrs[DEVLINK_ATTR_REGION_NAME]); snapshot_id = nla_get_u32(info->attrs[DEVLINK_ATTR_REGION_SNAPSHOT_ID]); - region = devlink_region_get_by_name(devlink, region_name); + if (info->attrs[DEVLINK_ATTR_PORT_INDEX]) { + index = nla_get_u32(info->attrs[DEVLINK_ATTR_PORT_INDEX]); + + port = devlink_port_get_by_index(devlink, index); + if (!port) + return -ENODEV; + } + + if (port) + region = devlink_port_region_get_by_name(port, region_name); + else + region = devlink_region_get_by_name(devlink, region_name); + if (!region) return -EINVAL; @@ -4268,9 +4694,11 @@ devlink_nl_cmd_region_new(struct sk_buff *skb, struct genl_info *info) { struct devlink *devlink = info->user_ptr[0]; struct devlink_snapshot *snapshot; + struct devlink_port *port = NULL; struct nlattr *snapshot_id_attr; struct devlink_region *region; const char *region_name; + unsigned int index; u32 snapshot_id; u8 *data; int err; @@ -4281,7 +4709,20 @@ devlink_nl_cmd_region_new(struct sk_buff *skb, struct genl_info *info) } region_name = nla_data(info->attrs[DEVLINK_ATTR_REGION_NAME]); - region = devlink_region_get_by_name(devlink, region_name); + + if (info->attrs[DEVLINK_ATTR_PORT_INDEX]) { + index = nla_get_u32(info->attrs[DEVLINK_ATTR_PORT_INDEX]); + + port = devlink_port_get_by_index(devlink, index); + if (!port) + return -ENODEV; + } + + if (port) + region = devlink_port_region_get_by_name(port, region_name); + else + region = devlink_region_get_by_name(devlink, region_name); + if (!region) { NL_SET_ERR_MSG_MOD(info->extack, "The requested region does not exist"); return -EINVAL; @@ -4317,7 +4758,12 @@ devlink_nl_cmd_region_new(struct sk_buff *skb, struct genl_info *info) } } - err = region->ops->snapshot(devlink, info->extack, &data); + if (port) + err = region->port_ops->snapshot(port, region->port_ops, + info->extack, &data); + else + err = region->ops->snapshot(devlink, region->ops, + info->extack, &data); if (err) goto err_snapshot_capture; @@ -4439,10 +4885,12 @@ static int devlink_nl_cmd_region_read_dumpit(struct sk_buff *skb, const struct genl_dumpit_info *info = genl_dumpit_info(cb); u64 ret_offset, start_offset, end_offset = U64_MAX; struct nlattr **attrs = info->attrs; + struct devlink_port *port = NULL; struct devlink_region *region; struct nlattr *chunks_attr; const char *region_name; struct devlink *devlink; + unsigned int index; void *hdr; int err; @@ -4463,8 +4911,21 @@ static int devlink_nl_cmd_region_read_dumpit(struct sk_buff *skb, goto out_unlock; } + if (info->attrs[DEVLINK_ATTR_PORT_INDEX]) { + index = nla_get_u32(info->attrs[DEVLINK_ATTR_PORT_INDEX]); + + port = devlink_port_get_by_index(devlink, index); + if (!port) + return -ENODEV; + } + region_name = nla_data(attrs[DEVLINK_ATTR_REGION_NAME]); - region = devlink_region_get_by_name(devlink, region_name); + + if (port) + region = devlink_port_region_get_by_name(port, region_name); + else + region = devlink_region_get_by_name(devlink, region_name); + if (!region) { err = -EINVAL; goto out_unlock; @@ -4501,6 +4962,11 @@ static int devlink_nl_cmd_region_read_dumpit(struct sk_buff *skb, if (err) goto nla_put_failure; + if (region->port) + if (nla_put_u32(skb, DEVLINK_ATTR_PORT_INDEX, + region->port->index)) + goto nla_put_failure; + err = nla_put_string(skb, DEVLINK_ATTR_REGION_NAME, region_name); if (err) goto nla_put_failure; @@ -5895,6 +6361,7 @@ devlink_nl_cmd_health_reporter_get_dumpit(struct sk_buff *msg, list_for_each_entry(devlink, &devlink_list, list) { if (!net_eq(devlink_net(devlink), sock_net(msg->sk))) continue; + mutex_lock(&devlink->lock); list_for_each_entry(port, &devlink->port_list, list) { mutex_lock(&port->reporters_lock); list_for_each_entry(reporter, &port->reporter_list, list) { @@ -5909,12 +6376,14 @@ devlink_nl_cmd_health_reporter_get_dumpit(struct sk_buff *msg, NLM_F_MULTI); if (err) { mutex_unlock(&port->reporters_lock); + mutex_unlock(&devlink->lock); goto out; } idx++; } mutex_unlock(&port->reporters_lock); } + mutex_unlock(&devlink->lock); } out: mutex_unlock(&devlink_mutex); @@ -6088,6 +6557,28 @@ devlink_nl_cmd_health_reporter_dump_clear_doit(struct sk_buff *skb, return 0; } +static int devlink_nl_cmd_health_reporter_test_doit(struct sk_buff *skb, + struct genl_info *info) +{ + struct devlink *devlink = info->user_ptr[0]; + struct devlink_health_reporter *reporter; + int err; + + reporter = devlink_health_reporter_get_from_info(devlink, info); + if (!reporter) + return -EINVAL; + + if (!reporter->ops->test) { + devlink_health_reporter_put(reporter); + return -EOPNOTSUPP; + } + + err = reporter->ops->test(reporter, info->extack); + + devlink_health_reporter_put(reporter); + return err; +} + struct devlink_stats { u64 rx_bytes; u64 rx_packets; @@ -6644,6 +7135,24 @@ __devlink_trap_group_action_set(struct devlink *devlink, struct devlink_trap_item *trap_item; int err; + if (devlink->ops->trap_group_action_set) { + err = devlink->ops->trap_group_action_set(devlink, group_item->group, + trap_action, extack); + if (err) + return err; + + list_for_each_entry(trap_item, &devlink->trap_list, list) { + if (strcmp(trap_item->group_item->group->name, group_name)) + continue; + if (trap_item->action != trap_action && + trap_item->trap->type != DEVLINK_TRAP_TYPE_DROP) + continue; + trap_item->action = trap_action; + } + + return 0; + } + list_for_each_entry(trap_item, &devlink->trap_list, list) { if (strcmp(trap_item->group_item->group->name, group_name)) continue; @@ -7000,7 +7509,8 @@ static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = { [DEVLINK_ATTR_BUS_NAME] = { .type = NLA_NUL_STRING }, [DEVLINK_ATTR_DEV_NAME] = { .type = NLA_NUL_STRING }, [DEVLINK_ATTR_PORT_INDEX] = { .type = NLA_U32 }, - [DEVLINK_ATTR_PORT_TYPE] = { .type = NLA_U16 }, + [DEVLINK_ATTR_PORT_TYPE] = NLA_POLICY_RANGE(NLA_U16, DEVLINK_PORT_TYPE_AUTO, + DEVLINK_PORT_TYPE_IB), [DEVLINK_ATTR_PORT_SPLIT_COUNT] = { .type = NLA_U32 }, [DEVLINK_ATTR_SB_INDEX] = { .type = NLA_U32 }, [DEVLINK_ATTR_SB_POOL_INDEX] = { .type = NLA_U16 }, @@ -7009,7 +7519,8 @@ static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = { [DEVLINK_ATTR_SB_POOL_THRESHOLD_TYPE] = { .type = NLA_U8 }, [DEVLINK_ATTR_SB_THRESHOLD] = { .type = NLA_U32 }, [DEVLINK_ATTR_SB_TC_INDEX] = { .type = NLA_U16 }, - [DEVLINK_ATTR_ESWITCH_MODE] = { .type = NLA_U16 }, + [DEVLINK_ATTR_ESWITCH_MODE] = NLA_POLICY_RANGE(NLA_U16, DEVLINK_ESWITCH_MODE_LEGACY, + DEVLINK_ESWITCH_MODE_SWITCHDEV), [DEVLINK_ATTR_ESWITCH_INLINE_MODE] = { .type = NLA_U8 }, [DEVLINK_ATTR_ESWITCH_ENCAP_MODE] = { .type = NLA_U8 }, [DEVLINK_ATTR_DPIPE_TABLE_NAME] = { .type = NLA_NUL_STRING }, @@ -7028,6 +7539,8 @@ static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = { [DEVLINK_ATTR_HEALTH_REPORTER_AUTO_RECOVER] = { .type = NLA_U8 }, [DEVLINK_ATTR_FLASH_UPDATE_FILE_NAME] = { .type = NLA_NUL_STRING }, [DEVLINK_ATTR_FLASH_UPDATE_COMPONENT] = { .type = NLA_NUL_STRING }, + [DEVLINK_ATTR_FLASH_UPDATE_OVERWRITE_MASK] = + NLA_POLICY_BITFIELD32(DEVLINK_SUPPORTED_FLASH_OVERWRITE_SECTIONS), [DEVLINK_ATTR_TRAP_NAME] = { .type = NLA_NUL_STRING }, [DEVLINK_ATTR_TRAP_ACTION] = { .type = NLA_U8 }, [DEVLINK_ATTR_TRAP_GROUP_NAME] = { .type = NLA_NUL_STRING }, @@ -7039,9 +7552,12 @@ static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = { [DEVLINK_ATTR_TRAP_POLICER_RATE] = { .type = NLA_U64 }, [DEVLINK_ATTR_TRAP_POLICER_BURST] = { .type = NLA_U64 }, [DEVLINK_ATTR_PORT_FUNCTION] = { .type = NLA_NESTED }, + [DEVLINK_ATTR_RELOAD_ACTION] = NLA_POLICY_RANGE(NLA_U8, DEVLINK_RELOAD_ACTION_DRIVER_REINIT, + DEVLINK_RELOAD_ACTION_MAX), + [DEVLINK_ATTR_RELOAD_LIMITS] = NLA_POLICY_BITFIELD32(DEVLINK_RELOAD_LIMITS_VALID_MASK), }; -static const struct genl_ops devlink_nl_ops[] = { +static const struct genl_small_ops devlink_nl_ops[] = { { .cmd = DEVLINK_CMD_GET, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, @@ -7309,6 +7825,14 @@ static const struct genl_ops devlink_nl_ops[] = { DEVLINK_NL_FLAG_NO_LOCK, }, { + .cmd = DEVLINK_CMD_HEALTH_REPORTER_TEST, + .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, + .doit = devlink_nl_cmd_health_reporter_test_doit, + .flags = GENL_ADMIN_PERM, + .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK_OR_PORT | + DEVLINK_NL_FLAG_NO_LOCK, + }, + { .cmd = DEVLINK_CMD_FLASH_UPDATE, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = devlink_nl_cmd_flash_update, @@ -7358,12 +7882,41 @@ static struct genl_family devlink_nl_family __ro_after_init = { .pre_doit = devlink_nl_pre_doit, .post_doit = devlink_nl_post_doit, .module = THIS_MODULE, - .ops = devlink_nl_ops, - .n_ops = ARRAY_SIZE(devlink_nl_ops), + .small_ops = devlink_nl_ops, + .n_small_ops = ARRAY_SIZE(devlink_nl_ops), .mcgrps = devlink_nl_mcgrps, .n_mcgrps = ARRAY_SIZE(devlink_nl_mcgrps), }; +static bool devlink_reload_actions_valid(const struct devlink_ops *ops) +{ + const struct devlink_reload_combination *comb; + int i; + + if (!devlink_reload_supported(ops)) { + if (WARN_ON(ops->reload_actions)) + return false; + return true; + } + + if (WARN_ON(!ops->reload_actions || + ops->reload_actions & BIT(DEVLINK_RELOAD_ACTION_UNSPEC) || + ops->reload_actions >= BIT(__DEVLINK_RELOAD_ACTION_MAX))) + return false; + + if (WARN_ON(ops->reload_limits & BIT(DEVLINK_RELOAD_LIMIT_UNSPEC) || + ops->reload_limits >= BIT(__DEVLINK_RELOAD_LIMIT_MAX))) + return false; + + for (i = 0; i < ARRAY_SIZE(devlink_reload_invalid_combinations); i++) { + comb = &devlink_reload_invalid_combinations[i]; + if (ops->reload_actions == BIT(comb->action) && + ops->reload_limits == BIT(comb->limit)) + return false; + } + return true; +} + /** * devlink_alloc - Allocate new devlink instance resources * @@ -7380,6 +7933,9 @@ struct devlink *devlink_alloc(const struct devlink_ops *ops, size_t priv_size) if (WARN_ON(!ops)) return NULL; + if (!devlink_reload_actions_valid(ops)) + return NULL; + devlink = kzalloc(sizeof(*devlink) + priv_size, GFP_KERNEL); if (!devlink) return NULL; @@ -7428,7 +7984,7 @@ EXPORT_SYMBOL_GPL(devlink_register); void devlink_unregister(struct devlink *devlink) { mutex_lock(&devlink_mutex); - WARN_ON(devlink_reload_supported(devlink) && + WARN_ON(devlink_reload_supported(devlink->ops) && devlink->reload_enabled); devlink_notify(devlink, DEVLINK_CMD_DEL); list_del(&devlink->list); @@ -7506,7 +8062,8 @@ static bool devlink_port_type_should_warn(struct devlink_port *devlink_port) { /* Ignore CPU and DSA flavours. */ return devlink_port->attrs.flavour != DEVLINK_PORT_FLAVOUR_CPU && - devlink_port->attrs.flavour != DEVLINK_PORT_FLAVOUR_DSA; + devlink_port->attrs.flavour != DEVLINK_PORT_FLAVOUR_DSA && + devlink_port->attrs.flavour != DEVLINK_PORT_FLAVOUR_UNUSED; } #define DEVLINK_PORT_TYPE_WARN_TIMEOUT (HZ * 3600) @@ -7555,11 +8112,12 @@ int devlink_port_register(struct devlink *devlink, devlink_port->index = port_index; devlink_port->registered = true; spin_lock_init(&devlink_port->type_lock); + INIT_LIST_HEAD(&devlink_port->reporter_list); + mutex_init(&devlink_port->reporters_lock); list_add_tail(&devlink_port->list, &devlink->port_list); INIT_LIST_HEAD(&devlink_port->param_list); + INIT_LIST_HEAD(&devlink_port->region_list); mutex_unlock(&devlink->lock); - INIT_LIST_HEAD(&devlink_port->reporter_list); - mutex_init(&devlink_port->reporters_lock); INIT_DELAYED_WORK(&devlink_port->type_warn_dw, &devlink_port_type_warn); devlink_port_type_warn_schedule(devlink_port); devlink_port_notify(devlink_port, DEVLINK_CMD_PORT_NEW); @@ -7576,13 +8134,14 @@ void devlink_port_unregister(struct devlink_port *devlink_port) { struct devlink *devlink = devlink_port->devlink; - WARN_ON(!list_empty(&devlink_port->reporter_list)); - mutex_destroy(&devlink_port->reporters_lock); devlink_port_type_warn_cancel(devlink_port); devlink_port_notify(devlink_port, DEVLINK_CMD_PORT_DEL); mutex_lock(&devlink->lock); list_del(&devlink_port->list); mutex_unlock(&devlink->lock); + WARN_ON(!list_empty(&devlink_port->reporter_list)); + WARN_ON(!list_empty(&devlink_port->region_list)); + mutex_destroy(&devlink_port->reporters_lock); } EXPORT_SYMBOL_GPL(devlink_port_unregister); @@ -7600,14 +8159,8 @@ static void __devlink_port_type_set(struct devlink_port *devlink_port, devlink_port_notify(devlink_port, DEVLINK_CMD_PORT_NEW); } -/** - * devlink_port_type_eth_set - Set port type to Ethernet - * - * @devlink_port: devlink port - * @netdev: related netdevice - */ -void devlink_port_type_eth_set(struct devlink_port *devlink_port, - struct net_device *netdev) +static void devlink_port_type_netdev_checks(struct devlink_port *devlink_port, + struct net_device *netdev) { const struct net_device_ops *ops = netdev->netdev_ops; @@ -7641,6 +8194,24 @@ void devlink_port_type_eth_set(struct devlink_port *devlink_port, err = ops->ndo_get_port_parent_id(netdev, &ppid); WARN_ON(err != -EOPNOTSUPP); } +} + +/** + * devlink_port_type_eth_set - Set port type to Ethernet + * + * @devlink_port: devlink port + * @netdev: related netdevice + */ +void devlink_port_type_eth_set(struct devlink_port *devlink_port, + struct net_device *netdev) +{ + if (netdev) + devlink_port_type_netdev_checks(devlink_port, netdev); + else + dev_warn(devlink_port->devlink->dev, + "devlink port type for port %d set to Ethernet without a software interface reference, device type not supported by the kernel?\n", + devlink_port->index); + __devlink_port_type_set(devlink_port, DEVLINK_PORT_TYPE_ETH, netdev); } EXPORT_SYMBOL_GPL(devlink_port_type_eth_set); @@ -7712,9 +8283,12 @@ EXPORT_SYMBOL_GPL(devlink_port_attrs_set); * devlink_port_attrs_pci_pf_set - Set PCI PF port attributes * * @devlink_port: devlink port + * @controller: associated controller number for the devlink port instance * @pf: associated PF for the devlink port instance + * @external: indicates if the port is for an external controller */ -void devlink_port_attrs_pci_pf_set(struct devlink_port *devlink_port, u16 pf) +void devlink_port_attrs_pci_pf_set(struct devlink_port *devlink_port, u32 controller, + u16 pf, bool external) { struct devlink_port_attrs *attrs = &devlink_port->attrs; int ret; @@ -7723,8 +8297,9 @@ void devlink_port_attrs_pci_pf_set(struct devlink_port *devlink_port, u16 pf) DEVLINK_PORT_FLAVOUR_PCI_PF); if (ret) return; - + attrs->pci_pf.controller = controller; attrs->pci_pf.pf = pf; + attrs->pci_pf.external = external; } EXPORT_SYMBOL_GPL(devlink_port_attrs_pci_pf_set); @@ -7732,11 +8307,13 @@ EXPORT_SYMBOL_GPL(devlink_port_attrs_pci_pf_set); * devlink_port_attrs_pci_vf_set - Set PCI VF port attributes * * @devlink_port: devlink port + * @controller: associated controller number for the devlink port instance * @pf: associated PF for the devlink port instance * @vf: associated VF of a PF for the devlink port instance + * @external: indicates if the port is for an external controller */ -void devlink_port_attrs_pci_vf_set(struct devlink_port *devlink_port, - u16 pf, u16 vf) +void devlink_port_attrs_pci_vf_set(struct devlink_port *devlink_port, u32 controller, + u16 pf, u16 vf, bool external) { struct devlink_port_attrs *attrs = &devlink_port->attrs; int ret; @@ -7745,8 +8322,10 @@ void devlink_port_attrs_pci_vf_set(struct devlink_port *devlink_port, DEVLINK_PORT_FLAVOUR_PCI_VF); if (ret) return; + attrs->pci_vf.controller = controller; attrs->pci_vf.pf = pf; attrs->pci_vf.vf = vf; + attrs->pci_vf.external = external; } EXPORT_SYMBOL_GPL(devlink_port_attrs_pci_vf_set); @@ -7771,15 +8350,30 @@ static int __devlink_port_phys_port_name_get(struct devlink_port *devlink_port, break; case DEVLINK_PORT_FLAVOUR_CPU: case DEVLINK_PORT_FLAVOUR_DSA: + case DEVLINK_PORT_FLAVOUR_UNUSED: /* As CPU and DSA ports do not have a netdevice associated * case should not ever happen. */ WARN_ON(1); return -EINVAL; case DEVLINK_PORT_FLAVOUR_PCI_PF: + if (attrs->pci_pf.external) { + n = snprintf(name, len, "c%u", attrs->pci_pf.controller); + if (n >= len) + return -EINVAL; + len -= n; + name += n; + } n = snprintf(name, len, "pf%u", attrs->pci_pf.pf); break; case DEVLINK_PORT_FLAVOUR_PCI_VF: + if (attrs->pci_vf.external) { + n = snprintf(name, len, "c%u", attrs->pci_vf.controller); + if (n >= len) + return -EINVAL; + len -= n; + name += n; + } n = snprintf(name, len, "pf%uvf%u", attrs->pci_vf.pf, attrs->pci_vf.vf); break; @@ -8431,7 +9025,7 @@ __devlink_param_driverinit_value_set(struct devlink *devlink, int devlink_param_driverinit_value_get(struct devlink *devlink, u32 param_id, union devlink_param_value *init_val) { - if (!devlink_reload_supported(devlink)) + if (!devlink_reload_supported(devlink->ops)) return -EOPNOTSUPP; return __devlink_param_driverinit_value_get(&devlink->param_list, @@ -8478,7 +9072,7 @@ int devlink_port_param_driverinit_value_get(struct devlink_port *devlink_port, { struct devlink *devlink = devlink_port->devlink; - if (!devlink_reload_supported(devlink)) + if (!devlink_reload_supported(devlink->ops)) return -EOPNOTSUPP; return __devlink_param_driverinit_value_get(&devlink_port->param_list, @@ -8627,6 +9221,57 @@ unlock: EXPORT_SYMBOL_GPL(devlink_region_create); /** + * devlink_port_region_create - create a new address region for a port + * + * @port: devlink port + * @ops: region operations and name + * @region_max_snapshots: Maximum supported number of snapshots for region + * @region_size: size of region + */ +struct devlink_region * +devlink_port_region_create(struct devlink_port *port, + const struct devlink_port_region_ops *ops, + u32 region_max_snapshots, u64 region_size) +{ + struct devlink *devlink = port->devlink; + struct devlink_region *region; + int err = 0; + + if (WARN_ON(!ops) || WARN_ON(!ops->destructor)) + return ERR_PTR(-EINVAL); + + mutex_lock(&devlink->lock); + + if (devlink_port_region_get_by_name(port, ops->name)) { + err = -EEXIST; + goto unlock; + } + + region = kzalloc(sizeof(*region), GFP_KERNEL); + if (!region) { + err = -ENOMEM; + goto unlock; + } + + region->devlink = devlink; + region->port = port; + region->max_snapshots = region_max_snapshots; + region->port_ops = ops; + region->size = region_size; + INIT_LIST_HEAD(®ion->snapshot_list); + list_add_tail(®ion->list, &port->region_list); + devlink_nl_region_notify(region, NULL, DEVLINK_CMD_REGION_NEW); + + mutex_unlock(&devlink->lock); + return region; + +unlock: + mutex_unlock(&devlink->lock); + return ERR_PTR(err); +} +EXPORT_SYMBOL_GPL(devlink_port_region_create); + +/** * devlink_region_destroy - destroy address region * * @region: devlink region to destroy @@ -8803,6 +9448,22 @@ static const struct devlink_trap devlink_trap_generic[] = { DEVLINK_TRAP(FLOW_ACTION_SAMPLE, CONTROL), DEVLINK_TRAP(FLOW_ACTION_TRAP, CONTROL), DEVLINK_TRAP(EARLY_DROP, DROP), + DEVLINK_TRAP(VXLAN_PARSING, DROP), + DEVLINK_TRAP(LLC_SNAP_PARSING, DROP), + DEVLINK_TRAP(VLAN_PARSING, DROP), + DEVLINK_TRAP(PPPOE_PPP_PARSING, DROP), + DEVLINK_TRAP(MPLS_PARSING, DROP), + DEVLINK_TRAP(ARP_PARSING, DROP), + DEVLINK_TRAP(IP_1_PARSING, DROP), + DEVLINK_TRAP(IP_N_PARSING, DROP), + DEVLINK_TRAP(GRE_PARSING, DROP), + DEVLINK_TRAP(UDP_PARSING, DROP), + DEVLINK_TRAP(TCP_PARSING, DROP), + DEVLINK_TRAP(IPSEC_PARSING, DROP), + DEVLINK_TRAP(SCTP_PARSING, DROP), + DEVLINK_TRAP(DCCP_PARSING, DROP), + DEVLINK_TRAP(GTP_PARSING, DROP), + DEVLINK_TRAP(ESP_PARSING, DROP), }; #define DEVLINK_TRAP_GROUP(_id) \ @@ -8837,6 +9498,7 @@ static const struct devlink_trap_group devlink_trap_group_generic[] = { DEVLINK_TRAP_GROUP(PTP_GENERAL), DEVLINK_TRAP_GROUP(ACL_SAMPLE), DEVLINK_TRAP_GROUP(ACL_TRAP), + DEVLINK_TRAP_GROUP(PARSER_ERROR_DROPS), }; static int devlink_trap_generic_verify(const struct devlink_trap *trap) @@ -9139,20 +9801,19 @@ devlink_trap_stats_update(struct devlink_stats __percpu *trap_stats, } static void -devlink_trap_report_metadata_fill(struct net_dm_hw_metadata *hw_metadata, - const struct devlink_trap_item *trap_item, - struct devlink_port *in_devlink_port, - const struct flow_action_cookie *fa_cookie) +devlink_trap_report_metadata_set(struct devlink_trap_metadata *metadata, + const struct devlink_trap_item *trap_item, + struct devlink_port *in_devlink_port, + const struct flow_action_cookie *fa_cookie) { - struct devlink_trap_group_item *group_item = trap_item->group_item; - - hw_metadata->trap_group_name = group_item->group->name; - hw_metadata->trap_name = trap_item->trap->name; - hw_metadata->fa_cookie = fa_cookie; + metadata->trap_name = trap_item->trap->name; + metadata->trap_group_name = trap_item->group_item->group->name; + metadata->fa_cookie = fa_cookie; + metadata->trap_type = trap_item->trap->type; spin_lock(&in_devlink_port->type_lock); if (in_devlink_port->type == DEVLINK_PORT_TYPE_ETH) - hw_metadata->input_dev = in_devlink_port->type_dev; + metadata->input_dev = in_devlink_port->type_dev; spin_unlock(&in_devlink_port->type_lock); } @@ -9170,21 +9831,17 @@ void devlink_trap_report(struct devlink *devlink, struct sk_buff *skb, { struct devlink_trap_item *trap_item = trap_ctx; - struct net_dm_hw_metadata hw_metadata = {}; devlink_trap_stats_update(trap_item->stats, skb->len); devlink_trap_stats_update(trap_item->group_item->stats, skb->len); - /* Control packets were not dropped by the device or encountered an - * exception during forwarding and therefore should not be reported to - * the kernel's drop monitor. - */ - if (trap_item->trap->type == DEVLINK_TRAP_TYPE_CONTROL) - return; + if (trace_devlink_trap_report_enabled()) { + struct devlink_trap_metadata metadata = {}; - devlink_trap_report_metadata_fill(&hw_metadata, trap_item, - in_devlink_port, fa_cookie); - net_dm_hw_report(skb, &hw_metadata); + devlink_trap_report_metadata_set(&metadata, trap_item, + in_devlink_port, fa_cookie); + trace_devlink_trap_report(devlink, skb, &metadata); + } } EXPORT_SYMBOL_GPL(devlink_trap_report); @@ -9543,6 +10200,7 @@ out: int devlink_compat_flash_update(struct net_device *dev, const char *file_name) { + struct devlink_flash_update_params params = {}; struct devlink *devlink; int ret; @@ -9555,8 +10213,10 @@ int devlink_compat_flash_update(struct net_device *dev, const char *file_name) goto out; } + params.file_name = file_name; + mutex_lock(&devlink->lock); - ret = devlink->ops->flash_update(devlink, file_name, NULL, NULL); + ret = devlink->ops->flash_update(devlink, ¶ms, NULL); mutex_unlock(&devlink->lock); out: @@ -9605,6 +10265,7 @@ int devlink_compat_switch_id_get(struct net_device *dev, static void __net_exit devlink_pernet_pre_exit(struct net *net) { struct devlink *devlink; + u32 actions_performed; int err; /* In case network namespace is getting destroyed, reload @@ -9613,9 +10274,12 @@ static void __net_exit devlink_pernet_pre_exit(struct net *net) mutex_lock(&devlink_mutex); list_for_each_entry(devlink, &devlink_list, list) { if (net_eq(devlink_net(devlink), net)) { - if (WARN_ON(!devlink_reload_supported(devlink))) + if (WARN_ON(!devlink_reload_supported(devlink->ops))) continue; - err = devlink_reload(devlink, &init_net, NULL); + err = devlink_reload(devlink, &init_net, + DEVLINK_RELOAD_ACTION_DRIVER_REINIT, + DEVLINK_RELOAD_LIMIT_UNSPEC, + &actions_performed, NULL); if (err && err != -EOPNOTSUPP) pr_warn("Failed to reload devlink instance into init_net\n"); } diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c index 9704522b0872..571f191c06d9 100644 --- a/net/core/drop_monitor.c +++ b/net/core/drop_monitor.c @@ -26,13 +26,14 @@ #include <linux/bitops.h> #include <linux/slab.h> #include <linux/module.h> -#include <net/drop_monitor.h> #include <net/genetlink.h> #include <net/netevent.h> #include <net/flow_offload.h> +#include <net/devlink.h> #include <trace/events/skb.h> #include <trace/events/napi.h> +#include <trace/events/devlink.h> #include <asm/unaligned.h> @@ -114,13 +115,14 @@ struct net_dm_alert_ops { int work, int budget); void (*work_item_func)(struct work_struct *work); void (*hw_work_item_func)(struct work_struct *work); - void (*hw_probe)(struct sk_buff *skb, - const struct net_dm_hw_metadata *hw_metadata); + void (*hw_trap_probe)(void *ignore, const struct devlink *devlink, + struct sk_buff *skb, + const struct devlink_trap_metadata *metadata); }; struct net_dm_skb_cb { union { - struct net_dm_hw_metadata *hw_metadata; + struct devlink_trap_metadata *hw_metadata; void *pc; }; }; @@ -432,8 +434,9 @@ out: } static void -net_dm_hw_summary_probe(struct sk_buff *skb, - const struct net_dm_hw_metadata *hw_metadata) +net_dm_hw_trap_summary_probe(void *ignore, const struct devlink *devlink, + struct sk_buff *skb, + const struct devlink_trap_metadata *metadata) { struct net_dm_hw_entries *hw_entries; struct net_dm_hw_entry *hw_entry; @@ -441,6 +444,9 @@ net_dm_hw_summary_probe(struct sk_buff *skb, unsigned long flags; int i; + if (metadata->trap_type == DEVLINK_TRAP_TYPE_CONTROL) + return; + hw_data = this_cpu_ptr(&dm_hw_cpu_data); spin_lock_irqsave(&hw_data->lock, flags); hw_entries = hw_data->hw_entries; @@ -450,7 +456,7 @@ net_dm_hw_summary_probe(struct sk_buff *skb, for (i = 0; i < hw_entries->num_entries; i++) { hw_entry = &hw_entries->entries[i]; - if (!strncmp(hw_entry->trap_name, hw_metadata->trap_name, + if (!strncmp(hw_entry->trap_name, metadata->trap_name, NET_DM_MAX_HW_TRAP_NAME_LEN - 1)) { hw_entry->count++; goto out; @@ -460,7 +466,7 @@ net_dm_hw_summary_probe(struct sk_buff *skb, goto out; hw_entry = &hw_entries->entries[hw_entries->num_entries]; - strlcpy(hw_entry->trap_name, hw_metadata->trap_name, + strlcpy(hw_entry->trap_name, metadata->trap_name, NET_DM_MAX_HW_TRAP_NAME_LEN - 1); hw_entry->count = 1; hw_entries->num_entries++; @@ -479,7 +485,7 @@ static const struct net_dm_alert_ops net_dm_alert_summary_ops = { .napi_poll_probe = trace_napi_poll_hit, .work_item_func = send_dm_alert, .hw_work_item_func = net_dm_hw_summary_work, - .hw_probe = net_dm_hw_summary_probe, + .hw_trap_probe = net_dm_hw_trap_summary_probe, }; static void net_dm_packet_trace_kfree_skb_hit(void *ignore, @@ -705,7 +711,7 @@ static void net_dm_packet_work(struct work_struct *work) } static size_t -net_dm_flow_action_cookie_size(const struct net_dm_hw_metadata *hw_metadata) +net_dm_flow_action_cookie_size(const struct devlink_trap_metadata *hw_metadata) { return hw_metadata->fa_cookie ? nla_total_size(hw_metadata->fa_cookie->cookie_len) : 0; @@ -713,7 +719,7 @@ net_dm_flow_action_cookie_size(const struct net_dm_hw_metadata *hw_metadata) static size_t net_dm_hw_packet_report_size(size_t payload_len, - const struct net_dm_hw_metadata *hw_metadata) + const struct devlink_trap_metadata *hw_metadata) { size_t size; @@ -743,7 +749,7 @@ net_dm_hw_packet_report_size(size_t payload_len, static int net_dm_hw_packet_report_fill(struct sk_buff *msg, struct sk_buff *skb, size_t payload_len) { - struct net_dm_hw_metadata *hw_metadata; + struct devlink_trap_metadata *hw_metadata; struct nlattr *attr; void *hdr; @@ -810,56 +816,56 @@ nla_put_failure: return -EMSGSIZE; } -static struct net_dm_hw_metadata * -net_dm_hw_metadata_clone(const struct net_dm_hw_metadata *hw_metadata) +static struct devlink_trap_metadata * +net_dm_hw_metadata_copy(const struct devlink_trap_metadata *metadata) { const struct flow_action_cookie *fa_cookie; - struct net_dm_hw_metadata *n_hw_metadata; + struct devlink_trap_metadata *hw_metadata; const char *trap_group_name; const char *trap_name; - n_hw_metadata = kzalloc(sizeof(*hw_metadata), GFP_ATOMIC); - if (!n_hw_metadata) + hw_metadata = kzalloc(sizeof(*hw_metadata), GFP_ATOMIC); + if (!hw_metadata) return NULL; - trap_group_name = kstrdup(hw_metadata->trap_group_name, GFP_ATOMIC); + trap_group_name = kstrdup(metadata->trap_group_name, GFP_ATOMIC); if (!trap_group_name) goto free_hw_metadata; - n_hw_metadata->trap_group_name = trap_group_name; + hw_metadata->trap_group_name = trap_group_name; - trap_name = kstrdup(hw_metadata->trap_name, GFP_ATOMIC); + trap_name = kstrdup(metadata->trap_name, GFP_ATOMIC); if (!trap_name) goto free_trap_group; - n_hw_metadata->trap_name = trap_name; + hw_metadata->trap_name = trap_name; - if (hw_metadata->fa_cookie) { + if (metadata->fa_cookie) { size_t cookie_size = sizeof(*fa_cookie) + - hw_metadata->fa_cookie->cookie_len; + metadata->fa_cookie->cookie_len; - fa_cookie = kmemdup(hw_metadata->fa_cookie, cookie_size, + fa_cookie = kmemdup(metadata->fa_cookie, cookie_size, GFP_ATOMIC); if (!fa_cookie) goto free_trap_name; - n_hw_metadata->fa_cookie = fa_cookie; + hw_metadata->fa_cookie = fa_cookie; } - n_hw_metadata->input_dev = hw_metadata->input_dev; - if (n_hw_metadata->input_dev) - dev_hold(n_hw_metadata->input_dev); + hw_metadata->input_dev = metadata->input_dev; + if (hw_metadata->input_dev) + dev_hold(hw_metadata->input_dev); - return n_hw_metadata; + return hw_metadata; free_trap_name: kfree(trap_name); free_trap_group: kfree(trap_group_name); free_hw_metadata: - kfree(n_hw_metadata); + kfree(hw_metadata); return NULL; } static void -net_dm_hw_metadata_free(const struct net_dm_hw_metadata *hw_metadata) +net_dm_hw_metadata_free(const struct devlink_trap_metadata *hw_metadata) { if (hw_metadata->input_dev) dev_put(hw_metadata->input_dev); @@ -871,7 +877,7 @@ net_dm_hw_metadata_free(const struct net_dm_hw_metadata *hw_metadata) static void net_dm_hw_packet_report(struct sk_buff *skb) { - struct net_dm_hw_metadata *hw_metadata; + struct devlink_trap_metadata *hw_metadata; struct sk_buff *msg; size_t payload_len; int rc; @@ -924,15 +930,19 @@ static void net_dm_hw_packet_work(struct work_struct *work) } static void -net_dm_hw_packet_probe(struct sk_buff *skb, - const struct net_dm_hw_metadata *hw_metadata) +net_dm_hw_trap_packet_probe(void *ignore, const struct devlink *devlink, + struct sk_buff *skb, + const struct devlink_trap_metadata *metadata) { - struct net_dm_hw_metadata *n_hw_metadata; + struct devlink_trap_metadata *n_hw_metadata; ktime_t tstamp = ktime_get_real(); struct per_cpu_dm_data *hw_data; struct sk_buff *nskb; unsigned long flags; + if (metadata->trap_type == DEVLINK_TRAP_TYPE_CONTROL) + return; + if (!skb_mac_header_was_set(skb)) return; @@ -940,7 +950,7 @@ net_dm_hw_packet_probe(struct sk_buff *skb, if (!nskb) return; - n_hw_metadata = net_dm_hw_metadata_clone(hw_metadata); + n_hw_metadata = net_dm_hw_metadata_copy(metadata); if (!n_hw_metadata) goto free; @@ -975,7 +985,7 @@ static const struct net_dm_alert_ops net_dm_alert_packet_ops = { .napi_poll_probe = net_dm_packet_trace_napi_poll_hit, .work_item_func = net_dm_packet_work, .hw_work_item_func = net_dm_hw_packet_work, - .hw_probe = net_dm_hw_packet_probe, + .hw_trap_probe = net_dm_hw_trap_packet_probe, }; static const struct net_dm_alert_ops *net_dm_alert_ops_arr[] = { @@ -983,25 +993,32 @@ static const struct net_dm_alert_ops *net_dm_alert_ops_arr[] = { [NET_DM_ALERT_MODE_PACKET] = &net_dm_alert_packet_ops, }; -void net_dm_hw_report(struct sk_buff *skb, - const struct net_dm_hw_metadata *hw_metadata) +#if IS_ENABLED(CONFIG_NET_DEVLINK) +static int net_dm_hw_probe_register(const struct net_dm_alert_ops *ops) { - rcu_read_lock(); - - if (!monitor_hw) - goto out; + return register_trace_devlink_trap_report(ops->hw_trap_probe, NULL); +} - net_dm_alert_ops_arr[net_dm_alert_mode]->hw_probe(skb, hw_metadata); +static void net_dm_hw_probe_unregister(const struct net_dm_alert_ops *ops) +{ + unregister_trace_devlink_trap_report(ops->hw_trap_probe, NULL); + tracepoint_synchronize_unregister(); +} +#else +static int net_dm_hw_probe_register(const struct net_dm_alert_ops *ops) +{ + return -EOPNOTSUPP; +} -out: - rcu_read_unlock(); +static void net_dm_hw_probe_unregister(const struct net_dm_alert_ops *ops) +{ } -EXPORT_SYMBOL_GPL(net_dm_hw_report); +#endif static int net_dm_hw_monitor_start(struct netlink_ext_ack *extack) { const struct net_dm_alert_ops *ops; - int cpu; + int cpu, rc; if (monitor_hw) { NL_SET_ERR_MSG_MOD(extack, "Hardware monitoring already enabled"); @@ -1025,13 +1042,24 @@ static int net_dm_hw_monitor_start(struct netlink_ext_ack *extack) kfree(hw_entries); } + rc = net_dm_hw_probe_register(ops); + if (rc) { + NL_SET_ERR_MSG_MOD(extack, "Failed to connect probe to devlink_trap_probe() tracepoint"); + goto err_module_put; + } + monitor_hw = true; return 0; + +err_module_put: + module_put(THIS_MODULE); + return rc; } static void net_dm_hw_monitor_stop(struct netlink_ext_ack *extack) { + const struct net_dm_alert_ops *ops; int cpu; if (!monitor_hw) { @@ -1039,12 +1067,11 @@ static void net_dm_hw_monitor_stop(struct netlink_ext_ack *extack) return; } + ops = net_dm_alert_ops_arr[net_dm_alert_mode]; + monitor_hw = false; - /* After this call returns we are guaranteed that no CPU is processing - * any hardware drops. - */ - synchronize_rcu(); + net_dm_hw_probe_unregister(ops); for_each_possible_cpu(cpu) { struct per_cpu_dm_data *hw_data = &per_cpu(dm_hw_cpu_data, cpu); @@ -1053,7 +1080,7 @@ static void net_dm_hw_monitor_stop(struct netlink_ext_ack *extack) del_timer_sync(&hw_data->send_timer); cancel_work_sync(&hw_data->dm_alert_work); while ((skb = __skb_dequeue(&hw_data->drop_queue))) { - struct net_dm_hw_metadata *hw_metadata; + struct devlink_trap_metadata *hw_metadata; hw_metadata = NET_DM_SKB_CB(skb)->hw_metadata; net_dm_hw_metadata_free(hw_metadata); @@ -1548,7 +1575,7 @@ static const struct nla_policy net_dm_nl_policy[NET_DM_ATTR_MAX + 1] = { [NET_DM_ATTR_HW_DROPS] = {. type = NLA_FLAG }, }; -static const struct genl_ops dropmon_ops[] = { +static const struct genl_small_ops dropmon_ops[] = { { .cmd = NET_DM_CMD_CONFIG, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, @@ -1598,8 +1625,8 @@ static struct genl_family net_drop_monitor_family __ro_after_init = { .pre_doit = net_dm_nl_pre_doit, .post_doit = net_dm_nl_post_doit, .module = THIS_MODULE, - .ops = dropmon_ops, - .n_ops = ARRAY_SIZE(dropmon_ops), + .small_ops = dropmon_ops, + .n_small_ops = ARRAY_SIZE(dropmon_ops), .mcgrps = dropmon_mcgrps, .n_mcgrps = ARRAY_SIZE(dropmon_mcgrps), }; diff --git a/net/core/filter.c b/net/core/filter.c index b5f3faac5e3b..c5e2a1c5fd8d 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -76,6 +76,10 @@ #include <net/bpf_sk_storage.h> #include <net/transp_v6.h> #include <linux/btf_ids.h> +#include <net/tls.h> + +static const struct bpf_func_proto * +bpf_sk_base_func_proto(enum bpf_func_id func_id); int copy_bpf_fprog_from_user(struct sock_fprog *dst, sockptr_t src, int len) { @@ -2160,13 +2164,234 @@ static int __bpf_redirect(struct sk_buff *skb, struct net_device *dev, return __bpf_redirect_no_mac(skb, dev, flags); } +#if IS_ENABLED(CONFIG_IPV6) +static int bpf_out_neigh_v6(struct net *net, struct sk_buff *skb) +{ + struct dst_entry *dst = skb_dst(skb); + struct net_device *dev = dst->dev; + u32 hh_len = LL_RESERVED_SPACE(dev); + const struct in6_addr *nexthop; + struct neighbour *neigh; + + if (dev_xmit_recursion()) { + net_crit_ratelimited("bpf: recursion limit reached on datapath, buggy bpf program?\n"); + goto out_drop; + } + + skb->dev = dev; + skb->tstamp = 0; + + if (unlikely(skb_headroom(skb) < hh_len && dev->header_ops)) { + struct sk_buff *skb2; + + skb2 = skb_realloc_headroom(skb, hh_len); + if (unlikely(!skb2)) { + kfree_skb(skb); + return -ENOMEM; + } + if (skb->sk) + skb_set_owner_w(skb2, skb->sk); + consume_skb(skb); + skb = skb2; + } + + rcu_read_lock_bh(); + nexthop = rt6_nexthop(container_of(dst, struct rt6_info, dst), + &ipv6_hdr(skb)->daddr); + neigh = ip_neigh_gw6(dev, nexthop); + if (likely(!IS_ERR(neigh))) { + int ret; + + sock_confirm_neigh(skb, neigh); + dev_xmit_recursion_inc(); + ret = neigh_output(neigh, skb, false); + dev_xmit_recursion_dec(); + rcu_read_unlock_bh(); + return ret; + } + rcu_read_unlock_bh(); + IP6_INC_STATS(dev_net(dst->dev), + ip6_dst_idev(dst), IPSTATS_MIB_OUTNOROUTES); +out_drop: + kfree_skb(skb); + return -ENETDOWN; +} + +static int __bpf_redirect_neigh_v6(struct sk_buff *skb, struct net_device *dev) +{ + const struct ipv6hdr *ip6h = ipv6_hdr(skb); + struct net *net = dev_net(dev); + int err, ret = NET_XMIT_DROP; + struct dst_entry *dst; + struct flowi6 fl6 = { + .flowi6_flags = FLOWI_FLAG_ANYSRC, + .flowi6_mark = skb->mark, + .flowlabel = ip6_flowinfo(ip6h), + .flowi6_oif = dev->ifindex, + .flowi6_proto = ip6h->nexthdr, + .daddr = ip6h->daddr, + .saddr = ip6h->saddr, + }; + + dst = ipv6_stub->ipv6_dst_lookup_flow(net, NULL, &fl6, NULL); + if (IS_ERR(dst)) + goto out_drop; + + skb_dst_set(skb, dst); + + err = bpf_out_neigh_v6(net, skb); + if (unlikely(net_xmit_eval(err))) + dev->stats.tx_errors++; + else + ret = NET_XMIT_SUCCESS; + goto out_xmit; +out_drop: + dev->stats.tx_errors++; + kfree_skb(skb); +out_xmit: + return ret; +} +#else +static int __bpf_redirect_neigh_v6(struct sk_buff *skb, struct net_device *dev) +{ + kfree_skb(skb); + return NET_XMIT_DROP; +} +#endif /* CONFIG_IPV6 */ + +#if IS_ENABLED(CONFIG_INET) +static int bpf_out_neigh_v4(struct net *net, struct sk_buff *skb) +{ + struct dst_entry *dst = skb_dst(skb); + struct rtable *rt = container_of(dst, struct rtable, dst); + struct net_device *dev = dst->dev; + u32 hh_len = LL_RESERVED_SPACE(dev); + struct neighbour *neigh; + bool is_v6gw = false; + + if (dev_xmit_recursion()) { + net_crit_ratelimited("bpf: recursion limit reached on datapath, buggy bpf program?\n"); + goto out_drop; + } + + skb->dev = dev; + skb->tstamp = 0; + + if (unlikely(skb_headroom(skb) < hh_len && dev->header_ops)) { + struct sk_buff *skb2; + + skb2 = skb_realloc_headroom(skb, hh_len); + if (unlikely(!skb2)) { + kfree_skb(skb); + return -ENOMEM; + } + if (skb->sk) + skb_set_owner_w(skb2, skb->sk); + consume_skb(skb); + skb = skb2; + } + + rcu_read_lock_bh(); + neigh = ip_neigh_for_gw(rt, skb, &is_v6gw); + if (likely(!IS_ERR(neigh))) { + int ret; + + sock_confirm_neigh(skb, neigh); + dev_xmit_recursion_inc(); + ret = neigh_output(neigh, skb, is_v6gw); + dev_xmit_recursion_dec(); + rcu_read_unlock_bh(); + return ret; + } + rcu_read_unlock_bh(); +out_drop: + kfree_skb(skb); + return -ENETDOWN; +} + +static int __bpf_redirect_neigh_v4(struct sk_buff *skb, struct net_device *dev) +{ + const struct iphdr *ip4h = ip_hdr(skb); + struct net *net = dev_net(dev); + int err, ret = NET_XMIT_DROP; + struct rtable *rt; + struct flowi4 fl4 = { + .flowi4_flags = FLOWI_FLAG_ANYSRC, + .flowi4_mark = skb->mark, + .flowi4_tos = RT_TOS(ip4h->tos), + .flowi4_oif = dev->ifindex, + .flowi4_proto = ip4h->protocol, + .daddr = ip4h->daddr, + .saddr = ip4h->saddr, + }; + + rt = ip_route_output_flow(net, &fl4, NULL); + if (IS_ERR(rt)) + goto out_drop; + if (rt->rt_type != RTN_UNICAST && rt->rt_type != RTN_LOCAL) { + ip_rt_put(rt); + goto out_drop; + } + + skb_dst_set(skb, &rt->dst); + + err = bpf_out_neigh_v4(net, skb); + if (unlikely(net_xmit_eval(err))) + dev->stats.tx_errors++; + else + ret = NET_XMIT_SUCCESS; + goto out_xmit; +out_drop: + dev->stats.tx_errors++; + kfree_skb(skb); +out_xmit: + return ret; +} +#else +static int __bpf_redirect_neigh_v4(struct sk_buff *skb, struct net_device *dev) +{ + kfree_skb(skb); + return NET_XMIT_DROP; +} +#endif /* CONFIG_INET */ + +static int __bpf_redirect_neigh(struct sk_buff *skb, struct net_device *dev) +{ + struct ethhdr *ethh = eth_hdr(skb); + + if (unlikely(skb->mac_header >= skb->network_header)) + goto out; + bpf_push_mac_rcsum(skb); + if (is_multicast_ether_addr(ethh->h_dest)) + goto out; + + skb_pull(skb, sizeof(*ethh)); + skb_unset_mac_header(skb); + skb_reset_network_header(skb); + + if (skb->protocol == htons(ETH_P_IP)) + return __bpf_redirect_neigh_v4(skb, dev); + else if (skb->protocol == htons(ETH_P_IPV6)) + return __bpf_redirect_neigh_v6(skb, dev); +out: + kfree_skb(skb); + return -ENOTSUPP; +} + +/* Internal, non-exposed redirect flags. */ +enum { + BPF_F_NEIGH = (1ULL << 1), + BPF_F_PEER = (1ULL << 2), +#define BPF_F_REDIRECT_INTERNAL (BPF_F_NEIGH | BPF_F_PEER) +}; + BPF_CALL_3(bpf_clone_redirect, struct sk_buff *, skb, u32, ifindex, u64, flags) { struct net_device *dev; struct sk_buff *clone; int ret; - if (unlikely(flags & ~(BPF_F_INGRESS))) + if (unlikely(flags & (~(BPF_F_INGRESS) | BPF_F_REDIRECT_INTERNAL))) return -EINVAL; dev = dev_get_by_index_rcu(dev_net(skb->dev), ifindex); @@ -2203,11 +2428,45 @@ static const struct bpf_func_proto bpf_clone_redirect_proto = { DEFINE_PER_CPU(struct bpf_redirect_info, bpf_redirect_info); EXPORT_PER_CPU_SYMBOL_GPL(bpf_redirect_info); +int skb_do_redirect(struct sk_buff *skb) +{ + struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); + struct net *net = dev_net(skb->dev); + struct net_device *dev; + u32 flags = ri->flags; + + dev = dev_get_by_index_rcu(net, ri->tgt_index); + ri->tgt_index = 0; + ri->flags = 0; + if (unlikely(!dev)) + goto out_drop; + if (flags & BPF_F_PEER) { + const struct net_device_ops *ops = dev->netdev_ops; + + if (unlikely(!ops->ndo_get_peer_dev || + !skb_at_tc_ingress(skb))) + goto out_drop; + dev = ops->ndo_get_peer_dev(dev); + if (unlikely(!dev || + !is_skb_forwardable(dev, skb) || + net_eq(net, dev_net(dev)))) + goto out_drop; + skb->dev = dev; + return -EAGAIN; + } + return flags & BPF_F_NEIGH ? + __bpf_redirect_neigh(skb, dev) : + __bpf_redirect(skb, dev, flags); +out_drop: + kfree_skb(skb); + return -EINVAL; +} + BPF_CALL_2(bpf_redirect, u32, ifindex, u64, flags) { struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); - if (unlikely(flags & ~(BPF_F_INGRESS))) + if (unlikely(flags & (~(BPF_F_INGRESS) | BPF_F_REDIRECT_INTERNAL))) return TC_ACT_SHOT; ri->flags = flags; @@ -2216,29 +2475,56 @@ BPF_CALL_2(bpf_redirect, u32, ifindex, u64, flags) return TC_ACT_REDIRECT; } -int skb_do_redirect(struct sk_buff *skb) +static const struct bpf_func_proto bpf_redirect_proto = { + .func = bpf_redirect, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_ANYTHING, + .arg2_type = ARG_ANYTHING, +}; + +BPF_CALL_2(bpf_redirect_peer, u32, ifindex, u64, flags) { struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); - struct net_device *dev; - dev = dev_get_by_index_rcu(dev_net(skb->dev), ri->tgt_index); - ri->tgt_index = 0; - if (unlikely(!dev)) { - kfree_skb(skb); - return -EINVAL; - } + if (unlikely(flags)) + return TC_ACT_SHOT; - return __bpf_redirect(skb, dev, ri->flags); + ri->flags = BPF_F_PEER; + ri->tgt_index = ifindex; + + return TC_ACT_REDIRECT; } -static const struct bpf_func_proto bpf_redirect_proto = { - .func = bpf_redirect, +static const struct bpf_func_proto bpf_redirect_peer_proto = { + .func = bpf_redirect_peer, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_ANYTHING, .arg2_type = ARG_ANYTHING, }; +BPF_CALL_2(bpf_redirect_neigh, u32, ifindex, u64, flags) +{ + struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info); + + if (unlikely(flags)) + return TC_ACT_SHOT; + + ri->flags = BPF_F_NEIGH; + ri->tgt_index = ifindex; + + return TC_ACT_REDIRECT; +} + +static const struct bpf_func_proto bpf_redirect_neigh_proto = { + .func = bpf_redirect_neigh, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_ANYTHING, + .arg2_type = ARG_ANYTHING, +}; + BPF_CALL_2(bpf_msg_apply_bytes, struct sk_msg *, msg, u32, bytes) { msg->apply_bytes = bytes; @@ -2704,6 +2990,23 @@ static const struct bpf_func_proto bpf_get_cgroup_classid_curr_proto = { .gpl_only = false, .ret_type = RET_INTEGER, }; + +BPF_CALL_1(bpf_skb_cgroup_classid, const struct sk_buff *, skb) +{ + struct sock *sk = skb_to_full_sk(skb); + + if (!sk || !sk_fullsock(sk)) + return 0; + + return sock_cgroup_classid(&sk->sk_cgrp_data); +} + +static const struct bpf_func_proto bpf_skb_cgroup_classid_proto = { + .func = bpf_skb_cgroup_classid, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, +}; #endif BPF_CALL_1(bpf_get_cgroup_classid, const struct sk_buff *, skb) @@ -3215,6 +3518,48 @@ static u32 __bpf_skb_max_len(const struct sk_buff *skb) SKB_MAX_ALLOC; } +BPF_CALL_4(sk_skb_adjust_room, struct sk_buff *, skb, s32, len_diff, + u32, mode, u64, flags) +{ + u32 len_diff_abs = abs(len_diff); + bool shrink = len_diff < 0; + int ret = 0; + + if (unlikely(flags || mode)) + return -EINVAL; + if (unlikely(len_diff_abs > 0xfffU)) + return -EFAULT; + + if (!shrink) { + ret = skb_cow(skb, len_diff); + if (unlikely(ret < 0)) + return ret; + __skb_push(skb, len_diff_abs); + memset(skb->data, 0, len_diff_abs); + } else { + if (unlikely(!pskb_may_pull(skb, len_diff_abs))) + return -ENOMEM; + __skb_pull(skb, len_diff_abs); + } + bpf_compute_data_end_sk_skb(skb); + if (tls_sw_has_ctx_rx(skb->sk)) { + struct strp_msg *rxm = strp_msg(skb); + + rxm->full_len += len_diff; + } + return ret; +} + +static const struct bpf_func_proto sk_skb_adjust_room_proto = { + .func = sk_skb_adjust_room, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_ANYTHING, + .arg3_type = ARG_ANYTHING, + .arg4_type = ARG_ANYTHING, +}; + BPF_CALL_4(bpf_skb_adjust_room, struct sk_buff *, skb, s32, len_diff, u32, mode, u64, flags) { @@ -3803,19 +4148,18 @@ static const struct bpf_func_proto bpf_skb_event_output_proto = { .arg5_type = ARG_CONST_SIZE_OR_ZERO, }; -BTF_ID_LIST(bpf_skb_output_btf_ids) -BTF_ID(struct, sk_buff) +BTF_ID_LIST_SINGLE(bpf_skb_output_btf_ids, struct, sk_buff) const struct bpf_func_proto bpf_skb_output_proto = { .func = bpf_skb_event_output, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_BTF_ID, + .arg1_btf_id = &bpf_skb_output_btf_ids[0], .arg2_type = ARG_CONST_MAP_PTR, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_PTR_TO_MEM, .arg5_type = ARG_CONST_SIZE_OR_ZERO, - .btf_id = bpf_skb_output_btf_ids, }; static unsigned short bpf_tunnel_key_af(u64 flags) @@ -4086,18 +4430,17 @@ static inline u64 __bpf_sk_cgroup_id(struct sock *sk) { struct cgroup *cgrp; + sk = sk_to_full_sk(sk); + if (!sk || !sk_fullsock(sk)) + return 0; + cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data); return cgroup_id(cgrp); } BPF_CALL_1(bpf_skb_cgroup_id, const struct sk_buff *, skb) { - struct sock *sk = skb_to_full_sk(skb); - - if (!sk || !sk_fullsock(sk)) - return 0; - - return __bpf_sk_cgroup_id(sk); + return __bpf_sk_cgroup_id(skb->sk); } static const struct bpf_func_proto bpf_skb_cgroup_id_proto = { @@ -4113,6 +4456,10 @@ static inline u64 __bpf_sk_ancestor_cgroup_id(struct sock *sk, struct cgroup *ancestor; struct cgroup *cgrp; + sk = sk_to_full_sk(sk); + if (!sk || !sk_fullsock(sk)) + return 0; + cgrp = sock_cgroup_ptr(&sk->sk_cgrp_data); ancestor = cgroup_ancestor(cgrp, ancestor_level); if (!ancestor) @@ -4124,12 +4471,7 @@ static inline u64 __bpf_sk_ancestor_cgroup_id(struct sock *sk, BPF_CALL_2(bpf_skb_ancestor_cgroup_id, const struct sk_buff *, skb, int, ancestor_level) { - struct sock *sk = skb_to_full_sk(skb); - - if (!sk || !sk_fullsock(sk)) - return 0; - - return __bpf_sk_ancestor_cgroup_id(sk, ancestor_level); + return __bpf_sk_ancestor_cgroup_id(skb->sk, ancestor_level); } static const struct bpf_func_proto bpf_skb_ancestor_cgroup_id_proto = { @@ -4149,7 +4491,7 @@ static const struct bpf_func_proto bpf_sk_cgroup_id_proto = { .func = bpf_sk_cgroup_id, .gpl_only = false, .ret_type = RET_INTEGER, - .arg1_type = ARG_PTR_TO_SOCKET, + .arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, }; BPF_CALL_2(bpf_sk_ancestor_cgroup_id, struct sock *, sk, int, ancestor_level) @@ -4161,7 +4503,7 @@ static const struct bpf_func_proto bpf_sk_ancestor_cgroup_id_proto = { .func = bpf_sk_ancestor_cgroup_id, .gpl_only = false, .ret_type = RET_INTEGER, - .arg1_type = ARG_PTR_TO_SOCKET, + .arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, .arg2_type = ARG_ANYTHING, }; #endif @@ -4199,24 +4541,23 @@ static const struct bpf_func_proto bpf_xdp_event_output_proto = { .arg5_type = ARG_CONST_SIZE_OR_ZERO, }; -BTF_ID_LIST(bpf_xdp_output_btf_ids) -BTF_ID(struct, xdp_buff) +BTF_ID_LIST_SINGLE(bpf_xdp_output_btf_ids, struct, xdp_buff) const struct bpf_func_proto bpf_xdp_output_proto = { .func = bpf_xdp_event_output, .gpl_only = true, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_BTF_ID, + .arg1_btf_id = &bpf_xdp_output_btf_ids[0], .arg2_type = ARG_CONST_MAP_PTR, .arg3_type = ARG_ANYTHING, .arg4_type = ARG_PTR_TO_MEM, .arg5_type = ARG_CONST_SIZE_OR_ZERO, - .btf_id = bpf_xdp_output_btf_ids, }; BPF_CALL_1(bpf_get_socket_cookie, struct sk_buff *, skb) { - return skb->sk ? sock_gen_cookie(skb->sk) : 0; + return skb->sk ? __sock_gen_cookie(skb->sk) : 0; } static const struct bpf_func_proto bpf_get_socket_cookie_proto = { @@ -4228,7 +4569,7 @@ static const struct bpf_func_proto bpf_get_socket_cookie_proto = { BPF_CALL_1(bpf_get_socket_cookie_sock_addr, struct bpf_sock_addr_kern *, ctx) { - return sock_gen_cookie(ctx->sk); + return __sock_gen_cookie(ctx->sk); } static const struct bpf_func_proto bpf_get_socket_cookie_sock_addr_proto = { @@ -4240,7 +4581,7 @@ static const struct bpf_func_proto bpf_get_socket_cookie_sock_addr_proto = { BPF_CALL_1(bpf_get_socket_cookie_sock, struct sock *, ctx) { - return sock_gen_cookie(ctx); + return __sock_gen_cookie(ctx); } static const struct bpf_func_proto bpf_get_socket_cookie_sock_proto = { @@ -4252,7 +4593,7 @@ static const struct bpf_func_proto bpf_get_socket_cookie_sock_proto = { BPF_CALL_1(bpf_get_socket_cookie_sock_ops, struct bpf_sock_ops_kern *, ctx) { - return sock_gen_cookie(ctx->sk); + return __sock_gen_cookie(ctx->sk); } static const struct bpf_func_proto bpf_get_socket_cookie_sock_ops_proto = { @@ -4265,7 +4606,7 @@ static const struct bpf_func_proto bpf_get_socket_cookie_sock_ops_proto = { static u64 __bpf_get_netns_cookie(struct sock *sk) { #ifdef CONFIG_NET_NS - return net_gen_cookie(sk ? sk->sk_net.net : &init_net); + return __net_gen_cookie(sk ? sk->sk_net.net : &init_net); #else return 0; #endif @@ -4313,10 +4654,8 @@ static const struct bpf_func_proto bpf_get_socket_uid_proto = { .arg1_type = ARG_PTR_TO_CTX, }; -#define SOCKOPT_CC_REINIT (1 << 0) - static int _bpf_setsockopt(struct sock *sk, int level, int optname, - char *optval, int optlen, u32 flags) + char *optval, int optlen) { char devname[IFNAMSIZ]; int val, valbool; @@ -4449,16 +4788,15 @@ static int _bpf_setsockopt(struct sock *sk, int level, int optname, sk->sk_prot->setsockopt == tcp_setsockopt) { if (optname == TCP_CONGESTION) { char name[TCP_CA_NAME_MAX]; - bool reinit = flags & SOCKOPT_CC_REINIT; strncpy(name, optval, min_t(long, optlen, TCP_CA_NAME_MAX-1)); name[TCP_CA_NAME_MAX-1] = 0; - ret = tcp_set_congestion_control(sk, name, false, - reinit, true); + ret = tcp_set_congestion_control(sk, name, false, true); } else { struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); + unsigned long timeout; if (optlen != sizeof(int)) return -EINVAL; @@ -4480,6 +4818,20 @@ static int _bpf_setsockopt(struct sock *sk, int level, int optname, tp->snd_ssthresh = val; } break; + case TCP_BPF_DELACK_MAX: + timeout = usecs_to_jiffies(val); + if (timeout > TCP_DELACK_MAX || + timeout < TCP_TIMEOUT_MIN) + return -EINVAL; + inet_csk(sk)->icsk_delack_max = timeout; + break; + case TCP_BPF_RTO_MIN: + timeout = usecs_to_jiffies(val); + if (timeout > TCP_RTO_MIN || + timeout < TCP_TIMEOUT_MIN) + return -EINVAL; + inet_csk(sk)->icsk_rto_min = timeout; + break; case TCP_SAVE_SYN: if (val < 0 || val > 1) ret = -EINVAL; @@ -4513,6 +4865,10 @@ static int _bpf_setsockopt(struct sock *sk, int level, int optname, else icsk->icsk_user_timeout = val; break; + case TCP_NOTSENT_LOWAT: + tp->notsent_lowat = val; + sk->sk_write_space(sk); + break; default: ret = -EINVAL; } @@ -4550,9 +4906,9 @@ static int _bpf_getsockopt(struct sock *sk, int level, int optname, tp = tcp_sk(sk); if (optlen <= 0 || !tp->saved_syn || - optlen > tp->saved_syn[0]) + optlen > tcp_saved_syn_len(tp->saved_syn)) goto err_clear; - memcpy(optval, tp->saved_syn + 1, optlen); + memcpy(optval, tp->saved_syn->data, optlen); break; default: goto err_clear; @@ -4600,9 +4956,7 @@ err_clear: BPF_CALL_5(bpf_sock_addr_setsockopt, struct bpf_sock_addr_kern *, ctx, int, level, int, optname, char *, optval, int, optlen) { - u32 flags = 0; - return _bpf_setsockopt(ctx->sk, level, optname, optval, optlen, - flags); + return _bpf_setsockopt(ctx->sk, level, optname, optval, optlen); } static const struct bpf_func_proto bpf_sock_addr_setsockopt_proto = { @@ -4636,11 +4990,7 @@ static const struct bpf_func_proto bpf_sock_addr_getsockopt_proto = { BPF_CALL_5(bpf_sock_ops_setsockopt, struct bpf_sock_ops_kern *, bpf_sock, int, level, int, optname, char *, optval, int, optlen) { - u32 flags = 0; - if (bpf_sock->op > BPF_SOCK_OPS_NEEDS_ECN) - flags |= SOCKOPT_CC_REINIT; - return _bpf_setsockopt(bpf_sock->sk, level, optname, optval, optlen, - flags); + return _bpf_setsockopt(bpf_sock->sk, level, optname, optval, optlen); } static const struct bpf_func_proto bpf_sock_ops_setsockopt_proto = { @@ -4654,9 +5004,99 @@ static const struct bpf_func_proto bpf_sock_ops_setsockopt_proto = { .arg5_type = ARG_CONST_SIZE, }; +static int bpf_sock_ops_get_syn(struct bpf_sock_ops_kern *bpf_sock, + int optname, const u8 **start) +{ + struct sk_buff *syn_skb = bpf_sock->syn_skb; + const u8 *hdr_start; + int ret; + + if (syn_skb) { + /* sk is a request_sock here */ + + if (optname == TCP_BPF_SYN) { + hdr_start = syn_skb->data; + ret = tcp_hdrlen(syn_skb); + } else if (optname == TCP_BPF_SYN_IP) { + hdr_start = skb_network_header(syn_skb); + ret = skb_network_header_len(syn_skb) + + tcp_hdrlen(syn_skb); + } else { + /* optname == TCP_BPF_SYN_MAC */ + hdr_start = skb_mac_header(syn_skb); + ret = skb_mac_header_len(syn_skb) + + skb_network_header_len(syn_skb) + + tcp_hdrlen(syn_skb); + } + } else { + struct sock *sk = bpf_sock->sk; + struct saved_syn *saved_syn; + + if (sk->sk_state == TCP_NEW_SYN_RECV) + /* synack retransmit. bpf_sock->syn_skb will + * not be available. It has to resort to + * saved_syn (if it is saved). + */ + saved_syn = inet_reqsk(sk)->saved_syn; + else + saved_syn = tcp_sk(sk)->saved_syn; + + if (!saved_syn) + return -ENOENT; + + if (optname == TCP_BPF_SYN) { + hdr_start = saved_syn->data + + saved_syn->mac_hdrlen + + saved_syn->network_hdrlen; + ret = saved_syn->tcp_hdrlen; + } else if (optname == TCP_BPF_SYN_IP) { + hdr_start = saved_syn->data + + saved_syn->mac_hdrlen; + ret = saved_syn->network_hdrlen + + saved_syn->tcp_hdrlen; + } else { + /* optname == TCP_BPF_SYN_MAC */ + + /* TCP_SAVE_SYN may not have saved the mac hdr */ + if (!saved_syn->mac_hdrlen) + return -ENOENT; + + hdr_start = saved_syn->data; + ret = saved_syn->mac_hdrlen + + saved_syn->network_hdrlen + + saved_syn->tcp_hdrlen; + } + } + + *start = hdr_start; + return ret; +} + BPF_CALL_5(bpf_sock_ops_getsockopt, struct bpf_sock_ops_kern *, bpf_sock, int, level, int, optname, char *, optval, int, optlen) { + if (IS_ENABLED(CONFIG_INET) && level == SOL_TCP && + optname >= TCP_BPF_SYN && optname <= TCP_BPF_SYN_MAC) { + int ret, copy_len = 0; + const u8 *start; + + ret = bpf_sock_ops_get_syn(bpf_sock, optname, &start); + if (ret > 0) { + copy_len = ret; + if (optlen < copy_len) { + copy_len = optlen; + ret = -ENOSPC; + } + + memcpy(optval, start, copy_len); + } + + /* Zero out unused buffer at the end */ + memset(optval + copy_len, 0, optlen - copy_len); + + return ret; + } + return _bpf_getsockopt(bpf_sock->sk, level, optname, optval, optlen); } @@ -4794,7 +5234,6 @@ static int bpf_fib_set_fwd_params(struct bpf_fib_lookup *params, memcpy(params->smac, dev->dev_addr, ETH_ALEN); params->h_vlan_TCI = 0; params->h_vlan_proto = 0; - params->ifindex = dev->ifindex; return 0; } @@ -4891,6 +5330,7 @@ static int bpf_ipv4_fib_lookup(struct net *net, struct bpf_fib_lookup *params, dev = nhc->nhc_dev; params->rt_metric = res.fi->fib_priority; + params->ifindex = dev->ifindex; /* xdp and cls_bpf programs are run in RCU-bh so * rcu_read_lock_bh is not needed here @@ -5016,6 +5456,7 @@ static int bpf_ipv6_fib_lookup(struct net *net, struct bpf_fib_lookup *params, dev = res.nh->fib_nh_dev; params->rt_metric = res.f6i->fib6_metric; + params->ifindex = dev->ifindex; /* xdp and cls_bpf programs are run in RCU-bh so rcu_read_lock_bh is * not needed here. @@ -5601,7 +6042,7 @@ static const struct bpf_func_proto bpf_sk_lookup_udp_proto = { BPF_CALL_1(bpf_sk_release, struct sock *, sk) { - if (sk_is_refcounted(sk)) + if (sk && sk_is_refcounted(sk)) sock_gen_put(sk); return 0; } @@ -5610,7 +6051,7 @@ static const struct bpf_func_proto bpf_sk_release_proto = { .func = bpf_sk_release, .gpl_only = false, .ret_type = RET_INTEGER, - .arg1_type = ARG_PTR_TO_SOCK_COMMON, + .arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, }; BPF_CALL_5(bpf_xdp_sk_lookup_udp, struct xdp_buff *, ctx, @@ -5992,7 +6433,7 @@ BPF_CALL_5(bpf_tcp_check_syncookie, struct sock *, sk, void *, iph, u32, iph_len u32 cookie; int ret; - if (unlikely(th_len < sizeof(*th))) + if (unlikely(!sk || th_len < sizeof(*th))) return -EINVAL; /* sk_listener() allows TCP_NEW_SYN_RECV, which makes no sense here. */ @@ -6045,7 +6486,7 @@ static const struct bpf_func_proto bpf_tcp_check_syncookie_proto = { .gpl_only = true, .pkt_access = true, .ret_type = RET_INTEGER, - .arg1_type = ARG_PTR_TO_SOCK_COMMON, + .arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, .arg2_type = ARG_PTR_TO_MEM, .arg3_type = ARG_CONST_SIZE, .arg4_type = ARG_PTR_TO_MEM, @@ -6059,7 +6500,7 @@ BPF_CALL_5(bpf_tcp_gen_syncookie, struct sock *, sk, void *, iph, u32, iph_len, u32 cookie; u16 mss; - if (unlikely(th_len < sizeof(*th) || th_len != th->doff * 4)) + if (unlikely(!sk || th_len < sizeof(*th) || th_len != th->doff * 4)) return -EINVAL; if (sk->sk_protocol != IPPROTO_TCP || sk->sk_state != TCP_LISTEN) @@ -6114,7 +6555,7 @@ static const struct bpf_func_proto bpf_tcp_gen_syncookie_proto = { .gpl_only = true, /* __cookie_v*_init_sequence() is GPL */ .pkt_access = true, .ret_type = RET_INTEGER, - .arg1_type = ARG_PTR_TO_SOCK_COMMON, + .arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, .arg2_type = ARG_PTR_TO_MEM, .arg3_type = ARG_CONST_SIZE, .arg4_type = ARG_PTR_TO_MEM, @@ -6123,7 +6564,7 @@ static const struct bpf_func_proto bpf_tcp_gen_syncookie_proto = { BPF_CALL_3(bpf_sk_assign, struct sk_buff *, skb, struct sock *, sk, u64, flags) { - if (flags != 0) + if (!sk || flags != 0) return -EINVAL; if (!skb_at_tc_ingress(skb)) return -EOPNOTSUPP; @@ -6147,7 +6588,233 @@ static const struct bpf_func_proto bpf_sk_assign_proto = { .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, - .arg2_type = ARG_PTR_TO_SOCK_COMMON, + .arg2_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, + .arg3_type = ARG_ANYTHING, +}; + +static const u8 *bpf_search_tcp_opt(const u8 *op, const u8 *opend, + u8 search_kind, const u8 *magic, + u8 magic_len, bool *eol) +{ + u8 kind, kind_len; + + *eol = false; + + while (op < opend) { + kind = op[0]; + + if (kind == TCPOPT_EOL) { + *eol = true; + return ERR_PTR(-ENOMSG); + } else if (kind == TCPOPT_NOP) { + op++; + continue; + } + + if (opend - op < 2 || opend - op < op[1] || op[1] < 2) + /* Something is wrong in the received header. + * Follow the TCP stack's tcp_parse_options() + * and just bail here. + */ + return ERR_PTR(-EFAULT); + + kind_len = op[1]; + if (search_kind == kind) { + if (!magic_len) + return op; + + if (magic_len > kind_len - 2) + return ERR_PTR(-ENOMSG); + + if (!memcmp(&op[2], magic, magic_len)) + return op; + } + + op += kind_len; + } + + return ERR_PTR(-ENOMSG); +} + +BPF_CALL_4(bpf_sock_ops_load_hdr_opt, struct bpf_sock_ops_kern *, bpf_sock, + void *, search_res, u32, len, u64, flags) +{ + bool eol, load_syn = flags & BPF_LOAD_HDR_OPT_TCP_SYN; + const u8 *op, *opend, *magic, *search = search_res; + u8 search_kind, search_len, copy_len, magic_len; + int ret; + + /* 2 byte is the minimal option len except TCPOPT_NOP and + * TCPOPT_EOL which are useless for the bpf prog to learn + * and this helper disallow loading them also. + */ + if (len < 2 || flags & ~BPF_LOAD_HDR_OPT_TCP_SYN) + return -EINVAL; + + search_kind = search[0]; + search_len = search[1]; + + if (search_len > len || search_kind == TCPOPT_NOP || + search_kind == TCPOPT_EOL) + return -EINVAL; + + if (search_kind == TCPOPT_EXP || search_kind == 253) { + /* 16 or 32 bit magic. +2 for kind and kind length */ + if (search_len != 4 && search_len != 6) + return -EINVAL; + magic = &search[2]; + magic_len = search_len - 2; + } else { + if (search_len) + return -EINVAL; + magic = NULL; + magic_len = 0; + } + + if (load_syn) { + ret = bpf_sock_ops_get_syn(bpf_sock, TCP_BPF_SYN, &op); + if (ret < 0) + return ret; + + opend = op + ret; + op += sizeof(struct tcphdr); + } else { + if (!bpf_sock->skb || + bpf_sock->op == BPF_SOCK_OPS_HDR_OPT_LEN_CB) + /* This bpf_sock->op cannot call this helper */ + return -EPERM; + + opend = bpf_sock->skb_data_end; + op = bpf_sock->skb->data + sizeof(struct tcphdr); + } + + op = bpf_search_tcp_opt(op, opend, search_kind, magic, magic_len, + &eol); + if (IS_ERR(op)) + return PTR_ERR(op); + + copy_len = op[1]; + ret = copy_len; + if (copy_len > len) { + ret = -ENOSPC; + copy_len = len; + } + + memcpy(search_res, op, copy_len); + return ret; +} + +static const struct bpf_func_proto bpf_sock_ops_load_hdr_opt_proto = { + .func = bpf_sock_ops_load_hdr_opt, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_PTR_TO_MEM, + .arg3_type = ARG_CONST_SIZE, + .arg4_type = ARG_ANYTHING, +}; + +BPF_CALL_4(bpf_sock_ops_store_hdr_opt, struct bpf_sock_ops_kern *, bpf_sock, + const void *, from, u32, len, u64, flags) +{ + u8 new_kind, new_kind_len, magic_len = 0, *opend; + const u8 *op, *new_op, *magic = NULL; + struct sk_buff *skb; + bool eol; + + if (bpf_sock->op != BPF_SOCK_OPS_WRITE_HDR_OPT_CB) + return -EPERM; + + if (len < 2 || flags) + return -EINVAL; + + new_op = from; + new_kind = new_op[0]; + new_kind_len = new_op[1]; + + if (new_kind_len > len || new_kind == TCPOPT_NOP || + new_kind == TCPOPT_EOL) + return -EINVAL; + + if (new_kind_len > bpf_sock->remaining_opt_len) + return -ENOSPC; + + /* 253 is another experimental kind */ + if (new_kind == TCPOPT_EXP || new_kind == 253) { + if (new_kind_len < 4) + return -EINVAL; + /* Match for the 2 byte magic also. + * RFC 6994: the magic could be 2 or 4 bytes. + * Hence, matching by 2 byte only is on the + * conservative side but it is the right + * thing to do for the 'search-for-duplication' + * purpose. + */ + magic = &new_op[2]; + magic_len = 2; + } + + /* Check for duplication */ + skb = bpf_sock->skb; + op = skb->data + sizeof(struct tcphdr); + opend = bpf_sock->skb_data_end; + + op = bpf_search_tcp_opt(op, opend, new_kind, magic, magic_len, + &eol); + if (!IS_ERR(op)) + return -EEXIST; + + if (PTR_ERR(op) != -ENOMSG) + return PTR_ERR(op); + + if (eol) + /* The option has been ended. Treat it as no more + * header option can be written. + */ + return -ENOSPC; + + /* No duplication found. Store the header option. */ + memcpy(opend, from, new_kind_len); + + bpf_sock->remaining_opt_len -= new_kind_len; + bpf_sock->skb_data_end += new_kind_len; + + return 0; +} + +static const struct bpf_func_proto bpf_sock_ops_store_hdr_opt_proto = { + .func = bpf_sock_ops_store_hdr_opt, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_PTR_TO_MEM, + .arg3_type = ARG_CONST_SIZE, + .arg4_type = ARG_ANYTHING, +}; + +BPF_CALL_3(bpf_sock_ops_reserve_hdr_opt, struct bpf_sock_ops_kern *, bpf_sock, + u32, len, u64, flags) +{ + if (bpf_sock->op != BPF_SOCK_OPS_HDR_OPT_LEN_CB) + return -EPERM; + + if (flags || len < 2) + return -EINVAL; + + if (len > bpf_sock->remaining_opt_len) + return -ENOSPC; + + bpf_sock->remaining_opt_len -= len; + + return 0; +} + +static const struct bpf_func_proto bpf_sock_ops_reserve_hdr_opt_proto = { + .func = bpf_sock_ops_reserve_hdr_opt, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, }; @@ -6164,6 +6831,7 @@ bool bpf_helper_changes_pkt_data(void *func) func == bpf_skb_change_tail || func == sk_skb_change_tail || func == bpf_skb_adjust_room || + func == sk_skb_adjust_room || func == bpf_skb_pull_data || func == sk_skb_pull_data || func == bpf_clone_redirect || @@ -6180,6 +6848,9 @@ bool bpf_helper_changes_pkt_data(void *func) func == bpf_lwt_seg6_adjust_srh || func == bpf_lwt_seg6_action || #endif +#ifdef CONFIG_INET + func == bpf_sock_ops_store_hdr_opt || +#endif func == bpf_lwt_in_push_encap || func == bpf_lwt_xmit_push_encap) return true; @@ -6298,7 +6969,7 @@ sock_addr_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return NULL; } default: - return bpf_base_func_proto(func_id); + return bpf_sk_base_func_proto(func_id); } } @@ -6317,7 +6988,7 @@ sk_filter_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_FUNC_perf_event_output: return &bpf_skb_event_output_proto; default: - return bpf_base_func_proto(func_id); + return bpf_sk_base_func_proto(func_id); } } @@ -6419,6 +7090,10 @@ tc_cls_act_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return bpf_get_skb_set_tunnel_proto(func_id); case BPF_FUNC_redirect: return &bpf_redirect_proto; + case BPF_FUNC_redirect_neigh: + return &bpf_redirect_neigh_proto; + case BPF_FUNC_redirect_peer: + return &bpf_redirect_peer_proto; case BPF_FUNC_get_route_realm: return &bpf_get_route_realm_proto; case BPF_FUNC_get_hash_recalc: @@ -6449,6 +7124,10 @@ tc_cls_act_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_FUNC_skb_get_xfrm_state: return &bpf_skb_get_xfrm_state_proto; #endif +#ifdef CONFIG_CGROUP_NET_CLASSID + case BPF_FUNC_skb_cgroup_classid: + return &bpf_skb_cgroup_classid_proto; +#endif #ifdef CONFIG_SOCK_CGROUP_DATA case BPF_FUNC_skb_cgroup_id: return &bpf_skb_cgroup_id_proto; @@ -6478,7 +7157,7 @@ tc_cls_act_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_sk_assign_proto; #endif default: - return bpf_base_func_proto(func_id); + return bpf_sk_base_func_proto(func_id); } } @@ -6519,7 +7198,7 @@ xdp_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_tcp_gen_syncookie_proto; #endif default: - return bpf_base_func_proto(func_id); + return bpf_sk_base_func_proto(func_id); } } @@ -6551,11 +7230,17 @@ sock_ops_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_FUNC_sk_storage_delete: return &bpf_sk_storage_delete_proto; #ifdef CONFIG_INET + case BPF_FUNC_load_hdr_opt: + return &bpf_sock_ops_load_hdr_opt_proto; + case BPF_FUNC_store_hdr_opt: + return &bpf_sock_ops_store_hdr_opt_proto; + case BPF_FUNC_reserve_hdr_opt: + return &bpf_sock_ops_reserve_hdr_opt_proto; case BPF_FUNC_tcp_sock: return &bpf_tcp_sock_proto; #endif /* CONFIG_INET */ default: - return bpf_base_func_proto(func_id); + return bpf_sk_base_func_proto(func_id); } } @@ -6601,7 +7286,7 @@ sk_msg_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_get_cgroup_classid_curr_proto; #endif default: - return bpf_base_func_proto(func_id); + return bpf_sk_base_func_proto(func_id); } } @@ -6622,6 +7307,8 @@ sk_skb_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &sk_skb_change_tail_proto; case BPF_FUNC_skb_change_head: return &sk_skb_change_head_proto; + case BPF_FUNC_skb_adjust_room: + return &sk_skb_adjust_room_proto; case BPF_FUNC_get_socket_cookie: return &bpf_get_socket_cookie_proto; case BPF_FUNC_get_socket_uid: @@ -6643,7 +7330,7 @@ sk_skb_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_skc_lookup_tcp_proto; #endif default: - return bpf_base_func_proto(func_id); + return bpf_sk_base_func_proto(func_id); } } @@ -6654,7 +7341,7 @@ flow_dissector_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_FUNC_skb_load_bytes: return &bpf_flow_dissector_load_bytes_proto; default: - return bpf_base_func_proto(func_id); + return bpf_sk_base_func_proto(func_id); } } @@ -6681,7 +7368,7 @@ lwt_out_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_FUNC_skb_under_cgroup: return &bpf_skb_under_cgroup_proto; default: - return bpf_base_func_proto(func_id); + return bpf_sk_base_func_proto(func_id); } } @@ -7350,6 +8037,20 @@ static bool sock_ops_is_valid_access(int off, int size, return false; info->reg_type = PTR_TO_SOCKET_OR_NULL; break; + case offsetof(struct bpf_sock_ops, skb_data): + if (size != sizeof(__u64)) + return false; + info->reg_type = PTR_TO_PACKET; + break; + case offsetof(struct bpf_sock_ops, skb_data_end): + if (size != sizeof(__u64)) + return false; + info->reg_type = PTR_TO_PACKET_END; + break; + case offsetof(struct bpf_sock_ops, skb_tcp_flags): + bpf_ctx_record_field_size(info, size_default); + return bpf_ctx_narrow_access_ok(off, size, + size_default); default: if (size != size_default) return false; @@ -8451,17 +9152,22 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type, return insn - insn_buf; switch (si->off) { - case offsetof(struct bpf_sock_ops, op) ... + case offsetof(struct bpf_sock_ops, op): + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_sock_ops_kern, + op), + si->dst_reg, si->src_reg, + offsetof(struct bpf_sock_ops_kern, op)); + break; + + case offsetof(struct bpf_sock_ops, replylong[0]) ... offsetof(struct bpf_sock_ops, replylong[3]): - BUILD_BUG_ON(sizeof_field(struct bpf_sock_ops, op) != - sizeof_field(struct bpf_sock_ops_kern, op)); BUILD_BUG_ON(sizeof_field(struct bpf_sock_ops, reply) != sizeof_field(struct bpf_sock_ops_kern, reply)); BUILD_BUG_ON(sizeof_field(struct bpf_sock_ops, replylong) != sizeof_field(struct bpf_sock_ops_kern, replylong)); off = si->off; - off -= offsetof(struct bpf_sock_ops, op); - off += offsetof(struct bpf_sock_ops_kern, op); + off -= offsetof(struct bpf_sock_ops, replylong[0]); + off += offsetof(struct bpf_sock_ops_kern, replylong[0]); if (type == BPF_WRITE) *insn++ = BPF_STX_MEM(BPF_W, si->dst_reg, si->src_reg, off); @@ -8682,6 +9388,49 @@ static u32 sock_ops_convert_ctx_access(enum bpf_access_type type, case offsetof(struct bpf_sock_ops, sk): SOCK_OPS_GET_SK(); break; + case offsetof(struct bpf_sock_ops, skb_data_end): + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_sock_ops_kern, + skb_data_end), + si->dst_reg, si->src_reg, + offsetof(struct bpf_sock_ops_kern, + skb_data_end)); + break; + case offsetof(struct bpf_sock_ops, skb_data): + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_sock_ops_kern, + skb), + si->dst_reg, si->src_reg, + offsetof(struct bpf_sock_ops_kern, + skb)); + *insn++ = BPF_JMP_IMM(BPF_JEQ, si->dst_reg, 0, 1); + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, data), + si->dst_reg, si->dst_reg, + offsetof(struct sk_buff, data)); + break; + case offsetof(struct bpf_sock_ops, skb_len): + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_sock_ops_kern, + skb), + si->dst_reg, si->src_reg, + offsetof(struct bpf_sock_ops_kern, + skb)); + *insn++ = BPF_JMP_IMM(BPF_JEQ, si->dst_reg, 0, 1); + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, len), + si->dst_reg, si->dst_reg, + offsetof(struct sk_buff, len)); + break; + case offsetof(struct bpf_sock_ops, skb_tcp_flags): + off = offsetof(struct sk_buff, cb); + off += offsetof(struct tcp_skb_cb, tcp_flags); + *target_size = sizeof_field(struct tcp_skb_cb, tcp_flags); + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct bpf_sock_ops_kern, + skb), + si->dst_reg, si->src_reg, + offsetof(struct bpf_sock_ops_kern, + skb)); + *insn++ = BPF_JMP_IMM(BPF_JEQ, si->dst_reg, 0, 1); + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct tcp_skb_cb, + tcp_flags), + si->dst_reg, si->dst_reg, off); + break; } return insn - insn_buf; } @@ -9356,7 +10105,7 @@ sk_lookup_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) case BPF_FUNC_sk_release: return &bpf_sk_release_proto; default: - return bpf_base_func_proto(func_id); + return bpf_sk_base_func_proto(func_id); } } @@ -9506,17 +10255,6 @@ BTF_SOCK_TYPE_xxx u32 btf_sock_ids[MAX_BTF_SOCK_TYPE]; #endif -static bool check_arg_btf_id(u32 btf_id, u32 arg) -{ - int i; - - /* only one argument, no need to check arg */ - for (i = 0; i < MAX_BTF_SOCK_TYPE; i++) - if (btf_sock_ids[i] == btf_id) - return true; - return false; -} - BPF_CALL_1(bpf_skc_to_tcp6_sock, struct sock *, sk) { /* tcp6_sock type is not generated in dwarf and hence btf, @@ -9534,8 +10272,7 @@ const struct bpf_func_proto bpf_skc_to_tcp6_sock_proto = { .func = bpf_skc_to_tcp6_sock, .gpl_only = false, .ret_type = RET_PTR_TO_BTF_ID_OR_NULL, - .arg1_type = ARG_PTR_TO_BTF_ID, - .check_btf_id = check_arg_btf_id, + .arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, .ret_btf_id = &btf_sock_ids[BTF_SOCK_TYPE_TCP6], }; @@ -9551,8 +10288,7 @@ const struct bpf_func_proto bpf_skc_to_tcp_sock_proto = { .func = bpf_skc_to_tcp_sock, .gpl_only = false, .ret_type = RET_PTR_TO_BTF_ID_OR_NULL, - .arg1_type = ARG_PTR_TO_BTF_ID, - .check_btf_id = check_arg_btf_id, + .arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, .ret_btf_id = &btf_sock_ids[BTF_SOCK_TYPE_TCP], }; @@ -9581,8 +10317,7 @@ const struct bpf_func_proto bpf_skc_to_tcp_timewait_sock_proto = { .func = bpf_skc_to_tcp_timewait_sock, .gpl_only = false, .ret_type = RET_PTR_TO_BTF_ID_OR_NULL, - .arg1_type = ARG_PTR_TO_BTF_ID, - .check_btf_id = check_arg_btf_id, + .arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, .ret_btf_id = &btf_sock_ids[BTF_SOCK_TYPE_TCP_TW], }; @@ -9605,8 +10340,7 @@ const struct bpf_func_proto bpf_skc_to_tcp_request_sock_proto = { .func = bpf_skc_to_tcp_request_sock, .gpl_only = false, .ret_type = RET_PTR_TO_BTF_ID_OR_NULL, - .arg1_type = ARG_PTR_TO_BTF_ID, - .check_btf_id = check_arg_btf_id, + .arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, .ret_btf_id = &btf_sock_ids[BTF_SOCK_TYPE_TCP_REQ], }; @@ -9627,7 +10361,37 @@ const struct bpf_func_proto bpf_skc_to_udp6_sock_proto = { .func = bpf_skc_to_udp6_sock, .gpl_only = false, .ret_type = RET_PTR_TO_BTF_ID_OR_NULL, - .arg1_type = ARG_PTR_TO_BTF_ID, - .check_btf_id = check_arg_btf_id, + .arg1_type = ARG_PTR_TO_BTF_ID_SOCK_COMMON, .ret_btf_id = &btf_sock_ids[BTF_SOCK_TYPE_UDP6], }; + +static const struct bpf_func_proto * +bpf_sk_base_func_proto(enum bpf_func_id func_id) +{ + const struct bpf_func_proto *func; + + switch (func_id) { + case BPF_FUNC_skc_to_tcp6_sock: + func = &bpf_skc_to_tcp6_sock_proto; + break; + case BPF_FUNC_skc_to_tcp_sock: + func = &bpf_skc_to_tcp_sock_proto; + break; + case BPF_FUNC_skc_to_tcp_timewait_sock: + func = &bpf_skc_to_tcp_timewait_sock_proto; + break; + case BPF_FUNC_skc_to_tcp_request_sock: + func = &bpf_skc_to_tcp_request_sock_proto; + break; + case BPF_FUNC_skc_to_udp6_sock: + func = &bpf_skc_to_udp6_sock_proto; + break; + default: + return bpf_base_func_proto(func_id); + } + + if (!perfmon_capable()) + return NULL; + + return func; +} diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index 29806eb765cf..e21950a2c897 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -932,8 +932,14 @@ bool __skb_flow_dissect(const struct net *net, int offset = 0; ops = skb->dev->dsa_ptr->tag_ops; - if (ops->flow_dissect && - !ops->flow_dissect(skb, &proto, &offset)) { + /* Tail taggers don't break flow dissection */ + if (!ops->tail_tag) { + if (ops->flow_dissect) + ops->flow_dissect(skb, &proto, &offset); + else + dsa_tag_generic_flow_dissect(skb, + &proto, + &offset); hlen -= offset; nhoff += offset; } diff --git a/net/core/net-procfs.c b/net/core/net-procfs.c index 6bbd06f7dc7d..c714e6a9dad4 100644 --- a/net/core/net-procfs.c +++ b/net/core/net-procfs.c @@ -116,6 +116,12 @@ static int dev_seq_show(struct seq_file *seq, void *v) return 0; } +static u32 softnet_backlog_len(struct softnet_data *sd) +{ + return skb_queue_len_lockless(&sd->input_pkt_queue) + + skb_queue_len_lockless(&sd->process_queue); +} + static struct softnet_data *softnet_get_online(loff_t *pos) { struct softnet_data *sd = NULL; @@ -159,12 +165,17 @@ static int softnet_seq_show(struct seq_file *seq, void *v) rcu_read_unlock(); #endif + /* the index is the CPU id owing this sd. Since offline CPUs are not + * displayed, it would be othrwise not trivial for the user-space + * mapping the data a specific CPU + */ seq_printf(seq, - "%08x %08x %08x %08x %08x %08x %08x %08x %08x %08x %08x\n", + "%08x %08x %08x %08x %08x %08x %08x %08x %08x %08x %08x %08x %08x\n", sd->processed, sd->dropped, sd->time_squeeze, 0, 0, 0, 0, 0, /* was fastroute */ 0, /* was cpu_collision */ - sd->received_rps, flow_limit_count); + sd->received_rps, flow_limit_count, + softnet_backlog_len(sd), (int)seq->index); return 0; } diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index efec66fa78b7..94fff0700bdd 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -1158,8 +1158,8 @@ static ssize_t traffic_class_show(struct netdev_queue *queue, * belongs to the root device it will be reported with just the * traffic class, so just "0" for TC 0 for example. */ - return dev->num_tc < 0 ? sprintf(buf, "%u%d\n", tc, dev->num_tc) : - sprintf(buf, "%u\n", tc); + return dev->num_tc < 0 ? sprintf(buf, "%d%d\n", tc, dev->num_tc) : + sprintf(buf, "%d\n", tc); } #ifdef CONFIG_XPS diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index 944ab214e5ae..dbc66b896287 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -19,6 +19,7 @@ #include <linux/net_namespace.h> #include <linux/sched/task.h> #include <linux/uidgid.h> +#include <linux/cookie.h> #include <net/sock.h> #include <net/netlink.h> @@ -69,16 +70,16 @@ EXPORT_SYMBOL_GPL(pernet_ops_rwsem); static unsigned int max_gen_ptrs = INITIAL_NET_GEN_PTRS; -static atomic64_t cookie_gen; +DEFINE_COOKIE(net_cookie); -u64 net_gen_cookie(struct net *net) +u64 __net_gen_cookie(struct net *net) { while (1) { u64 res = atomic64_read(&net->net_cookie); if (res) return res; - res = atomic64_inc_return(&cookie_gen); + res = gen_cookie_next(&net_cookie); atomic64_cmpxchg(&net->net_cookie, 0, res); } } @@ -1101,7 +1102,10 @@ static int __init net_ns_init(void) panic("Could not allocate generic netns"); rcu_assign_pointer(init_net.gen, ng); - net_gen_cookie(&init_net); + + preempt_disable(); + __net_gen_cookie(&init_net); + preempt_enable(); down_write(&pernet_ops_rwsem); if (setup_net(&init_net, &init_user_ns)) diff --git a/net/core/netpoll.c b/net/core/netpoll.c index 2338753e936b..c310c7c1cef7 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -297,7 +297,7 @@ static int netpoll_owner_active(struct net_device *dev) { struct napi_struct *napi; - list_for_each_entry(napi, &dev->napi_list, dev_list) { + list_for_each_entry_rcu(napi, &dev->napi_list, dev_list) { if (napi->poll_owner == smp_processor_id()) return 1; } diff --git a/net/core/pktgen.c b/net/core/pktgen.c index 44fdbb9c6e53..105978604ffd 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -922,7 +922,7 @@ static ssize_t pktgen_if_write(struct file *file, pkt_dev->min_pkt_size = value; pkt_dev->cur_pkt_size = value; } - sprintf(pg_result, "OK: min_pkt_size=%u", + sprintf(pg_result, "OK: min_pkt_size=%d", pkt_dev->min_pkt_size); return count; } @@ -939,7 +939,7 @@ static ssize_t pktgen_if_write(struct file *file, pkt_dev->max_pkt_size = value; pkt_dev->cur_pkt_size = value; } - sprintf(pg_result, "OK: max_pkt_size=%u", + sprintf(pg_result, "OK: max_pkt_size=%d", pkt_dev->max_pkt_size); return count; } @@ -959,7 +959,7 @@ static ssize_t pktgen_if_write(struct file *file, pkt_dev->max_pkt_size = value; pkt_dev->cur_pkt_size = value; } - sprintf(pg_result, "OK: pkt_size=%u", pkt_dev->min_pkt_size); + sprintf(pg_result, "OK: pkt_size=%d", pkt_dev->min_pkt_size); return count; } @@ -981,7 +981,7 @@ static ssize_t pktgen_if_write(struct file *file, i += len; pkt_dev->nfrags = value; - sprintf(pg_result, "OK: frags=%u", pkt_dev->nfrags); + sprintf(pg_result, "OK: frags=%d", pkt_dev->nfrags); return count; } if (!strcmp(name, "delay")) { @@ -1146,7 +1146,7 @@ static ssize_t pktgen_if_write(struct file *file, (!(pkt_dev->odev->priv_flags & IFF_TX_SKB_SHARING))))) return -ENOTSUPP; pkt_dev->burst = value < 1 ? 1 : value; - sprintf(pg_result, "OK: burst=%d", pkt_dev->burst); + sprintf(pg_result, "OK: burst=%u", pkt_dev->burst); return count; } if (!strcmp(name, "node")) { diff --git a/net/core/ptp_classifier.c b/net/core/ptp_classifier.c index d964a5147f22..e33fde06d528 100644 --- a/net/core/ptp_classifier.c +++ b/net/core/ptp_classifier.c @@ -107,6 +107,36 @@ unsigned int ptp_classify_raw(const struct sk_buff *skb) } EXPORT_SYMBOL_GPL(ptp_classify_raw); +struct ptp_header *ptp_parse_header(struct sk_buff *skb, unsigned int type) +{ + u8 *ptr = skb_mac_header(skb); + + if (type & PTP_CLASS_VLAN) + ptr += VLAN_HLEN; + + switch (type & PTP_CLASS_PMASK) { + case PTP_CLASS_IPV4: + ptr += IPV4_HLEN(ptr) + UDP_HLEN; + break; + case PTP_CLASS_IPV6: + ptr += IP6_HLEN + UDP_HLEN; + break; + case PTP_CLASS_L2: + break; + default: + return NULL; + } + + ptr += ETH_HLEN; + + /* Ensure that the entire header is present in this packet. */ + if (ptr + sizeof(struct ptp_header) > skb->data + skb->len) + return NULL; + + return (struct ptp_header *)ptr; +} +EXPORT_SYMBOL_GPL(ptp_parse_header); + void __init ptp_classifier_init(void) { static struct sock_filter ptp_filter[] __initdata = { diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 2b48cb0cc684..7cba279e7138 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -712,11 +712,10 @@ EXPORT_SYMBOL(kfree_skb_list); * * Must only be called from net_ratelimit()-ed paths. * - * Dumps up to can_dump_full whole packets if full_pkt, headers otherwise. + * Dumps whole packets if full_pkt, only headers otherwise. */ void skb_dump(const char *level, const struct sk_buff *skb, bool full_pkt) { - static atomic_t can_dump_full = ATOMIC_INIT(5); struct skb_shared_info *sh = skb_shinfo(skb); struct net_device *dev = skb->dev; struct sock *sk = skb->sk; @@ -726,9 +725,6 @@ void skb_dump(const char *level, const struct sk_buff *skb, bool full_pkt) int i, len, seg_len; if (full_pkt) - full_pkt = atomic_dec_if_positive(&can_dump_full) >= 0; - - if (full_pkt) len = skb->len; else len = min_t(int, skb->len, MAX_HEADER + 128); @@ -895,9 +891,6 @@ void __kfree_skb_defer(struct sk_buff *skb) void napi_consume_skb(struct sk_buff *skb, int budget) { - if (unlikely(!skb)) - return; - /* Zero budget indicate non-NAPI context called us, like netpoll */ if (unlikely(!budget)) { dev_consume_skb_any(skb); @@ -5561,6 +5554,73 @@ int skb_vlan_push(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci) } EXPORT_SYMBOL(skb_vlan_push); +/** + * skb_eth_pop() - Drop the Ethernet header at the head of a packet + * + * @skb: Socket buffer to modify + * + * Drop the Ethernet header of @skb. + * + * Expects that skb->data points to the mac header and that no VLAN tags are + * present. + * + * Returns 0 on success, -errno otherwise. + */ +int skb_eth_pop(struct sk_buff *skb) +{ + if (!pskb_may_pull(skb, ETH_HLEN) || skb_vlan_tagged(skb) || + skb_network_offset(skb) < ETH_HLEN) + return -EPROTO; + + skb_pull_rcsum(skb, ETH_HLEN); + skb_reset_mac_header(skb); + skb_reset_mac_len(skb); + + return 0; +} +EXPORT_SYMBOL(skb_eth_pop); + +/** + * skb_eth_push() - Add a new Ethernet header at the head of a packet + * + * @skb: Socket buffer to modify + * @dst: Destination MAC address of the new header + * @src: Source MAC address of the new header + * + * Prepend @skb with a new Ethernet header. + * + * Expects that skb->data points to the mac header, which must be empty. + * + * Returns 0 on success, -errno otherwise. + */ +int skb_eth_push(struct sk_buff *skb, const unsigned char *dst, + const unsigned char *src) +{ + struct ethhdr *eth; + int err; + + if (skb_network_offset(skb) || skb_vlan_tag_present(skb)) + return -EPROTO; + + err = skb_cow_head(skb, sizeof(*eth)); + if (err < 0) + return err; + + skb_push(skb, sizeof(*eth)); + skb_reset_mac_header(skb); + skb_reset_mac_len(skb); + + eth = eth_hdr(skb); + ether_addr_copy(eth->h_dest, dst); + ether_addr_copy(eth->h_source, src); + eth->h_proto = skb->protocol; + + skb_postpush_rcsum(skb, eth, sizeof(*eth)); + + return 0; +} +EXPORT_SYMBOL(skb_eth_push); + /* Update the ethertype of hdr and the skb csum value if required. */ static void skb_mod_eth_type(struct sk_buff *skb, struct ethhdr *hdr, __be16 ethertype) @@ -5955,8 +6015,7 @@ static int pskb_carve_inside_nonlinear(struct sk_buff *skb, const u32 off, size = SKB_WITH_OVERHEAD(ksize(data)); memcpy((struct skb_shared_info *)(data + size), - skb_shinfo(skb), offsetof(struct skb_shared_info, - frags[skb_shinfo(skb)->nr_frags])); + skb_shinfo(skb), offsetof(struct skb_shared_info, frags[0])); if (skb_orphan_frags(skb, gfp_mask)) { kfree(data); return -ENOMEM; diff --git a/net/core/skmsg.c b/net/core/skmsg.c index 649583158983..654182ecf87b 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -433,10 +433,12 @@ static int sk_psock_skb_ingress(struct sk_psock *psock, struct sk_buff *skb) static int sk_psock_handle_skb(struct sk_psock *psock, struct sk_buff *skb, u32 off, u32 len, bool ingress) { - if (ingress) - return sk_psock_skb_ingress(psock, skb); - else + if (!ingress) { + if (!sock_writeable(psock->sk)) + return -EAGAIN; return skb_send_sock_locked(psock->sk, skb, off, len); + } + return sk_psock_skb_ingress(psock, skb); } static void sk_psock_backlog(struct work_struct *work) @@ -494,14 +496,34 @@ end: struct sk_psock *sk_psock_init(struct sock *sk, int node) { - struct sk_psock *psock = kzalloc_node(sizeof(*psock), - GFP_ATOMIC | __GFP_NOWARN, - node); - if (!psock) - return NULL; + struct sk_psock *psock; + struct proto *prot; + + write_lock_bh(&sk->sk_callback_lock); + + if (inet_csk_has_ulp(sk)) { + psock = ERR_PTR(-EINVAL); + goto out; + } + + if (sk->sk_user_data) { + psock = ERR_PTR(-EBUSY); + goto out; + } + + psock = kzalloc_node(sizeof(*psock), GFP_ATOMIC | __GFP_NOWARN, node); + if (!psock) { + psock = ERR_PTR(-ENOMEM); + goto out; + } + prot = READ_ONCE(sk->sk_prot); psock->sk = sk; - psock->eval = __SK_NONE; + psock->eval = __SK_NONE; + psock->sk_proto = prot; + psock->saved_unhash = prot->unhash; + psock->saved_close = prot->close; + psock->saved_write_space = sk->sk_write_space; INIT_LIST_HEAD(&psock->link); spin_lock_init(&psock->link_lock); @@ -516,6 +538,8 @@ struct sk_psock *sk_psock_init(struct sock *sk, int node) rcu_assign_sk_user_data_nocopy(sk, psock); sock_hold(sk); +out: + write_unlock_bh(&sk->sk_callback_lock); return psock; } EXPORT_SYMBOL_GPL(sk_psock_init); @@ -603,6 +627,8 @@ void sk_psock_drop(struct sock *sk, struct sk_psock *psock) rcu_assign_sk_user_data(sk, NULL); if (psock->progs.skb_parser) sk_psock_stop_strp(sk, psock); + else if (psock->progs.skb_verdict) + sk_psock_stop_verdict(sk, psock); write_unlock_bh(&sk->sk_callback_lock); sk_psock_clear_state(psock, SK_PSOCK_TX_ENABLED); @@ -660,19 +686,8 @@ EXPORT_SYMBOL_GPL(sk_psock_msg_verdict); static int sk_psock_bpf_run(struct sk_psock *psock, struct bpf_prog *prog, struct sk_buff *skb) { - int ret; - - skb->sk = psock->sk; bpf_compute_data_end_sk_skb(skb); - ret = bpf_prog_run_pin_on_cpu(prog, skb); - /* strparser clones the skb before handing it to a upper layer, - * meaning skb_orphan has been called. We NULL sk on the way out - * to ensure we don't trigger a BUG_ON() in skb/sk operations - * later and because we are not charging the memory of this skb - * to any socket yet. - */ - skb->sk = NULL; - return ret; + return bpf_prog_run_pin_on_cpu(prog, skb); } static struct sk_psock *sk_psock_from_strp(struct strparser *strp) @@ -687,38 +702,35 @@ static void sk_psock_skb_redirect(struct sk_buff *skb) { struct sk_psock *psock_other; struct sock *sk_other; - bool ingress; sk_other = tcp_skb_bpf_redirect_fetch(skb); + /* This error is a buggy BPF program, it returned a redirect + * return code, but then didn't set a redirect interface. + */ if (unlikely(!sk_other)) { kfree_skb(skb); return; } psock_other = sk_psock(sk_other); + /* This error indicates the socket is being torn down or had another + * error that caused the pipe to break. We can't send a packet on + * a socket that is in this state so we drop the skb. + */ if (!psock_other || sock_flag(sk_other, SOCK_DEAD) || !sk_psock_test_state(psock_other, SK_PSOCK_TX_ENABLED)) { kfree_skb(skb); return; } - ingress = tcp_skb_bpf_ingress(skb); - if ((!ingress && sock_writeable(sk_other)) || - (ingress && - atomic_read(&sk_other->sk_rmem_alloc) <= - sk_other->sk_rcvbuf)) { - if (!ingress) - skb_set_owner_w(skb, sk_other); - skb_queue_tail(&psock_other->ingress_skb, skb); - schedule_work(&psock_other->work); - } else { - kfree_skb(skb); - } + skb_queue_tail(&psock_other->ingress_skb, skb); + schedule_work(&psock_other->work); } -static void sk_psock_tls_verdict_apply(struct sk_buff *skb, int verdict) +static void sk_psock_tls_verdict_apply(struct sk_buff *skb, struct sock *sk, int verdict) { switch (verdict) { case __SK_REDIRECT: + skb_set_owner_r(skb, sk); sk_psock_skb_redirect(skb); break; case __SK_PASS: @@ -736,11 +748,17 @@ int sk_psock_tls_strp_read(struct sk_psock *psock, struct sk_buff *skb) rcu_read_lock(); prog = READ_ONCE(psock->progs.skb_verdict); if (likely(prog)) { + /* We skip full set_owner_r here because if we do a SK_PASS + * or SK_DROP we can skip skb memory accounting and use the + * TLS context. + */ + skb->sk = psock->sk; tcp_skb_bpf_redirect_clear(skb); ret = sk_psock_bpf_run(psock, prog, skb); ret = sk_psock_map_verd(ret, tcp_skb_bpf_redirect_fetch(skb)); + skb->sk = NULL; } - sk_psock_tls_verdict_apply(skb, ret); + sk_psock_tls_verdict_apply(skb, psock->sk, ret); rcu_read_unlock(); return ret; } @@ -749,7 +767,9 @@ EXPORT_SYMBOL_GPL(sk_psock_tls_strp_read); static void sk_psock_verdict_apply(struct sk_psock *psock, struct sk_buff *skb, int verdict) { + struct tcp_skb_cb *tcp; struct sock *sk_other; + int err = -EIO; switch (verdict) { case __SK_PASS: @@ -758,16 +778,24 @@ static void sk_psock_verdict_apply(struct sk_psock *psock, !sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED)) { goto out_free; } - if (atomic_read(&sk_other->sk_rmem_alloc) <= - sk_other->sk_rcvbuf) { - struct tcp_skb_cb *tcp = TCP_SKB_CB(skb); - tcp->bpf.flags |= BPF_F_INGRESS; + tcp = TCP_SKB_CB(skb); + tcp->bpf.flags |= BPF_F_INGRESS; + + /* If the queue is empty then we can submit directly + * into the msg queue. If its not empty we have to + * queue work otherwise we may get OOO data. Otherwise, + * if sk_psock_skb_ingress errors will be handled by + * retrying later from workqueue. + */ + if (skb_queue_empty(&psock->ingress_skb)) { + err = sk_psock_skb_ingress(psock, skb); + } + if (err < 0) { skb_queue_tail(&psock->ingress_skb, skb); schedule_work(&psock->work); - break; } - goto out_free; + break; case __SK_REDIRECT: sk_psock_skb_redirect(skb); break; @@ -792,9 +820,9 @@ static void sk_psock_strp_read(struct strparser *strp, struct sk_buff *skb) kfree_skb(skb); goto out; } + skb_set_owner_r(skb, sk); prog = READ_ONCE(psock->progs.skb_verdict); if (likely(prog)) { - skb_orphan(skb); tcp_skb_bpf_redirect_clear(skb); ret = sk_psock_bpf_run(psock, prog, skb); ret = sk_psock_map_verd(ret, tcp_skb_bpf_redirect_fetch(skb)); @@ -817,8 +845,11 @@ static int sk_psock_strp_parse(struct strparser *strp, struct sk_buff *skb) rcu_read_lock(); prog = READ_ONCE(psock->progs.skb_parser); - if (likely(prog)) + if (likely(prog)) { + skb->sk = psock->sk; ret = sk_psock_bpf_run(psock, prog, skb); + skb->sk = NULL; + } rcu_read_unlock(); return ret; } @@ -842,6 +873,57 @@ static void sk_psock_strp_data_ready(struct sock *sk) rcu_read_unlock(); } +static int sk_psock_verdict_recv(read_descriptor_t *desc, struct sk_buff *skb, + unsigned int offset, size_t orig_len) +{ + struct sock *sk = (struct sock *)desc->arg.data; + struct sk_psock *psock; + struct bpf_prog *prog; + int ret = __SK_DROP; + int len = skb->len; + + /* clone here so sk_eat_skb() in tcp_read_sock does not drop our data */ + skb = skb_clone(skb, GFP_ATOMIC); + if (!skb) { + desc->error = -ENOMEM; + return 0; + } + + rcu_read_lock(); + psock = sk_psock(sk); + if (unlikely(!psock)) { + len = 0; + kfree_skb(skb); + goto out; + } + skb_set_owner_r(skb, sk); + prog = READ_ONCE(psock->progs.skb_verdict); + if (likely(prog)) { + tcp_skb_bpf_redirect_clear(skb); + ret = sk_psock_bpf_run(psock, prog, skb); + ret = sk_psock_map_verd(ret, tcp_skb_bpf_redirect_fetch(skb)); + } + sk_psock_verdict_apply(psock, skb, ret); +out: + rcu_read_unlock(); + return len; +} + +static void sk_psock_verdict_data_ready(struct sock *sk) +{ + struct socket *sock = sk->sk_socket; + read_descriptor_t desc; + + if (unlikely(!sock || !sock->ops || !sock->ops->read_sock)) + return; + + desc.arg.data = sk; + desc.error = 0; + desc.count = 1; + + sock->ops->read_sock(sk, &desc, sk_psock_verdict_recv); +} + static void sk_psock_write_space(struct sock *sk) { struct sk_psock *psock; @@ -871,6 +953,19 @@ int sk_psock_init_strp(struct sock *sk, struct sk_psock *psock) return strp_init(&psock->parser.strp, sk, &cb); } +void sk_psock_start_verdict(struct sock *sk, struct sk_psock *psock) +{ + struct sk_psock_parser *parser = &psock->parser; + + if (parser->enabled) + return; + + parser->saved_data_ready = sk->sk_data_ready; + sk->sk_data_ready = sk_psock_verdict_data_ready; + sk->sk_write_space = sk_psock_write_space; + parser->enabled = true; +} + void sk_psock_start_strp(struct sock *sk, struct sk_psock *psock) { struct sk_psock_parser *parser = &psock->parser; @@ -896,3 +991,15 @@ void sk_psock_stop_strp(struct sock *sk, struct sk_psock *psock) strp_stop(&parser->strp); parser->enabled = false; } + +void sk_psock_stop_verdict(struct sock *sk, struct sk_psock *psock) +{ + struct sk_psock_parser *parser = &psock->parser; + + if (!parser->enabled) + return; + + sk->sk_data_ready = parser->saved_data_ready; + parser->saved_data_ready = NULL; + parser->enabled = false; +} diff --git a/net/core/sock.c b/net/core/sock.c index 40a95e0c4bad..4e8729357122 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -413,18 +413,6 @@ static int sock_set_timeout(long *timeo_p, sockptr_t optval, int optlen, return 0; } -static void sock_warn_obsolete_bsdism(const char *name) -{ - static int warned; - static char warncomm[TASK_COMM_LEN]; - if (strcmp(warncomm, current->comm) && warned < 5) { - strcpy(warncomm, current->comm); - pr_warn("process `%s' is using obsolete %s SO_BSDCOMPAT\n", - warncomm, name); - warned++; - } -} - static bool sock_needs_netstamp(const struct sock *sk) { switch (sk->sk_family) { @@ -983,7 +971,6 @@ set_sndbuf: break; case SO_BSDCOMPAT: - sock_warn_obsolete_bsdism("setsockopt"); break; case SO_PASSCRED: @@ -1382,7 +1369,6 @@ int sock_getsockopt(struct socket *sock, int level, int optname, break; case SO_BSDCOMPAT: - sock_warn_obsolete_bsdism("getsockopt"); break; case SO_TIMESTAMP_OLD: @@ -2956,6 +2942,13 @@ void sk_stop_timer(struct sock *sk, struct timer_list* timer) } EXPORT_SYMBOL(sk_stop_timer); +void sk_stop_timer_sync(struct sock *sk, struct timer_list *timer) +{ + if (del_timer_sync(timer)) + __sock_put(sk); +} +EXPORT_SYMBOL(sk_stop_timer_sync); + void sock_init_data(struct socket *sock, struct sock *sk) { sk_init_common(sk); diff --git a/net/core/sock_diag.c b/net/core/sock_diag.c index c13ffbd33d8d..c9c45b935f99 100644 --- a/net/core/sock_diag.c +++ b/net/core/sock_diag.c @@ -11,7 +11,7 @@ #include <linux/tcp.h> #include <linux/workqueue.h> #include <linux/nospec.h> - +#include <linux/cookie.h> #include <linux/inet_diag.h> #include <linux/sock_diag.h> @@ -19,16 +19,17 @@ static const struct sock_diag_handler *sock_diag_handlers[AF_MAX]; static int (*inet_rcv_compat)(struct sk_buff *skb, struct nlmsghdr *nlh); static DEFINE_MUTEX(sock_diag_table_mutex); static struct workqueue_struct *broadcast_wq; -static atomic64_t cookie_gen; -u64 sock_gen_cookie(struct sock *sk) +DEFINE_COOKIE(sock_cookie); + +u64 __sock_gen_cookie(struct sock *sk) { while (1) { u64 res = atomic64_read(&sk->sk_cookie); if (res) return res; - res = atomic64_inc_return(&cookie_gen); + res = gen_cookie_next(&sock_cookie); atomic64_cmpxchg(&sk->sk_cookie, 0, res); } } diff --git a/net/core/sock_map.c b/net/core/sock_map.c index 119f52a99dc1..df09c39a4dd2 100644 --- a/net/core/sock_map.c +++ b/net/core/sock_map.c @@ -2,6 +2,7 @@ /* Copyright (c) 2017 - 2018 Covalent IO, Inc. http://covalent.io */ #include <linux/bpf.h> +#include <linux/btf_ids.h> #include <linux/filter.h> #include <linux/errno.h> #include <linux/file.h> @@ -147,8 +148,8 @@ static void sock_map_add_link(struct sk_psock *psock, static void sock_map_del_link(struct sock *sk, struct sk_psock *psock, void *link_raw) { + bool strp_stop = false, verdict_stop = false; struct sk_psock_link *link, *tmp; - bool strp_stop = false; spin_lock_bh(&psock->link_lock); list_for_each_entry_safe(link, tmp, &psock->link, list) { @@ -158,14 +159,19 @@ static void sock_map_del_link(struct sock *sk, map); if (psock->parser.enabled && stab->progs.skb_parser) strp_stop = true; + if (psock->parser.enabled && stab->progs.skb_verdict) + verdict_stop = true; list_del(&link->list); sk_psock_free_link(link); } } spin_unlock_bh(&psock->link_lock); - if (strp_stop) { + if (strp_stop || verdict_stop) { write_lock_bh(&sk->sk_callback_lock); - sk_psock_stop_strp(sk, psock); + if (strp_stop) + sk_psock_stop_strp(sk, psock); + else + sk_psock_stop_verdict(sk, psock); write_unlock_bh(&sk->sk_callback_lock); } } @@ -184,8 +190,6 @@ static int sock_map_init_proto(struct sock *sk, struct sk_psock *psock) { struct proto *prot; - sock_owned_by_me(sk); - switch (sk->sk_type) { case SOCK_STREAM: prot = tcp_bpf_get_proto(sk, psock); @@ -231,16 +235,16 @@ static int sock_map_link(struct bpf_map *map, struct sk_psock_progs *progs, { struct bpf_prog *msg_parser, *skb_parser, *skb_verdict; struct sk_psock *psock; - bool skb_progs; int ret; skb_verdict = READ_ONCE(progs->skb_verdict); skb_parser = READ_ONCE(progs->skb_parser); - skb_progs = skb_parser && skb_verdict; - if (skb_progs) { + if (skb_verdict) { skb_verdict = bpf_prog_inc_not_zero(skb_verdict); if (IS_ERR(skb_verdict)) return PTR_ERR(skb_verdict); + } + if (skb_parser) { skb_parser = bpf_prog_inc_not_zero(skb_parser); if (IS_ERR(skb_parser)) { bpf_prog_put(skb_verdict); @@ -265,15 +269,16 @@ static int sock_map_link(struct bpf_map *map, struct sk_psock_progs *progs, if (psock) { if ((msg_parser && READ_ONCE(psock->progs.msg_parser)) || - (skb_progs && READ_ONCE(psock->progs.skb_parser))) { + (skb_parser && READ_ONCE(psock->progs.skb_parser)) || + (skb_verdict && READ_ONCE(psock->progs.skb_verdict))) { sk_psock_put(sk, psock); ret = -EBUSY; goto out_progs; } } else { psock = sk_psock_init(sk, map->numa_node); - if (!psock) { - ret = -ENOMEM; + if (IS_ERR(psock)) { + ret = PTR_ERR(psock); goto out_progs; } } @@ -286,28 +291,31 @@ static int sock_map_link(struct bpf_map *map, struct sk_psock_progs *progs, goto out_drop; write_lock_bh(&sk->sk_callback_lock); - if (skb_progs && !psock->parser.enabled) { + if (skb_parser && skb_verdict && !psock->parser.enabled) { ret = sk_psock_init_strp(sk, psock); - if (ret) { - write_unlock_bh(&sk->sk_callback_lock); - goto out_drop; - } + if (ret) + goto out_unlock_drop; psock_set_prog(&psock->progs.skb_verdict, skb_verdict); psock_set_prog(&psock->progs.skb_parser, skb_parser); sk_psock_start_strp(sk, psock); + } else if (!skb_parser && skb_verdict && !psock->parser.enabled) { + psock_set_prog(&psock->progs.skb_verdict, skb_verdict); + sk_psock_start_verdict(sk,psock); } write_unlock_bh(&sk->sk_callback_lock); return 0; +out_unlock_drop: + write_unlock_bh(&sk->sk_callback_lock); out_drop: sk_psock_put(sk, psock); out_progs: if (msg_parser) bpf_prog_put(msg_parser); out: - if (skb_progs) { + if (skb_verdict) bpf_prog_put(skb_verdict); + if (skb_parser) bpf_prog_put(skb_parser); - } return ret; } @@ -322,8 +330,8 @@ static int sock_map_link_no_progs(struct bpf_map *map, struct sock *sk) if (!psock) { psock = sk_psock_init(sk, map->numa_node); - if (!psock) - return -ENOMEM; + if (IS_ERR(psock)) + return PTR_ERR(psock); } ret = sock_map_init_proto(sk, psock); @@ -384,7 +392,7 @@ static void *sock_map_lookup(struct bpf_map *map, void *key) struct sock *sk; sk = __sock_map_lookup_elem(map, *(u32 *)key); - if (!sk || !sk_fullsock(sk)) + if (!sk) return NULL; if (sk_is_refcounted(sk) && !refcount_inc_not_zero(&sk->sk_refcnt)) return NULL; @@ -402,7 +410,7 @@ static void *sock_map_lookup_sys(struct bpf_map *map, void *key) if (!sk) return ERR_PTR(-ENOENT); - sock_gen_cookie(sk); + __sock_gen_cookie(sk); return &sk->sk_cookie; } @@ -478,8 +486,6 @@ static int sock_map_update_common(struct bpf_map *map, u32 idx, return -EINVAL; if (unlikely(idx >= map->max_entries)) return -E2BIG; - if (inet_csk_has_ulp(sk)) - return -EINVAL; link = sk_psock_init_link(); if (!link) @@ -563,10 +569,12 @@ static bool sock_map_sk_state_allowed(const struct sock *sk) return false; } -static int sock_map_update_elem(struct bpf_map *map, void *key, - void *value, u64 flags) +static int sock_hash_update_common(struct bpf_map *map, void *key, + struct sock *sk, u64 flags); + +int sock_map_update_elem_sys(struct bpf_map *map, void *key, void *value, + u64 flags) { - u32 idx = *(u32 *)key; struct socket *sock; struct sock *sk; int ret; @@ -595,14 +603,41 @@ static int sock_map_update_elem(struct bpf_map *map, void *key, sock_map_sk_acquire(sk); if (!sock_map_sk_state_allowed(sk)) ret = -EOPNOTSUPP; + else if (map->map_type == BPF_MAP_TYPE_SOCKMAP) + ret = sock_map_update_common(map, *(u32 *)key, sk, flags); else - ret = sock_map_update_common(map, idx, sk, flags); + ret = sock_hash_update_common(map, key, sk, flags); sock_map_sk_release(sk); out: fput(sock->file); return ret; } +static int sock_map_update_elem(struct bpf_map *map, void *key, + void *value, u64 flags) +{ + struct sock *sk = (struct sock *)value; + int ret; + + if (unlikely(!sk || !sk_fullsock(sk))) + return -EINVAL; + + if (!sock_map_sk_is_suitable(sk)) + return -EOPNOTSUPP; + + local_bh_disable(); + bh_lock_sock(sk); + if (!sock_map_sk_state_allowed(sk)) + ret = -EOPNOTSUPP; + else if (map->map_type == BPF_MAP_TYPE_SOCKMAP) + ret = sock_map_update_common(map, *(u32 *)key, sk, flags); + else + ret = sock_hash_update_common(map, key, sk, flags); + bh_unlock_sock(sk); + local_bh_enable(); + return ret; +} + BPF_CALL_4(bpf_sock_map_update, struct bpf_sock_ops_kern *, sops, struct bpf_map *, map, void *, key, u64, flags) { @@ -681,8 +716,112 @@ const struct bpf_func_proto bpf_msg_redirect_map_proto = { .arg4_type = ARG_ANYTHING, }; +struct sock_map_seq_info { + struct bpf_map *map; + struct sock *sk; + u32 index; +}; + +struct bpf_iter__sockmap { + __bpf_md_ptr(struct bpf_iter_meta *, meta); + __bpf_md_ptr(struct bpf_map *, map); + __bpf_md_ptr(void *, key); + __bpf_md_ptr(struct sock *, sk); +}; + +DEFINE_BPF_ITER_FUNC(sockmap, struct bpf_iter_meta *meta, + struct bpf_map *map, void *key, + struct sock *sk) + +static void *sock_map_seq_lookup_elem(struct sock_map_seq_info *info) +{ + if (unlikely(info->index >= info->map->max_entries)) + return NULL; + + info->sk = __sock_map_lookup_elem(info->map, info->index); + + /* can't return sk directly, since that might be NULL */ + return info; +} + +static void *sock_map_seq_start(struct seq_file *seq, loff_t *pos) +{ + struct sock_map_seq_info *info = seq->private; + + if (*pos == 0) + ++*pos; + + /* pairs with sock_map_seq_stop */ + rcu_read_lock(); + return sock_map_seq_lookup_elem(info); +} + +static void *sock_map_seq_next(struct seq_file *seq, void *v, loff_t *pos) +{ + struct sock_map_seq_info *info = seq->private; + + ++*pos; + ++info->index; + + return sock_map_seq_lookup_elem(info); +} + +static int sock_map_seq_show(struct seq_file *seq, void *v) +{ + struct sock_map_seq_info *info = seq->private; + struct bpf_iter__sockmap ctx = {}; + struct bpf_iter_meta meta; + struct bpf_prog *prog; + + meta.seq = seq; + prog = bpf_iter_get_info(&meta, !v); + if (!prog) + return 0; + + ctx.meta = &meta; + ctx.map = info->map; + if (v) { + ctx.key = &info->index; + ctx.sk = info->sk; + } + + return bpf_iter_run_prog(prog, &ctx); +} + +static void sock_map_seq_stop(struct seq_file *seq, void *v) +{ + if (!v) + (void)sock_map_seq_show(seq, NULL); + + /* pairs with sock_map_seq_start */ + rcu_read_unlock(); +} + +static const struct seq_operations sock_map_seq_ops = { + .start = sock_map_seq_start, + .next = sock_map_seq_next, + .stop = sock_map_seq_stop, + .show = sock_map_seq_show, +}; + +static int sock_map_init_seq_private(void *priv_data, + struct bpf_iter_aux_info *aux) +{ + struct sock_map_seq_info *info = priv_data; + + info->map = aux->map; + return 0; +} + +static const struct bpf_iter_seq_info sock_map_iter_seq_info = { + .seq_ops = &sock_map_seq_ops, + .init_seq_private = sock_map_init_seq_private, + .seq_priv_size = sizeof(struct sock_map_seq_info), +}; + static int sock_map_btf_id; const struct bpf_map_ops sock_map_ops = { + .map_meta_equal = bpf_map_meta_equal, .map_alloc = sock_map_alloc, .map_free = sock_map_free, .map_get_next_key = sock_map_get_next_key, @@ -694,6 +833,7 @@ const struct bpf_map_ops sock_map_ops = { .map_check_btf = map_check_no_btf, .map_btf_name = "bpf_stab", .map_btf_id = &sock_map_btf_id, + .iter_seq_info = &sock_map_iter_seq_info, }; struct bpf_shtab_elem { @@ -855,8 +995,6 @@ static int sock_hash_update_common(struct bpf_map *map, void *key, WARN_ON_ONCE(!rcu_read_lock_held()); if (unlikely(flags > BPF_EXIST)) return -EINVAL; - if (inet_csk_has_ulp(sk)) - return -EINVAL; link = sk_psock_init_link(); if (!link) @@ -915,45 +1053,6 @@ out_free: return ret; } -static int sock_hash_update_elem(struct bpf_map *map, void *key, - void *value, u64 flags) -{ - struct socket *sock; - struct sock *sk; - int ret; - u64 ufd; - - if (map->value_size == sizeof(u64)) - ufd = *(u64 *)value; - else - ufd = *(u32 *)value; - if (ufd > S32_MAX) - return -EINVAL; - - sock = sockfd_lookup(ufd, &ret); - if (!sock) - return ret; - sk = sock->sk; - if (!sk) { - ret = -EINVAL; - goto out; - } - if (!sock_map_sk_is_suitable(sk)) { - ret = -EOPNOTSUPP; - goto out; - } - - sock_map_sk_acquire(sk); - if (!sock_map_sk_state_allowed(sk)) - ret = -EOPNOTSUPP; - else - ret = sock_hash_update_common(map, key, sk, flags); - sock_map_sk_release(sk); -out: - fput(sock->file); - return ret; -} - static int sock_hash_get_next_key(struct bpf_map *map, void *key, void *key_next) { @@ -971,7 +1070,7 @@ static int sock_hash_get_next_key(struct bpf_map *map, void *key, if (!elem) goto find_first_elem; - elem_next = hlist_entry_safe(rcu_dereference_raw(hlist_next_rcu(&elem->node)), + elem_next = hlist_entry_safe(rcu_dereference(hlist_next_rcu(&elem->node)), struct bpf_shtab_elem, node); if (elem_next) { memcpy(key_next, elem_next->key, key_size); @@ -983,7 +1082,7 @@ static int sock_hash_get_next_key(struct bpf_map *map, void *key, find_first_elem: for (; i < htab->buckets_num; i++) { head = &sock_hash_select_bucket(htab, i)->head; - elem_next = hlist_entry_safe(rcu_dereference_raw(hlist_first_rcu(head)), + elem_next = hlist_entry_safe(rcu_dereference(hlist_first_rcu(head)), struct bpf_shtab_elem, node); if (elem_next) { memcpy(key_next, elem_next->key, key_size); @@ -1119,7 +1218,7 @@ static void *sock_hash_lookup_sys(struct bpf_map *map, void *key) if (!sk) return ERR_PTR(-ENOENT); - sock_gen_cookie(sk); + __sock_gen_cookie(sk); return &sk->sk_cookie; } @@ -1128,7 +1227,7 @@ static void *sock_hash_lookup(struct bpf_map *map, void *key) struct sock *sk; sk = __sock_hash_lookup_elem(map, key); - if (!sk || !sk_fullsock(sk)) + if (!sk) return NULL; if (sk_is_refcounted(sk) && !refcount_inc_not_zero(&sk->sk_refcnt)) return NULL; @@ -1217,12 +1316,124 @@ const struct bpf_func_proto bpf_msg_redirect_hash_proto = { .arg4_type = ARG_ANYTHING, }; +struct sock_hash_seq_info { + struct bpf_map *map; + struct bpf_shtab *htab; + u32 bucket_id; +}; + +static void *sock_hash_seq_find_next(struct sock_hash_seq_info *info, + struct bpf_shtab_elem *prev_elem) +{ + const struct bpf_shtab *htab = info->htab; + struct bpf_shtab_bucket *bucket; + struct bpf_shtab_elem *elem; + struct hlist_node *node; + + /* try to find next elem in the same bucket */ + if (prev_elem) { + node = rcu_dereference(hlist_next_rcu(&prev_elem->node)); + elem = hlist_entry_safe(node, struct bpf_shtab_elem, node); + if (elem) + return elem; + + /* no more elements, continue in the next bucket */ + info->bucket_id++; + } + + for (; info->bucket_id < htab->buckets_num; info->bucket_id++) { + bucket = &htab->buckets[info->bucket_id]; + node = rcu_dereference(hlist_first_rcu(&bucket->head)); + elem = hlist_entry_safe(node, struct bpf_shtab_elem, node); + if (elem) + return elem; + } + + return NULL; +} + +static void *sock_hash_seq_start(struct seq_file *seq, loff_t *pos) +{ + struct sock_hash_seq_info *info = seq->private; + + if (*pos == 0) + ++*pos; + + /* pairs with sock_hash_seq_stop */ + rcu_read_lock(); + return sock_hash_seq_find_next(info, NULL); +} + +static void *sock_hash_seq_next(struct seq_file *seq, void *v, loff_t *pos) +{ + struct sock_hash_seq_info *info = seq->private; + + ++*pos; + return sock_hash_seq_find_next(info, v); +} + +static int sock_hash_seq_show(struct seq_file *seq, void *v) +{ + struct sock_hash_seq_info *info = seq->private; + struct bpf_iter__sockmap ctx = {}; + struct bpf_shtab_elem *elem = v; + struct bpf_iter_meta meta; + struct bpf_prog *prog; + + meta.seq = seq; + prog = bpf_iter_get_info(&meta, !elem); + if (!prog) + return 0; + + ctx.meta = &meta; + ctx.map = info->map; + if (elem) { + ctx.key = elem->key; + ctx.sk = elem->sk; + } + + return bpf_iter_run_prog(prog, &ctx); +} + +static void sock_hash_seq_stop(struct seq_file *seq, void *v) +{ + if (!v) + (void)sock_hash_seq_show(seq, NULL); + + /* pairs with sock_hash_seq_start */ + rcu_read_unlock(); +} + +static const struct seq_operations sock_hash_seq_ops = { + .start = sock_hash_seq_start, + .next = sock_hash_seq_next, + .stop = sock_hash_seq_stop, + .show = sock_hash_seq_show, +}; + +static int sock_hash_init_seq_private(void *priv_data, + struct bpf_iter_aux_info *aux) +{ + struct sock_hash_seq_info *info = priv_data; + + info->map = aux->map; + info->htab = container_of(aux->map, struct bpf_shtab, map); + return 0; +} + +static const struct bpf_iter_seq_info sock_hash_iter_seq_info = { + .seq_ops = &sock_hash_seq_ops, + .init_seq_private = sock_hash_init_seq_private, + .seq_priv_size = sizeof(struct sock_hash_seq_info), +}; + static int sock_hash_map_btf_id; const struct bpf_map_ops sock_hash_ops = { + .map_meta_equal = bpf_map_meta_equal, .map_alloc = sock_hash_alloc, .map_free = sock_hash_free, .map_get_next_key = sock_hash_get_next_key, - .map_update_elem = sock_hash_update_elem, + .map_update_elem = sock_map_update_elem, .map_delete_elem = sock_hash_delete_elem, .map_lookup_elem = sock_hash_lookup, .map_lookup_elem_sys_only = sock_hash_lookup_sys, @@ -1230,6 +1441,7 @@ const struct bpf_map_ops sock_hash_ops = { .map_check_btf = map_check_no_btf, .map_btf_name = "bpf_shtab", .map_btf_id = &sock_hash_map_btf_id, + .iter_seq_info = &sock_hash_iter_seq_info, }; static struct sk_psock_progs *sock_map_progs(struct bpf_map *map) @@ -1340,3 +1552,62 @@ void sock_map_close(struct sock *sk, long timeout) release_sock(sk); saved_close(sk, timeout); } + +static int sock_map_iter_attach_target(struct bpf_prog *prog, + union bpf_iter_link_info *linfo, + struct bpf_iter_aux_info *aux) +{ + struct bpf_map *map; + int err = -EINVAL; + + if (!linfo->map.map_fd) + return -EBADF; + + map = bpf_map_get_with_uref(linfo->map.map_fd); + if (IS_ERR(map)) + return PTR_ERR(map); + + if (map->map_type != BPF_MAP_TYPE_SOCKMAP && + map->map_type != BPF_MAP_TYPE_SOCKHASH) + goto put_map; + + if (prog->aux->max_rdonly_access > map->key_size) { + err = -EACCES; + goto put_map; + } + + aux->map = map; + return 0; + +put_map: + bpf_map_put_with_uref(map); + return err; +} + +static void sock_map_iter_detach_target(struct bpf_iter_aux_info *aux) +{ + bpf_map_put_with_uref(aux->map); +} + +static struct bpf_iter_reg sock_map_iter_reg = { + .target = "sockmap", + .attach_target = sock_map_iter_attach_target, + .detach_target = sock_map_iter_detach_target, + .show_fdinfo = bpf_iter_map_show_fdinfo, + .fill_link_info = bpf_iter_map_fill_link_info, + .ctx_arg_info_size = 2, + .ctx_arg_info = { + { offsetof(struct bpf_iter__sockmap, key), + PTR_TO_RDONLY_BUF_OR_NULL }, + { offsetof(struct bpf_iter__sockmap, sk), + PTR_TO_BTF_ID_OR_NULL }, + }, +}; + +static int __init bpf_sockmap_iter_init(void) +{ + sock_map_iter_reg.ctx_arg_info[1].btf_id = + btf_sock_ids[BTF_SOCK_TYPE_SOCK]; + return bpf_iter_reg_target(&sock_map_iter_reg); +} +late_initcall(bpf_sockmap_iter_init); diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index 6ada114bbcca..d86d8d11cfe4 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -22,7 +22,7 @@ #include <net/busy_poll.h> #include <net/pkt_sched.h> -static int two __maybe_unused = 2; +static int two = 2; static int three = 3; static int min_sndbuf = SOCK_MIN_SNDBUF; static int min_rcvbuf = SOCK_MIN_RCVBUF; @@ -546,7 +546,7 @@ static struct ctl_table net_core_table[] = { .mode = 0644, .proc_handler = proc_dointvec_minmax, .extra1 = SYSCTL_ZERO, - .extra2 = SYSCTL_ONE, + .extra2 = &two, }, { .procname = "devconf_inherit_init_net", @@ -587,6 +587,19 @@ static struct ctl_table netns_core_table[] = { { } }; +static int __init fb_tunnels_only_for_init_net_sysctl_setup(char *str) +{ + /* fallback tunnels for initns only */ + if (!strncmp(str, "initns", 6)) + sysctl_fb_tunnels_only_for_init_net = 1; + /* no fallback tunnels anywhere */ + else if (!strncmp(str, "none", 4)) + sysctl_fb_tunnels_only_for_init_net = 2; + + return 1; +} +__setup("fb_tunnels=", fb_tunnels_only_for_init_net_sysctl_setup); + static __net_init int sysctl_core_net_init(struct net *net) { struct ctl_table *tbl; |